Page MenuHomeClusterLabs Projects
Files F1842246

No OneTemporary
Actions

View Options

This file is larger than 256 KB, so syntax highlighting was skipped.
diff --git a/ChangeLog b/ChangeLog
index 33604799d7..17d3e4f4e1 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,4132 +1,4145 @@
+* Tue Nov 21 2023 Ken Gaillot <kgaillot@redhat.com> Pacemaker-2.1.7-rc2
+- 26 commits with 14 files changed, 119 insertions(+), 46 deletions(-)
+
+- Features added since Pacemaker-2.1.7-rc1
+ + Default of new node-pending-timeout option has been changed to 0
+ to preserve previous behavior
+
+- Fixes since Pacemaker-2.1.7-rc1
+ + build: Allow building with libxml2 2.12.0 and greater
+ + tools: crm_resource --wait will now wait if any actions are pending
+ (previously it would wait only if new actions were planned)
+ + tools: crm_verify --output-as=xml now includes detailed messages
+
* Mon Oct 30 2023 Ken Gaillot <kgaillot@redhat.com> Pacemaker-2.1.7-rc1
- 1345 commits with 358 files changed, 23622 insertions(+), 17197 deletions(-)
- Features added since Pacemaker-2.1.6
+ CIB: deprecate "ordering" attribute of "resource_set"
+ CIB: new cluster option "node-pending-timeout" (defaulting to 2 hours) to
fence nodes that do not join Pacemaker's controller group within this much
time after joining the cluster
+ controller: PCMK_node_start_state now works with Pacemaker Remote nodes
+ crm_verify: add --quiet option (currently same as default behavior)
+ tools: crm_node supports standard --output-as/--output-to arguments
+ tests: CTSlab.py was renamed to cts-lab
- Fixes since Pacemaker-2.1.6
+ logging: restore ability to enable XML trace logs by file and function
(regression introduced in 2.1.6)
+ scheduler: avoid double free with disabled recurring actions
(regression introduced in 2.1.5)
+ tools: consider dampening argument when setting values with attrd_updater
(regression introduced in 2.1.5)
+ tools: wait for reply from crm_node -R (regression introduced in 2.0.5)
+ CIB: be more strict about ignoring colocation elements without an ID
+ controller: do not check whether watchdog fencing is enabled
if "stonith-watchdog-timeout" is not configured
+ controller: don't try to execute agent action at shutdown
+ controller: avoid race condition when updating node state during join
+ controller: correctly determine state of a fenced node without a name
+ controller: wait a second between fencer connection attempts
+ libpacemaker: avoid shuffling clone instances unnecessarily
+ libpacemaker: get bundle container's promotion score from correct node
+ libpacemaker: role-based colocations now works with bundles
+ libpacemaker: clone-node-max now works with cloned groups
+ scheduler: compare anti-colocation dependent negative preferences against
stickiness
+ scheduler: consider explicit colocations with group members
+ scheduler: avoid fencing a pending node without a name
+ scheduler: properly evaluate rules in action meta-attributes
+ scheduler: properly sort rule-based blocks when overwriting values
+ tools: avoid showing pending nodes as having "<3.15.1" feature set in
crm_mon
+ tools: fix display of clone descriptions
+ tools: crm_resource now reports an error rather than time out when trying
to restart an unmanaged resource
+ tools: crm_resource now properly detects which promoted role name to use
in ban and move constraints
- Public API changes since Pacemaker-2.1.6 (all API/ABI backward-compatible)
+ libcib: cib_t now supports transactions via new cib_api_operations_t
methods, new cib_transaction value in enum cib_call_options, and new
cib_t transaction and user members
+ libcib: cib_t now supports setting the ACL user for methods via new
cib_api_operations_t set_user() method
+ libcib: deprecate cib_api_operations_t methods inputfd(), noop(), quit(),
set_op_callback(), and signon_raw()
+ libcib: deprecate cib_call_options values cib_mixed_update,
cib_scope_local, and cib_zero_copy
+ libcib: deprecate cib_t op_callback member
+ libcrmcluster: deprecate set_uuid()
+ libcrmcluster: send_cluster_message()'s data argument is const
+ libcrmcommon: add enum pcmk_rc_e values pcmk_rc_compression,
pcmk_rc_ns_resolution, and pcmk_rc_no_transaction
+ libcrmcommon,libpe_rules,libpe_status: many APIs have been moved from
libpe_rules and libpe_status to libcrmcommon, sometimes with new names
(deprecating the old ones), as described below
+ libcrmcommon: add (and deprecate) PCMK_DEFAULT_METADATA_TIMEOUT_MS defined
constant
+ libcrmcommon: add enum pcmk_rsc_flags
+ libcrmcommon: add enum pcmk_scheduler_flags
+ libcrmcommon: add pcmk_action_added_to_graph
+ libcrmcommon: add pcmk_action_always_in_graph
+ libcrmcommon: add pcmk_action_attrs_evaluated
+ libcrmcommon: add PCMK_ACTION_CANCEL string constant
+ libcrmcommon: add PCMK_ACTION_CLEAR_FAILCOUNT string constant
+ libcrmcommon: add PCMK_ACTION_CLONE_ONE_OR_MORE string constant
+ libcrmcommon: add PCMK_ACTION_DELETE string constant
+ libcrmcommon: add PCMK_ACTION_DEMOTE string constant
+ libcrmcommon: add pcmk_action_demote to enum action_tasks
+ libcrmcommon: add PCMK_ACTION_DEMOTED string constant
+ libcrmcommon: add pcmk_action_demoted to enum action_tasks
+ libcrmcommon: add pcmk_action_detect_loop
+ libcrmcommon: add PCMK_ACTION_DO_SHUTDOWN string constant
+ libcrmcommon: add pcmk_action_fence to enum action_tasks
+ libcrmcommon: add pcmk_action_inputs_deduplicated
+ libcrmcommon: add PCMK_ACTION_LIST string constant
+ libcrmcommon: add PCMK_ACTION_LOAD_STOPPED string constant
+ libcrmcommon: add PCMK_ACTION_LRM_DELETE string constant
+ libcrmcommon: add PCMK_ACTION_MAINTENANCE_NODES string constant
+ libcrmcommon: add PCMK_ACTION_META_DATA string constant
+ libcrmcommon: add pcmk_action_migratable
+ libcrmcommon: add PCMK_ACTION_MIGRATE_FROM string constant
+ libcrmcommon: add PCMK_ACTION_MIGRATE_TO string constant
+ libcrmcommon: add pcmk_action_migration_abort
+ libcrmcommon: add pcmk_action_min_runnable
+ libcrmcommon: add PCMK_ACTION_MONITOR string constant
+ libcrmcommon: add pcmk_action_monitor to enum action_tasks
+ libcrmcommon: add PCMK_ACTION_NOTIFIED string constant
+ libcrmcommon: add pcmk_action_notified to enum action_tasks
+ libcrmcommon: add PCMK_ACTION_NOTIFY string constant
+ libcrmcommon: add pcmk_action_notify to enum action_tasks
+ libcrmcommon: add PCMK_ACTION_OFF string constant
+ libcrmcommon: add PCMK_ACTION_ON string constant
+ libcrmcommon: add PCMK_ACTION_ONE_OR_MORE string constant
+ libcrmcommon: add pcmk_action_on_dc
+ libcrmcommon: add pcmk_action_optional
+ libcrmcommon: add PCMK_ACTION_PROMOTE string constant
+ libcrmcommon: add pcmk_action_promote to enum action_tasks
+ libcrmcommon: add PCMK_ACTION_PROMOTED string constant
+ libcrmcommon: add pcmk_action_promoted to enum action_tasks
+ libcrmcommon: add pcmk_action_pseudo
+ libcrmcommon: add PCMK_ACTION_REBOOT string constant
+ libcrmcommon: add PCMK_ACTION_RELOAD string constant
+ libcrmcommon: add PCMK_ACTION_RELOAD_AGENT string constant
+ libcrmcommon: add pcmk_action_reschedule
+ libcrmcommon: add pcmk_action_runnable
+ libcrmcommon: add PCMK_ACTION_RUNNING string constant
+ libcrmcommon: add pcmk_action_shutdown to enum action_tasks
+ libcrmcommon: add PCMK_ACTION_START string constant
+ libcrmcommon: add pcmk_action_start to enum action_tasks
+ libcrmcommon: add pcmk_action_started to enum action_tasks
+ libcrmcommon: add PCMK_ACTION_STATUS string constant
+ libcrmcommon: add PCMK_ACTION_STONITH string constant
+ libcrmcommon: add PCMK_ACTION_STOP string constant
+ libcrmcommon: add pcmk_action_stop to enum action_tasks
+ libcrmcommon: add PCMK_ACTION_STOPPED string constant
+ libcrmcommon: add pcmk_action_stopped to enum action_tasks
+ libcrmcommon: add pcmk_action_t type
+ libcrmcommon: add pcmk_action_unspecified to enum action_tasks
+ libcrmcommon: add PCMK_ACTION_VALIDATE_ALL string constant
+ libcrmcommon: add pcmk_assignment_methods_t type
+ libcrmcommon: add PCMK_DEFAULT_ACTION_TIMEOUT_MS defined constant
+ libcrmcommon: add pcmk_log_xml_as()
+ libcrmcommon: add PCMK_META_CLONE_MAX string constant
+ libcrmcommon: add PCMK_META_CLONE_MIN string constant
+ libcrmcommon: add PCMK_META_CLONE_NODE_MAX string constant
+ libcrmcommon: add PCMK_META_FAILURE_TIMEOUT string constant
+ libcrmcommon: add PCMK_META_MIGRATION_THRESHOLD string constant
+ libcrmcommon: add PCMK_META_PROMOTED_MAX string constant
+ libcrmcommon: add PCMK_META_PROMOTED_NODE_MAX string constant
+ libcrmcommon: add pcmk_multiply_active_block to enum rsc_recovery_type
+ libcrmcommon: add pcmk_multiply_active_restart to enum rsc_recovery_type
+ libcrmcommon: add pcmk_multiply_active_stop to enum rsc_recovery_type
+ libcrmcommon: add pcmk_multiply_active_unexpected to enum rsc_recovery_type
+ libcrmcommon: add PCMK_NODE_ATTR_TERMINATE string constant
+ libcrmcommon: add pcmk_node_t type
+ libcrmcommon: add pcmk_node_variant_cluster
+ libcrmcommon: add pcmk_node_variant_remote
+ libcrmcommon: add pcmk_no_action_flags
+ libcrmcommon: add pcmk_no_quorum_demote
+ libcrmcommon: add pcmk_no_quorum_fence
+ libcrmcommon: add pcmk_no_quorum_freeze
+ libcrmcommon: add pcmk_no_quorum_ignore
+ libcrmcommon: add pcmk_no_quorum_stop
+ libcrmcommon: add pcmk_on_fail_ban to enum action_fail_response
+ libcrmcommon: add pcmk_on_fail_block to enum action_fail_response
+ libcrmcommon: add pcmk_on_fail_demote to enum action_fail_response
+ libcrmcommon: add pcmk_on_fail_fence_node to enum action_fail_response
+ libcrmcommon: add pcmk_on_fail_ignore to enum action_fail_response
+ libcrmcommon: add pcmk_on_fail_reset_remote to enum action_fail_response
+ libcrmcommon: add pcmk_on_fail_restart to enum action_fail_response
+ libcrmcommon: add pcmk_on_fail_restart_container to enum action_fail_response
+ libcrmcommon: add pcmk_on_fail_standby_node to action_fail_response
+ libcrmcommon: add pcmk_on_fail_stop to enum action_fail_response
+ libcrmcommon: add pcmk_probe_always to enum pe_discover_e
+ libcrmcommon: add pcmk_probe_exclusive to enum pe_discover_e
+ libcrmcommon: add pcmk_probe_never to enum pe_discover_e
+ libcrmcommon: add pcmk_requires_fencing to enum rsc_start_requirement
+ libcrmcommon: add pcmk_requires_nothing to enum rsc_start_requirement
+ libcrmcommon: add pcmk_requires_quorum to enum rsc_start_requirement
+ libcrmcommon: add pcmk_resource_t type
+ libcrmcommon: add pcmk_role_promoted to enum rsc_role_e
+ libcrmcommon: add pcmk_role_started to enum rsc_role_e
+ libcrmcommon: add pcmk_role_stopped to enum rsc_role_e
+ libcrmcommon: add pcmk_role_unknown to enum rsc_role_e
+ libcrmcommon: add pcmk_role_unpromoted to enum rsc_role_e
+ libcrmcommon: add pcmk_rsc_match_anon_basename
+ libcrmcommon: add pcmk_rsc_match_basename
+ libcrmcommon: add pcmk_rsc_match_clone_only
+ libcrmcommon: add pcmk_rsc_match_current_node
+ libcrmcommon: add pcmk_rsc_match_history
+ libcrmcommon: add pcmk_rsc_methods_t type
+ libcrmcommon: add pcmk_rsc_variant_bundle
+ libcrmcommon: add pcmk_rsc_variant_clone
+ libcrmcommon: add pcmk_rsc_variant_group
+ libcrmcommon: add pcmk_rsc_variant_primitive
+ libcrmcommon: add pcmk_rsc_variant_unknown
+ libcrmcommon: add pcmk_scheduler_t type
+ libcrmcommon: add pcmk_tag_t type
+ libcrmcommon: add pcmk_ticket_t type
+ libcrmcommon: add PCMK_XA_FORMAT string constant
+ libcrmcommon: crm_ipc_send()'s message argument is now const
+ libcrmcommon: deprecate action_demote in enum action_tasks
+ libcrmcommon: deprecate action_demoted in enum action_tasks
+ libcrmcommon: deprecate action_fail_block in enum action_fail_response
+ libcrmcommon: deprecate action_fail_demote in enum action_fail_response
+ libcrmcommon: deprecate action_fail_fence in enum action_fail_response
+ libcrmcommon: deprecate action_fail_ignore in enum action_fail_response
+ libcrmcommon: deprecate action_fail_migrate in enum action_fail_response
+ libcrmcommon: deprecate action_fail_recover in enum action_fail_response
+ libcrmcommon: deprecate action_fail_reset_remote in enum action_fail_response
+ libcrmcommon: deprecate action_fail_standby in enum action_fail_response
+ libcrmcommon: deprecate action_fail_stop in action_fail_response
+ libcrmcommon: deprecate action_notified in enum action_tasks
+ libcrmcommon: deprecate action_notify in enum action_tasks
+ libcrmcommon: deprecate action_promote in enum action_tasks
+ libcrmcommon: deprecate action_promoted in enum action_tasks
+ libcrmcommon: deprecate action_restart_container in enum action_fail_response
+ libcrmcommon: deprecate CRMD_ACTION_CANCEL string constant
+ libcrmcommon: deprecate CRMD_ACTION_DELETE string constant
+ libcrmcommon: deprecate CRMD_ACTION_DEMOTE string constant
+ libcrmcommon: deprecate CRMD_ACTION_DEMOTED string constant
+ libcrmcommon: deprecate CRMD_ACTION_METADATA string constant
+ libcrmcommon: deprecate CRMD_ACTION_MIGRATE string constant
+ libcrmcommon: deprecate CRMD_ACTION_MIGRATED string constant
+ libcrmcommon: deprecate CRMD_ACTION_NOTIFIED string constant
+ libcrmcommon: deprecate CRMD_ACTION_NOTIFY string constant
+ libcrmcommon: deprecate CRMD_ACTION_PROMOTE string constant
+ libcrmcommon: deprecate CRMD_ACTION_PROMOTED string constant
+ libcrmcommon: deprecate CRMD_ACTION_RELOAD string constant
+ libcrmcommon: deprecate CRMD_ACTION_RELOAD_AGENT string constant
+ libcrmcommon: deprecate CRMD_ACTION_START string constant
+ libcrmcommon: deprecate CRMD_ACTION_STARTED string constant
+ libcrmcommon: deprecate CRMD_ACTION_STATUS string constant
+ libcrmcommon: deprecate CRMD_ACTION_STOP string constant
+ libcrmcommon: deprecate CRMD_ACTION_STOPPED string constant
+ libcrmcommon: deprecate CRMD_METADATA_CALL_TIMEOUT defined constant
+ libcrmcommon: deprecate crm_action_str()
+ libcrmcommon: deprecate CRM_DEFAULT_OP_TIMEOUT_S string constant
+ libcrmcommon: deprecate crm_element_name()
+ libcrmcommon: deprecate CRM_OP_FENCE string constant
+ libcrmcommon: deprecate CRM_OP_RELAXED_CLONE string constant
+ libcrmcommon: deprecate CRM_OP_RELAXED_SET string constant
+ libcrmcommon: deprecate crm_xml_replace()
+ libcrmcommon: deprecate enum pe_link_state
+ libcrmcommon: deprecate getDocPtr()
+ libcrmcommon: deprecate monitor_rsc in enum action_tasks
+ libcrmcommon: deprecate node_member
+ libcrmcommon: deprecate node_remote
+ libcrmcommon: deprecate no_action in enum action_tasks
+ libcrmcommon: deprecate no_quorum_demote
+ libcrmcommon: deprecate no_quorum_freeze
+ libcrmcommon: deprecate no_quorum_ignore
+ libcrmcommon: deprecate no_quorum_stop
+ libcrmcommon: deprecate no_quorum_suicide
+ libcrmcommon: deprecate pcmk_log_xml_impl()
+ libcrmcommon: deprecate pcmk_scheduler_t localhost member
+ libcrmcommon: deprecate pe_action_dangle
+ libcrmcommon: deprecate pe_action_dc
+ libcrmcommon: deprecate pe_action_dedup
+ libcrmcommon: deprecate pe_action_dumped
+ libcrmcommon: deprecate pe_action_have_node_attrs
+ libcrmcommon: deprecate pe_action_implied_by_stonith
+ libcrmcommon: deprecate pe_action_migrate_runnable
+ libcrmcommon: deprecate pe_action_optional
+ libcrmcommon: deprecate pe_action_print_always
+ libcrmcommon: deprecate pe_action_processed
+ libcrmcommon: deprecate pe_action_pseudo
+ libcrmcommon: deprecate pe_action_requires_any
+ libcrmcommon: deprecate pe_action_reschedule
+ libcrmcommon: deprecate pe_action_runnable
+ libcrmcommon: deprecate pe_action_tracking
+ libcrmcommon: deprecate pe_clone
+ libcrmcommon: deprecate pe_container
+ libcrmcommon: deprecate pe_discover_always in enum pe_discover_e
+ libcrmcommon: deprecate pe_discover_exclusive in enum pe_discover_e
+ libcrmcommon: deprecate pe_discover_never in enum pe_discover_e
+ libcrmcommon: deprecate pe_find_anon
+ libcrmcommon: deprecate pe_find_any
+ libcrmcommon: deprecate pe_find_clone
+ libcrmcommon: deprecate pe_find_current
+ libcrmcommon: deprecate pe_find_inactive
+ libcrmcommon: deprecate pe_find_renamed
+ libcrmcommon: deprecate pe_group
+ libcrmcommon: deprecate pe_native
+ libcrmcommon: deprecate pe_unknown
+ libcrmcommon: deprecate recovery_block in enum rsc_recovery_type
+ libcrmcommon: deprecate recovery_stop_only in enum rsc_recovery_type
+ libcrmcommon: deprecate recovery_stop_start in enum rsc_recovery_type
+ libcrmcommon: deprecate recovery_stop_unexpected in enum rsc_recovery_type
+ libcrmcommon: deprecate RSC_CANCEL string constant
+ libcrmcommon: deprecate RSC_DELETE string constant
+ libcrmcommon: deprecate RSC_DEMOTE string constant
+ libcrmcommon: deprecate RSC_DEMOTED string constant
+ libcrmcommon: deprecate RSC_METADATA string constant
+ libcrmcommon: deprecate RSC_MIGRATE string constant
+ libcrmcommon: deprecate RSC_MIGRATED string constant
+ libcrmcommon: deprecate RSC_NOTIFIED string constant
+ libcrmcommon: deprecate RSC_NOTIFY string constant
+ libcrmcommon: deprecate RSC_PROMOTE string constant
+ libcrmcommon: deprecate RSC_PROMOTED string constant
+ libcrmcommon: deprecate rsc_req_nothing in enum rsc_start_requirement
+ libcrmcommon: deprecate rsc_req_quorum in enum rsc_start_requirement
+ libcrmcommon: deprecate rsc_req_stonith in enum rsc_start_requirement
+ libcrmcommon: deprecate RSC_ROLE_PROMOTED in enum rsc_role_e
+ libcrmcommon: deprecate RSC_ROLE_STARTED in enum rsc_role_e
+ libcrmcommon: deprecate RSC_ROLE_STOPPED in enum rsc_role_e
+ libcrmcommon: deprecate RSC_ROLE_UNKNOWN in enum rsc_role_e
+ libcrmcommon: deprecate RSC_ROLE_UNPROMOTED
+ libcrmcommon: deprecate RSC_START string constant
+ libcrmcommon: deprecate RSC_STARTED string constant
+ libcrmcommon: deprecate RSC_STATUS string constant
+ libcrmcommon: deprecate RSC_STOP string constant
+ libcrmcommon: deprecate RSC_STOPPED string constant
+ libcrmcommon: deprecate shutdown_crm in enum action_tasks
+ libcrmcommon: deprecate started_rsc in enum action_tasks
+ libcrmcommon: deprecate start_rsc in enum action_tasks
+ libcrmcommon: deprecate stonith_node in enum action_tasks
+ libcrmcommon: deprecate stopped_rsc in enum action_tasks
+ libcrmcommon: deprecate stop_rsc in enum action_tasks
+ libcrmcommon: deprecate TYPE() macro
+ libcrmcommon: deprecate XML_ATTR_VERBOSE string constant
+ libcrmcommon: deprecate XML_CIB_ATTR_SOURCE string constant
+ libcrmcommon: deprecate XML_CIB_TAG_DOMAINS string constant
+ libcrmcommon: deprecate xml_has_children()
+ libcrmcommon: deprecate XML_NODE_EXPECTED string constant
+ libcrmcommon: deprecate XML_NODE_IN_CLUSTER string constant
+ libcrmcommon: deprecate XML_NODE_IS_PEER string constant
+ libcrmcommon: deprecate XML_NODE_JOIN_STATE string constant
+ libcrmcommon: deprecate XML_RSC_ATTR_FAIL_STICKINESS string constant
+ libcrmcommon: deprecate XML_RSC_ATTR_FAIL_TIMEOUT string constant
+ libcrmcommon: deprecate XML_RSC_ATTR_INCARNATION_MAX string constant
+ libcrmcommon: deprecate XML_RSC_ATTR_INCARNATION_MIN string constant
+ libcrmcommon: deprecate XML_RSC_ATTR_INCARNATION_NODEMAX string constant
+ libcrmcommon: deprecate XML_RSC_ATTR_PROMOTED_MAX string constant
+ libcrmcommon: deprecate XML_RSC_ATTR_PROMOTED_NODEMAX string constant
+ libcrmcommon: deprecate XML_TAG_DIFF_ADDED string constant
+ libcrmcommon: deprecate XML_TAG_DIFF_REMOVED string constant
+ libcrmcommon: deprecate XML_TAG_FRAGMENT
+ libcrmcommon: dump_xml_formatted()'s argument is now const
+ libcrmcommon: dump_xml_formatted_with_text()'s argument is const
+ libcrmcommon: dump_xml_unformatted()'s argument is now const
+ libcrmcommon: save_xml_to_file()'s xml argument is now const
+ libcrmcommon: validate_xml_verbose()'s xml_blob argument is const
+ libcrmcommon: write_xml_fd()'s xml argument is now const
+ libcrmcommon: write_xml_file()'s xml argument is now const
+ libcrmcommon: xml_top argument of xpath_search() is now const
+ libcrmcommon,libpe_rules,libpe_status: move enum pe_ordering, struct
pe_action_wrapper_s, struct pe_tag_s, struct pe_ticket_s, struct
resource_object_functions_s, enum node_type, enum pe_action_flags, enum
pe_discover_e, enum pe_find, enum pe_link_state, enum pe_obj_types, enum
pe_quorum_policy, enum pe_restart, struct pe_action_s, struct pe_node_s,
struct pe_node_shared_s, struct pe_resource_s, struct pe_working_set_s,
enum action_fail_response, enum action_tasks, enum pe_print_options, enum
rsc_recovery_type, enum rsc_role_e, and enum rsc_start_requirement to
libcrmcommon
+ libpacemaker,libpe_rules,libpe_status: use pcmk_action_t instead of
pe_action_t, pcmk_node_t instead of pe_node_t, pcmk_resource_t instead of
pe_resource_t, and pcmk_scheduler_t instead of pe_working_set_t in all API
structs and functions
+ libpacemaker: add pcmk_list_alternatives(), pcmk_list_providers(),
pcmk_list_standards(), and pcmk_list_agents() for functionality equivalent
to crm_resource --list-ocf-alternatives, --list-ocf-providers,
--list-standards, and --list-agents
+ libpe_rules,libpe_status: deprecate pe_action_t type
+ libpe_rules,libpe_status: deprecate pe_action_wrapper_t
+ libpe_rules,libpe_status: deprecate pe_node_t type
+ libpe_rules,libpe_status: deprecate pe_resource_t type
+ libpe_rules,libpe_status: deprecate pe_tag_t
+ libpe_rules,libpe_status: deprecate pe_ticket_t
+ libpe_rules,libpe_status: deprecate pe_working_set_t type
+ libpe_rules,libpe_status: deprecate resource_alloc_functions_t type
+ libpe_rules,libpe_status: deprecate resource_object_functions_t
+ libpe_status,libpe_rules: deprecate enum pe_ordering and all its values
+ libpe_status,libpe_rules: deprecate RSC_ROLE_MAX
+ libpe_status,libpe_rules: deprecate RSC_ROLE_PROMOTED_LEGACY_S string constant
+ libpe_status,libpe_rules: deprecate RSC_ROLE_PROMOTED_S string constant
+ libpe_status,libpe_rules: deprecate RSC_ROLE_STARTED_S string constant
+ libpe_status,libpe_rules: deprecate RSC_ROLE_STOPPED_S string constant
+ libpe_status,libpe_rules: deprecate RSC_ROLE_UNKNOWN_S
+ libpe_status,libpe_rules: deprecate RSC_ROLE_UNPROMOTED_LEGACY_S string constant
+ libpe_status,libpe_rules: deprecate RSC_ROLE_UNPROMOTED_S string constant
+ libpe_status: deprecate enum pe_check_parameters
+ libpe_status: deprecate pe_flag_check_config
+ libpe_status: deprecate pe_flag_concurrent_fencing
+ libpe_status: deprecate pe_flag_enable_unfencing
+ libpe_status: deprecate pe_flag_have_quorum
+ libpe_status: deprecate pe_flag_have_remote_nodes
+ libpe_status: deprecate pe_flag_have_status
+ libpe_status: deprecate pe_flag_have_stonith_resource
+ libpe_status: deprecate pe_flag_maintenance_mode
+ libpe_status: deprecate pe_flag_no_compat
+ libpe_status: deprecate pe_flag_no_counts
+ libpe_status: deprecate pe_flag_quick_location
+ libpe_status: deprecate pe_flag_sanitized
+ libpe_status: deprecate pe_flag_show_scores
+ libpe_status: deprecate pe_flag_show_utilization
+ libpe_status: deprecate pe_flag_shutdown_lock
+ libpe_status: deprecate pe_flag_startup_fencing
+ libpe_status: deprecate pe_flag_startup_probes
+ libpe_status: deprecate pe_flag_start_failure_fatal
+ libpe_status: deprecate pe_flag_stonith_enabled
+ libpe_status: deprecate pe_flag_stop_action_orphans
+ libpe_status: deprecate pe_flag_stop_everything
+ libpe_status: deprecate pe_flag_stop_rsc_orphans
+ libpe_status: deprecate pe_flag_symmetric_cluster
+ libpe_status: deprecate pe_rsc_allow_migrate
+ libpe_status: deprecate pe_rsc_allow_remote_remotes
+ libpe_status: deprecate pe_rsc_assigning
+ libpe_status: deprecate pe_rsc_block
+ libpe_status: deprecate pe_rsc_critical
+ libpe_status: deprecate pe_rsc_detect_loop
+ libpe_status: deprecate pe_rsc_failed
+ libpe_status: deprecate pe_rsc_failure_ignored
+ libpe_status: deprecate pe_rsc_fence_device
+ libpe_status: deprecate pe_rsc_is_container
+ libpe_status: deprecate pe_rsc_maintenance
+ libpe_status: deprecate pe_rsc_managed
+ libpe_status: deprecate pe_rsc_merging
+ libpe_status: deprecate pe_rsc_needs_fencing
+ libpe_status: deprecate pe_rsc_needs_quorum
+ libpe_status: deprecate pe_rsc_needs_unfencing
+ libpe_status: deprecate pe_rsc_notify
+ libpe_status: deprecate pe_rsc_orphan
+ libpe_status: deprecate pe_rsc_orphan_container_filler
+ libpe_status: deprecate pe_rsc_promotable
+ libpe_status: deprecate pe_rsc_provisional
+ libpe_status: deprecate pe_rsc_reload
+ libpe_status: deprecate pe_rsc_replica_container
+ libpe_status: deprecate pe_rsc_restarting
+ libpe_status: deprecate pe_rsc_runnable
+ libpe_status: deprecate pe_rsc_start_pending
+ libpe_status: deprecate pe_rsc_stop
+ libpe_status: deprecate pe_rsc_stop_unexpected
+ libpe_status: deprecate pe_rsc_unique
* Wed May 24 2023 Ken Gaillot <kgaillot@redhat.com> Pacemaker-2.1.6
- 1124 commits with 402 files changed, 25220 insertions(+), 14751 deletions(-)
- Features added since Pacemaker-2.1.5
+ CIB: deprecate "moon" in date_spec elements in rules
+ CIB: deprecate support for Nagios resources
+ CIB: utilization attributes may be set as transient
+ CIB: alerts and alert recipients support an "enabled" meta-attribute
+ All daemons support --output-as/--output-to options including
XML output with interactive options
+ tools: attrd_updater supports --wait parameter that can be set to
"no" (return immediately after submitting request, which is
the default and previous behavior), "local" (return after the
new value has taken effect on the local node), or "cluster" (return
after new value has taken effect on all nodes)
+ tools: attrd_updater supports -z/--utilization to modify utilization
attributes
+ tools: attrd_updater supports --pattern to affect all attributes
matching a given pattern
+ tools: crm_attribute supports --pattern with permanent node attributes
(in addition to previous support for transient attributes)
+ tools: crm_mon displays resource descriptions if --show-description or
--show-detail is given
+ tools: crm_mon shows maintenance mode when enabled per-resource
+ tools: crm_mon --interval can be used to update XML and text output
(in addition to previous support for HTML)
+ tools: crm_mon fencing history includes microseconds in timestamps
+ tools: crm_mon shows which node it was run on
+ tools: crm_mon shows whether Pacemaker or Pacemaker Remote is running or
shutting down
+ tools: deprecate crm_mon --simple-status
+ tools: crm_resource --element option can be used with --get-parameter,
--set-parameter, and --delete-parameter to modify resource
properties such as class, provider, type, and description
+ tools: crm_resource --list shows resource descriptions better
(including when --output-as=xml is used)
+ tools: crm_shadow supports standard --output-as/--output-to arguments
- Fixes since Pacemaker-2.1.5
+ pacemakerd: -S should wait for cluster to shut down before returning
(regression introduced in 2.1.1)
+ Pacemaker Remote: remote nodes wait for all-clear from cluster before
shutting down (regression introduced in 2.1.5)
+ tools: attrd_updater --query without --node shows attributes from all
nodes instead of local node (regression introduced in 2.1.5)
+ pacemaker-attrd: Preserve a Pacemaker Remote node's transient attributes
if its connection to the cluster is lost but reconnects
+ CIB manager: successful CIB schema upgrade always forces a write
+ controller: avoid election storm when joining node has CIB newer than DC
can accept
+ controller: avoid election storm due to incompatible CIB
+ controller: avoid use-after-free when disconnecting proxy IPCs during shutdown
+ controller: avoid double-incrementing failcount for simulated failures
+ controller: avoid reprobing remote nodes when target is a cluster node
+ controller: delay join finalization if a transition is in progress
+ controller: initial fencing timeout includes any priority-fencing-delay
+ controller: shutdown gracefully if scheduler connection is interrupted
during shutdown
+ fencer: avoid crash during shutdown when action is pending
+ fencer: calculate fencing timeout correctly when watchdog is used with
topology
+ fencer: apply priority-fencing-delay only to first device tried
+ fencer: total and per-device fencing timeouts include any
priority-fencing-delay and pcmk_delay_base
+ scheduler: fix a number of corner cases with colocations, including
preventing a resource from starting if it has a mandatory
colocation with a group whose start is blocked, preventing
optional anti-colocation from overriding infinite stickiness,
and correctly considering a group's colocation dependents
when the group is itself colocated with a clone
+ scheduler: honor as many mandatory colocations as possible before
considering any optional ones
+ scheduler: ensure earlier group member starts occur after later member stops
+ scheduler: handle orderings with bundles more correctly
+ scheduler: ensure expired results never affect resource state
+ scheduler: handle cleaned migrate_from history correctly
+ scheduler: prevent pending monitor of one clone instance from causing
unexpected stop of other instances
+ scheduler: prevent inactive clone instances from starting if probe is
unrunnable on any node
+ agents: SysInfo calculates cpu_load correctly
+ tools: cibadmin --scope accepts status
+ tools: crm_attribute -p "" works same as -p when called from resource agent
+ tools: crm_attribute recognizes "-INFINITY" as value instead of options
+ tools: crm_mon avoids displaying recurring monitors as pending if first
attempt fails
+ tools: crm_mon --daemonize shows disconnected message when CIB connection
is lost instead of continuing to display last known state
+ tools: crm_mon avoids crash when built without curses library support
+ tools: crm_mon supports --output-as=none correctly
+ tools: crm_resource --ban or --move works with single-replica bundles
+ tools: crm_shadow --commit now works with CIB_file
+ tools: crm_simulate failure injection avoids crash if node name is unknown
- Public API changes since Pacemaker-2.1.5
+ Python: New "pacemaker" Python module (packaged as python3-pacemaker in
RPMs built with "make rpm") contains supported public API with
BuildOptions and ExitStatus classes
+ libcib: add client_id() method member to cib_api_operations_t
+ libcib: deprecate cib_database
+ libcib: deprecate cib_quorum_override
+ libcib: deprecate the cib_api_operations_t:update() method
+ libcrmcluster: add pcmk_cluster_new()
+ libcrmcluster: add crm_join_nack_quiet
+ libcrmcluster: add pcmk_cluster_free()
+ libcrmcluster: node argument to send_cluster_message() is now const
+ libcrmcluster: node argument to send_cluster_text() is now const
+ libcrmcommon: add crm_time_usecs
+ libcrmcommon: add PCMK_META_ENABLED
+ libcrmcommon: add pcmk_pacemakerd_state_remote
+ libcrmcommon: add pcmk_rc_bad_xml_patch
+ libcrmcommon: add pcmk_rc_bad_input
+ libcrmcommon: add pcmk_rc_disabled
+ libcrmcommon: deprecate add_xml_nocopy()
+ libcrmcommon: deprecate log_data_element()
+ libcrmcommon: deprecate PCMK_RESOURCE_CLASS_NAGIOS
+ libcrmcommon: deprecate PCMK_RESOURCE_CLASS_UPSTART
+ libcrmcommon: deprecate XML_ATTR_UUID
+ libcrmcommon: deprecate XML_CIB_ATTR_REPLACE
+ libcrmcommon: deprecate xml_log_changes()
+ libcrmcommon: deprecate xml_log_options enum
+ libcrmcommon: deprecate xml_log_patchset()
+ libcrmcommon: argument to pcmk_xe_is_probe() is now const
+ libcrmcommon: argument to pcmk_xe_mask_probe_failure() is now const
+ libcrmcommon: patchset argument of xml_log_patchset() is now const
+ libcrmcommon: rsc_op_expected_rc() argument is now const
+ libcrmcommon: second argument to copy_in_properties() is now const
+ libcrmcommon: xml argument of xml_log_changes() is now const
+ libcrmservice: deprecate enum nagios_exitcode
+ libpacemaker: add pcmk_query_node_info()
+ libpacemaker: add pcmk_query_node_name()
+ libpacemaker: multiple arguments to pcmk_simulate() are now const
+ libpacemaker: node argument to pcmk_resource_digests() is now const
+ libpacemaker: node_types argument to pcmk_list_nodes() is now const
+ libpacemaker: pcmk_controller_status() node name arg is now const
+ libpe_rules: last argument to pe_expand_re_matches() is now const
+ libpe_rules: rule_data argument to pe_eval_nvpairs() is now const
+ libpe_rules: second argument to pe_eval_expr() and pe_eval_subexpr() is now const
+ libpe_rules: second argument to pe_eval_rules() is now const
+ libpe_rules: second argument to pe_unpack_nvpairs() is now const
+ libpe_status: add pe_rsc_detect_loop
+ libpe_status: add pe_rsc_replica_container
+ libpe_status: deprecate fixed member of pe_node_t
+ libpe_status: argument to pe_rsc_is_bundled() is now const
+ libpe_status: argument to rsc_printable_id() is now const
+ libpe_status: first argument to calculate_active_ops() is now const
+ libpe_status: first argument to pe_find_node() is now const
+ libpe_status: first argument to pe_find_node_any() is now const
+ libpe_status: first argument to pe_find_node_id() is now const
+ libpe_status: first argument to resource_object_functions_t:is_filtered() is now const
* Wed Dec 7 2022 Ken Gaillot <kgaillot@redhat.com> Pacemaker-2.1.5
- 1287 commits with 447 files changed, 33546 insertions(+), 21518 deletions(-)
- Features added since Pacemaker-2.1.4
+ CIB: access control lists (ACLs) for groups are supported
+ CIB: ACL target and group XML supports "name" attribute to specify a name
that is not a unique XML ID
+ CIB: deprecate pacemaker-next schema
+ CIB: deprecate first-instance and then-instance in ordering constraints
and rsc-instance and with-rsc-instance in colocation constraints
(only usable with pacemaker-next schema)
+ CIB: deprecate "collocated" and "ordered" meta-attributes for groups
(true is default, and resource sets should be used instead of false)
+ build: support building with -D_TIME_BITS=64
+ build: support building with compilers that are strict about void
+ build: allow building RPMs from source distribution
+ fencer: deprecate stand-alone mode
+ agents: ClusterMon, controld, HealthCPU, ifspeed, and SysInfo agents support
OCF 1.1 standard
+ agents: non-functional SystemHealth agent has been removed
+ tools: non-functional ipmiservicelogd and notifyServicelogEvent tools have
been removed
+ tools: crm_attribute supports querying all attributes on a given node
+ tools: crm_attribute --query, --delete, and --update support
regular expressions
+ tools: crm_error supports standard --output-as/--output-to arguments
+ tools: crm_error lists all return codes if none are specified
+ tools: crm_mon --show-detail displays the CRM feature set of each node
and makes display of fencing actions more technical
+ tools: crm_resource --why checks node health
+ tools: crm_resource --constraints now accepts --recursive (equivalent to
--stack) and --force (to show constraints for a group member
instead of the group)
- Fixes since Pacemaker-2.1.4
+ tools: crm_error does not print spurious output when given a negative
return code argument (regression introduced in 2.0.4)
+ tools: avoid crash if crm_resource is given extraneous arguments
(regression introduced in 2.0.5)
+ tools: stonith_admin --validate XML output shows correct validation status
and errors (regressions introduced in 2.0.5 and 2.1.2)
+ tools: crm_resource --list-operations shows pending operations as pending
instead of complete (regression introduced in 2.1.0)
+ controller: move resources if appropriate after they are reordered in CIB
(regression introduced in 2.1.3)
+ fencing: allow fence devices to be registered if local node is not in CIB
(regression introduced in 2.1.3)
+ tools: crm_mon --one-shot should succeed even if pacemaker is shutting down
(regression introduced in 2.1.3)
+ tools: avoid memory leak in crm_mon (regression introduced in 2.1.3)
+ tools: crm_attribute --quiet outputs nothing instead of "(null)" if
attribute has no value (regression introduced in 2.1.3)
+ tools: accept deprecated and unused attrd_updater --quiet option
(regression introduced in 2.1.3)
+ CIB: avoid crashes when XML IDs grow very long
+ controller: pre-load agent metadata asynchronously to avoid timeout when
agent's metadata action runs crm_node
+ controller: avoid timing issue that increments resource fail count twice
+ fencing: unfence all nodes after device configuration changes
+ fencing: avoid memory leaks when processing topology requests
+ fencing: ignore node that executed action when checking whether actions
are equivalent
+ scheduler,controller: calculate secure digest consistently
+ scheduler: consider roles when blocking colocation dependents
+ scheduler: prioritize group colocations properly
+ scheduler: properly consider effect of "with group" colocations
+ scheduler: handle corner cases in live migrations
+ scheduler: avoid perpetual moving of bundle containers in certain situations
+ scheduler: properly calculate resource parameter digests without history
+ scheduler: do not enforce stop if newer monitor indicates resource was not
running on target of failed migrate_to
+ scheduler: do not enforce stop on rejoined node after failed migrate_to
+ scheduler: don't demote on expected node when multiple-active is set to
stop_unexpected
+ scheduler: prevent resources running on multiple nodes after partial live
migration
+ scheduler: restart resource instead of reload if extra parameters in
operation change
+ schemas: Consider days, minutes, seconds, and yeardays in date expressions
valid
+ schemas: Consider in_range with an end and duration valid
+ schemas: Consider score and score-attribute optional in rules
+ tools: crm_resource --digests uses most recent operation history entry
+ tools: if multiple return code options are given to crm_error, use the
last one
+ tools: crm_resource correctly detects if a resource is unmanaged
or disabled even if there are multiple settings using rules
- Public API changes since Pacemaker-2.1.4
+ libcib: add cib_api_operations_t:set_primary
+ libcib: add cib_api_operations_t:set_secondary
+ libcib: deprecate cib_api_operations_t:delete_absolute()
+ libcib: deprecate cib_api_operations_t:is_master
+ libcib: deprecate cib_api_operations_t:set_master
+ libcib: deprecate cib_api_operations_t:set_slave
+ libcib: deprecate cib_api_operations_t:set_slave_all
+ libcrmcommon: deprecated XML_CIB_TAG_MASTER constant is usable again
(regression introduced in 2.1.0)
+ libcrmcommon: pcmk_ipc_api_t supports attribute manager IPC
+ libcrmcommon: add pcmk_rc_unpack_error
+ libcrmcommon: add CRM_EX_FAILED_PROMOTED
+ libcrmcommon: add CRM_EX_NONE
+ libcrmcommon: add CRM_EX_PROMOTED
+ libcrmcommon: add pcmk_readable_score()
+ libcrmcommon: add PCMK_XA_PROMOTED_MAX_LEGACY string constant
+ libcrmcommon: add PCMK_XA_PROMOTED_NODE_MAX_LEGACY string constant
+ libcrmcommon: argument to crm_time_check() is now const
+ libcrmcommon: argument to pcmk_controld_api_replies_expected() is now const
+ libcrmcommon: argument to pcmk_xml_attrs2nvpairs() is now const
+ libcrmcommon: argument to xml2list() is now const
+ libcrmcommon: argument to xml_acl_denied() is now const
+ libcrmcommon: argument to xml_acl_enabled() is now const
+ libcrmcommon: argument to xml_get_path() is now const
+ libcrmcommon: arguments to crm_time_add() are now const
+ libcrmcommon: arguments to crm_time_compare() are now const
+ libcrmcommon: arguments to crm_time_subtract() are now const
+ libcrmcommon: argv argument to crm_log_preinit() is now char *const *
+ libcrmcommon: crm_time_calculate_duration() arguments are now const
+ libcrmcommon: deprecate CRM_ATTR_RA_VERSION
+ libcrmcommon: deprecate crm_destroy_xml()
+ libcrmcommon: deprecate crm_ipc_server_error
+ libcrmcommon: deprecate crm_ipc_server_info
+ libcrmcommon: deprecate CRM_OP_LRM_QUERY
+ libcrmcommon: deprecate crm_str()
+ libcrmcommon: deprecate PCMK_XE_PROMOTED_MAX_LEGACY string constant
+ libcrmcommon: deprecate PCMK_XE_PROMOTED_NODE_MAX_LEGACY constant
+ libcrmcommon: deprecate score2char()
+ libcrmcommon: deprecate score2char_stack()
+ libcrmcommon: deprecate XML_ATTR_RA_VERSION
+ libcrmcommon: deprecate xml_get_path()
+ libcrmcommon: deprecate XML_PARANOIA_CHECKS
+ libcrmcommon: deprecate XML_TAG_OP_VER_ATTRS
+ libcrmcommon: deprecate XML_TAG_OP_VER_META
+ libcrmcommon: deprecate XML_TAG_RSC_VER_ATTRS
+ libcrmcommon: dt argument of crm_time_get_gregorian() is now const
+ libcrmcommon: dt argument of crm_time_get_isoweek() is now const
+ libcrmcommon: dt argument of crm_time_get_ordinal() is now const
+ libcrmcommon: dt argument of crm_time_get_timeofday() is now const
+ libcrmcommon: dt argument of crm_time_get_timezone() is now const
+ libcrmcommon: first argument to create_reply() is now const
+ libcrmcommon: first argument to crm_copy_xml_element() is now const
+ libcrmcommon: first argument to find_xml_node() is now const
+ libcrmcommon: first argument to get_message_xml() is now const
+ libcrmcommon: first argument to pcmk_ipc_name() is now const
+ libcrmcommon: first argument to xml_patch_versions() is now const
+ libcrmcommon: last argument to crm_write_blackbox() is now const
+ libcrmcommon: add pcmk_rc_duplicate_id
+ libcrmcommon: add pcmk_result_get_strings()
+ libcrmcommon: add pcmk_result_type enum
+ libcrmcommon: add PCMK_XE_DATE_EXPRESSION constant
+ libcrmcommon: add PCMK_XE_OP_EXPRESSION constant
+ libcrmcommon: add PCMK_XE_RSC_EXPRESSION constant
+ libcrmcommon: first argument to crm_time_as_string() is now const
+ libcrmcommon: crm_time_t argument to crm_time_log_alias() is now const
+ libcrmcommon: argument to crm_time_get_seconds() is now const
+ libcrmcommon: argument to crm_time_get_seconds_since_epoch() is now const
+ libcrmcommon: sixth argument to log_data_element() is now const
+ libcrmcommon: source argument to crm_time_set() is now const
+ libcrmcommon: source argument to crm_time_set_timet() is now const
+ libcrmcommon: source argument to pcmk_copy_time() is now const
+ libpacemaker: add pcmk_check_rule()
+ libpacemaker: add pcmk_check_rules()
+ libpacemaker: add pcmk_show_result_code()
+ libpacemaker: add pcmk_list_result_codes()
+ libpacemaker: add pcmk_rc_disp_flags enum
+ libpacemaker: ipc_name argument to pcmk_pacemakerd_status() is now const
+ libpe_rules: deprecate version_expr enum value
+ libpe_rules: second argument to pe_eval_nvpairs() is now const
+ libpe_status: argument to pe_rsc_is_anon_clone() is now const
+ libpe_status: argument to pe_rsc_is_unique_clone() is now const
+ libpe_status: deprecate enum pe_graph_flags
+ libpe_status: first argument to pe_rsc_is_clone() is now const
+ libpe_status: two arguments to get_rsc_attributes() are now const
+ libpe_status: second argument to pe_eval_versioned_attributes() is now const
+ libpe_status: second argument to pe_rsc_params() is now const
+ libstonithd: deprecate stonith_event_t:message
+ libstonithd: deprecate stonith_event_t:type
+ libstonithd: last argument to stonith_api_operations_t:register_device()
is now const
+ libstonithd: last argument to stonith_api_operations_t:register_level() is
now const
+ libstonithd: last argument to
stonith_api_operations_t:register_level_full() is now const
+ libstonithd: params argument to stonith_api_operations_t:validate() is now
const
* Mon Jun 13 2022 Ken Gaillot <kgaillot@redhat.com> Pacemaker-2.1.4
- Changesets: 17
- Diff: 9 files changed, 52 insertions(+), 18 deletions(-)
- Fixes since Pacemaker-2.1.3
+ fencing: get target-by-attribute working again (regression in 2.1.3)
+ fencing: avoid use-after-free when processing self-fencing requests
with topology (regression in 2.1.3)
+ resources: typo in HealthSMART meta-data (regression in 2.1.3)
+ fencing: avoid memory leaks when processing topology requests
+ fencing: delegate shouldn't matter when checking equivalent fencing
+ tools: fix CSS syntax error in crm_mon --output-as=html
* Wed Jun 1 2022 Ken Gaillot <kgaillot@redhat.com> Pacemaker-2.1.3
- Changesets: 814
- Diff: 332 files changed, 23435 insertions(+), 12137 deletions(-)
- Features added since Pacemaker-2.1.2
+ Internal failures of resource actions (such as an OCF agent not being
found) are shown with a detailed exit reason in logs, crm_mon output, etc.
+ Support for CIB <node> entries with type="ping" is deprecated (this was an
undocumented means of defining a quorum-only node)
+ build: configure script supports experimental --enable-nls option to
enable native language translations (currently only Chinese
translations of certain help text are available)
+ rpm: crm_attribute is now part of the pacemaker-cli package instead of
the pacemaker package
+ CIB: resources support allow-unhealthy-nodes meta-attribute to exempt
the resource from bans due to node health checks (particularly useful
for health monitoring resources themselves)
+ CIB: multiple-active cluster property can be set to "stop_unexpected" to
leave the expected instance running and stop only any unexpected ones
+ CIB: bundles support resource utilization
+ pacemakerd: regularly check that subdaemons are active and accepting IPC
connections so sbd can self-fence a node with a malfunctioning
subdaemon
+ pacemaker-schedulerd: support --output-as/--output-to options including
XML output with interactive options
+ tools: cibadmin --show-access option to show CIB colorized for ACLs
+ tools: crm_attribute supports standard --output-as/--output-to options
+ tools: crm_mon output indicates if a node's health is yellow or red
+ tools: for probes that failed because the service is not installed or
locally configured, crm_mon displays the resource as stopped rather
than failed
+ tools: crm_rule supports standard --output-as/--output-to options,
allows passing multiple -r options, and is no longer experimental
+ tools: stonith_admin fencing commands display reasons for failures
+ resource agents: HealthSMART supports OCF 1.1 standard and new
OCF_RESKEY_dampen and OCF_RESKEY_smartctl parameters
- Fixes since Pacemaker-2.1.2
+ build: avoid circular library dependency (regression introduced in 2.1.0)
+ systemd: if pacemakerd exits immediately after starting, wait 1 second
before trying to respawn, and allow 5 attempts
+ fencer: get fencing completion time correctly
(regression introduced in 2.1.2)
+ fencer: avoid memory leak when broadcasting history differences
(regression introduced in 2.1.0)
+ controller: correctly match "node down" events so remote nodes don't get
fenced when connection is stopped
(regression introduced in 2.1.2)
+ executor: avoid possible double free during notify operation
(regression introduced in 2.1.1)
+ tools: get stonith_admin -T/--tag option working again
(regression introduced in 2.0.3)
+ resources: use correct syntax in Stateful meta-data
(regression introduced in 2.1.0)
+ corosync: repeat corosync_cfg_trackstart if first attempt fails
+ libcrmcommon: retry IPC requests after EAGAIN errors
+ executor,scheduler: treat "no secrets" fence results as a hard error
+ fencing: handle dynamic target query failures better
+ fencing: don't set stonith action to pending if fork fails
+ pacemakerd: avoid race condition when subdaemaon is checked while exiting
+ scheduler: avoid memory leak when displaying clones in certain conditions
+ scheduler: properly set data set flags when scheduling actions
+ tools: support command-line crm_attribute calls on Pacemaker remote nodes
whose node name in the cluster differs from their local hostname
+ tools: prevent possible crm_resource crashes if multiple commands specified
- Public API changes since Pacemaker-2.1.2
+ libcrmcommon: pcmk_ipc_api_t supports scheduler IPC
+ libpacemaker: add pcmk_status() (equivalent to crm_mon)
+ libcib: deprecate get_object_parent()
+ libcib: deprecate get_object_path()
+ libcib: deprecate get_object_root()
+ libcrmcommon: add pcmk_cib_parent_name_for()
+ libcrmcommon: add pcmk_cib_xpath_for()
+ libcrmcommon: add pcmk_find_cib_element()
+ libcrmcommon: deprecate crm_xml_add_boolean()
+ libpe_status: add pe_flag_check_config
+ libpe_status: add pe_node_shared_s:data_set
+ libpe_status: add pe_rsc_restarting flag
+ libpe_status: add pe_rsc_stop_unexpected flag
+ libpe_status: add recovery_stop_unexpected to enum rsc_recovery_type
+ libpe_status: deprecate node_ping
+ libpe_status: deprecate pe_order_stonith_stop
+ libpe_status: deprecate pe_rsc_starting and pe_rsc_stopping
+ libstonithd: add exit_reason member to stonith_history_t
+ libstonithd: deprecate stonith_t:call_timeout
+ libstonithd: stonith_api_del_notification() with NULL second argument
removes all notifications
* Tue Nov 23 2021 Ken Gaillot <kgaillot@redhat.com> Pacemaker-2.1.2
- Changesets: 462
- Diff: 223 files changed, 16518 insertions(+), 11743 deletions(-)
- Features added since Pacemaker-2.1.1
+ build: when built with --with-initdir, Pacemaker uses the value to find
LSB resources (in addition to being where Pacemaker's own
init scripts are installed)
+ build: cmocka is new dependency for unit tests ("make check")
+ rpm: fence_watchdog now comes with pacemaker package (not pacemaker-cli)
+ daemons: metadata for cluster options supports OCF 1.1 standard
+ executor: nagios warning results now map to OCF "degraded" result code
+ fencing: pcmk_delay_base can optionally specify different delays per node
+ fencing: pcmk_host_map supports escaped characters such as spaces in values
+ resources: HealthIOWait agent supports OCF 1.1 standard, and validate works
+ tools: crm_mon shows exit reasons for actions failed due to internal errors
+ tools: crm_mon failed action display is more human-friendly by default
+ tools: crm_resource --force-* now outputs exit reasons if available
- Fixes since Pacemaker-2.1.1
+ pkg-config: return correct value for ocfdir (regression introduced in 2.1.0)
+ tools: fix crm_mon --hide-headers and related options
(regression introduced in 2.0.4)
+ attrd: check election status upon node loss to avoid election timeout
+ controller: improved handling of executor connection failures
+ executor: properly detect systemd unit existence
+ pacemakerd: recover properly from Corosync crash
+ fencing: fencing results are now sorted with sub-second resolution
+ fencing: fix fence_watchdog version output, metadata output, and man page
+ fencing: mark state as done if remapped "on" times out
+ tools: map LSB status to OCF correctly with crm_resource --force-check
- Public API changes since Pacemaker-2.1.1
+ libcrmcommon: deprecate PCMK_OCF_EXEC_ERROR
+ libcrmcommon: deprecate PCMK_OCF_PENDING
+ libcrmcommon: deprecate PCMK_OCF_SIGNAL
+ libcrmcommon: add CRM_EX_DEGRADED and CRM_EX_DEGRADED_PROMOTED
+ libcrmcommon: add enum pcmk_exec_status
+ libcrmcommon: add PCMK_EXEC_MAX
+ libcrmcommon: add PCMK_EXEC_NO_FENCE_DEVICE
+ libcrmcommon: add PCMK_EXEC_NO_SECRETS
+ libcrmcommon: add pcmk_exec_status_str()
+ libcrmcommon: add pcmk_rc2ocf()
+ libcrmcommon: deprecate PCMK_OCF_TIMEOUT
+ libcrmservice: add services_result2ocf()
+ libcrmservice: deprecate enum op_status
+ libcrmservice: deprecate LSB_ROOT_DIR
+ libcrmservice: deprecate NAGIOS_NOT_INSTALLED
+ libcrmservice: deprecate NAGIOS_STATE_DEPENDENT
+ libcrmservice: deprecate services_get_ocf_exitcode()
+ libcrmservice: deprecate services_list() and services_action_create()
+ libcrmservice: deprecate services_lrm_status_str()
+ libpacemaker: add enum pcmk_sim_flags
+ libpacemaker: add pcmk_injections_t
+ libpacemaker: add pcmk_free_injections()
+ libpacemaker: add pcmk_simulate()
+ libstonithd: add opaque member to stonith_event_t
+ libstonithd: add opaque member to stonith_callback_data_t
* Thu Sep 09 2021 Ken Gaillot <kgaillot@redhat.com> Pacemaker-2.1.1
- Changesets: 231
- Diff:
102 files changed, 4912 insertions(+), 3428 deletions(-)
- Features added since Pacemaker-2.1.0
+ enhanced support for OCF Resource Agent API 1.1 standard
+ ocf:pacemaker:attribute and ocf:pacemaker:ping agents now support 1.1
+ tools: crm_resource passes output format to agents so they will use it if
supported
+ tools: crm_resource --validate and --force-check options accept optional
check level to pass to agent
+ tools: crm_mon XML output includes stonith-timeout-ms and
priority-fencing-delay-ms cluster properties
+ pacemakerd: support --output-as/--output-to options including XML output
with interactive options such as --features
- Fixes since Pacemaker-2.1.0
+ pacemaker-attrd: avoid repeated unfencing of remote nodes when DC joined
cluster after remote was up
+ controller: ensure newly joining node learns the node names of non-DCs
+ controller: ensure lost node's transient attributes are cleared without DC
+ scheduler: avoid invalid transition when group member is unmanaged
(CLBZ#5423)
+ scheduler: don't schedule probes of unmanaged resources on pending nodes
+ executor: avoid crash after TLS connection errors
(regression introduced in 2.0.4)
+ fencing: avoid repeated attempts to get (nonexistent) meta-data for
watchdog device (regression introduced in 2.1.0)
+ fencing: select correct device when pcmk_host_check="dynamic-list" and
pcmk_host_map are both specified (CLBZ#5474)
+ tools: crm_attribute supports node attribute values starting with a '-'
again (regression introduced in 2.1.0)
+ tools: crm_attribute deprecated --get-value option does not require an
argument (regression introduced in 2.1.0)
+ tools: avoid crm_mon memory leaks when filtering by resource or node
(regressions introduced in 2.0.4 and 2.0.5)
+ tools: exit with status 0 (not 64) for --version argument to crm_rule,
crm_error, crm_diff, and crm_node (regression introduced in 2.0.4)
and crm_attribute (regression introduced in 2.1.0)
+ tools: crm_mon should show active unmanaged resources on offline nodes
without requiring -r/--inactive
+ tools: better crm_resource error messages for unsupported resource types
+ tools: crm_simulate --show-failcounts includes all relevant information
+ tools: crm_mon should not show inactive group members without --inactive
+ tools: crm_mon XML output should show members of cloned groups
+ libcrmcommon: correctly handle case-sensitive XML IDs
- Public API changes since Pacemaker-2.1.0
+ libcrmcommon: add pcmk_section_e type
+ libcrmcommon: add pcmk_show_opt_e type
+ libcrmcommon: add pcmk_pacemakerd_api_shutdown()
+ libpe_status: deprecate enum pe_print_options
* Tue Jun 08 2021 Ken Gaillot <kgaillot@redhat.com> Pacemaker-2.1.0
- Changesets: 849
- Diff: 327 files changed, 22089 insertions(+), 12633 deletions(-)
- Features added since Pacemaker-2.0.5
+ support for OCF Resource Agent API 1.1 standard
- allow Promoted and Unpromoted role names in CIB (in addition to Master
and Slave, which are deprecated), and use new role names in output,
logs, and constraints created by crm_resource --ban
- advertise 1.1 support to agents, and provide notify_promoted_* and
notify_unpromoted_* environment variables to agents with notify actions
- support "reloadable" parameter attribute and "reload-agent" action in
agents that advertise 1.1 support
- support 1.1 standard in ocf:pacemaker:Dummy, ocf:pacemaker:remote, and
ocf:pacemaker:Stateful resource agents
- add "promoted-only" (in addition to "master-only", which is deprecated)
in crm_mon XML output for bans
+ support for noncritical resources
- colocation constraints accept an "influence" attribute that determines
whether dependent influences main resource's location (the default of
"true" preserves the previous behavior, while "false" makes the
dependent stop if it reaches its migration-threshold in failures rather
than cause both resources to move to another node)
- resources accept a "critical" meta-attribute that serves as default for
all colocation constraints involving the resource as the dependent, as
well as groups involving the resource
+ detail log uses millisecond-resolution timestamps when Pacemaker is built
with libqb 2.0 or later
+ CIB: deprecate the remove-after-stop cluster property, can_fail action
meta-attribute, and support for Upstart-based resources
+ controller: the PCMK_panic_action environment variable may be set to
sync-crash or sync-reboot to attempt to synchronize local
disks before crashing or rebooting, which can be helpful to
record cached log messages but runs the risk of the sync
hanging and leaving the host running after a critical error
+ tools: CIB_file="-" can be used to get the CIB from standard input
+ tools: crmadmin, crm_resource, crm_simulate, and crm_verify support
standard --output-as/--output-to options (including XML output,
intended for parsing by scripts and higher-level tools)
+ tools: crm_attribute accepts -p/--promotion option to operate on
promotion score (replacing crm_master, which is deprecated)
+ tools: crm_resource accepts --promoted option (replacing --master, which
is deprecated)
+ tools: crm_resource accepts --digests advanced option
+ tools: crm_simulate accepts --show-attrs and --show-failcounts options
- Build process changes since Pacemaker-2.0.5
+ Pacemaker requires newer versions of certain dependencies, including
Python 3.2 or later (support for Python 2 has been dropped), glib 2.32.0
or later, libqb 0.17.0 or later, GnuTLS 2.12.0 or later (to enable
Pacemaker Remote support), rpm 4.11.0 (if building RPMs), and a C library
that provides setenv() and unsetenv()
+ configure: --enable-legacy-links (which is deprecated) defaults to "no",
meaning that symbolic links will not be created for the
Pacemaker 1 daemon names
+ configure: --enable-compat-2.0 prevents certain output changes (most
significantly role names) to maintain compatibility with older
tools, scripts, and resource agents that rely on previous output
+ configure: --with-resource-stickiness-default sets a resource-stickiness
default in newly created CIBs
+ configure: --with-concurrent-fencing-default specifies default for
concurrent-fencing cluster property
+ configure: --with-sbd-sync-default specifies default for syncing start-up with sbd
+ configure: --with-ocfrapath specifies resource agent directories to search
+ configure: --with-ocfrainstalldir specifies where to install ocf:pacemaker agents
+ configure: --with-gnutls="no" explicitly disables support for
Pacemaker Remote and the remote-tls-port cluster property
+ configure: --with-acl has been removed (support for ACLs is always built)
+ configure: deprecated --with-pkgname, --with-pkg-name, --with-brand,
--enable-ansi, and --enable-no-stack options have been removed
+ environment variables file (typically /etc/sysconfig/pacemaker or
/etc/default/pacemaker) will be installed when "make install" is run
+ documentation has dependency on python3-sphinx instead of publican, and is
generated beneath doc/sphinx
- Fixes since Pacemaker-2.0.5
+ controller: always refresh agent meta-data after start, in case agent was
updated (regression introduced in 1.1.18)
+ tools: avoid crash when running crm_mon in daemonized mode with CGI output
(regression introduced in 2.0.3)
+ tools: correctly treat unspecified node as all nodes instead of local node
when attrd_updater --query or crm_resource --cleanup is run on a
Pacemaker Remote node (regressions introduced in 1.1.14 and 1.1.17)
+ tools: exit with status 0 (not 64) for --version argument to crm_simulate
(regression introduced in 2.0.4) and crm_resource and crmadmin
(regression introduced in 2.0.5)
+ pacemaker-attrd: avoid race condition where transient attributes for a
leaving node could be reinstated when the node rejoins,
potentially causing a node that was just rebooted to exit
the cluster immediately after rejoining
+ controller,scheduler: fix year 2038 issues affecting shutdowns,
remote node fencing, last-rc-change, and
ticket last-granted dates
+ controller: retry scheduler connection after failure, to avoid cluster
stopping on a node without stopping resources (clbz#5445)
+ fencing: avoid pending fencing entry getting "stuck" in history if
originating node was unreachable when result was received
+ fencing: retry getting agent meta-data if initial attempt fails
+ fencing: detect when devices have been removed from configuration
+ scheduler: constrain clone-min, clone-max, clone-node-max, promoted-max,
and promoted-node-max options to non-negative values
+ scheduler: constrain resource priorities and node-health-base to score range
+ scheduler: treat invalid duration fields in time-based rules as 0, not -1
+ scheduler: node attribute rule expressions with a value-source of "param"
or "meta" work when rsc or rsc-pattern with an inverted match
is given, as well as when rsc-pattern with a regular
match is given
+ scheduler: node attribute rule expressions with a value-source of "param"
work with a resource parameter that itself is determined by a
node attribute rule expression
+ scheduler: avoid remote connection shutdown hanging when connection
history for node hosting connection is not last in CIB status
+ scheduler: route monitor cancellations behind moving remote connections correctly
+ libcrmcommon: avoid potential integer overflow when adding seconds to times
+ tools: cibsecret syncs to remote nodes and guest nodes as well as
cluster nodes
+ tools: show other available cluster information in crm_mon even if
fence history is not available
+ tools: retry failed fencer and CIB connections in crm_mon
+ tools: crm_mon reports if Pacemaker is waiting for sbd at start-up
+ tools: respect rules when showing node attributes in crm_mon
+ tools: improve messages when crm_mon is run on disconnected remote node
+ tools: constrain node IDs to non-negative values for crm_node -N
+ tools: crm_node -l on restarted node works even when Corosync 2 is used
without node names specified in Corosync configuration
+ tools: fix issues in calculation of non-sensitive resource parameter
digests that made crm_simulate wrongly think configuration changed
- C API changes since Pacemaker-2.0.5
+ all: new PCMK_ALLOW_DEPRECATED constant controls API availability
+ libcrmcluster: deprecate crm_terminate_member()
+ libcrmcluster: deprecate crm_terminate_member_no_mainloop()
+ libcrmcommon: add CRMD_ACTION_RELOAD_AGENT string constant
+ libcrmcommon: add PCMK_OCF_MAJOR_VERSION string constant
+ libcrmcommon: add PCMK_OCF_MINOR_VERSION string constant
+ libcrmcommon: add PCMK_OCF_RUNNING_PROMOTED enum value
+ libcrmcommon: add PCMK_OCF_VERSION string constant
+ libcrmcommon: add PCMK_XE_PROMOTABLE_LEGACY string constant
+ libcrmcommon: add PCMK_XE_PROMOTED_MAX_LEGACY string constant
+ libcrmcommon: add PCMK_XE_PROMOTED_NODE_MAX_LEGACY string constant
+ libcrmcommon: add enum ocf_exitcode (moved from libcrmservice)
+ libcrmcommon: deprecate __builtin_expect()
+ libcrmcommon: deprecate __likely()
+ libcrmcommon: deprecate __unlikely()
+ libcrmcommon: deprecate crm_atoi()
+ libcrmcommon: deprecate crm_build_path()
+ libcrmcommon: deprecate crm_config_error global variable
+ libcrmcommon: deprecate crm_config_warning global variable
+ libcrmcommon: deprecate crm_ftoa()
+ libcrmcommon: deprecate crm_hash_table_size()
+ libcrmcommon: deprecate crm_itoa()
+ libcrmcommon: deprecate crm_itoa_stack()
+ libcrmcommon: deprecate crm_log_cli_init()
+ libcrmcommon: deprecate crm_parse_int()
+ libcrmcommon: deprecate crm_parse_ll()
+ libcrmcommon: deprecate crm_str_hash()
+ libcrmcommon: deprecate crm_str_table_dup()
+ libcrmcommon: deprecate crm_str_table_new()
+ libcrmcommon: deprecate crm_strcase_equal()
+ libcrmcommon: deprecate crm_strcase_hash()
+ libcrmcommon: deprecate crm_strcase_table_new()
+ libcrmcommon: deprecate crm_strip_trailing_newline()
+ libcrmcommon: deprecate crm_ttoa()
+ libcrmcommon: deprecate EOS constant
+ libcrmcommon: deprecate GListPtr type
+ libcrmcommon: deprecate g_str_hash_traditional()
+ libcrmcommon: deprecate MAX_IPC_DELAY constant
+ libcrmcommon: deprecate pcmk_format_named_time()
+ libcrmcommon: deprecate pcmk_format_nvpair()
+ libcrmcommon: deprecate pcmk_numeric_strcasecmp()
+ libcrmcommon: deprecate PCMK_OCF_DEGRADED_MASTER enum value
+ libcrmcommon: deprecate PCMK_OCF_FAILED_MASTER enum value
+ libcrmcommon: deprecate PCMK_OCF_RUNNING_MASTER enum value
+ libcrmcommon: deprecate pcmk_scan_nvpair()
+ libcrmcommon: deprecate XML_CIB_TAG_MASTER string constant
+ libcrmcommon: deprecate XML_RSC_ATTR_MASTER_MAX string constant
+ libcrmcommon: deprecate XML_RSC_ATTR_MASTER_NODEMAX string constant
+ libcrmservice: enum ocf_exitcode is obtained from libcrmcommon
+ libpacemaker: add pcmk_controller_status() function
+ libpacemaker: add pcmk_designated_controller() function
+ libpacemaker: add pcmk_list_nodes() function
+ libpacemaker: add pcmk_pacemakerd_status() function
+ libpacemaker: add pcmk_resource_digests() function
+ libpe_status: add parameter_cache member to pe_resource_t
+ libpe_status: add pe_order_promoted_implies_first enum value
+ libpe_status: add pe_rsc_params()
+ libpe_status: add RSC_ROLE_PROMOTED enum value
+ libpe_status: add RSC_ROLE_PROMOTED_LEGACY_S string constant
+ libpe_status: add RSC_ROLE_PROMOTED_S string constant
+ libpe_status: add RSC_ROLE_UNPROMOTED enum value
+ libpe_status: add RSC_ROLE_UNPROMOTED_LEGACY_S string constant
+ libpe_status: add RSC_ROLE_UNPROMOTED_S string constant
+ libpe_status: add priv member to pcmk_working_set_t, for Pacemaker use only
+ libpe_status: deprecate pe_order_implies_first_master enum value
+ libpe_status: deprecate pe_print_details enum value
+ libpe_status: deprecate pe_print_dev enum value
+ libpe_status: deprecate pe_print_html enum value
+ libpe_status: deprecate pe_print_log enum value
+ libpe_status: deprecate pe_print_max_details enum value
+ libpe_status: deprecate pe_print_ncurses enum value
+ libpe_status: deprecate pe_print_xml enum value
+ libpe_status: deprecate pe_resource_t parameters member
+ libpe_status: deprecate RSC_ROLE_MASTER enum value
+ libpe_status: deprecate RSC_ROLE_MASTER_S string constant
+ libpe_status: deprecate RSC_ROLE_SLAVE enum value
+ libpe_status: deprecate RSC_ROLE_SLAVE_S string constant
+ libpe_status: ignore ->parameter() resource object function's create argument
* Wed Dec 02 2020 Chris Lumens <clumens@redhat.com> Pacemaker-2.0.5
- Changesets: 534
- Diff: 286 files changed, 23133 insertions(+), 14626 deletions(-)
- Features added since Pacemaker-2.0.4
+ configuration: Add type="integer" to rule elements, allowing for
specifying 64-bit integers and specifying
double-precision floating point numbers when
type="number".
+ daemons: Recognize new OCF agent status codes 190 (degraded) and 191
(degraded master) to be treated as success but displayed as
errors.
+ sbd-integration: support SBD_SYNC_RESOURCE_STARTUP environment
variable to better synchronize Pacemaker start-up
and shutdown with SBD
+ scheduler: Add rule-based tests to op_defaults and rsc_defaults.
+ scheduler: Add on-fail=demote and no-quorum-policy=demote recovery
policies for promoted resources.
+ tools: Add --resource= to filter crm_mon output for a resource.
+ tools: Add -P to crmadmin to show pacemakerd status.
+ tools: In cibsecret, read value to set from input (or stdin) if not specified.
- Fixes for regressions introduced in Pacemaker-2.0.4
+ tools: Add the node name back to bundle instances in crm_mon.
+ tools: get stonith_admin --list-targets working again
- Fixes for regressions introduced in Pacemaker-2.0.3
+ tools: Fix adding HTTP headers to crm_mon in daemon mode.
+ tools: Show expected score of ping attributes in crm_mon XML output
- Fixes for regressions introduced in Pacemaker-2.0.1
+ scheduler: require pre-/post-start notifications correctly.
- Changes since Pacemaker-2.0.4
+ Prevent the bypassing of ACLs by direct IPC (CVE-2020-25654)
+ build: Fix a build issue on Fedora s390x.
+ build: Fix python2 vs. python3 packaging problems on openSUSE Tumbleweed
+ build: Update pkgconfig files for CI testing
+ controller: avoid recovery delay when shutdown locks expire
+ controller: Log correct timeout for timed-out stonith monitor
+ fencer: avoid infinite loop if device is removed during operation
+ fencer: avoid possible use-of-NULL when parsing metadata
+ libfencing: add `port` or `plug` parameter according to metadata on
`validate` if no `pcmk_host_argument` specified
+ libfencing: respect `pcmk_host_argument=none` on `validate`
+ scheduler: disallow on-fail=stop for stop operations
+ scheduler: don't schedule a dangling migration stop if one already occurred
+ scheduler: don't select instance to be promoted on a guest that can't run
+ scheduler: fix build when DEFAULT_CONCURRENT_FENCING_TRUE is set
+ scheduler: Remove pe_print_expanded_xml print option.
+ scheduler: Use pcmk_monitor_timeout as stonith start timeout
+ tools: Add management status to crm_mon's group output.
+ tools: Add "No active resources" to one case in crm_mon output.
+ tools: Allow tags and alerts in cibadmin --scope
+ tools: Avoid crm_node on Pacemaker Remote nodes failing when other
executor actions are occurring.
+ tools: Avoid pending fence actions getting stuck in crm_mon display
+ tools: "Connectivity is lost" may not be displayed even if the ping
communication is lost.
+ tools: Display stop-all-resources in crm_mon's cluster options.
+ tools: don't use pssh -q option in cibsecret unless supported
+ tools: Fix adding the http-equiv header to crm_mon in daemon mode.
+ tools: If a clone or group is disabled, display that in crm_mon as part
of the resource's header.
+ tools: crm_node -l and -p now work from Pacemaker Remote nodes
+ tools: Don't display crm_resource error messages twice.
+ tools: Print inactive resources by default with crm_mon xml output.
+ tools: properly detect local node name in cibsecret
+ tools: Revert some crm_resource string-related checks on variables
that aren't strings.
+ tools: Use bash in cibsecret
+ xml: Mark new crm_mon attributes as optional in schema
* Mon Jun 15 2020 Klaus Wenninger <klaus.wenninger@aon.at> Pacemaker-2.0.4
- Changesets: 515
- Diff: 269 files changed, 22560 insertions(+), 13726 deletions(-)
- Features added since Pacemaker-2.0.3
+ build: Add support for glib-based unit tests.
+ controller: add new feature 'shutdown-locks'
Optionally allow a gracefully shutdown node to have the resources
locked to it for a configurable time.
So that it can be restarted with exactly the same resources
running as before.
+ controller/fencing/scheduler: add new feature 'priority-fencing-delay'
Optionally derive the priority of a node from the resource-priorities
of the resources it is running.
In a fencing-race the node with the highest priority has a certain
advantage over the others as fencing requests for that node are
executed with an additional delay.
controlled via cluster option priority-fencing-delay (default = 0)
+ stonith_admin: add --delay option (default = 0) to support enforced
fencing delay
+ tools: Add --include= and --exclude= to crm_mon.
+ tools: Add --node= to filter crm_mon output for a node (or tag).
+ tools: Allow more fine grained filtering of fence-history in crm_mon.
+ tools: Allow crm_rule to check some date_specs.
- Fixes for regressions introduced in Pacemaker-2.0.0
+ tools: ensure that getting the local node name using crm_node
always works from Pacemaker Remote node command line
- Changes since Pacemaker-2.0.3
+ build: improve checking headers for C++ fitness
+ build: restore build on latest OpenSUSE
+ fencing: Report an error getting history in output instead of empty history
+ fencing: Improve parameter handling for RHCS-style fence-agents
- make parameter `action` shown as not required
- add `port` or `plug` parameter according to metadata
- `plug` parameter shown as non-required in the metadata
+ controller: clear leaving node's transient attributes even if there is no DC
+ controller: don't ack same request twice
+ iso8601: Fix crm_time_parse_offset() to parse offset with plus sign.
+ libcrmcommon, libpe: validate interval specs correctly
+ libcrmcommon: Add pcmk_str_is_infinity, pcmk_str_is_minus_infinity and
pcmk__unregister_formats.
+ libcrmcommon: Extend what pcmk__split_range can do.
+ libfencing: Export formatted output functions.
+ libpe_status: Add node list arg to output messages preventing weird
behavior + potential segfaults
+ libpe_status: Update the maint mode message for HTML output.
+ fencing, tools: Fix arguments to stonith-event.
+ scheduler: don't incorporate dependencies' colocations multiple times
+ scheduler: ensure attenuated scores still have some effect
+ scheduler: ignore colocation constraints with 0 score
+ scheduler: make sure cluster-wide maintenance-mode=true overrides
per-resource settings
+ scheduler: properly detect whether guest node is fenceable
+ scheduler: do not differentiate case where all the nodes have equal priority
+ tests: Add tests for pe_cron_range_satisfied.
+ tests: Add tests for the current behavior of pcmk__split_range.
+ tools, lib: Use standard pacemaker return codes in crm_rule.
+ tools: Correct stonith-event arguments in crm_mon.
+ tools: Fix man pages for crm_mon & crm_diff.
+ tools: Make crm_mon --interval understand more formats.
+ tools: Fix --html-title= in crm_mon.
+ tools: Print errors to stderr for crm_mon's legacy xml.
+ tools: use return codes consistently in stonith_admin
+ tools: Use glib for cmdline handling in crm_diff, crm_simulate & crm_error
+ xml: Add a new version of the tags schema.
+ based: populate cib_nodes when 'cibadmin -R -scope=configuration'
+ cibsecret: don't use pssh -q option unless supported
+ fencing: avoid infinite loop if device is removed during operation
+ fencing: avoid possible use-of-NULL when parsing metadata
+ fencing: Remove dangling 'pending' for completed DC fencing. (CLBZ#5401)
* Mon Nov 25 2019 Ken Gaillot <kgaillot@redhat.com> Pacemaker-2.0.3
- Changesets: 601
- Diff: 227 files changed, 17862 insertions(+), 10471 deletions(-)
- Features added since Pacemaker-2.0.2
+ controller: new 'fence-reaction' cluster option specifies whether local node
should 'stop' or 'panic' if notified of own fencing
+ controller: more cluster properties support ISO 8601 time specifications
+ controller: calculate cluster recheck interval dynamically when possible
+ Pacemaker Remote: allow file for environment variables when used in bundle
+ Pacemaker Remote: allow configurable listen address and TLS priorities
+ tools: crm_mon now supports standard --output-as/--output-to options
+ tools: crm_mon HTML output supports user-defined CSS stylesheet
+ tools: stonith_admin supports HTML output in addition to text and XML
+ tools: crm_simulate supports --repeat option to repeat profiling tests
+ tools: new pcmk_simtimes tool compares crm_simulate profiling output
+ agents: SysInfo supports K, T, and P units in addition to Kb and G
- Changes since Pacemaker-2.0.2
+ fencer: do not block concurrent fencing actions on a device
(regression since 2.0.2)
+ all: avoid Year 2038 issues
+ all: allow ISO 8601 strings of form "<date>T<time> <offset>"
+ rpm: pacemaker-cts package now explicitly requires pacemaker-cli
+ controller: set timeout on scheduler responses to avoid infinite wait
+ controller: confirm cancel of failed monitors, to avoid transition timeout
+ executor: let controller cancel monitors, to avoid transition timeout
+ executor: return error for stonith probes if stonith connection was lost
+ fencer: ensure concurrent fencing commands always get triggered to execute
+ fencer: fail pending actions and re-sync history after crash and restart
+ fencer: don't let command with long delay block other pending commands
+ fencer: allow functioning even if CIB updates arrive unceasingly
+ scheduler: wait for probe actions to complete to prevent unnecessary
restart/re-promote of dependent resources
+ scheduler: avoid invalid transition when guest node host is not fenceable
+ scheduler: properly detect dangling migrations, to avoid restart loop
+ scheduler: avoid scheduling actions on remote node that is shutting down
+ scheduler: avoid delay in recovery of failed remote connections
+ scheduler: clarify action failure log messages by including failure time
+ scheduler: calculate secure digests for unfencing, for replaying saved CIBs
+ libcrmcommon: avoid possible use-of-NULL when applying XML diffs
+ libcrmcommon: correctly apply XML diffs with multiple move/create changes
+ libcrmcommon: return error when applying XML diffs with unknown operations
+ tools: avoid duplicate lines between nodes in crm_simulate dot graph
+ tools: count disabled/blocked resources correctly in crm_mon/crm_simulate
+ tools: crm_mon --interval now accepts ISO 8601 and has correct help
+ tools: organize crm_mon text output with list headings, indents, bullets
+ tools: crm_report: fail if tar is not available
+ tools: crm_report: correct argument parsing
+ tools: crm_report: don't ignore log if unrelated file is too large
+ tools: stonith_admin --list-targets should show what fencer would use
+ agents: calculate #health_disk correctly in SysInfo
+ agents: handle run-as-user properly in ClusterMon
* Tue Jun 04 2019 Ken Gaillot <kgaillot@redhat.com> Pacemaker-2.0.2
- Changesets: 288
- Diff: 225 files changed, 28494 insertions(+), 24465 deletions(-)
- Features added since Pacemaker-2.0.1
+ tools: crm_resource --validate can get resource parameters from command line
+ tools: crm_resource --clear prints out any cleared constraints
+ tools: new crm_rule tool for checking rule expiration (experimental)
+ tools: stonith_admin supports XML output for machine parsing (experimental)
+ resources: new HealthIOWait resource agent for node health tracking
- Changes since Pacemaker-2.0.1
+ Important security fixes for CVE-2018-16878, CVE-2018-16877, CVE-2019-3885
+ build: crm_report bug report URL is now configurable at build time
+ build: private libpengine/libtransitioner libraries combined as libpacemaker
+ controller: avoid memory leak when duplicate monitor is scheduled
+ scheduler: respect order constraints when resources are being probed
+ scheduler: one group stop shouldn't make another required
+ libcrmcommon: handle out-of-range integers in configuration better
+ libcrmcommon: export logfile environment variable if using default
+ libcrmcommon: avoid segmentation fault when beginning formatted text list
+ libcrmservice: fix use-after-free memory error in alert handling
+ libstonithd: handle more than 64KB output from fence agents
* Mon Mar 4 2019 Ken Gaillot <kgaillot@redhat.com> Pacemaker-2.0.1
- Changesets: 592
- Diff: 173 files changed, 9268 insertions(+), 5344 deletions(-)
- Features added since Pacemaker-2.0.0
+ Pacemaker bundles support podman for container management
+ fencing: SBD may be used in a cluster that has guest nodes or bundles
+ fencing: fencing history is synchronized among all nodes
+ fencing: stonith_admin has option to clear fence history
+ tools: crm_mon can show fencing action failures and history
+ tools: crm_resource --clear supports new --expired option
+ Pacemaker Remote: new options to restrict TLS Diffie-Hellman prime length
- Changes since Pacemaker-2.0.0
+ scheduler: clone notifications could be scheduled for a stopped
Pacemaker Remote node and block all further cluster actions
(regression since 2.0.0)
+ libcrmcommon: correct behavior for completing interrupted live migrations
(regression since 2.0.0)
+ tools: crm_resource -C could fail to clean up all failures in one run
(regression since 2.0.0)
+ Pacemaker Remote: avoid unnecessary downtime when moving resource to
Pacemaker Remote node that fails to come up (regression since 1.1.18)
+ tools: restore stonith_admin ability to confirm unseen nodes are down
(regression since 1.1.12)
+ build: minor logging fixes to allow compatibility with GCC 9 -Werror
+ build: spec file now puts XML schemas in new pacemaker-schemas package
+ build: spec file now provides virtual pcmk-cluster-manager package
+ pacemaker-attrd: wait a short time before re-attempting failed writes
+ pacemaker-attrd: ignore attribute delays when writing after node (re-)join
+ pacemaker-attrd: start new election immediately if writer is lost
+ pacemaker-attrd: clear election dampening when the writer leaves
+ pacemaker-attrd: detect alert configuration changes when CIB is replaced
+ CIB: inform originator of CIB upgrade failure
+ controller: support resource agents that require node name even for meta-data
+ controller: don't record pending clone notifications in CIB
+ controller: DC detects completion of another node's shutdown more accurately
+ controller: shut down DC if unable to update node attributes
+ controller: handle corosync peer/join notifications for new node in any order
+ controller: clear election dampening when DC is lost
+ executor: cancel recurring monitors if fence device registration is lost
+ fencing: check for fence device update when resource defaults change
+ fencing: avoid pacemaker-fenced crash possible with stonith_admin misuse
+ fencing: limit fencing history to 500 entries
+ fencing: stonith_admin now complains if no action option is specified
+ pacemakerd: do not modify kernel.sysrq on Linux
+ scheduler: regression test compatibility with glib 2.59.0
+ scheduler: avoid unnecessary recovery of cleaned guest nodes and bundles
+ scheduler: ensure failures causing fencing not expired until fencing done
+ scheduler: start unique clone instances in numerical order
+ scheduler: convert unique clones to anonymous clones when not supported
+ scheduler: associate pending tasks with correct clone instance
+ scheduler: ensure bundle clone notifications are directed to correct host
+ scheduler: avoid improper bundle monitor rescheduling or fail count clearing
+ scheduler: honor asymmetric orderings even when restarting
+ scheduler: don't order non-DC shutdowns before DC fencing
+ ACLs: assume unprivileged ACL user if can't get user info
+ Pacemaker Remote: get Diffie-Hellman prime bit length from GnuTLS API
+ libcrmservice: cancel DBus call when cancelling systemd/upstart actions
+ libcrmservice: order systemd resources relative to pacemaker_remote
+ libpe_status: add public API constructor/destructor for pe_working_set_t
+ tools: fix crm_resource --clear when lifetime was used with ban/move
+ tools: fix crm_resource --move when lifetime was used with previous move
+ tools: make crm_mon CIB connection errors non-fatal if previously successful
+ tools: improve crm_mon messages when generating HTML output
+ tools: crm_mon cluster connection failure is now "critical" in nagios mode
+ tools: crm_mon listing of standby nodes shows if they have active resources
+ tools: crm_diff now ignores attribute ordering when comparing in CIB mode
+ tools: improve crm_report detection of logs, CIB directory, and processes
+ tools: crm_verify returns reliable exit codes
+ tools: crm_simulate resource history uses same name as live cluster would
* Fri Jul 6 2018 Ken Gaillot <kgaillot@redhat.com> Pacemaker-2.0.0
- Changesets: 885
- Diff: 549 files changed, 89865 insertions(+), 95100 deletions(-)
- Deprecated features removed since Pacemaker-1.1.18
+ All of these have newer forms, and the cluster will automatically convert
most older syntax usage in saved configurations to newer syntax as needed
+ Drop support for heartbeat and corosync 1 (whether using CMAN or plugin)
+ Drop support for rolling upgrades from Pacemaker versions older than 1.1.11
+ Drop support for built-in SMTP and SNMP in crm_mon
+ Drop support for legacy option aliases including default-action-timeout,
default-resource-stickiness, resource-failure-stickiness,
default-resource-failure-stickiness, is-managed-default,
and all names using underbar instead of dash
+ Drop support for "requires" operation meta-attribute
+ Drop support for the pcmk_*_cmd, pcmk_arg_map, and pcmk_poweroff_action
fence resource parameters
+ Drop support for deprecated command-line options to crmadmin,
crm_attribute, crm_resource, crm_verify, crm_mon, and stonith_admin
+ Drop support for operation meta-attributes in instance_attributes
+ Drop support for PCMK_legacy and LRMD_MAX_CHILDREN environment variables
+ Drop support for undocumented resource isolation feature
+ Drop support for processing very old saved CIB files (including
pre-0.6.0 start failure entries, pre-0.6.5 operation history entries,
pre-0.7 transition keys, pre-1.1.4 migration history entries,
pre-1.0 XML configuration schemas, pre-1.1.6 ticket state entries, and
pre-1.1.7 failed recurring operation history entries)
- Features added since Pacemaker-1.1.18
+ The pacemaker daemons have been renamed to make logs more intuitive
and easier to search
+ The default location of the Pacemaker detail log is now
/var/log/pacemaker/pacemaker.log (instead of being directly in /var/log),
and Pacemaker will no longer use Corosync's logging preferences;
configure script options are available to change default log locations
+ The detail log's message format has been improved
+ The master XML tag is deprecated in favor of using a standard clone tag
with a new "promotable" meta-attribute set to true, and the "master-max"
and "master-node-max" master meta-attributes are deprecated in favor of
new "promoted-max" and "promoted-node-max" clone meta-attributes;
documentation now refers to these as promotable clones rather than
master/slave, stateful, or multistate clones, and refers to
promotion scores instead of master scores
+ Administration-related documentation has been moved from the
"Pacemaker Explained" document to a new "Pacemaker Administration" document
+ record-pending now defaults to TRUE (pending actions are shown in status)
+ All Python code in Pacemaker now supports both Python 2.7 and Python 3
+ The command-line tools now return consistent, well-defined exit codes;
crm_error has an --exit option to list these
+ Pacemaker's systemd unit files now remove systemd's spawned process limit
+ mount, path, and timer systemd unit types are now supported as resources
+ A negative stonith-watchdog-timeout now tells the cluster to automatically
calculate the value based on SBD_WATCHDOG_TIMEOUT (which was the behavior
of 0 before 1.1.15; 0 retains its post-1.1.15 behavior of disabling use of
the watchdog as a fencing device)
+ The undocumented restart-type and role_after_failure
resource meta-attributes are now deprecated
+ Regression testing code has been consolidated and overhauled
(the most obvious change is new command names)
+ build: create /etc/pacemaker directory when installing
+ build: improved portability to BSD-based platforms
+ tools: crm_resource --cleanup now cleans only failed operation history;
crm_resource --reprobe retains the previous behavior of cleaning all
operation history
+ tools: add stonith_admin --validate option to check device configuration
+ tools: crm_node is now in the pacemaker-cli package (instead of pacemaker)
+ alerts: add epoch and usec alert variables for improved SNMP alerts
+ controller: deprecate "crmd-*" cluster options in favor of new names
+ scheduler: deprecate stonith-action value "poweroff" (use "off" instead)
+ scheduler: deprecate require-all in rsc_order
+ libcrmcluster: prefer corosync name over ring0_addr
+ xml: allow local "kind" in resource_set within rsc_order
- Changes since Pacemaker-1.1.18
+ Restore systemd unit dependency on DBus (regression in 1.1.17)
+ CIB: handle mixed-case node names when modifying attributes (regression in 1.1.17)
+ scheduler: avoid crash when logging ignored failure timeout (regression in 1.1.17)
+ attrd: ensure node name is broadcast at start-up (regression in 1.1.18)
+ scheduler: unfence before probing or starting fence devices (regression in 1.1.18)
+ tools: treat INFINITY correctly in crm_failcount (regression in 1.1.17)
+ tools: show master scores with crm_simulate -sL (regression in 1.1.18)
+ tools: crm_master did not work without explicit --lifetime (regression in 1.1.18)
+ Numerous changes to public C API of libraries
+ Choose current node correctly when a resource is multiply active
+ controller,executor,tools: avoid minor memory leaks
+ CIB: don't use empty CIB if real CIB has bad permissions
+ controller: avoid double free after ACL rejection of resource deletion
+ controller: don't record pending clone notifications in CIB
+ controller: always write faked failures to CIB whenever possible
+ controller: quorum gain without a node join should cause new transition
+ executor: handle systemd actions correctly when used with "service:"
+ executor: find absolute LSB paths when used with "service:"
+ scheduler: handle "requires" of "quorum" or "nothing" properly
+ scheduler: ensure orphaned recurring monitors have interval set
+ scheduler: handle pending migrations correctly when record-pending is true
+ scheduler: don't time out failures that cause fencing until fencing completes
+ scheduler: handle globally-unique bundle children correctly
+ scheduler: use correct default timeout for monitors
+ scheduler: "symmetrical" defaults to "false" for serialize orders
+ scheduler: avoid potential use-of-NULL when unpacking ordering constraint
+ scheduler: properly cancel recurring monitors
+ scheduler: do not schedule notifications for unrunnable actions
+ scheduler: ensure stops occur after stopped remote connections come back up
+ scheduler: consider only allowed nodes when ordering start after all recovery
+ scheduler: avoid graph loop from ordering bundle child stops/demotes after container fencing
+ scheduler: remote connection resources are safe to require only quorum
+ scheduler: correctly observe colocation with bundles in Master role
+ scheduler: restart resource after failed demote when appropriate
+ Pacemaker Remote: always use most recent remote proxy
+ tools: crm_node now gets correct node name and ID on Pacemaker Remote nodes
+ tools: correctly check crm_resource --move for master role
+ tools: cibsecret --help/--version doesn't require cluster to be running
+ tools: ignore attribute placement when crm_diff compares in cib mode
+ tools: prevent notify actions from causing crm_resource --wait to hang
+ resources: drop broken configdir parameter from ocf:pacemaker:controld
- For further details, see:
https://wiki.clusterlabs.org/wiki/Pacemaker_2.0_Changes
* Tue Nov 14 2017 Ken Gaillot <kgaillot@redhat.com> Pacemaker-1.1.18
- Update source tarball to revision: a9fbd15
- Changesets: 644
- Diff: 167 files changed, 9753 insertions(+), 5596 deletions(-)
- Features added since Pacemaker-1.1.17
+ warnings are now logged when using legacy syntax to be removed in 2.0
+ agents: ifspeed agent is now installed when building
+ agents: ifspeed agent can optionally detect interface name from IP address
+ alerts: support alert filters
+ alerts: experimental support for alerts for node attribute changes
+ crmd,pengine: support unfencing of remote nodes
+ pengine: bundles now support all constraint types
+ pengine: bundles now support rkt containers
+ pengine: bundles support new container-attribute-target parameter
+ pengine,tools: logs and crm_mon show why resources changed state
+ stonith-ng: support new fencing resource parameter pcmk_delay_base
+ tools: new crm_resource option --why explains why resources are stopped
- Changes since Pacemaker-1.1.17
+ many documentation improvements
+ agents: ifspeed properly calculates speed of hfi1 interfaces
+ agents: ClusterMon now interprets "update" less than 1000 as seconds
+ attrd: don't lose attributes set between attrd start-up and cluster join
+ attrd: fix multiple minor memory leaks
+ crmd: correctly record that unfencing is complete
+ crmd: error more quickly if remote start fails due to missing key
+ lrmd: remote resource operations return immediate error if key setup fails
+ lrmd: allow pre-1.1.15 cluster nodes to connect to current Pacemaker Remote
+ pengine: guest nodes are now probed like other nodes
+ pengine: probe remote nodes for guest node resources
+ pengine: do not probe guest/bundle connections until guest/bundle is active
+ pengine: allow resources to stop prior to probes completing
+ pengine: bundles wait only for other containers on same node to be probed
+ pengine: have bundles log to stderr so 'docker logs'/'journalctl -M' works
+ pengine: only pass requests for promote/demote flags onto the bundle's child
+ pengine: do not map ports into Docker container when net=host is specified
+ pengine: allow resources inside bundles to receive clone notifications
+ pengine: default to non-interleaved bundle ordering for safety
+ pengine: ensure bundle nodes and child resources are correctly cleaned up
+ pengine: prevent graph loops when fencing the host underneath a bundle
+ pengine: fix multiple memory issues (use-after-free, use-of-NULL) with bundles
+ pengine: resources in bundles respect failcounts
+ pengine: ensure nested container connections run on the same host
+ pengine: ensure unrecoverable remote nodes are fenced even with no resources
+ pengine: handle resource migrating behind a migrating remote connection
+ pengine: don't prefer to keep unique instances on same node
+ pengine: exclude exclusive resources and nodes from symmetric default score
+ pengine: if ignoring failure, also ignore migration-threshold
+ pengine: restore the ability to send the transition graph via the disk if it gets too big
+ pengine: validate no-quorum-policy=suicide correctly
+ pengine: avoid crash when alerts section has comments
+ pengine: detect permanent master scores at start-up
+ pengine: do not re-add a node's default score for each location constraint
+ pengine: make sure calculated resource scores are consistent on different architectures
+ pengine: retrigger unfencing for changed device parameters only when necessary
+ pengine: don't schedule reload and restart in same transition (CLBZ#5309, regression introduced in 1.1.15)
+ stonith-ng: make fencing-device reappear properly after reenabling
+ stonith-ng: include pcmk_on_action in meta-data so 'on' can be overridden
+ tools: allow crm_report to work with no log files specified
+ tools: fix use-after-free in crm_diff introduced in 1.1.17
+ tools: allow crm_resource to operate on anonymous clones in unknown states
+ tools: crm_resource --cleanup on appropriate nodes if we don't know state of resource
+ tools: prevent disconnection from crmd during crm_resource --cleanup
+ tools: improve messages for crm_resource --force-* options
+ tools: crm_mon: avoid infinite process spawning if -E script can't be run
+ tools: crm_mon: don't show previous exit-reason for failed action with none
+ libcrmservice: list systemd unit files, not only active units (CLBZ#5299)
+ libcrmservice: parse long description correctly for LSB meta-data
* Thu Jul 06 2017 Ken Gaillot <kgaillot@redhat.com> Pacemaker-1.1.17
- Update source tarball to revision: 301bc44
- Changesets: 539
- Diff: 177 files changed, 11525 insertions(+), 5036 deletions(-)
- Features added since Pacemaker-1.1.16
+ New "bundle" resource type for Docker container use cases (experimental)
+ New "PCMK_node_start_state" environment variable to start node in standby
+ New "value-source" rule expression attribute in location constraints to
compare a node attribute against a resource parameter
+ New "stonith-max-attempts" cluster option to specify how many times
fencing can fail for a target before the cluster will no longer
immediately re-attempt it (previously hard-coded at 10)
+ New "cluster-ipc-limit" cluster option to avoid IPC client eviction in
large clusters
+ Failures are now tracked per operation type, as well as per node and
resource (the "fail-count" and "last-failure" node attribute names now end
in "#OPERATION_INTERVAL")
+ attrd: Pacemaker Remote node attributes and regular expressions are now
supported on legacy cluster stacks (heartbeat, CMAN, and corosync plugin)
+ tools: New "crm_resource --validate" option
+ tools: New "stonith_admin --list-targets" option
+ tools: New "crm_attribute --pattern" option to match a regular expression
+ tools: "crm_resource --cleanup" and "crm_failcount" can now take
--operation and --interval options to operate on a single operation type
- Changes since Pacemaker-1.1.16
+ Fix multiple memory issues (leaks, use-after-free) in libraries
+ pengine: unmanaging a guest node resource puts guest in maintenance mode
+ cib: broadcasts of cib changes should always pass ACL checks
+ crmd,libcrmcommon: update throttling when CPUs are hot-plugged
+ crmd: abort transition whenever we lose quorum
+ crmd: avoid attribute write-out on join when atomic attrd is used
+ crmd: check for too many stonith failures only when aborting for that reason
+ crmd: correctly clear failure counts only for a specified node
+ crmd: don't fence old DC if it's shutting down as soon-to-be DC joins
+ crmd: forget stonith failures when forgetting node
+ crmd: all nodes should track stonith failure counts in case they become DC
+ crmd: update cache status for guest node whose host is fenced
+ dbus: prevent lrmd from hanging on dbus calls
+ fencing: detect newly added constraints for stonith devices
+ pengine: order remote actions after connection recovery
(regression introduced in 1.1.15)
+ pengine: quicker recovery from failed demote
+ libcib: determine remote nodes correctly from node status entries
+ libcrmcommon: avoid evicting IPC client if messages spike briefly
+ libcrmcommon: better XML comment handling prevents infinite election loop
+ libcrmcommon: set month correctly in date/time string sent to alert agents
+ libfencing,fencing: intelligently remap "action" wrongly specified in config
+ libservices: ensure completed ops aren't on blocked ops list
+ libservices: properly detect and cancel in-flight systemd/upstart ops
+ libservices: properly watch writable DBus handles
+ libservices: systemd service that is reloading doesn't cause monitor failure
+ pacemaker_remoted: allow graceful shutdown while unmanaged
+ pengine,libpe_status: don't clear same fail-count twice
+ pengine: consider guest node unclean if its host is unclean
+ pengine: do not re-add a node's default score for each location constraint
+ pengine: avoid restarting services when recovering remote connection
+ pengine: better guest node recovery when host fails
+ pengine: guest node fencing doesn't require stonith enabled
+ pengine: allow probes of guest node connection resources
+ pengine: properly handle allow-migrate explicitly set for remote connection
+ pengine: fence failed remote nodes even if no resources can run on them
+ tools: resource agents will now get the correct node name on
Pacemaker Remote nodes when using crm_node and crm_attribute
+ tools: avoid grep crashes in crm_report when looking for system logs
+ tools: crm_resource -C now clears last-failure as well as fail-count
+ tools: implement crm_failcount command-line options correctly
+ tools: properly ignore version with crm_diff --no-version
* Wed Nov 30 2016 Ken Gaillot <kgaillot@redhat.com> Pacemaker-1.1.16
- Update source tarball to revision: 76876b3
- Changesets: 382
- Diff: 145 files changed, 7200 insertions(+), 5621 deletions(-)
- Features added since Pacemaker-1.1.15
+ Location constraints may use rsc-pattern, with submatches expanded
+ node-health-base available with node-health-strategy=progressive
+ new Pacemaker Development document for working on pacemaker code base
+ new PCMK_panic_action variable allows crash instead of reboot on panic
+ resources: add resource agent for managing a node attribute
+ systemd: include socket units when listing all systemd agents
- Changes since Pacemaker-1.1.15
+ Important security fix for CVE-2016-7035
+ Logging is now synchronous when blackboxes are enabled
+ All python code except CTS is now compatible with python 2.6+ and 3.2+
+ build: take advantage of compiler features for security and performance
+ build: update SuSE spec modifications for recent spec changes
+ build: avoid watchdog reboot when upgrading pacemaker_remote with sbd
+ build: numerous other improvements in environment detection, etc.
+ cib: fix infinite loop when no schema validates
+ crmd: cl#5185 - record pending operations in CIB before they are performed
+ crmd: don't abort transitions for CIB comment changes
+ crmd: resend shutdown request if DC loses original request
+ documentation: install improved README in doc instead of now-removed AUTHORS
+ documentation: clarify licensing and provide copy of all licenses
+ documentation: document various features and upgrades better
+ fence_legacy: use "list" action when searching cluster-glue agents
+ libcib: don't stop sending alerts after releasing DC role
+ libcrmcommon: properly handle XML comments when comparing v2 patchset diffs
+ libcrmcommon: report errors consistently when waiting for data on connection
+ libpengine: avoid potential use-of-NULL
+ libservices: use DBusError API properly
+ pacemaker_remote: init script stop should always return 0
+ pacemaker_remote: allow remote clients to timeout/reconnect
+ pacemaker_remote: correctly calculate remaining timeout when receiving messages
+ pengine: avoid transition loop for start-then-stop + unfencing
+ pengine: correctly update dependent actions of un-runnable clones
+ pengine: do not fence a node in maintenance mode if it shuts down cleanly
+ pengine: set OCF_RESKEY_CRM_meta_notify_active_* for multistate resources
+ resources: ping - avoid temporary files for fping check, support FreeBSD
+ resources: SysInfo - better support for FreeBSD
+ resources: variable name typo in docker-wrapper
+ systemd: order pacemaker after time-sync target
+ tools: correct attrd_updater help and error messages when using CMAN
+ tools: crm_standby --version/--help should work without cluster running
+ tools: make crm_report sanitize CIB before generating readable version
+ tools: display pending resource state by default when available
+ tools: avoid matching other process with same PID in ClusterMon
* Tue Jun 21 2016 Ken Gaillot <kgaillot@redhat.com> Pacemaker-1.1.15
- Update source tarball to revision: 32fa6a5
- Changesets: 533
- Diff: 219 files changed, 6659 insertions(+), 3989 deletions(-)
- Features added since Pacemaker-1.1.14
+ Event-driven alerts allow scripts to be called after significant events
+ build: Some files moved from pacemaker package to pacemaker-cli for cleaner pacemaker-remote dependencies
+ build: ./configure --with-configdir argument for /etc/sysconfig, /etc/default, etc.
+ fencing: Simplify watchdog integration
+ fencing: Support concurrent fencing actions via new pcmk_action_limit option
+ remote: pacemaker_remote may be stopped without disabling resource first
+ remote: Report integration status of Pacemaker Remote nodes in CIB node_state
+ tools: crm_mon now reports why resources are not starting
+ tools: crm_report now obscures passwords in logfiles
+ tools: attrd_updater --update-both/--update-delay options allow changing dampening value
+ tools: allow stonith_admin -H '*' to show history for all nodes
- Changes since Pacemaker-1.1.14
+ Fix multiple memory issues (leaks, use-after-free) in daemons, libraries and tools
+ Make various log messages more user-friendly
+ Improve FreeBSD and Hurd support
+ attrd: Prevent possible segfault on exit
+ cib: Fix regression to restore support for compressed CIB larger than 1MB
+ common: fix regression in 1.1.14 that made have-watchdog always true
+ controld: handle DLM "wait fencing" state better
+ crmd: Fix regression so that fenced unseen nodes do not remain unclean
+ crmd: Take start-delay into account when calculation action timeouts
+ crmd: Avoid timeout on older peers when cancelling a resource operation
+ fencing: Allow fencing by node ID (e.g. by DLM) even if node left cluster
+ lrmd: Fix potential issues when cluster is stopped via systemd shutdown
+ pacemakerd: Properly respawn stonithd if it fails
+ pengine: Fix regression with multiple monitor levels that could ignore failure
+ pengine: Correctly set OCF_RESKEY_CRM_meta_timeout when start-delay is configured
+ pengine: Properly order actions for master/slave resources in anti-colocations
+ pengine: Respect asymmetrical ordering when trying to move resources
+ pengine: Properly order stop actions on guest node relative to host stonith
+ pengine: Correctly block actions dependent on unrunnable clones
+ remote: Allow remote nodes to have node attributes even with legacy attrd
+ remote: Recover from remote node fencing more quickly
+ remote: Place resources on newly rejoined remote nodes more quickly
+ resources: ping agent can now use fping6 for IPv6 hosts
+ resources: SysInfo now resets #health_disk to green when there's sufficient free disk
+ tools: crm_report is now more efficient and handles Pacemaker Remote nodes better
+ tools: Prevent crm_resource segfault when --resource is not supplied with --restart
+ tools: crm_shadow --display option now works
+ tools: crm_resource --restart handles groups, target-roles and moving resources better
* Thu Jan 14 2016 Ken Gaillot <kgaillot@redhat.com> Pacemaker-1.1.14
- Update source tarball to revision: f0b585a
- Changesets: 724
- Diff: 179 files changed, 13142 insertions(+), 7695 deletions(-)
- Features added since Pacemaker-1.1.13
+ crm_resource: Indicate common reasons why a resource may not start after a cleanup
+ crm_resource: New --force-promote and --force-demote options for debugging
+ fencing: Support targeting fencing topologies by node name pattern or node attribute
+ fencing: Remap sequential topology reboots to all-off-then-all-on
+ pengine: Allow resources to start and stop as soon as their state is known on all nodes
+ pengine: Include a list of all and available nodes with clone notifications
+ pengine: Addition of the clone resource clone-min metadata option
+ pengine: Support of multiple-active=block for resource groups
+ remote: Resources that create guest nodes can be included in a group resource
+ remote: reconnect_interval option for remote nodes to delay reconnect after fence
- Changes since Pacemaker-1.1.13
+ improve support for building on FreeBSD and Debian
+ fix multiple memory issues (leaks, use-after-free, double free, use-of-NULL) in components and tools
+ cib: Do not terminate due to badly behaving clients
+ cman: handle corosync-invented node names of the form Node{id} for peers not in its node list
+ controld: replace bashism
+ crm_node: Display node state with -l and quorum status with -q, if available
+ crmd: resources would sometimes be restarted when only non-unique parameters changed
+ crmd: fence remote node after connection failure only once
+ crmd: handle resources named the same as cluster nodes
+ crmd: Pre-emptively fail in-flight actions when lrmd connections fail
+ crmd: Record actions in the CIB as failed if we cannot execute them
+ crm_report: Enable password sanitizing by default
+ crm_report: Allow log file discovery to be disabled
+ crm_resource: Allow the resource configuration to be modified for --force-{check,start,..} calls
+ crm_resource: Compensate for -C and -p being called with the child resource for clones
+ crm_resource: Correctly clean up all children for anonymous cloned groups
+ crm_resource: Correctly clean up failcounts for inactive anonymous clones
+ crm_resource: Correctly observe --force when deleting and updating attributes
+ crm_shadow: Fix "crm_shadow --diff"
+ crm_simulate: Prevent segfault on arches with 64bit time_t
+ fencing: ensure "required"/"automatic" only apply to "on" actions
+ fencing: Return a provider for the internal fencing agent "#watchdog" instead of logging an error
+ fencing: ignore stderr output of fence agents (often used for debug messages)
+ fencing: fix issue where deleting a fence device attribute can delete the device
+ libcib: potential user input overflow
+ libcluster: overhaul peer cache management
+ log: make syslog less noisy
+ log: fix various misspellings in log messages
+ lrmd: cancel currently pending STONITH op if stonithd connection is lost
+ lrmd: Finalize all pending and recurring operations when cleaning up a resource
+ pengine: Bug cl#5247 - Imply resources running on a container are stopped when the container is stopped
+ pengine: cl#5235 - Prevent graph loops that can be introduced by "load_stopped -> migrate_to" ordering
+ pengine: Correctly bypass fencing for resources that do not require it
+ pengine: do not timeout remote node recurring monitor op failure until after fencing
+ pengine: Ensure recurring monitor operations are cancelled when clone instances are de-allocated
+ pengine: fixes segfault in pengine when fencing remote node
+ pengine: properly handle blocked clone actions
+ pengine: ensure failed actions that occurred in node shutdown are displayed
+ remote: Correctly display the usage of the ocf:pacemaker:remote resource agent
+ remote: do not fail operations because of a migration
+ remote: enable reloads for select remote connection options
+ resources: allow for top output with or without percent sign in HealthCPU
+ resources: Prevent an error message on stopping "Dummy" resource
+ systemd: Prevent segfault when logging failed operations
+ systemd: Reconnect to System DBus if the connection is closed
+ systemd: set systemd resources' timeout values higher than systemd's own default
+ tools: Do not send command lines to syslog
+ tools: update SNMP MIB
+ upstart: Ensure pending structs are correctly unreferenced
* Wed Jun 24 2015 Andrew Beekhof <andrew@beekhof.net> Pacemaker-1.1.13
- Update source tarball to revision: 2a1847e
- Changesets: 750
- Diff: 156 files changed, 11323 insertions(+), 3725 deletions(-)
- Features added since Pacemaker-1.1.12
+ Allow fail-counts to be removed en-mass when the new attrd is in operation
+ attrd supports private attributes (not written to CIB)
+ crmd: Ensure a watchdog device is in use if stonith-watchdog-timeout is configured
+ crmd: If configured, trigger the watchdog immediately if we lose quorum and no-quorum-policy=suicide
+ crm_diff: Support generating a difference without versions details if --no-version/-u is supplied
+ crm_resource: Implement an intelligent restart capability
+ Fencing: Advertise the watchdog device for fencing operations
+ Fencing: Allow the cluster to recover resources if the watchdog is in use
+ fencing: cl#5134 - Support random fencing delay to avoid double fencing
+ mcp: Allow orphan children to initiate node panic via SIGQUIT
+ mcp: Turn on sbd integration if pacemakerd finds it running
+ mcp: Two new error codes that result in machine reset or power off
+ Officially support the resource-discovery attribute for location constraints
+ PE: Allow natural ordering of colocation sets
+ PE: Support non-actionable degraded mode for OCF
+ pengine: cl#5207 - Display "UNCLEAN" for resources running on unclean offline nodes
+ remote: pcmk remote client tool for use with container wrapper script
+ Support machine panics for some kinds of errors (via sbd if available)
+ tools: add crm_resource --wait option
+ tools: attrd_updater supports --query and --all options
+ tools: attrd_updater: Allow attributes to be set for other nodes
- Changes since Pacemaker-1.1.12
+ pengine: exclusive discovery implies rsc is only allowed on exclusive subset of nodes
+ acl: Correctly implement the 'reference' acl directive
+ acl: Do not delay evaluation of added nodes in some situations
+ attrd: b22b1fe did uuid test too early
+ attrd: Clean out the node cache when requested by the admin
+ attrd: fixes double free in attrd legacy
+ attrd: properly write attributes for peers once uuid is discovered
+ attrd: refresh should force an immediate write-out of all attributes
+ attrd: Simplify how node deletions happen
+ Bug rhbz#1067544 - Tools: Correctly handle --ban, --move and --locate for master/slave groups
+ Bug rhbz#1181824 - Ensure the DC can be reliably fenced
+ cib: Ability to upgrade cib validation schema in legacy mode
+ cib: Always generate digests for cib diffs in legacy mode
+ cib: assignment where comparison intended
+ cib: Avoid nodeid conflicts we don't care about
+ cib: Correctly add "update-origin", "update-client" and "update-user" attributes for cib
+ cib: Correctly set up signal handlers
+ cib: Correctly track node state
+ cib: Do not update on disk backups if we're just querying them
+ cib: Enable cib legacy mode for plugin-based clusters
+ cib: Ensure file-based backends treat '-o section' consistently with the native backend
+ cib: Ensure upgrade operations from a non-DC get an acknowledgement
+ cib: No need to enforce cib digests for v2 diffs in legacy mode
+ cib: Revert d153b86 to instantly get cib synchronized in legacy mode
+ cib: tls sock cleanup for remote cib connections
+ cli: Ensure subsequent unknown long options are correctly detected
+ cluster: Invoke crm_remove_conflicting_peer() only when the new node's uname is being assigned in the node cache
+ common: Increment current and age for lib common as a result of APIs being added
+ corosync: Bug cl#5232 - Somewhat gracefully handle nodes with invalid UUIDs
+ corosync: Avoid unnecessary repeated CMAP API calls
+ crmd/pengine: handle on-fail=ignore properly
+ crmd: Add "on_node" attribute for *_last_failure_0 lrm resource operations
+ crmd: All peers need to track node shutdown requests
+ crmd: Cached copies of transient attributes cease to be valid once a node leaves the membership
+ crmd: Correctly add the local option that validates against schema for pengine to calculate
+ crmd: Disable debug logging that results in significant overhead
+ crmd: do not remove connection resources during re-probe
+ crmd: don't update fail count twice for same failure
+ crmd: Ensure remote connection resources timeout properly during 'migrate_from' action
+ crmd: Ensure throttle_mode() does something on Linux
+ crmd: Fixes crash when remote connection migration fails
+ crmd: gracefully handle remote node disconnects during op execution
+ crmd: Handle remote connection failures while executing ops on remote connection
+ crmd: include remote nodes when forcing cluster wide resource reprobe
+ crmd: never stop recurring monitor ops for pcmk remote during incomplete migration
+ crmd: Prevent the old version of DC from being fenced when it shuts down for rolling-upgrade
+ crmd: Prevent use-of-NULL during reprobe
+ crmd: properly update job limit for baremetal remote-nodes
+ crmd: Remote-node throttle jobs count towards cluster-node hosting conneciton rsc
+ crmd: Reset stonith failcount to recover transitioner when the node rejoins
+ crmd: resolves memory leak in crmd.
+ crmd: respect start-failure-is-fatal even for artifically injected events
+ crmd: Wait for all pending operations to complete before poking the policy engine
+ crmd: When container's host is fenced, cancel in-flight operations
+ crm_attribute: Correctly update config options when -o crm_config is specified
+ crm_failcount: Better error reporting when no resource is specified
+ crm_mon: add exit reason to resource failure output
+ crm_mon: Fill CRM_notify_node in traps with node's uname rather than node's id if possible
+ crm_mon: Repair notification delivery when the v2 patch format is in use
+ crm_node: Correctly remove nodes from the CIB by nodeid
+ crm_report: More patterns for finding logs on non-DC nodes
+ crm_resource: Allow resource restart operations to be node specific
+ crm_resource: avoid deletion of lrm cache on node with resource discovery disabled.
+ crm_resource: Calculate how long to wait for a restart based on the resource timeouts
+ crm_resource: Clean up memory in --restart error paths
+ crm_resource: Display the locations of all anonymous clone children when supplying the children's common ID
+ crm_resource: Ensure --restart sets/clears meta attributes
+ crm_resource: Ensure fail-counts are purged when we redetect the state of all resources
+ crm_resource: Implement --timeout for resource restart operations
+ crm_resource: Include group members when calculating the next timeout
+ crm_resource: Memory leak in error paths
+ crm_resource: Prevent use-after-free
+ crm_resource: Repair regression test outputs
+ crm_resource: Use-after-free when restarting a resource
+ dbus: ref count leaks
+ dbus: Ensure both the read and write queues get dispatched
+ dbus: Fail gracefully if malloc fails
+ dbus: handle dispatch queue when multiple replies need to be processed
+ dbus: Notice when dbus connections get disabled
+ dbus: Remove double-free introduced while trying to make coverity shut up
+ ensure if B is colocated with A, B can never run without A
+ fence_legacy: Avoid passing 'port' to cluster-glue agents
+ fencing: Allow nodes to be purged from the member cache
+ fencing: Correctly make args for fencing agents
+ fencing: Correctly wait for self-fencing to occur when the watchdog is in use
+ fencing: Ensure the hostlist parameter is set for watchdog agents
+ fencing: Force 'stonith-ng' as the system name
+ fencing: Gracefully handle invalid metadata from agents
+ fencing: If configured, wait stonith-watchdog-timer seconds for self-fencing to complete
+ fencing: Reject actions for devices that haven't been explicitly registered yet
+ ipc: properly allocate server enforced buffer size on client
+ ipc: use server enforced buffer during ipc client send
+ lrmd, services: interpret LSB status codes properly
+ lrmd: add back support for class heartbeat agents
+ lrmd: cancel pending async connection during disconnect
+ lrmd: enable ipc proxy for docker-wrapper privileged mode
+ lrmd: fix rescheduling of systemd monitor op during start
+ lrmd: Handle systemd reporting 'done' before a resource is actually stopped
+ lrmd: Hint to child processes that using sd_notify is not required
+ lrmd: Log with the correct personality
+ lrmd: Prevent glib assert triggered by timers being removed from mainloop more than once
+ lrmd: report original timeout when systemd operation completes
+ lrmd: store failed operation exit reason in cib
+ mainloop: resolves race condition mainloop poll involving modification of ipc connections
+ make targetted reprobe for remote node work, crm_resource -C -N <remote node>
+ mcp: Allow a configurable delay when debugging shutdown issues
+ mcp: Avoid requiring 'export' for SYS-V sysconfig options
+ Membership: Detect and resolve nodes that change their ID
+ pacemakerd: resolves memory leak of xml structure in pacemakerd
+ pengine: ability to launch resources in isolated containers
+ pengine: add #kind=remote for baremetal remote-nodes
+ pengine: allow baremetal remote-nodes to recover without requiring fencing when cluster-node fails
+ pengine: allow remote-nodes to be placed in maintenance mode
+ pengine: Avoid trailing whitespaces when printing resource state
+ pengine: cl#5130 - Choose nodes capable of running all the colocated utilization resources
+ pengine: cl#5130 - Only check the capacities of the nodes that are allowed to run the resource
+ pengine: Correctly compare feature set to determine how to unpack meta attributes
+ pengine: disable migrations for resources with isolation containers
+ pengine: disable reloading of resources within isolated container wrappers
+ pengine: Do not aggregate children in a pending state into the started/stopped/etc lists
+ pengine: Do not record duplicate copies of the failed actions
+ pengine: Do not reschedule monitors that are no longer needed while resource definitions have changed
+ pengine: Fence baremetal remote when recurring monitor op fails
+ pengine: Fix colocation with unmanaged resources
+ pengine: Fix the behaviors of multi-state resources with asymmetrical ordering
+ pengine: fixes pengine crash with orphaned remote node connection resource
+ pengine: fixes segfault caused by malformed log warning
+ pengine: handle cloned isolated resources in a sane way
+ pengine: handle isolated resource scenario, cloned group of isolated resources
+ pengine: Handle ordering between stateful and migratable resources
+ pengine: imply stop in container node resources when host node is fenced
+ pengine: only fence baremetal remote when connection can fails or can not be recovered
+ pengine: only kill process group on timeout when on-fail does not equal block.
+ pengine: per-node control over resource discovery
+ pengine: prefer migration target for remote node connections
+ pengine: prevent disabling rsc discovery per node in certain situations
+ pengine: Prevent use-after-free in sort_rsc_process_order()
+ pengine: properly handle ordering during remote connection partial migration
+ pengine: properly recover remote-nodes when cluster-node proxy goes offline
+ pengine: remove unnecessary whitespace from notify environment variables
+ pengine: require-all feature for ordered clones
+ pengine: Resolve memory leaks
+ pengine: resource discovery mode for location constraints
+ pengine: restart master instances on instance attribute changes
+ pengine: Turn off legacy unpacking of resource options into the meta hashtable
+ pengine: Watchdog integration is sufficient for fencing
+ Perform systemd reloads asynchronously
+ ping: Correctly advertise multiplier default
+ Prefer to inherit the watchdog timeout from SBD
+ properly record stop args after reload
+ provide fake meta data for ra class heartbeat
+ remote: report timestamps for remote connection resource operations
+ remote: Treat recv msg timeout as a disconnect
+ service: Prevent potential use-of-NULL in metadata lookups
+ solaris: Allow compilation when dirent.d_type is not available
+ solaris: Correctly replace the linux swab functions
+ solaris: Disable throttling since /proc doesn't exist
+ stonith-ng: Correctly observe the watchdog completion timeout
+ stonith-ng: Correctly track node state
+ stonith-ng: Reset mainloop source IDs after removing them
+ systemd: Correctly handle long running stop actions
+ systemd: Ensure failed monitor operations always return
+ systemd: Ensure we don't call dbus_message_unref() with NULL
+ systemd: fix crash caused when canceling in-flight operation
+ systemd: Kindly ask dbus NOT to kill the process if the dbus connection fails
+ systemd: Perform actions asynchronously
+ systemd: Perform monitor operations without blocking
+ systemd: Tell systemd not to take DBus down from underneath us
+ systemd: Trick systemd into not stopping our services before us during shutdown
+ tools: Improve crm_mon output with certain option combinations
+ upstart: Monitor actions always return 'ok' or 'not running'
+ upstart: Perform more parts of monitor operations without blocking
+ xml: add 'require-all' to xml schema for constraints
+ xml: cl#5231 - Unset the deleted attributes in the resulting diffs
+ xml: Clone the latest constraint schema in preparation for changes"
+ xml: Correctly create v1 patchsets when deleting attributes
+ xml: Do not change the ordering of properties when applying v1 cib diffs
+ xml: Do not dump deleted attributes
+ xml: Do not prune leaves from v1 cib diffs that are being created with digests
+ xml: Ensure ACLs are reapplied before calculating what a replace operation changed
+ xml: Fix upgrade-1.3.xsl to correctly transform ACL rules with "attribute"
+ xml: Prevent assert errors in crm_element_value() on applying a patch without version information
+ xml: Prevent potential use-of-NULL
* Tue Jul 22 2014 Andrew Beekhof <andrew@beekhof.net> Pacemaker-1.1.12
- Update source tarball to revision: 93a037d
- Changesets: 795
- Diff: 195 files changed, 13772 insertions(+), 6176 deletions(-)
- Features added since Pacemaker-1.1.11
+ Changes to the ACL schema to support nodes and unix groups
+ cib: Check ACLs prior to making the update instead of parsing the diff afterwards
+ cib: Default ACL support to on
+ cib: Enable the more efficient xml patchset format
+ cib: Implement zero-copy status update
+ cib: Send all r/w operations via the cluster connection and have all nodes process them
+ crmd: Set "cluster-name" property to corosync's "cluster_name" by default for corosync-2
+ crm_mon: Display brief output if "-b/--brief" is supplied or 'b' is toggled
+ crm_report: Allow ssh alternatives to be used
+ crm_ticket: Support multiple modifications for a ticket in an atomic operation
+ extra: Add logrotate configuration file for /var/log/pacemaker.log
+ Fencing: Add the ability to call stonith_api_time() from stonith_admin
+ logging: daemons always get a log file, unless explicitly set to configured 'none'
+ logging: allows the user to specify a log level that is output to syslog
+ PE: Automatically re-unfence a node if the fencing device definition changes
+ pengine: cl#5174 - Allow resource sets and templates for location constraints
+ pengine: Support cib object tags
+ pengine: Support cluster-specific instance attributes based on rules
+ pengine: Support id-ref in nvpair with optional "name"
+ pengine: Support per-resource maintenance mode
+ pengine: Support site-specific instance attributes based on rules
+ tools: Allow crm_shadow to create older configuration versions
+ tools: Display pending state in crm_mon/crm_resource/crm_simulate if --pending/-j is supplied (cl#5178)
+ xml: Add the ability to have lightweight schema revisions
+ xml: Enable resource sets in location constraints for 1.2 schema
+ xml: Support resources that require unfencing
- Changes since Pacemaker-1.1.11
+ acl: Authenticate pacemaker-remote requests with the node name as the client
+ acl: Read access must be explicitly granted
+ attrd: Ensure attribute dampening is always observed
+ attrd: Remove offline nodes from node cache for "peer-remove" requests
+ Bug cl#5055 - Improved migration support.
+ Bug cl#5184 - Ensure pending probes that ultimately fail are correctly updated
+ Bug cl#5196 - pengine: Check values after expanding templates
+ Bug cl#5212 - Do not promote instances when quorum is lots and no-quorum-policy=freeze
+ Bug cl#5213 - Ensure role colocation with -INFINITY is enforced
+ Bug cl#5213 - Limit the scope of the previous commit to the masters role
+ Bug cl#5219 - pengine: Allow unrelated resources with a common colocation target to remain promoted
+ Bug cl#5222 - cib: Repair rolling update capability
+ Bug cl#5222 - Enable legacy mode whenever a broadcast update is detected
+ Bug rhbz#1036631 - Stop members of cloned groups when dependencies are stopped
+ Bug rhbz#1054307 - cname pattern match should be more restrictive in init script
+ Bug rhbz#1057697 - Use native DBus library for systemd/upstart support to avoid problematic use of threads
+ Bug rhbz#1097457 - Limit the scope of the previous fix and include a helpful comment
+ Bug rhbz#1097457 - Prevent invalid transition when resource are ordered to start after the container they're started in
+ cib: allow setting permanent remote-node attributes
+ cib: Auto-detect which patchset format to use
+ cib: Determine the best value of validate-with if one is not supplied
+ cib: Do not disable cib disk writes if on-disk cib is corrupt
+ cib: Ensure 'cibadmin -R/--replace' commands get replies
+ cib: Erasing the cib is an admin action, bump the admin_epoch instead
+ cib: Fix remote cib based on TLS
+ cib: Ignore patch failures if we already have their contents
+ cib: Validate that everyone still sees the same configuration once all updates have completed
+ cibadmin: Allow priviliged clients to perform tasks as unpriviliged users
+ cibadmin: Remove dangerous commands that exposed unnecessary implementation internal details
+ cluster: Fix segfault on removing a node
+ cluster: Prevent search of unames from attempting to create node entries for unknown nodes
+ cluster: Remove unknown offline nodes with conflicting unames from node cache
+ controld: Do not consider the dlm up until the address list is present
+ controld: handling startup fencing within the controld agent, not the dlm
+ controld: Return OCF_ERR_INSTALLED instead of OCF_NOT_INSTALLED
+ crmd: Ack pending operations that were cancelled due to rsc deletion
+ crmd: Actions can only be executed if their pre-requisits completed successfully
+ crmd: avoid double free caused by nested hash table removal
+ crmd: Avoid spamming the cib by triggering a transition only once per non-status change
+ crmd: Correctly react to successful unfencing operations
+ crmd: Correctly recognise operation cancellations we initiated
+ crmd: Do not erase the status section for unfenced nodes
+ crmd: Do not overwrite existing node state when fencing completes
+ crmd: Do not start timers for already completed operations
+ crmd: Ensure crm_config options are re-read on updates
+ crmd: Fenced nodes that return prior to an election do not need to have their status section reset
+ crmd: make lrm_state hash table not case sensitive
+ crmd: make node_state erase correctly
+ crmd: Only write fence_averride if open() returns a positive file descriptor
+ crmd: Prevent manual fencing confirmations from attempting to create node entries for unknown nodes
+ crmd: Prevent SIGPIPE when notifying CMAN about fencing operations
+ crmd: Remove state of unknown nodes with conflicting unames from CIB
+ crmd: Remove unknown nodes with conflicting unames from CIB
+ crmd: Report unsuccessful unfencing operations
+ crm_diff: Allow the generation of xml patchsets without digests
+ crm_mon: Allow the file created by --as-html to be world readable
+ crm_mon: Ensure resource attributes have been unpacked before displaying connectivity data
+ crm_node: Only remove the named resource from the cib
+ crm_report: Gracefully handle rediculously large logfiles
+ crm_report: Only gather dlm data if dlm_controld is running
+ crm_resource: Gracefully handle -EACCESS when querying the cib
+ crm_verify: Perform a full set of calculations whenever the status section is present
+ fencing: Advertise support for reboot/on/off in the metadata for legacy agents
+ fencing: Automatically switch from 'list' to 'status' to 'static-list' if those actions are not advertised in the metadata
+ fencing: Cache metadata lookups to avoid repeated blocking during device registration
+ fencing: Correctly record which peer performed the fencing operation
+ fencing: default to 'off' when agent does not advertise 'reboot' in metadata
+ fencing: Do not unregister/register all stonith devices on every resource agent change
+ fencing: Execute all required fencing devices regardless of what topology level they are at
+ fencing: Fence using all required devices
+ fencing: Pass the correct options when looking up the history by node name
+ fencing: Update stonith device list only if stonith is enabled
+ get_cluster_type: failing concurrent tool invocations on heartbeat
+ ignore SIGPIPE when gnutls is in use
+ iso8601: Different logic is needed when logging and calculating durations
+ iso8601: Fix memory leak in duration calculation
+ Logging: Bootstrap daemon logging before processing arguments but configure it afterwards
+ lrmd: Cancel recurring operations before stop action is executed
+ lrmd: Expose logging variables expected by OCF agents
+ lrmd: Handle systemd reporting 'done' before a resource is actually stopped/started
+ lrmd: Merge duplicate recurring monitor operations
+ lrmd: Prevent OCF agents from logging to random files due to "value" of setenv() being NULL
+ lrmd: Provide stderr output from agents if available, otherwise fall back to stdout
+ mainloop: Better handle the killing of processes in the act of exiting
+ mainloop: Canceling in-flight operations should not fail if child process has already exited.
+ mainloop: Fixes use after free in process monitor code
+ mcp: Tell systemd not to respawn us if we exit with rc=100
+ membership: Avoid duplicate peer entries in the peer cache
+ pengine: Allow container nodes to migrate with connection resource
+ pengine: avoid assert by searching for stop action on correct node during LogActions
+ pengine: Block restart of resources if any dependent resource in a group is unmanaged
+ pengine: cl#5186 - Avoid running rsc on two nodes when node is fenced during migration
+ pengine: cl#5187 - Prevent resources in an anti-colocation from even temporarily running on a same node
+ pengine: cl#5200 - Before migrating utilization-using resources to a node, take off the load that will no longer run there if it's not introducing transition loop
+ pengine: Correctly handle origin offsets in the future
+ pengine: Correctly observe requires=nothing
+ pengine: Default sequential to TRUE for resource sets for consistency with colocation sets
+ pengine: Delay unfencing until after we know the state of all resources that require unfencing
+ pengine: Do not initiate fencing for unclean nodes when fencing is disabled
+ pengine: Ensure instance numbers are preserved for cloned templates
+ pengine: Ensure unfencing only happens once, even if the transition is interrupted
+ pengine: Fencing devices default to only requiring quorum in order to start
+ pengine: fixes invalid transition caused by clones with more than 10 instances
+ pengine: Force record pending for migrate_to actions
+ pengine: handles edge case where container order constraints are not honored during migration
+ pengine: Ignore failure-timeout only if the failed operation has on-fail="block"
+ pengine: Mark unrunnable stop actions as "blocked" and show the correct current locations
+ pengine: Memory leaks
+ pengine: properly handle fencing of container remote-nodes when the container is orphaned
+ pengine: properly place resource within a container when container is a remote-node.
+ pengine: Unfencing is based on device probes, there is no need to unfence when normal resources are found active
+ pengine: Use "#cluster-name" in rules for setting cluster-specific instance attributes
+ pengine: Use "#site-name" in rules for setting site-specific instance attributes
+ remote: Allow baremetal remote-node connection resources to migrate
+ remote: clear remote-node status correctly
+ remote: Enable migration support for baremetal connection resources by default
+ remote: Handle request/response ipc proxy correctly
+ services: Correctly reset the nice value for lrmd's children
+ services: Do not allow duplicate recurring op entries
+ services: Do not block synced service executions
+ services: Fixes segfault associated with cancelling in-flight recurring operations.
+ services: Remove cancelled recurring ops from internal lists as early as possible
+ services: Remove file descriptors from mainloop as soon as we have drained them
+ services: Reset the scheduling policy and priority for lrmd's children without replying on SCHED_RESET_ON_FORK
+ services_action_cancel: Interpret return code from mainloop_child_kill() correctly
+ stonith_admin: Ensure pointers passed to sscanf() are properly initialized
+ stonith_api_time_helper now returns when the most recent fencing operation completed
+ systemd: Prevent use-of-NULL when determining if an agent exists
+ systemd: Try to handle dbus actions that complete prior to configuring a callback
+ Tools: Non-daemons shouldn't abort just because xml parsing failed
+ Upstart: Allow comilation with glib versions older than 2.28
+ Upstart: Do not attempt upstart jobs if we cannot connect to dbus
+ When data was old, it fixed so that the newest cib might not be acquired.
+ xml: Check all available schemas when doing upgrades
+ xml: Correctly determine the lowest allowed schema version
+ xml: Correctly enforce ACLs after a replace operation
+ xml: Correctly infer attribute changes after a replace operation
+ xml: Create the correct diff when only part of a document is changed
+ xml: Detect attribute ordering changes
+ xml: Detect content that is added and removed in the same update
+ xml: Do not prune meaningful leaves from v1 patchsets
+ xml: Empty patchsets are considered to have applied cleanly
+ xml: Ensure patches always have version details set
+ xml: Find the minimal set of changes when part of a document is replaced
+ xml: If validate-with is missing, we find the most recent schema that accepts it and go from there
+ xml: Introduce a 'move' primitive for v2 patch sets
+ xml: Preserve the attribute order in the patch for subsequent digest validation
+ xml: Resolve memory leak when logging xml blobs
+ xml: Update xml validation to allow '<node type=remote />'
* Thu Feb 13 2014 David Vossel <davidvossel@gmail.com> Pacemaker-1.1.11
- Update source tarball to revision: 33f9d09
- Changesets: 462
- Diff: 147 files changed, 6810 insertions(+), 4057 deletions(-)
- Features added since Pacemaker-1.1.10
+ attrd: A truly atomic version of attrd for use where CPG is used for cluster communication
+ cib: Allow values to be added/updated and removed in a single update
+ cib: Support XML comments in diffs
+ Core: Allow blackbox logging to be disabled with SIGUSR2
+ crmd: Do not block on proxied calls from pacemaker_remoted
+ crmd: Enable cluster-wide throttling when the cib heavily exceeds its target load
+ crmd: Make the per-node action limit directly configurable in the CIB
+ crmd: Slow down recovery on nodes with IO load
+ crmd: Track CPU usage on cluster nodes and slow down recovery on nodes with high CPU/IO load
+ crm_mon: add --hide-headers option to hide all headers
+ crm_node: Display partition output in sorted order
+ crm_report: Collect logs directly from journald if available
+ Fencing: On timeout, clean up the agent's entire process group
+ Fencing: Support agents that need the host to be unfenced at startup
+ ipc: Raise the default buffer size to 128k
+ PE: Add a special attribute for distinguishing between real nodes and containers in constraint rules
+ PE: Allow location constraints to take a regex pattern to match against resource IDs
+ pengine: Distinguish between the agent being missing and something the agent needs being missing
+ remote: Properly version the remote connection protocol
- Changes since Pacemaker-1.1.10
+ Bug rhbz#1011618 - Consistently use 'Slave' as the role for unpromoted master/slave resources
+ Bug rhbz#1057697 - Use native DBus library for systemd and upstart support to avoid problematic use of threads
+ attrd: Any variable called 'cluster' makes the daemon crash before reaching main()
+ attrd: Avoid infinite write loop for unknown peers
+ attrd: Drop all attributes for peers that left the cluster
+ attrd: Give remote-nodes ability to set attributes with attrd
+ attrd: Prevent inflation of attribute dampen intervals
+ attrd: Support SI units for attribute dampening
+ Bug cl#5171 - pengine: Don't prevent clones from running due to dependent resources
+ Bug cl#5179 - Corosync: Attempt to retrieve a peer's node name if it is not already known
+ Bug cl#5181 - corosync: Ensure node IDs are written to the CIB as unsigned integers
+ Bug rhbz#902407 - crm_resource: Handle --ban for master/slave resources as advertised
+ cib: Correctly check for archived configuration files
+ cib: Correctly log short-form xml diffs
+ cib: Fix remote cib based on TLS
+ cibadmin: Report errors during sign-off
+ cli: Do not enabled blackbox for cli tools
+ cluster: Fix segfault on removing a node
+ cman: Do not start pacemaker if cman startup fails
+ cman: Start clvmd and friends from the init script if enabled
+ Command-line tools should stop after an assertion failure
+ controld: Use the correct variant of dlm_controld for corosync-2 clusters
+ cpg: Correctly set the group name length
+ cpg: Ensure the CPG group is always null-terminated
+ cpg: Only process one message at a time to allow other priority jobs to be performed
+ crmd: Correctly observe the configured batch-limit
+ crmd: Correctly update expected state when the previous DC shuts down
+ crmd: Correcty update the history cache when recurring ops change their return code
+ crmd: Don't add node_state to cib, if we have not seen or fenced this node yet
+ crmd: don't segfault on shutdown when using heartbeat
+ crmd: Prevent recurring monitors being cancelled due to notify operations
+ crmd: Reliably detect and act on reprobe operations from the policy engine
+ crmd: When a peer expectedly shuts down, record the new join and expected states into the cib
+ crmd: When the DC gracefully shuts down, record the new expected state into the cib
+ crm_attribute: Do not swallow hostname lookup failures
+ crm_mon: Do not display duplicates of failed actions
+ crm_mon: Reduce flickering in interactive mode
+ crm_resource: Observe --master modifier for --move
+ crm_resource: Provide a meaningful error if --master is used for primitives and groups
+ fencing: Allow fencing for node after topology entries are deleted
+ fencing: Apply correct score to the resource of group
+ fencing: Ignore changes to non-fencing resources
+ fencing: Observe pcmk_host_list during automatic unfencing
+ fencing: Put all fencing agent processes into their own process group
+ fencing: Wait until all possible replies are recieved before continuing with unverified devices
+ ipc: Compress msgs based on client's actual max send size
+ ipc: Have the ipc server enforce a minimum buffer size all clients must use.
+ iso8601: Prevent dates from jumping backwards a day in some timezones
+ lrmd: Correctly calculate metadata for the 'service' class
+ lrmd: Correctly cancel monitor actions for lsb/systemd/service resources on cleaning up
+ mcp: Remove LSB hints that instruct chkconfig to start pacemaker at boot time
+ mcp: Some distros complain when LSB scripts do not include Default-Start/Stop directives
+ pengine: Allow fencing of baremetal remote nodes
+ pengine: cl#5186 - Avoid running rsc on two nodes when node is fenced during migration
+ pengine: Correctly account for the location preferences of things colocated with a group
+ pengine: Correctly handle demotion of grouped masters that are partially demoted
+ pengine: Disable container node probes due to constraint conflicts
+ pengine: Do not allow colocation with blocked clone instances
+ pengine: Do not re-allocate clone instances that are blocked in the Stopped state
+ pengine: Do not restart resources that depend on unmanaged resources
+ pengine: Force record pending for migrate_to actions
+ pengine: Location constraints with role=Started should prevent masters from running at all
+ pengine: Order demote/promote of resources on remote nodes to happen only once the connection is up
+ pengine: Properly handle orphaned multistate resources living on remote-nodes
+ pengine: Properly shutdown orphaned remote connection resources
+ pengine: Recover unexpectedly running container nodes.
+ remote: Add support for ipv6 into pacemaker_remote daemon
+ remote: Handle endian changes between client and server and improve forward compatibility
+ services: Fixes segfault associated with cancelling in-flight recurring operations.
+ services: Reset the scheduling policy and priority for lrmd's children without replying on SCHED_RESET_ON_FORK
* Fri Jul 26 2013 Andrew Beekhof <andrew@beekhof.net> Pacemaker-1.1.10
- Update source tarball to revision: ab2e209
- Changesets: 602
- Diff: 143 files changed, 8162 insertions(+), 5159 deletions(-)
- Features added since Pacemaker-1.1.9
+ Core: Convert all exit codes to positive errno values
+ crm_error: Add the ability to list and print error symbols
+ crm_resource: Allow individual resources to be reprobed
+ crm_resource: Allow options to be set recursively
+ crm_resource: Implement --ban for moving resources away from nodes and --clear (replaces --unmove)
+ crm_resource: Support OCF tracing when using --force-(check|start|stop)
+ PE: Allow active nodes in our current membership to be fenced without quorum
+ PE: Suppress meaningless IDs when displaying anonymous clone status
+ Turn off auto-respawning of systemd services when the cluster starts them
+ Bug cl#5128 - pengine: Support maintenance mode for a single node
- Changes since Pacemaker-1.1.9
+ crmd: cib: stonithd: Memory leaks resolved and improved use of glib reference counting
+ attrd: Fixes deleted attributes during dc election
+ Bug cf#5153 - Correctly display clone failcounts in crm_mon
+ Bug cl#5133 - pengine: Correctly observe on-fail=block for failed demote operation
+ Bug cl#5148 - legacy: Correctly remove a node that used to have a different nodeid
+ Bug cl#5151 - Ensure node names are consistently compared without case
+ Bug cl#5152 - crmd: Correctly clean up fenced nodes during membership changes
+ Bug cl#5154 - Do not expire failures when on-fail=block is present
+ Bug cl#5155 - pengine: Block the stop of resources if any depending resource is unmanaged
+ Bug cl#5157 - Allow migration in the absence of some colocation constraints
+ Bug cl#5161 - crmd: Prevent memory leak in operation cache
+ Bug cl#5164 - crmd: Fixes crash when using pacemaker-remote
+ Bug cl#5164 - pengine: Fixes segfault when calculating transition with remote-nodes.
+ Bug cl#5167 - crm_mon: Only print "stopped" node list for incomplete clone sets
+ Bug cl#5168 - Prevent clones from being bounced around the cluster due to location constraints
+ Bug cl#5170 - Correctly support on-fail=block for clones
+ cib: Correctly read back archived configurations if the primary is corrupted
+ cib: The result is not valid when diffs fail to apply cleanly for CLI tools
+ cib: Restore the ability to embed comments in the configuration
+ cluster: Detect and warn about node names with capitals
+ cman: Do not pretend we know the state of nodes we've never seen
+ cman: Do not unconditionally start cman if it is already running
+ cman: Support non-blocking CPG calls
+ Core: Ensure the blackbox is saved on abnormal program termination
+ corosync: Detect the loss of members for which we only know the nodeid
+ corosync: Do not pretend we know the state of nodes we've never seen
+ corosync: Ensure removed peers are erased from all caches
+ corosync: Nodes that can persist in sending CPG messages must be alive afterall
+ crmd: Do not get stuck in S_POLICY_ENGINE if a node we couldn't fence returns
+ crmd: Do not update fail-count and last-failure for old failures
+ crmd: Ensure all membership operations can complete while trying to cancel a transition
+ crmd: Ensure operations for cleaned up resources don't block recovery
+ crmd: Ensure we return to a stable state if there have been too many fencing failures
+ crmd: Initiate node shutdown if another node claims to have successfully fenced us
+ crmd: Prevent messages for remote crmd clients from being relayed to wrong daemons
+ crmd: Properly handle recurring monitor operations for remote-node agent
+ crmd: Store last-run and last-rc-change for all operations
+ crm_mon: Ensure stale pid files are updated when a new process is started
+ crm_report: Correctly collect logs when 'uname -n' reports fully qualified names
+ fencing: Fail the operation once all peers have been exhausted
+ fencing: Restore the ability to manually confirm that fencing completed
+ ipc: Allow unpriviliged clients to clean up after server failures
+ ipc: Restore the ability for members of the haclient group to connect to the cluster
+ legacy: Support "crm_node --remove" with a node name for corosync plugin (bnc#805278)
+ lrmd: Default to the upstream location for resource agent scratch directory
+ lrmd: Pass errors from lsb metadata generation back to the caller
+ pengine: Correctly handle resources that recover before we operate on them
+ pengine: Delete the old resource state on every node whenever the resource type is changed
+ pengine: Detect constraints with inappropriate actions (ie. promote for a clone)
+ pengine: Ensure per-node resource parameters are used during probes
+ pengine: If fencing is unavailable or disabled, block further recovery for resources that fail to stop
+ pengine: Implement the rest of get_timet_now() and rename to get_effective_time
+ pengine: Re-initiate _active_ recurring monitors that previously failed but have timed out
+ remote: Workaround for inconsistent tls handshake behavior between gnutls versions
+ systemd: Ensure we get shut down correctly by systemd
+ systemd: Reload systemd after adding/removing override files for cluster services
+ xml: Check for and replace non-printing characters with their octal equivalent while exporting xml text
+ xml: Prevent lockups by setting a more reliable buffer allocation strategy
* Fri Mar 08 2013 Andrew Beekhof <andrew@beekhof.net> Pacemaker-1.1.9
- Update source tarball to revision: 7e42d77
- Statistics:
Changesets: 731
Diff: 1301 files changed, 92909 insertions(+), 57455 deletions(-)
- Features added in Pacemaker-1.1.9
+ corosync: Allow cman and corosync 2.0 nodes to use a name other than uname()
+ corosync: Use queues to avoid blocking when sending CPG messages
+ ipc: Compress messages that exceed the configured IPC message limit
+ ipc: Use queues to prevent slow clients from blocking the server
+ ipc: Use shared memory by default
+ lrmd: Support nagios remote monitoring
+ lrmd: Pacemaker Remote Daemon for extending pacemaker functionality outside corosync cluster.
+ pengine: Check for master/slave resources that are not OCF agents
+ pengine: Support a 'requires' resource meta-attribute for controlling whether it needs quorum, fencing or nothing
+ pengine: Support for resource container
+ pengine: Support resources that require unfencing before start
- Changes since Pacemaker-1.1.8
+ attrd: Correctly handle deletion of non-existant attributes
+ Bug cl#5135 - Improved detection of the active cluster type
+ Bug rhbz#913093 - Use crm_node instead of uname
+ cib: Avoid use-after-free by correctly support cib_no_children for non-xpath queries
+ cib: Correctly process XML diff's involving element removal
+ cib: Performance improvements for non-DC nodes
+ cib: Prevent error message by correctly handling peer replies
+ cib: Prevent ordering changes when applying xml diffs
+ cib: Remove text nodes from cib replace operations
+ cluster: Detect node name collisions in corosync
+ cluster: Preserve corosync membership state when matching node name/id entries
+ cman: Force fenced to terminate on shutdown
+ cman: Ignore qdisk 'nodes'
+ core: Drop per-user core directories
+ corosync: Avoid errors when closing failed connections
+ corosync: Ensure peer state is preserved when matching names to nodeids
+ corosync: Clean up CMAP connections after querying node name
+ corosync: Correctly detect corosync 2.0 clusters even if we don't have permission to access it
+ crmd: Bug cl#5144 - Do not updated the expected status of failed nodes
+ crmd: Correctly determin if cluster disconnection was abnormal
+ crmd: Correctly relay messages for remote clients (bnc#805626, bnc#804704)
+ crmd: Correctly stall the FSA when waiting for additional inputs
+ crmd: Detect and recover when we are evicted from CPG
+ crmd: Differentiate between a node that is up and coming up in peer_update_callback()
+ crmd: Have cib operation timeouts scale with node count
+ crmd: Improved continue/wait logic in do_dc_join_finalize()
+ crmd: Prevent election storms caused by getrusage() values being too close
+ crmd: Prevent timeouts when performing pacemaker level membership negotiation
+ crmd: Prevent use-after-free of fsa_message_queue during exit
+ crmd: Store all current actions when stalling the FSA
+ crm_mon: Do not try to render a blank cib and indicate the previous output is now stale
+ crm_mon: Fixes crm_mon crash when using snmp traps.
+ crm_mon: Look for the correct error codes when applying configuration updates
+ crm_report: Ensure policy engine logs are found
+ crm_report: Fix node list detection
+ crm_resource: Have crm_resource generate a valid transition key when sending resource commands to the crmd
+ date/time: Bug cl#5118 - Correctly convert seconds-since-epoch to the current time
+ fencing: Attempt to provide more information that just 'generic error' for failed actions
+ fencing: Correctly record completed but previously unknown fencing operations
+ fencing: Correctly terminate when all device options have been exhausted
+ fencing: cov#739453 - String not null terminated
+ fencing: Do not merge new fencing requests with stale ones from dead nodes
+ fencing: Do not start fencing until entire device topology is found or query results timeout.
+ fencing: Do not wait for the query timeout if all replies have arrived
+ fencing: Fix passing of parameters from CMAN containing '='
+ fencing: Fix non-comparison when sorting devices by priority
+ fencing: On failure, only try a topology device once from the remote level.
+ fencing: Only try peers for non-topology based operations once
+ fencing: Retry stonith device for duration of action's timeout period.
+ heartbeat: Remove incorrect assert during cluster connect
+ ipc: Bug cl#5110 - Prevent 100% CPU usage when looking for synchronous replies
+ ipc: Use 50k as the default compression threshold
+ legacy: Prevent assertion failure on routing ais messages (bnc#805626)
+ legacy: Re-enable logging from the pacemaker plugin
+ legacy: Relax the 'active' check for plugin based clusters to avoid false negatives
+ legacy: Skip peer process check if the process list is empty in crm_is_corosync_peer_active()
+ mcp: Only define HA_DEBUGLOG to avoid agent calls to ocf_log printing everything twice
+ mcp: Re-attach to existing pacemaker components when mcp fails
+ pengine: Any location constraint for the slave role applies to all roles
+ pengine: Avoid leaking memory when cleaning up failcounts and using containers
+ pengine: Bug cl#5101 - Ensure stop order is preserved for partially active groups
+ pengine: Bug cl#5140 - Allow set members to be stopped when the subseqent set has require-all=false
+ pengine: Bug cl#5143 - Prevent shuffling of anonymous master/slave instances
+ pengine: Bug rhbz#880249 - Ensure orphan masters are demoted before being stopped
+ pengine: Bug rhbz#880249 - Teach the PE how to recover masters into primitives
+ pengine: cl#5025 - Automatically clear failcount for start/monitor failures after resource parameters change
+ pengine: cl#5099 - Probe operation uses the timeout value from the minimum interval monitor by default (#bnc776386)
+ pengine: cl#5111 - When clone/master child rsc has on-fail=stop, insure all children stop on failure.
+ pengine: cl#5142 - Do not delete orphaned children of an anonymous clone
+ pengine: Correctly unpack active anonymous clones
+ pengine: Ensure previous migrations are closed out before attempting another one
+ pengine: Introducing the whitebox container resources feature
+ pengine: Prevent double-free for cloned primitive from template
+ pengine: Process rsc_ticket dependencies earlier for correctly allocating resources (bnc#802307)
+ pengine: Remove special cases for fencing resources
+ pengine: rhbz#902459 - Remove rsc node status for orphan resources
+ systemd: Gracefully handle unexpected DBus return types
+ Replace the use of the insecure mktemp(3) with mkstemp(3)
* Thu Sep 20 2012 Andrew Beekhof <andrew@beekhof.net> Pacemaker-1.1.8
- Update source tarball to revision: 1a5341f
- Statistics:
Changesets: 1019
Diff: 2107 files changed, 117258 insertions(+), 73606 deletions(-)
- All APIs have been cleaned up and reduced to essentials
- Pacemaker now includes a replacement lrmd that supports systemd and upstart agents
- Config and state files (cib.xml, PE inputs and core files) have moved to new locations
- The crm shell has become a separate project and no longer included with Pacemaker
- All daemons/tools now have a unified set of error codes based on errno.h (see crm_error)
- Changes since Pacemaker-1.1.7
+ Core: Bug cl#5032 - Rewrite the iso8601 date handling code
+ Core: Correctly extract the version details from a diff
+ Core: Log blackbox contents, if enabled, when an error occurs
+ Core: Only LOG_NOTICE and higher are sent to syslog
+ Core: Replace use of IPC from clplumbing with IPC from libqb
+ Core: SIGUSR1 now enables blackbox logging, SIGTRAP to write out
+ Core: Support a blackbox for additional logging detail after crashes/errors
+ Promote support for advanced fencing logic to the stable schema
+ Promote support for node starting scores to the stable schema
+ Promote support for service and systemd to the stable schema
+ attrd: Differentiate between updating all our attributes and everybody updating all theirs too
+ attrd: Have single-shot clients wait for an ack before disconnecting
+ cib: cl#5026 - Synced cib updates should not return until the cpg broadcast is complete.
+ corosync: Detect when the first corosync has not yet formed and handle it gracefully
+ corosync: Obtain a full list of configured nodes, including their names, when we connect to the quorum API
+ corosync: Obtain a node name from DNS if one was not already known
+ corosync: Populate the cib nodelist from corosync if available
+ corosync: Use the CFG API and DNS to determine node names if not configured in corosync.conf
+ crmd: Block after 10 failed fencing attempts for a node
+ crmd: cl#5051 - Fixes file leak in PE ipc connection initialization.
+ crmd: cl#5053 - Fixes fail-count not being updated properly.
+ crmd: cl#5057 - Restart sub-systems correctly (bnc#755671)
+ crmd: cl#5068 - Fixes crm_node -R option so it works with corosync 2.0
+ crmd: Correctly re-establish failed attrd connections
+ crmd: Detect when the quorum API isn't configured for corosync 2.0
+ crmd: Do not overwrite any configured node type (eg. quorum node)
+ crmd: Enable use of new lrmd daemon and client library in crmd.
+ crmd: Overhaul the way node state is recorded and updated in the CIB
+ fencing: Bug rhbz#853537 - Prevent use-of-NULL when the cib libraries are not available
+ fencing: cl#5073 - Add 'off' as an valid value for stonith-action option.
+ fencing: cl#5092 - Always timeout stonith operations if timeout period expires.
+ fencing: cl#5093 - Stonith per device timeout option
+ fencing: Clean up if we detect a failed connection
+ fencing: Delegate complex self fencing requests - we wont be around to see it to completion
+ fencing: Ensure all peers are notified of complex fencing op completion
+ fencing: Fix passing of fence_legacy parameters containing '='
+ fencing: Gracefully handle metadata requests for unknown agents
+ fencing: Return cached dynamic target list for busy devices.
+ fencing: rhbz#801355 - Abort transition on DC when external fencing operation is detected
+ fencing: rhbz#801355 - Merge fence requests for identical operations already in progress.
+ fencing: rhbz#801355 - Report fencing operations external of pacemaker to cib
+ fencing: Specify the action to perform using action= instead of the older option=
+ fencing: Stop building fake metadata for broken agents
+ fencing: Tolerate agents that report empty metadata in the admin tool
+ mcp: Correctly retry the connection to corosync on failure
+ mcp: Do not shut down IPC until the last client exits
+ mcp: Prevent use-after-free when running against corosync 1.x
+ pengine: Bug cl#5059 - Use the correct action's status when calculating required actions for interleaved clones
+ pengine: Bypass online/offline checking resource detection for ping/quorum nodes
+ pengine: cl#5044 - migrate_to no longer requires load_stopped for avoiding possible transition loop
+ pengine: cl#5069 - Honor 'on-fail=ignore' even when operation is disabled.
+ pengine: cl#5070 - Allow influence of promotion score when multistate rsc is left hand of colocation
+ pengine: cl#5072 - Fixes monitor op stopping after rsc promotion.
+ pengine: cl#5072 - Fixes pengine regression test failures
+ pengine: Correctly set the status for nodes not intended to run Pacemaker
+ pengine: Do not append instance numbers to anonymous clones
+ pengine: Fix failcount expiration
+ pengine: Fix memory leaks found by valgrind
+ pengine: Fix use-after-free and use-of-NULL errors detected by coverity
+ pengine: Fixes use of colocation scores other than +/- INFINITY
+ pengine: Improve detection of rejoining nodes
+ pengine: Prevent use-of-NULL when tracing is enabled
+ pengine: Stonith resources are allowed to start even if their probes haven't completed on partially active nodes
+ services: New class called 'service' which expands to the correct (LSB/systemd/upstart) standard
+ services: Support Asynchronous systemd/upstart actions
+ Tools: crm_shadow - Bug cl#5062 - Correctly set argv[0] when forking a shell process
+ Tools: crm_report: Always include system logs (if we can find them)
* Wed Mar 28 2012 Andrew Beekhof <andrew@beekhof.net> Pacemaker-1.1.7
- Update source tarball to revision: bc7ff2c
- Statistics:
Changesets: 513
Diff: 1171 files changed, 90472 insertions(+), 19368 deletions(-)
- Changes since Pacemaker-1.1.6.1
+ ais: Prepare for corosync versions using IPC from libqb
+ cib: Correctly shutdown in the presence of peers without relying on timers
+ cib: Don't halt disk writes if the previous digest is missing
+ cib: Determine when there are no peers to respond to our shutdown request and exit
+ cib: Ensure no additional messages are processed after we begin terminating
+ Cluster: Hook up the callbacks to the corosync quorum notifications
+ Core: basename() may modify its input, do not pass in a constant
+ Core: Bug cl#5016 - Prevent failures in recurring ops from being lost
+ Core: Bug rhbz#800054 - Correctly retrieve heartbeat uuids
+ Core: Correctly determine when an XML file should be decompressed
+ Core: Correctly track the length of a string without reading from uninitialzied memory (valgrind)
+ Core: Ensure signals are handled eventually in the absense of timer sources or IPC messages
+ Core: Prevent use-of-NULL in crm_update_peer()
+ Core: Strip text nodes from on disk xml files
+ Core: Support libqb for logging
+ corosync: Consistently set the correct uuid with get_node_uuid()
+ Corosync: Correctly disconnect from corosync variants
+ Corosync: Correctly extract the node id from membership udpates
+ corosync: Correctly infer lost members from the quorum API
+ Corosync: Default to using the nodeid as the node's uuid (instead of uname)
+ corosync: Ensure we catch nodes that leave the membership, even if the ringid doesn't change
+ corosync: Hook up CPG membership
+ corosync: Relax a development assert and gracefully handle the error condition
+ corosync: Remove deprecated member of the CFG API
+ corosync: Treat CS_ERR_QUEUE_FULL the same as CS_ERR_TRY_AGAIN
+ corosync: Unset the process list when nodes dissappear on us
+ crmd: Also purge fencing results when we enter S_NOT_DC
+ crmd: Bug cl#5015 - Remove the failed operation as well as the resulting fail-count and last-failure attributes
+ crmd: Correctly determine when a node can suicide with fencing
+ crmd: Election - perform the age comparison only once
+ crmd: Fast-track shutdown if we couldn't request it via attrd
+ crmd: Leave it up to the PE to decide which ops can/cannot be reload
+ crmd: Prevent use-after-free when calling delete_resource due to CRM_OP_REPROBE
+ crmd: Supply format arguments in the correct order
+ fencing: Add missing format parameter
+ fencing: Add the fencing topology section to the 1.1 configuration schema
+ fencing: fence_legacy - Drop spurilous host argument from status query
+ fencing: fence_legacy - Ensure port is available as an environment variable when calling monitor
+ fencing: fence_pcmk - don't block if nothing is specified on stdin
+ fencing: Fix log format error
+ fencing: Fix segfault caused by passing garbage to dlsym()
+ fencing: Fix use-of-NULL in process_remote_stonith_query()
+ fencing: Fix use-of-NULL when listing installed devices
+ fencing: Implement support for advanced fencing topologies: eg. kdump || (network && disk) || power
+ fencing: More gracefully handle failed 'list' operations for devices that only support a single connection
+ fencing: Prevent duplicate free when listing devices
+ fencing: Prevent uninitialized pointers being passed to free
+ fencing: Prevent use-after-free, we may need the query result for subsequent operations
+ fencing: Provide enough data to construct an entry in the node's fencing history
+ fencing: Standardize on /one/ method for clients to request members be fenced
+ fencing: Supress errors when listing all registered devices
+ mcp: corosync_cfg_state_track was removed from the corosync API, luckily we didnt use it for anything
+ mcp: Do not specify a WorkingDirectory in the systemd unit file - startup fails if its not available
+ mcp: Set the HA_quorum_type env variable consistently with our corosync plugin
+ mcp: Shut down if one of our child processes can/should not be respawned
+ pengine: Bug cl#5000 - Ensure ordering is preserved when depending on partial sets
+ pengine: Bug cl#5028 - Unmanaged services should block shutdown unless in maintenance mode
+ pengine: Bug cl#5038 - Prevent restart of anonymous clones when clone-max decreases
+ pengine: Bug cl#5007 - Fixes use of colocation constraints with multi-state resources
+ pengine: Bug cl#5014 - Prevent asymmetrical order constraints from causing resource stops
+ pengine: Bug cl#5000 - Implements ability to create rsc_order constraint sets such that A can start after B or C has started.
+ pengine: Correctly migrate a resource that has just migrated
+ pengine: Correct return from error path
+ pengine: Detect reloads of previously migrated resources
+ pengine: Ensure post-migration stop actions occur before node shutdown
+ pengine: Log as loudly as possible when we cannot shut down a cluster node
+ pengine: Reload of a resource no longer causes a restart of dependent resources
+ pengine: Support limiting the number of concurrent live migrations
+ pengine: Support referencing templates in constraints
+ pengine: Support of referencing resource templates in resource sets
+ pengine: Support to make tickets standby for relinquishing tickets gracefully
+ stonith: A "start" operation of a stonith resource does a "monitor" on the device beyond registering it
+ stonith: Bug rhbz#745526 - Ensure stonith_admin actually gets called by fence_pcmk
+ Stonith: Ensure all nodes receive and deliver notifications of the manual override
+ stonith: Fix the stonith timeout issue (cl#5009, bnc#727498)
+ Stonith: Implement a manual override for when nodes are known to be safely off
+ Tools: Bug cl#5003 - Prevent use-after-free in crm_simlate
+ Tools: crm_mon - Support to display tickets (based on Yuusuke Iida's work)
+ Tools: crm_simulate - Support to grant/revoke/standby/activate tickets from the new ticket state section
+ Tools: Implement crm_node functionality for native corosync
+ Fix a number of potential problems reported by coverity
* Wed Aug 31 2011 Andrew Beekhof <andrew@beekhof.net> 1.1.6
- Update source tarball to revision: 676e5f25aa46 tip
- Statistics:
Changesets: 376
Diff: 1761 files changed, 36259 insertions(+), 140578 deletions(-)
- Changes since Pacemaker-1.1.5
+ ais: check for retryable errors when dispatching AIS messages
+ ais: Correctly disconnect from Corosync and Cman based clusters
+ ais: Followup to previous patch - Ensure we drain the corosync queue of messages when Glib tells us there is input
+ ais: Handle IPC error before checking for NULL data (bnc#702907)
+ cib: Check the validation version before adding the originator details of a CIB change
+ cib: Remove disconnected remote connections from mainloop
+ cman: Correctly override existing fenced operations
+ cman: Dequeue all the cman emitted events and not only the first one leaving the others in the event's queue.
+ cman: Don't call fenced_join and fenced_leave when notifying cman of a fencing event.
+ cman: We need to run the crmd as root for CMAN so that we can ACK fencing operations
+ Core: Cancelled and pending operations do not count as failed
+ Core: Ensure there is sufficient space for EOS when building short-form option strings
+ Core: Fix variable expansion in pkg-config files
+ Core: Partial revert of accidental commit in previous patch
+ Core: Use dlopen to load heartbeat libraries on-demand
+ crmd: Bug lf#2509 - Watch for config option changes from the CIB even if we're not the DC
+ crmd: Bug lf#2528 - Introduce a slight delay when creating a transition to allow attrd time to perform its updates
+ crmd: Bug lf#2559 - Fail actions that were scheduled for a failed/fenced node
+ crmd: Bug lf#2584 - Allow nodes to fence themselves if they're the last one standing
+ crmd: Bug lf#2632 - Correctly handle nodes that return faster than stonith
+ crmd: Cancel timers for actions that were pending on dead nodes
+ crmd: Catch fence operations that claim to succeed but did not really
+ crmd: Do not wait for actions that were pending on dead nodes
+ crmd: Ensure we do not attempt to perform action on failed nodes
+ crmd: Prevent use-of-NULL by g_hash_table_iter_next()
+ crmd: Recurring actions shouldn't cause the last non-recurring action to be forgotten
+ crmd: Store only the last and last failed operation in the CIB
+ mcp: dirname() modifies the input path - pass in a copy of the logfile path
+ mcp: Enable stack detection logic instead of forcing 'corosync'
+ mcp: Fix spelling mistake in systemd service script that prevents shutdown
+ mcp: Shut down if corosync becomes unavailable
+ mcp: systemd control file is now functional
+ pengine: Before migrating an utilization-using resource to a node, take off the load which will no longer run there (lf#2599, bnc#695440)
+ pengine: Before migrating an utilization-using resource to a node, take off the load which will no longer run there (regression tests) (lf#2599, bnc#695440)
+ pengine: Bug lf#2574 - Prevent shuffling by choosing the correct clone instance to stop
+ pengine: Bug lf#2575 - Use uname for migration variables, id is a UUID on heartbeat
+ pengine: Bug lf#2581 - Avoid group restart when clone (re)starts on an unrelated node
+ pengine: Bug lf#2613, lf#2619 - Group migration after failures and non-default utilization policies
+ pengine: Bug suse#707150 - Prevent services being active if dependencies on clones are not satisfied
+ pengine: Correctly recognise which recurring operations are currently active
+ pengine: Demote from Master does not clear previous errors
+ pengine: Ensure restarts due to definition changes cause the start action to be re-issued not probes
+ pengine: Ensure role is preserved for unmanaged resources
+ pengine: Ensure unmanaged resources have the correct role set so the correct monitor operation is chosen
+ pengine: Fix memory leak for re-allocated resources reported by valgrind
+ pengine: Implement cluster ticket and deadman
+ pengine: Implement resource template
+ pengine: Correctly determine the state of multi-state resources with a partial operation history
+ pengine: Only allocate master/slave resources once
+ pengine: Partial revert of 'Minor code cleanup CS: cf6bca32376c On: 2011-08-15'
+ pengine: Resolve memory leak reported by valgrind
+ pengine: Restore the ability to save inputs to disk
+ Shell: implement -w,--wait option to wait for the transition to finish
+ Shell: repair template list command
+ Shell: set of commands to examine logs, reports, etc
+ Stonith: Consolidate pcmk_host_map into run_stonith_agent so that it is applied consistently
+ Stonith: Deprecate pcmk_arg_map for the saner pcmk_host_argument
+ Stonith: Fix use-of-NULL by g_hash_table_lookup
+ Stonith: Improved pcmk_host_map parsing
+ Stonith: Prevent use-of-NULL by g_hash_table_lookup
+ Stonith: Prevent use-of-NULL when no Linux-HA stonith agents are present
+ stonith: Add missing entries to stonith_error2string()
+ Stonith: Correctly finish sending agent options if the initial write is interrupted
+ stonith: Correctly handle synchronous calls
+ stonith: Coverity - Correctly construct result list for the query API call
+ stonith: Coverity - Remove badly constructed memory allocation from the query API call
+ stonith: Ensure completed operations are recorded as such in the history
+ Stonith: Ensure device parameters are passed to the daemon during registration
+ stonith: Fix use-of-NULL in stonith_api_device_list()
+ stonith: stonith_admin - Prevent use of uninitialized pointer by --history command
+ Tools: Bug lf#2528 - Make progress when attrd_updater is called repeatedly within the dampen interval but with the same value
+ Tools: crm_report - Correctly extract data from the local node
+ Tools: crm_report - Remove newlines when detecting the node list
+ Tools: crm_report - Repair the ability to extract data from the local machine
+ Tools: crm_report - Report on all detected backtraces
* Fri Feb 11 2011 Andrew Beekhof <andrew@beekhof.net> 1.1.5
- Update source tarball to revision: baad6636a053
- Statistics:
Changesets: 184
Diff: 605 files changed, 46103 insertions(+), 26417 deletions(-)
- Changes since Pacemaker-1.1.4
+ Add the ability to delegate sub-sections of the cluster to non-root users via ACLs
Needs to be enabled at compile time, not enabled by default.
+ ais: Bug lf#2550 - Report failed processes immediately
+ Core: Prevent recently introduced use-after-free in replace_xml_child()
+ Core: Reinstate the logic that skips past non-XML_ELEMENT_NODE children
+ Core: Remove extra calls to xmlCleanupParser resulting in use-after-free
+ Core: Repair reference to child-of-child after removal of xml_child_iter_filter from get_message_xml()
+ crmd: Bug lf#2545 - Ensure notify variables are accurate for stop operations
+ crmd: Cancel recurring operations while we're still connected to the lrmd
+ crmd: Reschedule the PE_START action if its not already running when we try to use it
+ crmd: Update failcount for failed promote and demote operations
+ pengine: Bug lf#2445 - Avoid relying on stickness for stable clone placement
+ pengine: Bug lf#2445 - Do not override configured clone stickiness values
+ pengine: Bug lf#2493 - Don't imply colocation requirements when applying ordering constraints with clones
+ pengine: Bug lf#2495 - Prevent segfault by validating the contents of ordering sets
+ pengine: Bug lf#2508 - Correctly reconstruct the status of anonymous cloned groups
+ pengine: Bug lf#2518 - Avoid spamming the logs with errors for orphan resources
+ pengine: Bug lf#2544 - Prevent unstable clone placement by factoring in the current node's score before all others
+ pengine: Bug lf#2554 - target-role alone is not sufficient to promote resources
+ pengine: Correct target_rc for probes of inactive resources (fix regression introduced by cs:ac3f03006e95)
+ pengine: Ensure that fencing has completed for stop actions on stonith-dependent resources (lf#2551)
+ pengine: Only update the node's promotion score if the resource is active there
+ pengine: Only use the promotion score from the current clone instance
+ pengine: Prevent use-of-NULL resulting from variable shadowing spotted by Coverity
+ pengine: Prevent use-of-NULL when there is status for an undefined node
+ pengine: Prevet use-after-free resulting from unintended recursion when chosing a node to promote master/slave resources
+ Shell: don't create empty optional sections (bnc#665131)
+ Stonith: Teach stonith_admin to automagically obtain the current node attributes for the target from the CIB
+ tools: Bug lf#2527 - Prevent use-of-NULL in crm_simulate
+ Tools: Prevent crm_resource commands from being lost due to the use of cib_scope_local
* Wed Oct 20 2010 Andrew Beekhof <andrew@beekhof.net> 1.1.4
- Update source tarball to revision: 75406c3eb2c1 tip
- Statistics:
Changesets: 169
Diff: 772 files changed, 56172 insertions(+), 39309 deletions(-)
- Changes since Pacemaker-1.1.3
+ Italian translation of Clusters from Scratch
+ Significant performance enhancements to the Policy Engine and CIB
+ cib: Bug lf#2506 - Don't remove client's when notifications fail, they might just be too big
+ cib: Drop invalid/failed connections from the client hashtable
+ cib: Ensure all diffs sent to peers have sufficient ordering information
+ cib: Ensure non-change diffs can preserve the ordering on the other side
+ cib: Fix the feature set check
+ cib: Include version information on our synthesised diffs when nothing changed
+ cib: Optimize the way we detect group/set ordering changes - 15% speedup
+ cib: Prevent false detection of config updates with the new diff format
+ cib: Reduce unnecessary copying when comparing xml objects
+ cib: Repair the processing of updates sent from peer nodes
+ cib: Revert part of a recent commit that purged still valid connections
+ cib: The feature set version check is only valid if the current value is non-NULL
+ Core: Actually removing diff markers is necessary
+ Core: Bug lf#2506 - Drop the compression limit because Heartbeat's IPC code sucks
+ Core: Cache Relax-NG schemas - profiling indicates many cycles are wasted needlessly re-parsing them
+ Core: Correctly compare against crm_log_level in the logging macros
+ Core: Correctly extract the version details from a diff
+ Core: Correctly hook up the RNG schema cache
+ Core: Correctly use lazy_xml_sort() for v2 digests
+ Core: Don't compress large payload elements unless we're approaching message limits
+ Core: Don't insert empty ID tags when applying diffs
+ Core: Enable the improve v2 digests
+ Core: Ensure ordering is preserved when applying diffs
+ Core: Fix the CRM_CHECK macro
+ Core: Modify the v2 digest algorithm so that some fields are sorted
+ Core: Prevent use-after-free when creating a CIB update for a timed out action
+ Core: Prevent use-of-NULL when cleaning up RelaxNG data structures
+ Core: Provide significant performance improvements by implementing versioned diffs and digests
+ crmd: All pending operations should be recorded, even recurring ones with high start delays
+ crmd: Don't abort transitions when probes are completed on a node
+ crmd: Don't hide stop events that time out - allowing faster recovery in the presence of overloaded hosts
+ crmd: Ensure the CIB is always writable on the DC by removing a timing hole
+ crmd: Include the correct transition details for timed out operations
+ crmd: Prevent use of NULL by making copies of the operation's hash table
+ crmd: There's no need to check the cib version from the 'added' part of diff updates
+ crmd: Use the supplied timeout for stop actions
+ mcp: Ensure valgrind is able to log its output somewhere
+ mcp: Use 99/01 for the start/stop sequence to avoid problems with services (such as libvirtd) started by init - Patch from Vladislav Bogdanov
+ pengine: Ensure fencing of the DC preceeds the STONITH_DONE operation
+ pengine: Fix memory leak introduced as part of the conversion to GHashTables
+ pengine: Fix memory leak when processing completed migration actions
+ pengine: Fix typo leading to use-of-NULL in the new ordering code
+ pengine: Free memory in recently introduced helper function
+ pengine: lf#2478 - Implement improved handling and recovery of atomic resource migrations
+ pengine: Obtain massive speedup by prepending to the list of ordering constraints (which can grow quite large)
+ pengine: Optimize the logic for deciding which non-grouped anonymous clone instances to probe for
+ pengine: Prevent clones from being stopped because resources colocated with them cannot be active
+ pengine: Try to ensure atomic migration ops occur within a single transition
+ pengine: Use hashtables instead of linked lists for performance sensitive datastructures
+ pengine: Use the original digest algorithm for parameter lists
+ stonith: cleanup children on timeout in fence_legacy
+ Stonith: Fix two memory leaks
+ Tools: crm_shadow - Avoid replacing the entire configuration (including status)
* Tue Sep 21 2010 Andrew Beekhof <andrew@beekhof.net> 1.1.3
- Update source tarball to revision: e3bb31c56244 tip
- Statistics:
Changesets: 352
Diff: 481 files changed, 14130 insertions(+), 11156 deletions(-)
- Changes since Pacemaker-1.1.2.1
+ ais: Bug lf#2401 - Improved processing when the peer crmd processes join/leave
+ ais: Correct the logic for conecting to plugin based clusters
+ ais: Do not supply a process list in mcp-mode
+ ais: Drop support for whitetank in the 1.1 release series
+ ais: Get an initial dump of the node membership when connecting to quorum-based clusters
+ ais: Guard against saturated cpg connections
+ ais: Handle CS_ERR_TRY_AGAIN in more cases
+ ais: Move the code for finding uid before the fork so that the child does no logging
+ ais: Never allow quorum plugins to affect connection to the pacemaker plugin
+ ais: Sign everyone up for peer process updates, not just the crmd
+ ais: The cluster type needs to be set before initializing classic openais connections
+ cib: Also free query result for xpath operations that return more than one hit
+ cib: Attempt to resolve memory corruption when forking a child to write the cib to disk
+ cib: Correctly free memory when writing out the cib to disk
+ cib: Fix the application of unversioned diffs
+ cib: Remove old developmental error logging
+ cib: Restructure the 'valid peer' check for deciding which instructions to ignore
+ cman: Correctly process membership/quorum changes from the pcmk plugin. Allow other message types through untouched
+ cman: Filter directed messages not intended for us
+ cman: Grab the initial membership when we connect
+ cman: Keep the list of peer processes up-to-date
+ cman: Make sure our common hooks are called after a cman membership update
+ cman: Make sure we can compile without cman present
+ cman: Populate sender details for cpg messages
+ cman: Update the ringid for cman based clusters
+ Core: Correctly unpack HA_Messages containing multiple entries with the same name
+ Core: crm_count_member() should only track nodes that have the full stack up
+ Core: New developmental logging system inspired by the kernel and a PoC from Lars Ellenberg
+ crmd: All nodes should see status updates, not just he DC
+ crmd: Allow non-DC nodes to clear failcounts too
+ crmd: Base DC election on process relative uptime
+ crmd: Bug lf#2439 - cancel_op() can also return HA_RSCBUSY
+ crmd: Bug lf#2439 - Handle asynchronous notification of resource deletion events
+ crmd: Bug lf#2458 - Ensure stop actions always have the relevant resource attributes
+ crmd: Disable age as a criteria for cman based clusters, its not reliable enough
+ crmd: Ensure we activate the DC timer if we detect an alternate DC
+ crmd: Factor the nanosecond component of process uptime in elections
+ crmd: Fix assertion failure when performing async resource failures
+ crmd: Fix handling of async resource deletion results
+ crmd: Include the action for crm graph operations
+ crmd: Make sure the membership cache is accurate after a sucessful fencing operation
+ crmd: Make sure we always poke the FSA after a transition to clear any TE_HALT actions
+ crmd: Offer crm-level membership once the peer starts the crmd process
+ crmd: Only need to request quorum update for plugin based clusters
+ crmd: Prevent assertion failure for stop actions resulting from cs: 3c0bc17c6daf
+ crmd: Prevent everyone from loosing DC elections by correctly initializing all relevant variables
+ crmd: Prevent segmentation fault
+ crmd: several fixes for async resource delete (thanks to beekhof)
+ crmd: Use the correct define/size for lrm resource IDs
+ Introduce two new cluster types 'cman' and 'corosync', replaces 'quorum_provider' concept
+ mcp: Add missing headers when built without heartbeat support
+ mcp: Correctly initialize the string containing the list of active daemons
+ mcp: Fix macro expansion in init script
+ mcp: Fix the expansion of the pid file in the init script
+ mcp: Handle CS_ERR_TRY_AGAIN when connecting to libcfg
+ mcp: Make sure we can compile the mcp without cman present
+ mcp: New master control process for (re)spawning pacemaker daemons
+ mcp: Read config early so we can re-initialize logging asap if daemonizing
+ mcp: Rename the mcp binary to pacemakerd and create a 'pacemaker' init script
+ mcp: Resend our process list after every CPG change
+ mcp: Tell chkconfig we need to shut down early on
+ pengine: Avoid creating invalid ordering constraints for probes that are not needed
+ pengine: Bug lf#1959 - Fail unmanaged resources should not prevent other services from shutting down
+ pengine: Bug lf#2422 - Ordering dependencies on partially active groups not observed properly
+ pengine: Bug lf#2424 - Use notify oepration definition if it exists in the configuration
+ pengine: Bug lf#2433 - No services should be stopped until probes finish
+ pengine: Bug lf#2453 - Enforce clone ordering in the absense of colocation constraints
+ pengine: Bug lf#2476 - Repair on-fail=block for groups and primitive resources
+ pengine: Correctly detect when there is a real failcount that expired and needs to be cleared
+ pengine: Correctly handle pseudo action creation
+ pengine: Correctly order clone startup after group/clone start
+ pengine: Correct use-after-free introduced in the prior patch
+ pengine: Do not demote resources because something that requires it can not run
+ pengine: Fix colocation for interleaved clones
+ pengine: Fix colocation with partially active groups
+ pengine: Fix potential use-after-free defect from coverity
+ pengine: Fix previous merge
+ pengine: Fix use-after-free in order_actions() reported by valgrind
+ pengine: Make the current data set a global variable so it does not need to be passed around everywhere
+ pengine: Prevent endless loop when looking for operation definitions in the configuration
+ pengine: Prevent segfault by ensuring the arguments to do_calculations() are initialized
+ pengine: Rewrite the ordering constraint logic to be simplicity, clarity and maintainability
+ pengine: Wait until stonith is available, do not fall back to shutdown for nodes requesting termination
+ Resolve coverity RESOURCE_LEAK defects
+ Shell: Complete the transition to using crm_attribute instead of crm_failcount and crm_standby
+ stonith: Advertise stonith-ng options in the metadata
+ stonith: Bug lf#2461 - Prevent segfault by not looking up operations if the hashtable has not been initialized yet
+ stonith: Bug lf#2473 - Add the timeout at the top level where the daemon is looking for it
+ Stonith: Bug lf#2473 - Ensure stonith operations complete within the timeout and are terminated if they run too long
+ stonith: Bug lf#2473 - Ensure timeouts are included for fencing operations
+ stonith: Bug lf#2473 - Gracefully handle remote operations that arrive late (after we have done notifications)
+ stonith: Correctly parse pcmk_host_list parameters that appear on a single line
+ stonith: Map poweron/poweroff back to on/off expected by the stonith tool from cluster-glue
+ stonith: pass the configuration to the stonith program via environment variables (bnc#620781)
+ Stonith: Use the timeout specified by the user
+ Support starting plugin-based Pacemaker clusters with the MCP as well
+ Tools: Bug lf#2456 - Fix assertion failure in crm_resource
+ tools: crm_node - Repair the ability to connect to openais based clusters
+ tools: crm_node - Use the correct short option for --cman
+ tools: crm_report - corosync.conf wont necessarily contain the text 'pacemaker' anymore
+ Tools: crm_simulate - Fix use-after-free in when terminating
+ tools: crm_simulate - Resolve coverity USE_AFTER_FREE defect
+ Tools: Drop the 'pingd' daemon and resource agent in favor of ocf:pacemaker:ping
+ Tools: Fix recently introduced use-of-NULL
+ Tools: Fix use-after-free defects from coverity
* Wed May 12 2010 Andrew Beekhof <andrew@beekhof.net> 1.1.2
- Update source tarball to revision: c25c972a25cc tip
- Statistics:
Changesets: 339
Diff: 708 files changed, 37918 insertions(+), 10584 deletions(-)
- Changes since Pacemaker-1.1.1
+ ais: Do not count votes from offline nodes and calculate current votes before sending quorum data
+ ais: Ensure the list of active processes sent to clients is always up-to-date
+ ais: Look for the correct conf variable for turning on file logging
+ ais: Need to find a better and thread-safe way to set core_uses_pid. Disable for now.
+ ais: Use the threadsafe version of getpwnam
+ Core: Bump the feature set due to the new failcount expiry feature
+ Core: fix memory leaks exposed by valgrind
+ Core: Bug lf#2414 - Prevent use-after-free reported by valgrind when doing xpath based deletions
+ crmd: Bug lf#2414 - Prevent use-after-free of the PE connection after it dies
+ crmd: Bug lf#2414 - Prevent use-after-free of the stonith-ng connection
+ crmd: Bug lf#2401 - Improved detection of partially active peers
+ crmd: Bug lf#2379 - Ensure the cluster terminates when the PE is not available
+ crmd: Do not allow the target_rc to be misused by resource agents
+ crmd: Do not ignore action timeouts based on FSA state
+ crmd: Ensure we don't get stuck in S_PENDING if we lose an election to someone that never talks to us again
+ crmd: Fix memory leaks exposed by valgrind
+ crmd: Remove race condition that could lead to multiple instances of a clone being active on a machine
+ crmd: Send erase_status_tag() calls to the local CIB when the DC is fenced, since there is no DC to accept them
+ crmd: Use global fencing notifications to prevent secondary fencing operations of the DC
+ pengine: Bug lf#2317 - Avoid needless restart of primitive depending on a clone
+ pengine: Bug lf#2361 - Ensure clones observe mandatory ordering constraints if the LHS is unrunnable
+ pengine: Bug lf#2383 - Combine failcounts for all instances of an anonymous clone on a host
+ pengine: Bug lf#2384 - Fix intra-set colocation and ordering
+ pengine: Bug lf#2403 - Enforce mandatory promotion (colocation) constraints
+ pengine: Bug lf#2412 - Correctly find clone instances by their prefix
+ pengine: Do not be so quick to pull the trigger on nodes that are coming up
+ pengine: Fix memory leaks exposed by valgrind
+ pengine: Rewrite native_merge_weights() to avoid Fix use-after-free
+ Shell: Bug bnc#590035 - always reload status if working with the cluster
+ Shell: Bug bnc#592762 - Default to using the status section from the live CIB
+ Shell: Bug lf#2315 - edit multiple meta_attributes sets in resource management
+ Shell: Bug lf#2221 - enable comments
+ Shell: Bug bnc#580492 - implement new cibstatus interface and commands
+ Shell: Bug bnc#585471 - new cibstatus import command
+ Shell: check timeouts also against the default-action-timeout property
+ Shell: new configure filter command
+ Tools: crm_mon - fix memory leaks exposed by valgrind
* Tue Feb 16 2010 Andrew Beekhof <andrew@beekhof.net> - 1.1.1
- First public release of Pacemaker 1.1
- Package reference documentation in a doc subpackage
- Move cts into a subpackage so that it can be easily consumed by others
- Update source tarball to revision: 17d9cd4ee29f
+ New stonith daemon that supports global notifications
+ Service placement influenced by the physical resources
+ A new tool for simulating failures and the cluster’s reaction to them
+ Ability to serialize an otherwise unrelated a set of resource actions (eg. Xen migrations)
* Mon Jan 18 2010 Andrew Beekhof <andrew@beekhof.net> - 1.0.7
- Update source tarball to revision: 2eed906f43e9 (stable-1.0) tip
- Statistics:
Changesets: 193
Diff: 220 files changed, 15933 insertions(+), 8782 deletions(-)
- Changes since 1.0.5-4
+ pengine: Bug 2213 - Ensure groups process location constraints so that clone-node-max works for cloned groups
+ pengine: Bug lf#2153 - non-clones should not restart when clones stop/start on other nodes
+ pengine: Bug lf#2209 - Clone ordering should be able to prevent startup of dependent clones
+ pengine: Bug lf#2216 - Correctly identify the state of anonymous clones when deciding when to probe
+ pengine: Bug lf#2225 - Operations that require fencing should wait for 'stonith_complete' not 'all_stopped'.
+ pengine: Bug lf#2225 - Prevent clone peers from stopping while another is instance is (potentially) being fenced
+ pengine: Correctly anti-colocate with a group
+ pengine: Correctly unpack ordering constraints for resource sets to avoid graph loops
+ Tools: crm: load help from crm_cli.txt
+ Tools: crm: resource sets (bnc#550923)
+ Tools: crm: support for comments (LF 2221)
+ Tools: crm: support for description attribute in resources/operations (bnc#548690)
+ Tools: hb2openais: add EVMS2 CSM processing (and other changes) (bnc#548093)
+ Tools: hb2openais: do not allow empty rules, clones, or groups (LF 2215)
+ Tools: hb2openais: refuse to convert pure EVMS volumes
+ cib: Ensure the loop for login message terminates
+ cib: Finally fix reliability of receiving large messages over remote plaintext connections
+ cib: Fix remote notifications
+ cib: For remote connections, default to CRM_DAEMON_USER since thats the only one that the cib can validate the password for using PAM
+ cib: Remote plaintext - Retry sending parts of the message that did not fit the first time
+ crmd: Ensure batch-limit is correctly enforced
+ crmd: Ensure we have the latest status after a transition abort
+ (bnc#547579,547582): Tools: crm: status section editing support
+ shell: Add allow-migrate as allowed meta-attribute (bnc#539968)
+ Medium: Build: Do not automatically add -L/lib, it could cause 64-bit arches to break
+ Medium: pengine: Bug lf#2206 - rsc_order constraints always use score at the top level
+ Medium: pengine: Only complain about target-role=master for non m/s resources
+ Medium: pengine: Prevent non-multistate resources from being promoted through target-role
+ Medium: pengine: Provide a default action for resource-set ordering
+ Medium: pengine: Silently fix requires=fencing for stonith resources so that it can be set in op_defaults
+ Medium: Tools: Bug lf#2286 - Allow the shell to accept template parameters on the command line
+ Medium: Tools: Bug lf#2307 - Provide a way to determin the nodeid of past cluster members
+ Medium: Tools: crm: add update method to template apply (LF 2289)
+ Medium: Tools: crm: direct RA interface for ocf class resource agents (LF 2270)
+ Medium: Tools: crm: direct RA interface for stonith class resource agents (LF 2270)
+ Medium: Tools: crm: do not add score which does not exist
+ Medium: Tools: crm: do not consider warnings as errors (LF 2274)
+ Medium: Tools: crm: do not remove sets which contain id-ref attribute (LF 2304)
+ Medium: Tools: crm: drop empty attributes elements
+ Medium: Tools: crm: exclude locations when testing for pathological constraints (LF 2300)
+ Medium: Tools: crm: fix exit code on single shot commands
+ Medium: Tools: crm: fix node delete (LF 2305)
+ Medium: Tools: crm: implement -F (--force) option
+ Medium: Tools: crm: rename status to cibstatus (LF 2236)
+ Medium: Tools: crm: revisit configure commit
+ Medium: Tools: crm: stay in crm if user specified level only (LF 2286)
+ Medium: Tools: crm: verify changes on exit from the configure level
+ Medium: ais: Some clients such as gfs_controld want a cluster name, allow one to be specified in corosync.conf
+ Medium: cib: Clean up logic for receiving remote messages
+ Medium: cib: Create valid notification control messages
+ Medium: cib: Indicate where the remote connection came from
+ Medium: cib: Send password prompt to stderr so that stdout can be redirected
+ Medium: cts: Fix rsh handling when stdout is not required
+ Medium: doc: Fill in the section on removing a node from an AIS-based cluster
+ Medium: doc: Update the docs to reflect the 0.6/1.0 rolling upgrade problem
+ Medium: doc: Use Publican for docbook based documentation
+ Medium: fencing: stonithd: add metadata for stonithd instance attributes (and support in the shell)
+ Medium: fencing: stonithd: ignore case when comparing host names (LF 2292)
+ Medium: tools: Make crm_mon functional with remote connections
+ Medium: xml: Add stopped as a supported role for operations
+ Medium: xml: Bug bnc#552713 - Treat node unames as text fields not IDs
+ Medium: xml: Bug lf#2215 - Create an always-true expression for empty rules when upgrading from 0.6
* Thu Oct 29 2009 Andrew Beekhof <andrew@beekhof.net> - 1.0.5-4
- Include the fixes from CoroSync integration testing
- Move the resource templates - they are not documentation
- Ensure documentation is placed in a standard location
- Exclude documentation that is included elsewhere in the package
- Update the tarball from upstream to version ee19d8e83c2a
+ cib: Correctly clean up when both plaintext and tls remote ports are requested
+ pengine: Bug bnc#515172 - Provide better defaults for lt(e) and gt(e) comparisions
+ pengine: Bug lf#2197 - Allow master instances placemaker to be influenced by colocation constraints
+ pengine: Make sure promote/demote pseudo actions are created correctly
+ pengine: Prevent target-role from promoting more than master-max instances
+ ais: Bug lf#2199 - Prevent expected-quorum-votes from being populated with garbage
+ ais: Prevent deadlock - don't try to release IPC message if the connection failed
+ cib: For validation errors, send back the full CIB so the client can display the errors
+ cib: Prevent use-after-free for remote plaintext connections
+ crmd: Bug lf#2201 - Prevent use-of-NULL when running heartbeat
* Wed Oct 13 2009 Andrew Beekhof <andrew@beekhof.net> - 1.0.5-3
- Update the tarball from upstream to version 38cd629e5c3c
+ Core: Bug lf#2169 - Allow dtd/schema validation to be disabled
+ pengine: Bug lf#2106 - Not all anonymous clone children are restarted after configuration change
+ pengine: Bug lf#2170 - stop-all-resources option had no effect
+ pengine: Bug lf#2171 - Prevent groups from starting if they depend on a complex resource which can not
+ pengine: Disable resource management if stonith-enabled=true and no stonith resources are defined
+ pengine: do not include master score if it would prevent allocation
+ ais: Avoid excessive load by checking for dead children every 1s (instead of 100ms)
+ ais: Bug rh#525589 - Prevent shutdown deadlocks when running on CoroSync
+ ais: Gracefully handle changes to the AIS nodeid
+ crmd: Bug bnc#527530 - Wait for the transition to complete before leaving S_TRANSITION_ENGINE
+ crmd: Prevent use-after-free with LOG_DEBUG_3
+ Medium: xml: Mask the "symmetrical" attribute on rsc_colocation constraints (bnc#540672)
+ Medium (bnc#520707): Tools: crm: new templates ocfs2 and clvm
+ Medium: Build: Invert the disable ais/heartbeat logic so that --without (ais|heartbeat) is available to rpmbuild
+ Medium: pengine: Bug lf#2178 - Indicate unmanaged clones
+ Medium: pengine: Bug lf#2180 - Include node information for all failed ops
+ Medium: pengine: Bug lf#2189 - Incorrect error message when unpacking simple ordering constraint
+ Medium: pengine: Correctly log resources that would like to start but can not
+ Medium: pengine: Stop ptest from logging to syslog
+ Medium: ais: Include version details in plugin name
+ Medium: crmd: Requery the resource metadata after every start operation
* Fri Aug 21 2009 Tomas Mraz <tmraz@redhat.com> - 1.0.5-2.1
- rebuilt with new openssl
* Wed Aug 19 2009 Andrew Beekhof <andrew@beekhof.net> - 1.0.5-2
- Add versioned perl dependency as specified by
https://fedoraproject.org/wiki/Packaging/Perl#Packages_that_link_to_libperl
- No longer remove RPATH data, it prevents us finding libperl.so and no other
libraries were being hardcoded
- Compile in support for heartbeat
- Conditionally add heartbeat-devel and corosynclib-devel to the -devel requirements
depending on which stacks are supported
* Mon Aug 17 2009 Andrew Beekhof <andrew@beekhof.net> - 1.0.5
- Add dependency on resource-agents
- Use the version of the configure macro that supplies --prefix, --libdir, etc
- Update the tarball from upstream to version 462f1569a437 (Pacemaker 1.0.5 final)
+ Tools: crm_resource - Advertise --move instead of --migrate
+ Medium: Extra: New node connectivity RA that uses system ping and attrd_updater
+ Medium: crmd: Note that dc-deadtime can be used to mask the brokeness of some switches
* Tue Aug 11 2009 Ville Skyttä <ville.skytta@iki.fi> - 1.0.5-0.7.c9120a53a6ae.hg
- Use bzipped upstream tarball.
* Wed Jul 29 2009 Andrew Beekhof <andrew@beekhof.net> - 1.0.5-0.6.c9120a53a6ae.hg
- Add back missing build auto* dependencies
- Minor cleanups to the install directive
* Tue Jul 28 2009 Andrew Beekhof <andrew@beekhof.net> - 1.0.5-0.5.c9120a53a6ae.hg
- Add a leading zero to the revision when alphatag is used
* Tue Jul 28 2009 Andrew Beekhof <andrew@beekhof.net> - 1.0.5-0.4.c9120a53a6ae.hg
- Incorporate the feedback from the cluster-glue review
- Realistically, the version is a 1.0.5 pre-release
- Use the global directive instead of define for variables
- Use the haclient/hacluster group/user instead of daemon
- Use the _configure macro
- Fix install dependencies
* Fri Jul 24 2009 Andrew Beekhof <andrew@beekhof.net> - 1.0.4-3
- Initial Fedora checkin
- Include an AUTHORS and license file in each package
- Change the library package name to pacemaker-libs to be more
Fedora compliant
- Remove execute permissions from xml related files
- Reference the new cluster-glue devel package name
- Update the tarball from upstream to version c9120a53a6ae
+ pengine: Only prevent migration if the clone dependency is stopping/starting on the target node
+ pengine: Bug 2160 - Don't shuffle clones due to colocation
+ pengine: New implementation of the resource migration (not stop/start) logic
+ Medium: Tools: crm_resource - Prevent use-of-NULL by requiring a resource name for the -A and -a options
+ Medium: pengine: Prevent use-of-NULL in find_first_action()
* Tue Jul 14 2009 Andrew Beekhof <andrew@beekhof.net> - 1.0.4-2
- Reference authors from the project AUTHORS file instead of listing in description
- Change Source0 to reference the Mercurial repo
- Cleaned up the summaries and descriptions
- Incorporate the results of Fedora package self-review
* Thu Jun 04 2009 Andrew Beekhof <abeekhof@suse.de> - 1.0.4
- Update source tarball to revision: 1d87d3e0fc7f (stable-1.0)
- Statistics:
Changesets: 209
Diff: 266 files changed, 12010 insertions(+), 8276 deletions(-)
- Changes since Pacemaker-1.0.3
+ (bnc#488291): ais: do not rely on byte endianness on ptr cast
+ (bnc#507255): Tools: crm: delete rsc/op_defaults (these meta_attributes are killing me)
+ (bnc#507255): Tools: crm: import properly rsc/op_defaults
+ (LF 2114): Tools: crm: add support for operation instance attributes
+ ais: Bug lf#2126 - Messages replies cannot be routed to transient clients
+ ais: Fix compilation for the latest Corosync API (v1719)
+ attrd: Do not perform all updates as complete refreshes
+ cib: Fix huge memory leak affecting heartbeat-based clusters
+ Core: Allow xpath queries to match attributes
+ Core: Generate the help text directly from a tool options struct
+ Core: Handle differences in 0.6 messaging format
+ crmd: Bug lf#2120 - All transient node attribute updates need to go via attrd
+ crmd: Correctly calculate how long an FSA action took to avoid spamming the logs with errors
+ crmd: Fix another large memory leak affecting Heartbeat based clusters
+ lha: Restore compatibility with older versions
+ pengine: Bug bnc#495687 - Filesystem is not notified of successful STONITH under some conditions
+ pengine: Make running a cluster with STONITH enabled but no STONITH resources an error and provide details on resolutions
+ pengine: Prevent use-ofNULL when using resource ordering sets
+ pengine: Provide inter-notification ordering guarantees
+ pengine: Rewrite the notification code to be understanable and extendable
+ Tools: attrd - Prevent race condition resulting in the cluster forgetting the node wishes to shut down
+ Tools: crm: regression tests
+ Tools: crm_mon - Fix smtp notifications
+ Tools: crm_resource - Repair the ability to query meta attributes
+ Low Build: Bug lf#2105 - Debian package should contain pacemaker doc and crm templates
+ Medium (bnc#507255): Tools: crm: handle empty rsc/op_defaults properly
+ Medium (bnc#507255): Tools: crm: use the right obj_type when creating objects from xml nodes
+ Medium (LF 2107): Tools: crm: revisit exit codes in configure
+ Medium: cib: Do not bother validating updates that only affect the status section
+ Medium: Core: Include supported stacks in version information
+ Medium: crmd: Record in the CIB, the cluster infrastructure being used
+ Medium: cts: Do not combine crm_standby arguments - the wrapper can not process them
+ Medium: cts: Fix the CIBAusdit class
+ Medium: Extra: Refresh showscores script from Dominik
+ Medium: pengine: Build a statically linked version of ptest
+ Medium: pengine: Correctly log the actions for resources that are being recovered
+ Medium: pengine: Correctly log the occurrence of promotion events
+ Medium: pengine: Implememt node health based on a patch from Mark Hamzy
+ Medium: Tools: Add examples to help text outputs
+ Medium: Tools: crm: catch syntax errors for configure load
+ Medium: Tools: crm: implement erasing nodes in configure erase
+ Medium: Tools: crm: work with parents only when managing xml objects
+ Medium: Tools: crm_mon - Add option to run custom notification program on resource operations (Patch by Dominik Klein)
+ Medium: Tools: crm_resource - Allow --cleanup to function on complex resources and cluster-wide
+ Medium: Tools: haresource2cib.py - Patch from horms to fix conversion error
+ Medium: Tools: Include stack information in crm_mon output
+ Medium: Tools: Two new options (--stack,--constraints) to crm_resource for querying how a resource is configured
* Wed Apr 08 2009 Andrew Beekhof <abeekhof@suse.de> - 1.0.3
- Update source tarball to revision: b133b3f19797 (stable-1.0) tip
- Statistics:
Changesets: 383
Diff: 329 files changed, 15471 insertions(+), 15119 deletions(-)
- Changes since Pacemaker-1.0.2
+ Added tag SLE11-HAE-GMC for changeset 9196be9830c2
+ ais plugin: Fix quorum calculation (bnc#487003)
+ ais: Another memory fix leak in error path
+ ais: Bug bnc#482847, bnc#482905 - Force a clean exit of OpenAIS once Pacemaker has finished unloading
+ ais: Bug bnc#486858 - Fix update_member() to prevent spamming clients with membership events containing no changes
+ ais: Centralize all quorum calculations in the ais plugin and allow expected votes to be configured int he cib
+ ais: Correctly handle a return value of zero from openais_dispatch_recv()
+ ais: Disable logging to a file
+ ais: Fix memory leak in error path
+ ais: IPC messages are only in scope until a response is sent
+ All signal handlers used with CL_SIGNAL() need to be as minimal as possible
+ cib: Bug bnc#482885 - Simplify CIB disk-writes to prevent data loss. Required a change to the backup filename format
+ cib: crmd: Revert part of 9782ab035003. Complex shutdown routines need G_main_add_SignalHandler to avoid race coditions
+ crm: Avoid infinite loop during crm configure edit (bnc#480327)
+ crmd: Avoid a race condition by waiting for the attrd update to trigger a transition automatically
+ crmd: Bug bnc#480977 - Prevent extra, partial, shutdown when a node restarts too quickly
+ crmd: Bug bnc#480977 - Prevent extra, partial, shutdown when a node restarts too quickly (verified)
+ crmd: Bug bnc#489063 - Ensure the DC is always unset after we 'lose' an election
+ crmd: Bug BSC#479543 - Correctly find the migration source for timed out migrate_from actions
+ crmd: Call crm_peer_init() before we start the FSA - prevents a race condition when used with Heartbeat
+ crmd: Erasing the status section should not be forced to the local node
+ crmd: Fix memory leak in cib notication processing code
+ crmd: Fix memory leak in transition graph processing
+ crmd: Fix memory leaks found by valgrind
+ crmd: More memory leaks fixes found by valgrind
+ fencing: stonithd: is_heartbeat_cluster is a no-no if there is no heartbeat support
+ pengine: Bug bnc#466788 - Exclude nodes that can not run resources
+ pengine: Bug bnc#466788 - Make colocation based on node attributes work
+ pengine: Bug BNC#478687 - Do not crash when clone-max is 0
+ pengine: Bug bnc#488721 - Fix id-ref expansion for clones, the doc-root for clone children is not the cib root
+ pengine: Bug bnc#490418 - Correctly determine node state for nodes wishing to be terminated
+ pengine: Bug LF#2087 - Correctly parse the state of anonymous clones that have multiple instances on a given node
+ pengine: Bug lf#2089 - Meta attributes are not inherited by clone children
+ pengine: Bug lf#2091 - Correctly restart modified resources that were found active by a probe
+ pengine: Bug lf#2094 - Fix probe ordering for cloned groups
+ pengine: Bug LF:2075 - Fix large pingd memory leaks
+ pengine: Correctly attach orphaned clone children to their parent
+ pengine: Correctly handle terminate node attributes that are set to the output from time()
+ pengine: Ensure orphaned clone members are hooked up to the parent when clone-max=0
+ pengine: Fix memory leak in LogActions
+ pengine: Fix the determination of whether a group is active
+ pengine: Look up the correct promotion preference for anonymous masters
+ pengine: Simplify handling of start failures by changing the default migration-threshold to INFINITY
+ pengine: The ordered option for clones no longer causes extra start/stop operations
+ RA: Bug bnc#490641 - Shut down dlm_controld with -TERM instead of -KILL
+ RA: pingd: Set default ping interval to 1 instead of 0 seconds
+ Resources: pingd - Correctly tell the ping daemon to shut down
+ Tools: Bug bnc#483365 - Ensure the command from cluster_test includes a value for --log-facility
+ Tools: cli: fix and improve delete command
+ Tools: crm: add and implement templates
+ Tools: crm: add support for command aliases and some common commands (i.e. cd,exit)
+ Tools: crm: create top configuration nodes if they are missing
+ Tools: crm: fix parsing attributes for rules (broken by the previous changeset)
+ Tools: crm: new ra set of commands
+ Tools: crm: resource agents information management
+ Tools: crm: rsc/op_defaults
+ Tools: crm: support for no value attribute in nvpairs
+ Tools: crm: the new configure monitor command
+ Tools: crm: the new configure node command
+ Tools: crm_mon - Prevent use-of-NULL when summarizing an orphan
+ Tools: hb2openais: create clvmd clone for respawn evmsd in ha.cf
+ Tools: hb2openais: fix a serious recursion bug in xml node processing
+ Tools: hb2openais: fix ocfs2 processing
+ Tools: pingd - prevent double free of getaddrinfo() output in error path
+ Tools: The default re-ping interval for pingd should be 1s not 1ms
+ Medium (bnc#479049): Tools: crm: add validation of resource type for the configure primitive command
+ Medium (bnc#479050): Tools: crm: add help for RA parameters in tab completion
+ Medium (bnc#479050): Tools: crm: add tab completion for primitive params/meta/op
+ Medium (bnc#479050): Tools: crm: reimplement cluster properties completion
+ Medium (bnc#486968): Tools: crm: listnodes function requires no parameters (do not mix completion with other stuff)
+ Medium: ais: Remove the ugly hack for dampening AIS membership changes
+ Medium: cib: Fix memory leaks by using mainloop_add_signal
+ Medium: cib: Move more logging to the debug level (was info)
+ Medium: cib: Overhaul the processing of synchronous replies
+ Medium: Core: Add library functions for instructing the cluster to terminate nodes
+ Medium: crmd: Add new expected-quorum-votes option
+ Medium: crmd: Allow up to 5 retires when an attrd update fails
+ Medium: crmd: Automatically detect and use new values for crm_config options
+ Medium: crmd: Bug bnc#490426 - Escalated shutdowns stall when there are pending resource operations
+ Medium: crmd: Clean up and optimize the DC election algorithm
+ Medium: crmd: Fix memory leak in shutdown
+ Medium: crmd: Fix memory leaks spotted by Valgrind
+ Medium: crmd: Ignore join messages from hosts other than our DC
+ Medium: crmd: Limit the scope of resource updates to the status section
+ Medium: crmd: Prevent the crmd from being respawned if its told to shut down when it did not ask to be
+ Medium: crmd: Re-check the election status after membership events
+ Medium: crmd: Send resource updates via the local CIB during elections
+ Medium: pengine: Bug bnc#491441 - crm_mon does not display operations returning 'uninstalled' correctly
+ Medium: pengine: Bug lf#2101 - For location constraints, role=Slave is equivalent to role=Started
+ Medium: pengine: Clean up the API - removed ->children() and renamed ->find_child() to fine_rsc()
+ Medium: pengine: Compress the display of healthy anonymous clones
+ Medium: pengine: Correctly log the actions for resources that are being recovered
+ Medium: pengine: Determin a promotion score for complex resources
+ Medium: pengine: Ensure clones always have a value for globally-unique
+ Medium: pengine: Prevent orphan clones from being allocated
+ Medium: RA: controld: Return proper exit code for stop op.
+ Medium: Tools: Bug bnc#482558 - Fix logging test in cluster_test
+ Medium: Tools: Bug bnc#482828 - Fix quoting in cluster_test logging setup
+ Medium: Tools: Bug bnc#482840 - Include directory path to CTSlab.py
+ Medium: Tools: crm: add more user input checks
+ Medium: Tools: crm: do not check resource status of we are working with a shadow
+ Medium: Tools: crm: fix id-refs and allow reference to top objects (i.e. primitive)
+ Medium: Tools: crm: ignore comments in the CIB
+ Medium: Tools: crm: multiple column output would not work with small lists
+ Medium: Tools: crm: refuse to delete running resources
+ Medium: Tools: crm: rudimentary if-else for templates
+ Medium: Tools: crm: Start/stop clones via target-role.
+ Medium: Tools: crm_mon - Compress the node status for healthy and offline nodes
+ Medium: Tools: crm_shadow - Return 0/cib_ok when --create-empty succeeds
+ Medium: Tools: crm_shadow - Support -e, the short form of --create-empty
+ Medium: Tools: Make attrd quieter
+ Medium: Tools: pingd - Avoid using various clplumbing functions as they seem to leak
+ Medium: Tools: Reduce pingd logging
* Mon Feb 16 2009 Andrew Beekhof <abeekhof@suse.de> - 1.0.2
- Update source tarball to revision: d232d19daeb9 (stable-1.0) tip
- Statistics:
Changesets: 441
Diff: 639 files changed, 20871 insertions(+), 21594 deletions(-)
- Changes since Pacemaker-1.0.1
+ (bnc#450815): Tools: crm cli: do not generate id for the operations tag
+ ais: Add support for the new AIS IPC layer
+ ais: Always set header.error to the correct default: SA_AIS_OK
+ ais: Bug BNC#456243 - Ensure the membership cache always contains an entry for the local node
+ ais: Bug BNC:456208 - Prevent deadlocks by not logging in the child process before exec()
+ ais: By default, disable supprt for the WIP openais IPC patch
+ ais: Detect and handle situations where ais and the crm disagree on the node name
+ ais: Ensure crm_peer_seq is updated after a membership update
+ ais: Make sure all IPC header fields are set to sane defaults
+ ais: Repair and streamline service load now that whitetank startup functions correctly
+ build: create and install doc files
+ cib: Allow clients without mainloop to connect to the cib
+ cib: CID:18 - Fix use-of-NULL in cib_perform_op
+ cib: CID:18 - Repair errors introduced in b5a18704477b - Fix use-of-NULL in cib_perform_op
+ cib: Ensure diffs contain the correct values of admin_epoch
+ cib: Fix four moderately sized memory leaks detected by Valgrind
+ Core: CID:10 - Prevent indexing into an array of schemas with a negative value
+ Core: CID:13 - Fix memory leak in log_data_element
+ Core: CID:15 - Fix memory leak in crm_get_peer
+ Core: CID:6 - Fix use-of-NULL in copy_ha_msg_input
+ Core: Fix crash in the membership code preventing node shutdown
+ Core: Fix more memory leaks foudn by valgrind
+ Core: Prevent unterminated strings after decompression
+ crmd: Bug BNC:467995 - Delay marking STONITH operations complete until STONITH tells us so
+ crmd: Bug LF:1962 - Do not NACK peers because they are not (yet) in our membership. Just ignore them.
+ crmd: Bug LF:2010 - Ensure fencing cib updates create the node_state entry if needed to preent re-fencing during cluster startup
+ crmd: Correctly handle reconnections to attrd
+ crmd: Ensure updates for lost migrate operations indicate which node it tried to migrating to
+ crmd: If there are no nodes to finalize, start an election.
+ crmd: If there are no nodes to welcome, start an election.
+ crmd: Prevent node attribute loss by detecting attrd disconnections immediately
+ crmd: Prevent node re-probe loops by ensuring mandatory actions always complete
+ pengine: Bug 2005 - Fix startup ordering of cloned stonith groups
+ pengine: Bug 2006 - Correctly reprobe cloned groups
+ pengine: Bug BNC:465484 - Fix the no-quorum-policy=suicide option
+ pengine: Bug LF:1996 - Correctly process disabled monitor operations
+ pengine: CID:19 - Fix use-of-NULL in determine_online_status
+ pengine: Clones now default to globally-unique=false
+ pengine: Correctly calculate the number of available nodes for the clone to use
+ pengine: Only shoot online nodes with no-quorum-policy=suicide
+ pengine: Prevent on-fail settings being ignored after a resource is successfully stopped
+ pengine: Prevent use-of-NULL for failed migrate actions in process_rsc_state()
+ pengine: Remove an optimization for the terminate node attribute that caused the cluster to block indefinitly
+ pengine: Repar the ability to colocate based on node attributes other than uname
+ pengine: Start the correct monitor operation for unmanaged masters
+ stonith: CID:3 - Fix another case of exceptionally poor error handling by the original stonith developers
+ stonith: CID:5 - Checking for NULL and then dereferencing it anyway is an interesting approach to error handling
+ stonithd: Sending IPC to the cluster is a privileged operation
+ stonithd: wrong checks for shmid (0 is a valid id)
+ Tools: attrd - Correctly determine when an attribute has stopped changing and should be committed to the CIB
+ Tools: Bug 2003 - pingd does not correctly detect failures when the interface is down
+ Tools: Bug 2003 - pingd does not correctly handle node-down events on multi-NIC systems
+ Tools: Bug 2021 - pingd does not detect sequence wrapping correctly, incorrectly reports nodes offline
+ Tools: Bug BNC:468066 - Do not use the result of uname() when its no longer in scope
+ Tools: Bug BNC:473265 - crm_resource -L dumps core
+ Tools: Bug LF:2001 - Transient node attributes should be set via attrd
+ Tools: Bug LF:2036 - crm_resource cannot set/get parameters for cloned resources
+ Tools: Bug LF:2046 - Node attribute updates are lost because attrd can take too long to start
+ Tools: Cause the correct clone instance to be failed with crm_resource -F
+ Tools: cluster_test - Allow the user to select a stack and fix CTS invocation
+ Tools: crm cli: allow rename only if the resource is stopped
+ Tools: crm cli: catch system errors on file operations
+ Tools: crm cli: completion for ids in configure
+ Tools: crm cli: drop '-rsc' from attributes for order constraint
+ Tools: crm cli: exit with an appropriate exit code
+ Tools: crm cli: fix wrong order of action and resource in order constraint
+ Tools: crm cli: fox wrong exit code
+ Tools: crm cli: improve handling of cib attributes
+ Tools: crm cli: new command: configure rename
+ Tools: crm cli: new command: configure upgrade
+ Tools: crm cli: new command: node delete
+ Tools: crm cli: prevent key errors on missing cib attributes
+ Tools: crm cli: print long help for help topics
+ Tools: crm cli: return on syntax error when parsing score
+ Tools: crm cli: rsc_location can be without nvpairs
+ Tools: crm cli: short node preference location constraint
+ Tools: crm cli: sometimes, on errors, level would change on single shot use
+ Tools: crm cli: syntax: drop a bunch of commas (remains of help tables conversion)
+ Tools: crm cli: verify user input for sanity
+ Tools: crm: find expressions within rules (do not always skip xml nodes due to used id)
+ Tools: crm_master should not define a set id now that attrd is used. Defining one can break lookups
+ Tools: crm_mon Use the OID assigned to the project by IANA for SNMP traps
+ Medium (bnc#445622): Tools: crm cli: improve the node show command and drop node status
+ Medium (LF 2009): stonithd: improve timeouts for remote fencing
+ Medium: ais: Allow dead peers to be removed from membership calculations
+ Medium: ais: Pass node deletion events on to clients
+ Medium: ais: Sanitize ipc usage
+ Medium: ais: Supply the node uname in addtion to the id
+ Medium: Build: Clean up configure to ensure NON_FATAL_CFLAGS is consistent with CFLAGS (ie. includes -g)
+ Medium: Build: Install cluster_test
+ Medium: Build: Use more restrictive CFLAGS and fix the resulting errors
+ Medium: cib: CID:20 - Fix potential use-after-free in cib_native_signon
+ Medium: Core: Bug BNC:474727 - Set a maximum time to wait for IPC messages
+ Medium: Core: CID:12 - Fix memory leak in decode_transition_magic error path
+ Medium: Core: CID:14 - Fix memory leak in calculate_xml_digest error path
+ Medium: Core: CID:16 - Fix memory leak in date_to_string error path
+ Medium: Core: Try to track down the cause of XML parsing errors
+ Medium: crmd: Bug BNC:472473 - Do not wait excessive amounts of time for lost actions
+ Medium: crmd: Bug BNC:472473 - Reduce the transition timeout to action_timeout+network_delay
+ Medium: crmd: Do not fast-track the processing of LRM refreshes when there are pending actions.
+ Medium: crmd: do_dc_join_filter_offer - Check the 'join' message is for the current instance before deciding to NACK peers
+ Medium: crmd: Find option values without having to do a config upgrade
+ Medium: crmd: Implement shutdown using a transient node attribute
+ Medium: crmd: Update the crmd options to use dashes instead of underscores
+ Medium: cts: Add 'cluster reattach' to the suite of automated regression tests
+ Medium: cts: cluster_test - Make some usability enhancements
+ Medium: CTS: cluster_test - suggest a valid port number
+ Medium: CTS: Fix python import order
+ Medium: cts: Implement an automated SplitBrain test
+ Medium: CTS: Remove references to deleted classes
+ Medium: Extra: Resources - Use HA_VARRUN instead of HA_RSCTMP for state files as Heartbeat removes HA_RSCTMP at startup
+ Medium: HB: Bug 1933 - Fake crmd_client_status_callback() calls because HB does not provide them for already running processes
+ Medium: pengine: CID:17 - Fix memory leak in find_actions_by_task error path
+ Medium: pengine: CID:7,8 - Prevent hypothetical use-of-NULL in LogActions
+ Medium: pengine: Defer logging the actions performed on a resource until we have processed ordering constraints
+ Medium: pengine: Remove the symmetrical attribute of colocation constraints
+ Medium: Resources: pingd - fix the meta defaults
+ Medium: Resources: Stateful - Add missing meta defaults
+ Medium: stonithd: exit if we the pid file cannot be locked
+ Medium: Tools: Allow attrd clients to specify the ID the attribute should be created with
+ Medium: Tools: attrd - Allow attribute updates to be performed from a hosts peer
+ Medium: Tools: Bug LF:1994 - Clean up crm_verify return codes
+ Medium: Tools: Change the pingd defaults to ping hosts once every second (instead of 5 times every 10 seconds)
+ Medium: Tools: cibmin - Detect resource operations with a view to providing email/snmp/cim notification
+ Medium: Tools: crm cli: add back symmetrical for order constraints
+ Medium: Tools: crm cli: generate role in location when converting from xml
+ Medium: Tools: crm cli: handle shlex exceptions
+ Medium: Tools: crm cli: keep order of help topics
+ Medium: Tools: crm cli: refine completion for ids in configure
+ Medium: Tools: crm cli: replace inf with INFINITY
+ Medium: Tools: crm cli: streamline cib load and parsing
+ Medium: Tools: crm cli: supply provider only for ocf class primitives
+ Medium: Tools: crm_mon - Add support for sending mail notifications of resource events
+ Medium: Tools: crm_mon - Include the DC version in status summary
+ Medium: Tools: crm_mon - Sanitize startup and option processing
+ Medium: Tools: crm_mon - switch to event-driven updates and add support for sending snmp traps
+ Medium: Tools: crm_shadow - Replace the --locate option with the saner --edit
+ Medium: Tools: hb2openais: do not remove Evmsd resources, but replace them with clvmd
+ Medium: Tools: hb2openais: replace crmadmin with crm_mon
+ Medium: Tools: hb2openais: replace the lsb class with ocf for o2cb
+ Medium: Tools: hb2openais: reuse code
+ Medium: Tools: LF:2029 - Display an error if crm_resource is used to reset the operation history of non-primitive resources
+ Medium: Tools: Make pingd resilient to attrd failures
+ Medium: Tools: pingd - fix the command line switches
+ Medium: Tools: Rename ccm_tool to crm_node
* Tue Nov 18 2008 Andrew Beekhof <abeekhof@suse.de> - 1.0.1
- Update source tarball to revision: 6fc5ce8302ab (stable-1.0) tip
- Statistics:
Changesets: 170
Diff: 816 files changed, 7633 insertions(+), 6286 deletions(-)
- Changes since Pacemaker-1.0.1
+ ais: Allow the crmd to get callbacks whenever a node state changes
+ ais: Create an option for starting the mgmtd daemon automatically
+ ais: Ensure HA_RSCTMP exists for use by resource agents
+ ais: Hook up the openais.conf config logging options
+ ais: Zero out the PID of disconnecting clients
+ cib: Ensure global updates cause a disk write when appropriate
+ Core: Add an extra snaity check to getXpathResults() to prevent segfaults
+ Core: Do not redefine __FUNCTION__ unnecessarily
+ Core: Repair the ability to have comments in the configuration
+ crmd: Bug:1975 - crmd should wait indefinitely for stonith operations to complete
+ crmd: Ensure PE processing does not occur for all error cases in do_pe_invoke_callback
+ crmd: Requests to the CIB should cause any prior PE calculations to be ignored
+ heartbeat: Wait for membership 'up' events before removing stale node status data
+ pengine: Bug LF:1988 - Ensure recurring operations always have the correct target-rc set
+ pengine: Bug LF:1988 - For unmanaged resources we need to skip the usual can_run_resources() checks
+ pengine: Ensure the terminate node attribute is handled correctly
+ pengine: Fix optional colocation
+ pengine: Improve up the detection of 'new' nodes joining the cluster
+ pengine: Prevent assert failures in master_color() by ensuring unmanaged masters are always reallocated to their current location
+ Tools: crm cli: parser: return False on syntax error and None for comments
+ Tools: crm cli: unify template and edit commands
+ Tools: crm_shadow - Show more line number information after validation failures
+ Tools: hb2openais: add option to upgrade the CIB to v3.0
+ Tools: hb2openais: add U option to getopts and update usage
+ Tools: hb2openais: backup improved and multiple fixes
+ Tools: hb2openais: fix class/provider reversal
+ Tools: hb2openais: fix testing
+ Tools: hb2openais: move the CIB update to the end
+ Tools: hb2openais: update logging and set logfile appropriately
+ Tools: LF:1969 - Attrd never sets any properties in the cib
+ Tools: Make attrd functional on OpenAIS
+ Medium: ais: Hook up the options for specifying the expected number of nodes and total quorum votes
+ Medium: ais: Look for pacemaker options inside the service block with 'name: pacemaker' instead of creating an addtional configuration block
+ Medium: ais: Provide better feedback when nodes change nodeids (in openais.conf)
+ Medium: cib: Always store cib contents on disk with num_updates=0
+ Medium: cib: Ensure remote access ports are cleaned up on shutdown
+ Medium: crmd: Detect deleted resource operations automatically
+ Medium: crmd: Erase a nodes resource operations and transient attributes after a successful STONITH
+ Medium: crmd: Find a more appropriate place to update quorum and refresh attrd attributes
+ Medium: crmd: Fix the handling of unexpected PE exits to ensure the current CIB is stored
+ Medium: crmd: Fix the recording of pending operations in the CIB
+ Medium: crmd: Initiate an attrd refresh _after_ the status section has been fully repopulated
+ Medium: crmd: Only the DC should update quorum in an openais cluster
+ Medium: Ensure meta attributes are used consistantly
+ Medium: pengine: Allow group and clone level resource attributes
+ Medium: pengine: Bug N:437719 - Ensure scores from colocated resources count when allocating groups
+ Medium: pengine: Prevent lsb scripts from being used in globally unique clones
+ Medium: pengine: Make a best-effort guess at a migration threshold for people with 0.6 configs
+ Medium: Resources: controld - ensure we are part of a clone with globally_unique=false
+ Medium: Tools: attrd - Automatically refresh all attributes after a CIB replace operation
+ Medium: Tools: Bug LF:1985 - crm_mon - Correctly process failed cib queries to allow reconnection after cluster restarts
+ Medium: Tools: Bug LF:1987 - crm_verify incorrectly warns of configuration upgrades for the most recent version
+ Medium: Tools: crm (bnc#441028): check for key error in attributes management
+ Medium: Tools: crm_mon - display the meaning of the operation rc code instead of the status
+ Medium: Tools: crm_mon - Fix the display of timing data
+ Medium: Tools: crm_verify - check that we are being asked to validate a complete config
+ Medium: xml: Relax the restriction on the contents of rsc_locaiton.node
* Thu Oct 16 2008 Andrew Beekhof <abeekhof@suse.de> - 1.0.0
- Update source tarball to revision: 388654dfef8f tip
- Statistics:
Changesets: 261
Diff: 3021 files changed, 244985 insertions(+), 111596 deletions(-)
- Changes since f805e1b30103
+ add the crm cli program
+ ais: Move the service id definition to a common location and make sure it is always used
+ build: rename hb2openais.sh to .in and replace paths with vars
+ cib: Implement --create for crm_shadow
+ cib: Remove dead files
+ Core: Allow the expected number of quorum votes to be configrable
+ Core: cl_malloc and friends were removed from Heartbeat
+ Core: Only call xmlCleanupParser() if we parsed anything. Doing so unconditionally seems to cause a segfault
+ hb2openais.sh: improve pingd handling; several bugs fixed
+ hb2openais: fix clone creation; replace EVMS strings
+ new hb2openais.sh conversion script
+ pengine: Bug LF:1950 - Ensure the current values for all notification variables are always set (even if empty)
+ pengine: Bug LF:1955 - Ensure unmanaged masters are unconditionally repromoted to ensure they are monitored correctly.
+ pengine: Bug LF:1955 - Fix another case of filtering causing unmanaged master failures
+ pengine: Bug LF:1955 - Umanaged mode prevents master resources from being allocated correctly
+ pengine: Bug N:420538 - Anit-colocation caused a positive node preference
+ pengine: Correctly handle unmanaged resources to prevent them from being started elsewhere
+ pengine: crm_resource - Fix the --migrate command
+ pengine: MAke stonith-enabled default to true and warn if no STONITH resources are found
+ pengine: Make sure orphaned clone children are created correctly
+ pengine: Monitors for unmanaged resources do not need to wait for start/promote/demote actions to complete
+ stonithd (LF 1951): fix remote stonith operations
+ stonithd: fix handling of timeouts
+ stonithd: fix logic for stonith resource priorities
+ stonithd: implement the fence-timeout instance attribute
+ stonithd: initialize value before reading fence-timeout
+ stonithd: set timeouts for fencing ops to the timeout of the start op
+ stonithd: stonith rsc priorities (new feature)
+ Tools: Add hb2openais - a tool for upgrading a Heartbeat cluster to use OpenAIS instead
+ Tools: crm_verify - clean up the upgrade logic to prevent crash on invalid configurations
+ Tools: Make pingd functional on Linux
+ Update version numbers for 1.0 candidates
+ Medium: ais: Add support for a synchronous call to retrieve the nodes nodeid
+ Medium: ais: Use the agreed service number
+ Medium: Build: Reliably detect heartbeat libraries during configure
+ Medium: Build: Supply prototypes for libreplace functions when needed
+ Medium: Build: Teach configure how to find corosync
+ Medium: Core: Provide better feedback if Pacemaker is started by a stack it does not support
+ Medium: crmd: Avoid calling GHashTable functions with NULL
+ Medium: crmd: Delay raising I_ERROR when the PE exits until we have had a chance to save the current CIB
+ Medium: crmd: Hook up the stonith-timeout option to stonithd
+ Medium: crmd: Prevent potential use-of-NULL in global_timer_callback
+ Medium: crmd: Rationalize the logging of graph aborts
+ Medium: pengine: Add a stonith_timeout option and remove new options that are better set in rsc_defaults
+ Medium: pengine: Allow external entities to ask for a node to be shot by creating a terminate=true transient node attribute
+ Medium: pengine: Bug LF:1950 - Notifications do not contain all documented resource state fields
+ Medium: pengine: Bug N:417585 - Do not restart group children whos individual score drops below zero
+ Medium: pengine: Detect clients that disconnect before receiving their reply
+ Medium: pengine: Implement a true maintenance mode
+ Medium: pengine: Implement on-fail=standby for NTT. Derived from a patch by Satomi TANIGUCHI
+ Medium: pengine: Print the correct message when stonith is disabled
+ Medium: pengine: ptest - check the input is valid before proceeding
+ Medium: pengine: Revert group stickiness to the 'old way'
+ Medium: pengine: Use the correct attribute for action 'requires' (was prereq)
+ Medium: stonithd: Fix compilation without full heartbeat install
+ Medium: stonithd: exit with better code on empty host list
+ Medium: tools: Add a new regression test for CLI tools
+ Medium: tools: crm_resource - return with non-zero when a resource migration command is invalid
+ Medium: tools: crm_shadow - Allow the admin to start with an empty CIB (and no cluster connection)
+ Medium: xml: pacemaker-0.7 is now an alias for the 1.0 schema
* Mon Sep 22 2008 Andrew Beekhof <abeekhof@suse.de> - 0.7.3
- Update source tarball to revision: 33e677ab7764+ tip
- Statistics:
Changesets: 133
Diff: 89 files changed, 7492 insertions(+), 1125 deletions(-)
- Changes since f805e1b30103
+ Tools: add the crm cli program
+ Core: cl_malloc and friends were removed from Heartbeat
+ Core: Only call xmlCleanupParser() if we parsed anything. Doing so unconditionally seems to cause a segfault
+ new hb2openais.sh conversion script
+ pengine: Bug LF:1950 - Ensure the current values for all notification variables are always set (even if empty)
+ pengine: Bug LF:1955 - Ensure unmanaged masters are unconditionally repromoted to ensure they are monitored correctly.
+ pengine: Bug LF:1955 - Fix another case of filtering causing unmanaged master failures
+ pengine: Bug LF:1955 - Umanaged mode prevents master resources from being allocated correctly
+ pengine: Bug N:420538 - Anit-colocation caused a positive node preference
+ pengine: Correctly handle unmanaged resources to prevent them from being started elsewhere
+ pengine: crm_resource - Fix the --migrate command
+ pengine: MAke stonith-enabled default to true and warn if no STONITH resources are found
+ pengine: Make sure orphaned clone children are created correctly
+ pengine: Monitors for unmanaged resources do not need to wait for start/promote/demote actions to complete
+ stonithd (LF 1951): fix remote stonith operations
+ Tools: crm_verify - clean up the upgrade logic to prevent crash on invalid configurations
+ Medium: ais: Add support for a synchronous call to retrieve the nodes nodeid
+ Medium: ais: Use the agreed service number
+ Medium: pengine: Allow external entities to ask for a node to be shot by creating a terminate=true transient node attribute
+ Medium: pengine: Bug LF:1950 - Notifications do not contain all documented resource state fields
+ Medium: pengine: Bug N:417585 - Do not restart group children whos individual score drops below zero
+ Medium: pengine: Implement a true maintenance mode
+ Medium: pengine: Print the correct message when stonith is disabled
+ Medium: stonithd: exit with better code on empty host list
+ Medium: xml: pacemaker-0.7 is now an alias for the 1.0 schema
* Wed Aug 20 2008 Andrew Beekhof <abeekhof@suse.de> - 0.7.1
- Update source tarball to revision: f805e1b30103+ tip
- Statistics:
Changesets: 184
Diff: 513 files changed, 43408 insertions(+), 43783 deletions(-)
- Changes since 0.7.0-19
+ Fix compilation when GNUTLS isn't found
+ admin: Fix use-after-free in crm_mon
+ Build: Remove testing code that prevented heartbeat-only builds
+ cib: Use single quotes so that the xpath queries for nvpairs will succeed
+ crmd: Always connect to stonithd when the TE starts and ensure we notice if it dies
+ crmd: Correctly handle a dead PE process
+ crmd: Make sure async-failures cause the failcount to be incremented
+ pengine: Bug LF:1941 - Handle failed clone instance probes when clone-max < #nodes
+ pengine: Parse resource ordering sets correctly
+ pengine: Prevent use-of-NULL - order->rsc_rh will not always be non-NULL
+ pengine: Unpack colocation sets correctly
+ Tools: crm_mon - Prevent use-of-NULL for orphaned resources
+ Medium: ais: Add support for a synchronous call to retrieve the nodes nodeid
+ Medium: ais: Allow transient clients to receive membership updates
+ Medium: ais: Avoid double-free in error path
+ Medium: ais: Include in the mebership nodes for which we have not determined their hostname
+ Medium: ais: Spawn the PE from the ais plugin instead of the crmd
+ Medium: cib: By default, new configurations use the latest schema
+ Medium: cib: Clean up the CIB if it was already disconnected
+ Medium: cib: Only increment num_updates if something actually changed
+ Medium: cib: Prevent use-after-free in client after abnormal termination of the CIB
+ Medium: Core: Fix memory leak in xpath searches
+ Medium: Core: Get more details regarding parser errors
+ Medium: Core: Repair expand_plus_plus - do not call char2score on unexpanded values
+ Medium: Core: Switch to the libxml2 parser - its significantly faster
+ Medium: Core: Use a libxml2 library function for xml -> text conversion
+ Medium: crmd: Asynchronous failure actions have no parameters
+ Medium: crmd: Avoid calling glib functions with NULL
+ Medium: crmd: Do not allow an election to promote a node from S_STARTING
+ Medium: crmd: Do not vote if we have not completed the local startup
+ Medium: crmd: Fix te_update_diff() now that get_object_root() functions differently
+ Medium: crmd: Fix the lrmd xpath expressions to not contain quotes
+ Medium: crmd: If we get a join offer during an election, better restart the election
+ Medium: crmd: No further processing is needed when using the LRMs API call for failing resources
+ Medium: crmd: Only update have-quorum if the value changed
+ Medium: crmd: Repair the input validation logic in do_te_invoke
+ Medium: cts: CIBs can no longer contain comments
+ Medium: cts: Enable a bunch of tests that were incorrectly disabled
+ Medium: cts: The libxml2 parser wont allow v1 resources to use integers as parameter names
+ Medium: Do not use the cluster UID and GID directly. Look them up based on the configured value of HA_CCMUSER
+ Medium: Fix compilation when heartbeat is not supported
+ Medium: pengine: Allow groups to be involved in optional ordering constraints
+ Medium: pengine: Allow sets of operations to be reused by multiple resources
+ Medium: pengine: Bug LF:1941 - Mark extra clone instances as orphans and do not show inactive ones
+ Medium: pengine: Determin the correct migration-threshold during resource expansion
+ Medium: pengine: Implement no-quorum-policy=suicide (FATE #303619)
+ Medium: pengine: Clean up resources after stopping old copies of the PE
+ Medium: pengine: Teach the PE how to stop old copies of itself
+ Medium: Tools: Backport hb_report updates
+ Medium: Tools: cib_shadow - On create, spawn a new shell with CIB_shadow and PS1 set accordingly
+ Medium: Tools: Rename cib_shadow to crm_shadow
* Fri Jul 18 2008 Andrew Beekhof <abeekhof@suse.de> - 0.7.0-19
- Update source tarball to revision: 007c3a1c50f5 (unstable) tip
- Statistics:
Changesets: 108
Diff: 216 files changed, 4632 insertions(+), 4173 deletions(-)
- Changes added since unstable-0.7
+ admin: Fix use-after-free in crm_mon
+ ais: Change the tag for the ais plugin to "pacemaker" (used in openais.conf)
+ ais: Log terminated processes as an error
+ cib: Performance - Reorganize things to avoid calculating the XML diff twice
+ pengine: Bug LF:1941 - Handle failed clone instance probes when clone-max < #nodes
+ pengine: Fix memory leak in action2xml
+ pengine: Make OCF_ERR_ARGS a node-level error rather than a cluster-level one
+ pengine: Properly handle clones that are not installed on all nodes
+ Medium: admin: cibadmin - Show any validation errors if the upgrade failed
+ Medium: admin: cib_shadow - Implement --locate to display the underlying filename
+ Medium: admin: cib_shadow - Implement a --diff option
+ Medium: admin: cib_shadow - Implement a --switch option
+ Medium: admin: crm_resource - create more compact constraints that do not use lifetime (which is deprecated)
+ Medium: ais: Approximate born_on for OpenAIS based clusters
+ Medium: cib: Remove do_id_check, it is a poor substitute for ID validation by a schema
+ Medium: cib: Skip construction of pre-notify messages if no-one wants one
+ Medium: Core: Attempt to streamline some key functions to increase performance
+ Medium: Core: Clean up XML parser after validation
+ Medium: crmd: Detect and optimize the CRMs behavior when processing diffs of an LRM refresh
+ Medium: Fix memory leaks when resetting the name of an XML object
+ Medium: pengine: Prefer the current location if it is one of a group of nodes with the same (highest) score
* Wed Jun 25 2008 Andrew Beekhof <abeekhof@suse.de> - 0.7.0
- Update source tarball to revision: bde0c7db74fb tip
- Statistics:
Changesets: 439
Diff: 676 files changed, 41310 insertions(+), 52071 deletions(-)
- Changes added since stable-0.6
+ A new tool for setting up and invoking CTS
+ Admin: All tools now use --node (-N) for specifying node unames
+ Admin: All tools now use --xml-file (-x) and --xml-text (-X) for specifying where to find XML blobs
+ cib: Cleanup the API - remove redundant input fields
+ cib: Implement CIB_shadow - a facility for making and testing changes before uploading them to the cluster
+ cib: Make registering per-op callbacks an API call and renamed (for clarity) the API call for requesting notifications
+ Core: Add a facility for automatically upgrading old configurations
+ Core: Adopt libxml2 as the XML processing library - all external clients need to be recompiled
+ Core: Allow sending TLS messages larger than the MTU
+ Core: Fix parsing of time-only ISO dates
+ Core: Smarter handling of XML values containing quotes
+ Core: XML memory corruption - catch, and handle, cases where we are overwriting an attribute value with itself
+ Core: The xml ID type does not allow UUIDs that start with a number
+ Core: Implement XPath based versions of query/delete/replace/modify
+ Core: Remove some HA2.0.(3,4) compatibility code
+ crmd: Overhaul the detection of nodes that are starting vs. failed
+ pengine: Bug LF:1459 - Allow failures to expire
+ pengine: Have the PE do non-persistent configuration upgrades before performing calculations
+ pengine: Replace failure-stickiness with a simple 'migration-threshold'
+ tengine: Simplify the design by folding the tengine process into the crmd
+ Medium: Admin: Bug LF:1438 - Allow the list of all/active resource operations to be queried by crm_resource
+ Medium: Admin: Bug LF:1708 - crm_resource should print a warning if an attribute is already set as a meta attribute
+ Medium: Admin: Bug LF:1883 - crm_mon should display fail-count and operation history
+ Medium: Admin: Bug LF:1883 - crm_mon should display operation timing data
+ Medium: Admin: Bug N:371785 - crm_resource -C does not also clean up fail-count attributes
+ Medium: Admin: crm_mon - include timing data for failed actions
+ Medium: ais: Read options from the environment since objdb is not completely usable yet
+ Medium: cib: Add sections for op_defaults and rsc_defaults
+ Medium: cib: Better matching notification callbacks (for detecting duplicates and removal)
+ Medium: cib: Bug LF:1348 - Allow rules and attribute sets to be referenced for use in other objects
+ Medium: cib: BUG LF:1918 - By default, all cib calls now timeout after 30s
+ Medium: cib: Detect updates that decrease the version tuple
+ Medium: cib: Implement a client-side operation timeout - Requires LHA update
+ Medium: cib: Implement callbacks and async notifications for remote connections
+ Medium: cib: Make cib->cmds->update() an alias for modify at the API level (also implemented in cibadmin)
+ Medium: cib: Mark the CIB as disconnected if the IPC connection is terminated
+ Medium: cib: New call option 'cib_can_create' which can be passed to modify actions - allows the object to be created if it does not exist yet
+ Medium: cib: Reimplement get|set|delete attributes using XPath
+ Medium: cib: Remove some useless parts of the API
+ Medium: cib: Remove the 'attributes' scaffolding from the new format
+ Medium: cib: Implement the ability for clients to connect to remote servers
+ Medium: Core: Add support for validating xml against RelaxNG schemas
+ Medium: Core: Allow more than one item to be modified/deleted in XPath based operations
+ Medium: Core: Fix the sort_pairs function for creating sorted xml objects
+ Medium: Core: iso8601 - Implement subtract_duration and fix subtract_time
+ Medium: Core: Reduce the amount of xml copying
+ Medium: Core: Support value='value+=N' XML updates (in addtion to value='value++')
+ Medium: crmd: Add support for lrm_ops->fail_rsc if its available
+ Medium: crmd: HB - watch link status for node leaving events
+ Medium: crmd: Bug LF:1924 - Improved handling of lrmd disconnects and shutdowns
+ Medium: crmd: Do not wait for actions with a start_delay over 5 minutes. Confirm them immediately
+ Medium: pengine: Bug LF:1328 - Do not fencing nodes in clusters without managed resources
+ Medium: pengine: Bug LF:1461 - Give transient node attributes (in <status/>) preference over persistent ones (in <nodes/>)
+ Medium: pengine: Bug LF:1884, Bug LF:1885 - Implement N:M ordering and colocation constraints
+ Medium: pengine: Bug LF:1886 - Create a resource and operation 'defaults' config section
+ Medium: pengine: Bug LF:1892 - Allow recurring actions to be triggered at known times
+ Medium: pengine: Bug LF:1926 - Probes should complete before stop actions are invoked
+ Medium: pengine: Fix the standby when its set as a transient attribute
+ Medium: pengine: Implement a global 'stop-all-resources' option
+ Medium: pengine: Implement cibpipe, a tool for performing/simulating config changes "offline"
+ Medium: pengine: We do not allow colocation with specific clone instances
+ Medium: Tools: pingd - Implement a stack-independent version of pingd
+ Medium: xml: Ship an xslt for upgrading from 0.6 to 0.7
* Thu Jun 19 2008 Andrew Beekhof <abeekhof@suse.de> - 0.6.5
- Update source tarball to revision: b9fe723d1ac5 tip
- Statistics:
Changesets: 48
Diff: 37 files changed, 1204 insertions(+), 234 deletions(-)
- Changes since Pacemaker-0.6.4
+ Admin: Repair the ability to delete failcounts
+ ais: Audit IPC handling between the AIS plugin and CRM processes
+ ais: Have the plugin create needed /var/lib directories
+ ais: Make sure the sync and async connections are assigned correctly (not swapped)
+ cib: Correctly detect configuration changes - num_updates does not count
+ pengine: Apply stickiness values to the whole group, not the individual resources
+ pengine: Bug N:385265 - Ensure groups are migrated instead of remaining partially active on the current node
+ pengine: Bug N:396293 - Enforce mandatory group restarts due to ordering constraints
+ pengine: Correctly recover master instances found active on more than one node
+ pengine: Fix memory leaks reported by Valgrind
+ Medium: Admin: crm_mon - Misc improvements from Satomi Taniguchi
+ Medium: Bug LF:1900 - Resource stickiness should not allow placement in asynchronous clusters
+ Medium: crmd: Ensure joins are completed promptly when a node taking part dies
+ Medium: pengine: Avoid clone instance shuffling in more cases
+ Medium: pengine: Bug LF:1906 - Remove an optimization in native_merge_weights() causing group scores to behave eratically
+ Medium: pengine: Make use of target_rc data to correctly process resource operations
+ Medium: pengine: Prevent a possible use of NULL in sort_clone_instance()
+ Medium: tengine: Include target rc in the transition key - used to correctly determin operation failure
* Thu May 22 2008 Andrew Beekhof <abeekhof@suse.de> - 0.6.4
- Update source tarball to revision: 226d8e356924 tip
- Statistics:
Changesets: 55
Diff: 199 files changed, 7103 insertions(+), 12378 deletions(-)
- Changes since Pacemaker-0.6.3
+ crmd: Bug LF:1881 LF:1882 - Overhaul the logic for operation cancelation and deletion
+ crmd: Bug LF:1894 - Make sure cancelled recurring operations are cleaned out from the CIB
+ pengine: Bug N:387749 - Colocation with clones causes unnecessary clone instance shuffling
+ pengine: Ensure 'master' monitor actions are cancelled _before_ we demote the resource
+ pengine: Fix assert failure leading to core dump - make sure variable is properly initialized
+ pengine: Make sure 'slave' monitoring happens after the resource has been demoted
+ pengine: Prevent failure stickiness underflows (where too many failures become a _positive_ preference)
+ Medium: Admin: crm_mon - Only complain if the output file could not be opened
+ Medium: Common: filter_action_parameters - enable legacy handling only for older versions
+ Medium: pengine: Bug N:385265 - The failure stickiness of group children is ignored until it reaches -INFINITY
+ Medium: pengine: Implement master and clone colocation by exlcuding nodes rather than setting ones score to INFINITY (similar to cs: 756afc42dc51)
+ Medium: tengine: Bug LF:1875 - Correctly find actions to cancel when their node leaves the cluster
* Wed Apr 23 2008 Andrew Beekhof <abeekhof@suse.de> - 0.6.3
- Update source tarball to revision: fd8904c9bc67 tip
- Statistics:
Changesets: 117
Diff: 354 files changed, 19094 insertions(+), 11338 deletions(-)
- Changes since Pacemaker-0.6.2
+ Admin: Bug LF:1848 - crm_resource - Pass set name and id to delete_resource_attr() in the correct order
+ Build: SNMP has been moved to the management/pygui project
+ crmd: Bug LF1837 - Unmanaged resources prevent crmd from shutting down
+ crmd: Prevent use-after-free in lrm interface code (Patch based on work by Keisuke MORI)
+ pengine: Allow the cluster to make progress by not retrying failed demote actions
+ pengine: Anti-colocation with slave should not prevent master colocation
+ pengine: Bug LF 1768 - Wait more often for STONITH ops to complete before starting resources
+ pengine: Bug LF1836 - Allow is-managed-default=false to be overridden by individual resources
+ pengine: Bug LF185 - Prevent pointless master/slave instance shuffling by ignoring the master-pref of stopped instances
+ pengine: Bug N-191176 - Implement interleaved ordering for clone-to-clone scenarios
+ pengine: Bug N-347004 - Ensure clone notifications are always sent when an instance is stopped/started
+ pengine: Bug N-347004 - Include notification ordering is correct for interleaved clones
+ pengine: Bug PM-11 - Directly link probe_complete to starting clone instances
+ pengine: Bug PM1 - Fix setting failcounts when applied to complex resources
+ pengine: Bug PM12, LF1648 - Extensive revision of group ordering
+ pengine: Bug PM7 - Ensure masters are always demoted before they are stopped
+ pengine: Create probes after allocation to allow smarter handling of anonymous clones
+ pengine: Do not prioritize clone instances that must be moved
+ pengine: Fix error in previous commit that allowed more than the required number of masters to be promoted
+ pengine: Group start ordering fixes
+ pengine: Implement promote/demote ordering for cloned groups
+ tengine: Repair failcount updates
+ tengine: Use the correct offset when updating failcount
+ Medium: Admin: Add a summary output that can be easily parsed by CTS for audit purposes
+ Medium: Build: Make configure fail if bz2 or libxml2 are not present
+ Medium: Build: Re-instate a better default for LCRSODIR
+ Medium: CIB: Bug LF-1861 - Filter irrelvant error status from synchronous CIB clients
+ Medium: Core: Bug 1849 - Invalid conversion of ordinal leap year to gregorian date
+ Medium: Core: Drop compatibility code for 2.0.4 and 2.0.5 clusters
+ Medium: crmd: Bug LF-1860 - Automatically cancel recurring ops before demote and promote operations (not only stops)
+ Medium: crmd: Save the current CIB contents if we detect the PE crashed
+ Medium: pengine: Bug LF:1866 - Fix version check when applying compatibility handling for failed start operations
+ Medium: pengine: Bug LF:1866 - Restore the ability to have start failures not be fatal
+ Medium: pengine: Bug PM1 - Failcount applies to all instances of non-unique clone
+ Medium: pengine: Correctly set the state of partially active master/slave groups
+ Medium: pengine: Do not claim to be stopping an already stopped orphan
+ Medium: pengine: Ensure implies_left ordering constraints are always effective
+ Medium: pengine: Indicate each resources 'promotion' score
+ Medium: pengine: Prevent a possible use-of-NULL
+ Medium: pengine: Reprocess the current action if it changed (so that any prior dependencies are updated)
+ Medium: tengine: Bug LF-1859 - Wait for fail-count updates to complete before terminating the transition
+ Medium: tengine: Bug LF:1859 - Do not abort graphs due to our own failcount updates
+ Medium: tengine: Bug LF:1859 - Prevent the TE from interupting itself
* Thu Feb 14 2008 Andrew Beekhof <abeekhof@suse.de> - 0.6.2
- Update source tarball to revision: 28b1a8c1868b tip
- Statistics:
Changesets: 11
Diff: 7 files changed, 58 insertions(+), 18 deletions(-)
- Changes since Pacemaker-0.6.1
+ haresources2cib.py: set default-action-timeout to the default (20s)
+ haresources2cib.py: update ra parameters lists
+ Medium: SNMP: Allow the snmp subagent to be built (patch from MATSUDA, Daiki)
+ Medium: Tools: Make sure the autoconf variables in haresources2cib are expanded
* Tue Feb 12 2008 Andrew Beekhof <abeekhof@suse.de> - 0.6.1
- Update source tarball to revision: e7152d1be933 tip
- Statistics:
Changesets: 25
Diff: 37 files changed, 1323 insertions(+), 227 deletions(-)
- Changes since Pacemaker-0.6.0
+ CIB: Ensure changes to top-level attributes (like admin_epoch) cause a disk write
+ CIB: Ensure the archived file hits the disk before returning
+ CIB: Repair the ability to do 'atomic increment' updates (value="value++")
+ crmd: Bug #7 - Connecting to the crmd immediately after startup causes use-of-NULL
+ Medium: CIB: Mask cib_diff_resync results from the caller - they do not need to know
+ Medium: crmd: Delay starting the IPC server until we are fully functional
+ Medium: CTS: Fix the startup patterns
+ Medium: pengine: Bug 1820 - Allow the first resource in a group to be migrated
+ Medium: pengine: Bug 1820 - Check the colocation dependencies of resources to be migrated
* Mon Jan 14 2008 Andrew Beekhof <abeekhof@suse.de> - 0.6.0
- This is the first release of the Pacemaker Cluster Resource Manager formerly part of Heartbeat.
- For those looking for the GUI, mgmtd, CIM or TSA components, they are now found in
the new pacemaker-pygui project. Build dependencies prevent them from being
included in Heartbeat (since the built-in CRM is no longer supported) and,
being non-core components, are not included with Pacemaker.
- Update source tarball to revision: c94b92d550cf
- Statistics:
Changesets: 347
Diff: 2272 files changed, 132508 insertions(+), 305991 deletions(-)
- Test hardware:
+ 6-node vmware cluster (sles10-sp1/256MB/vmware stonith) on a single host (opensuse10.3/2GB/2.66GHz Quad Core2)
+ 7-node EMC Centera cluster (sles10/512MB/2GHz Xeon/ssh stonith)
- Notes: Heartbeat Stack
+ All testing was performed with STONITH enabled
+ The CRM was enabled using the "crm respawn" directive
- Notes: OpenAIS Stack
+ This release contains a preview of support for the OpenAIS cluster stack
+ The current release of the OpenAIS project is missing two important
patches that we require. OpenAIS packages containing these patches are
available for most major distributions at:
http://download.opensuse.org/repositories/server:/ha-clustering
+ The OpenAIS stack is not currently recommended for use in clusters that
have shared data as STONITH support is not yet implimented
+ pingd is not yet available for use with the OpenAIS stack
+ 3 significant OpenAIS issues were found during testing of 4 and 6 node
clusters. We are activly working together with the OpenAIS project to
get these resolved.
- Pending bugs encountered during testing:
+ OpenAIS #1736 - Openais membership took 20s to stabilize
+ Heartbeat #1750 - ipc_bufpool_update: magic number in head does not match
+ OpenAIS #1793 - Assertion failure in memb_state_gather_enter()
+ OpenAIS #1796 - Cluster message corruption
- Changes since Heartbeat-2.1.2-24
+ Add OpenAIS support
+ Admin: crm_uuid - Look in the right place for Heartbeat UUID files
+ admin: Exit and indicate a problem if the crmd exits while crmadmin is performing a query
+ cib: Fix CIB_OP_UPDATE calls that modify the whole CIB
+ cib: Fix compilation when supporting the heartbeat stack
+ cib: Fix memory leaks caused by the switch to get_message_xml()
+ cib: HA_VALGRIND_ENABLED needs to be set _and_ set to 1|yes|true
+ cib: Use get_message_xml() in preference to cl_get_struct()
+ cib: Use the return value from call to write() in cib_send_plaintext()
+ Core: ccm nodes can legitimately have a node id of 0
+ Core: Fix peer-process tracking for the Heartbeat stack
+ Core: Heartbeat does not send status notifications for nodes that were already part of the cluster. Fake them instead
+ CRM: Add children to HA_Messages such that the field name matches F_XML_TAGNAME
+ crm: Adopt a more flexible appraoch to enabling Valgrind
+ crm: Fix compilation when bzip2 is not installed
+ CRM: Future-proof get_message_xml()
+ crmd: Filter election responses based on time not FSA state
+ crmd: Handle all possible peer states in crmd_ha_status_callback()
+ crmd: Make sure the current date/time is set - prevents use-of-NULL when evaluating rules
+ crmd: Relax an assertion regrading ccm membership instances
+ crmd: Use (node->processes&crm_proc_ais) to accurately update the CIB after replace operations
+ crmd: Heartbeat: Accurately record peer client status
+ pengine: Bug 1777 - Allow colocation with a resource in the Stopped state
+ pengine: Bug 1822 - Prevent use-of-NULL in PromoteRsc()
+ pengine: Implement three recovery policies based on op_status and op_rc
+ pengine: Parse fail-count correctly (it may be set to ININFITY)
+ pengine: Prevent graph-loop when stonith agents need to be moved around before a STONITH op
+ pengine: Prevent graph-loops when two operations have the same name+interval
+ tengine: Cancel active timers when destroying graphs
+ tengine: Ensure failcount is set correctly for failed stops/starts
+ tengine: Update failcount for oeprations that time out
+ Medium: admin: Prevent hang in crm_mon -1 when there is no cib connection - Patch from Junko IKEDA
+ Medium: cib: Require --force|-f when performing potentially dangerous commands with cibadmin
+ Medium: cib: Tweak the shutdown code
+ Medium: Common: Only count peer processes of active nodes
+ Medium: Core: Create generic cluster sign-in method
+ Medium: core: Fix compilation when Heartbeat support is disabled
+ Medium: Core: General cleanup for supporting two stacks
+ Medium: Core: iso6601 - Support parsing of time-only strings
+ Medium: core: Isolate more code that is only needed when SUPPORT_HEARTBEAT is enabled
+ Medium: crm: Improved logging of errors in the XML parser
+ Medium: crmd: Fix potential use-of-NULL in string comparison
+ Medium: crmd: Reimpliment syncronizing of CIB queries and updates when invoking the PE
+ Medium: crm_mon: Indicate when a node is both in standby mode and offline
+ Medium: pengine: Bug 1822 - Do not try an promote groups if not all of it is active
+ Medium: pengine: on_fail=nothing is an alias for 'ignore' not 'restart'
+ Medium: pengine: Prevent a potential use-of-NULL in cron_range_satisfied()
+ snmp subagent: fix a problem on displaying an unmanaged group
+ snmp subagent: use the syslog setting
+ snmp: v2 support (thanks to Keisuke MORI)
+ snmp_subagent - made it not complain about some things if shutting down
diff --git a/INSTALL.md b/INSTALL.md
index 1845e42d20..e03c594918 100644
--- a/INSTALL.md
+++ b/INSTALL.md
@@ -1,83 +1,83 @@
# How to Install Pacemaker
## Build Dependencies
| Version | Fedora-based | Suse-based | Debian-based |
|:---------------:|:------------------:|:------------------:|:--------------:|
| 1.13 or later | automake | automake | automake |
| 2.64 or later | autoconf | autoconf | autoconf |
| | libtool | libtool | libtool |
| | libtool-ltdl-devel | | libltdl-dev |
| | libuuid-devel | libuuid-devel | uuid-dev |
| 0.27 or later | pkgconfig | pkgconfig | pkg-config |
| 2.42.0 or later | glib2-devel | glib2-devel | libglib2.0-dev |
-| | libxml2-devel | libxml2-devel | libxml2-dev |
+| 2.6.0 or later | libxml2-devel | libxml2-devel | libxml2-dev |
| | libxslt-devel | libxslt-devel | libxslt-dev |
| | bzip2-devel | libbz2-devel | libbz2-dev |
| 0.17.0 or later | libqb-devel | libqb-devel | libqb-dev |
| 3.4 or later | python3 | python3 | python3 |
| 0.18 or later | gettext-devel | gettext-tools | gettext |
| 0.18 or later | | | autopoint |
Also:
* make must be GNU (or compatible) (setting MAKE=gmake might also work but is
untested)
* GNU (or compatible) getopt must be somewhere on the PATH
### Cluster Stack Dependencies
*Only corosync is currently supported*
| Version | Fedora-based | Suse-based | Debian-based |
|:---------------:|:------------------:|:------------------:|:--------------:|
| 2.0.0 or later | corosynclib | libcorosync | corosync |
| 2.0.0 or later | corosynclib-devel | libcorosync-devel | |
| | | | libcfg-dev |
| | | | libcpg-dev |
| | | | libcmap-dev |
| | | | libquorum-dev |
### Optional Build Dependencies
| Feature Enabled | Version | Fedora-based | Suse-based | Debian-based |
|:-----------------------------------------------:|:--------------:|:-----------------------:|:-----------------------:|:-----------------------:|
| Pacemaker Remote and encrypted remote CIB admin | 2.12.0 or later| gnutls-devel | libgnutls-devel | libgnutls-dev |
| encrypted remote CIB admin | | pam-devel | pam-devel | libpam0g-dev |
| interactive crm_mon | | ncurses-devel | ncurses-devel | ncurses-dev |
| systemd support | | systemd-devel | systemd-devel | libsystemd-dev |
| systemd/upstart resource support | | dbus-devel | dbus-devel | libdbus-1-dev |
| Linux-HA style fencing agents | | cluster-glue-libs-devel | libglue-devel | cluster-glue-dev |
| documentation | | asciidoc or asciidoctor | asciidoc or asciidoctor | asciidoc or asciidoctor |
| documentation | | help2man | help2man | help2man |
| documentation | | inkscape | inkscape | inkscape |
| documentation | | docbook-style-xsl | docbook-xsl-stylesheets | docbook-xsl |
| documentation | | python3-sphinx | python3-sphinx | python3-sphinx |
| documentation (PDF) | | latexmk texlive texlive-capt-of texlive-collection-xetex texlive-fncychap texlive-framed texlive-multirow texlive-needspace texlive-tabulary texlive-titlesec texlive-threeparttable texlive-upquote texlive-wrapfig texlive-xetex | texlive texlive-latex | texlive texlive-latex-extra |
| annotated source code as HTML via "make global" | | global | global | global |
| RPM packages via "make rpm" | 4.11 or later | rpm | rpm | (n/a) |
| unit tests | 1.1.0 or later | libcmocka-devel | libcmocka-devel | libcmocka-dev |
## Optional testing dependencies
* procps and psmisc (if running cts-exec, cts-fencing, or CTS)
* valgrind (if running CTS valgrind tests)
* python3-systemd (if using CTS on cluster nodes running systemd)
* nmap (if not specifying an IP address base)
* oprofile (if running CTS profiling tests)
* dlm (to log DLM debugging info after CTS tests)
* xmllint (to validate tool output in cts-cli)
## Simple install
$ make && sudo make install
If GNU make is not your default make, use "gmake" instead.
## Detailed install
First, browse the build options that are available:
$ ./autogen.sh
$ ./configure --help
Re-run ./configure with any options you want, then proceed with the simple
method.
diff --git a/configure.ac b/configure.ac
index f20b80a012..9eb753953b 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1,2236 +1,2236 @@
dnl
dnl autoconf for Pacemaker
dnl
dnl Copyright 2009-2023 the Pacemaker project contributors
dnl
dnl The version control history for this file may have further details.
dnl
dnl This source code is licensed under the GNU General Public License version 2
dnl or later (GPLv2+) WITHOUT ANY WARRANTY.
dnl ==============================================
dnl Bootstrap autotools
dnl ==============================================
# Require a minimum version of autoconf itself
AC_PREREQ(2.64)
dnl AC_CONFIG_MACRO_DIR is deprecated as of autoconf 2.70 (2020-12-08).
dnl Once we can require that version, we can simplify this, and no longer
dnl need ACLOCAL_AMFLAGS in Makefile.am.
m4_ifdef([AC_CONFIG_MACRO_DIRS],
[AC_CONFIG_MACRO_DIRS([m4])],
[AC_CONFIG_MACRO_DIR([m4])])
m4_include([m4/version.m4])
AC_INIT([pacemaker], VERSION_NUMBER, [users@clusterlabs.org], [pacemaker],
PCMK_URL)
LT_CONFIG_LTDL_DIR([libltdl])
AC_CONFIG_AUX_DIR([libltdl/config])
dnl Where #defines that autoconf makes (e.g. HAVE_whatever) go
dnl
dnl include/config.h
dnl - Internal API
dnl - Contains all defines
dnl - include/config.h.in is generated automatically by autoheader
dnl - Not to be included in any header files except crm_internal.h
dnl (which is also not to be included in any other header files)
dnl
dnl include/crm_config.h
dnl - External API
dnl - Contains a subset of defines
dnl - include/crm_config.h.in is manually edited to select the subset
dnl - Should not include HAVE_* defines
dnl - Safe to include anywhere
AC_CONFIG_HEADERS([include/config.h include/crm_config.h])
dnl 1.13: minimum automake version required
dnl foreign: don't require GNU-standard top-level files
dnl tar-ustar: use (older) POSIX variant of generated tar rather than v7
dnl subdir-objects: keep .o's with their .c's (no-op in 2.0+)
AM_INIT_AUTOMAKE([1.13 foreign tar-ustar subdir-objects])
dnl Require minimum version of pkg-config
PKG_PROG_PKG_CONFIG(0.27)
AS_IF([test x"${PKG_CONFIG}" != x""], [],
[AC_MSG_FAILURE([Could not find required build tool pkg-config (0.27 or later)])])
PKG_INSTALLDIR
PKG_NOARCH_INSTALLDIR
dnl ==============================================
dnl Compiler checks and helpers
dnl ==============================================
dnl A particular compiler can be forced by setting the CC environment variable
AC_PROG_CC
dnl C++ is needed only to run maintainer utilities, not to build
AC_PROG_CXX
dnl Use at least C99 if possible (automatic for autoconf >= 2.70)
m4_version_prereq([2.70], [:], [AC_PROG_CC_STDC])
# cc_supports_flag <compiler-flag>
# Return success if the C compiler supports the given flag
cc_supports_flag() {
local CFLAGS="-Werror $@"
AC_MSG_CHECKING([whether $CC supports $@])
AC_COMPILE_IFELSE([AC_LANG_PROGRAM([[ ]], [[ ]])],
[RC=0; AC_MSG_RESULT([yes])],
[RC=1; AC_MSG_RESULT([no])])
return $RC
}
# cc_temp_flags <compiler-flags>
# Use the given flags for subsequent C compilation. These can be reverted to
# what was used previously with cc_restore_flags. This allows certain tests to
# use specific flags without affecting anything else.
cc_temp_flags() {
ac_save_CFLAGS="$CFLAGS"
CFLAGS="$*"
}
# cc_restore_flags
# Restore C compiler flags to what they were before the last cc_temp_flags
# call.
cc_restore_flags() {
CFLAGS=$ac_save_CFLAGS
}
# Check for fatal warning support
AS_IF([test $enable_fatal_warnings -ne $DISABLED dnl
&& test x"$GCC" = x"yes" && cc_supports_flag -Werror],
[WERROR="-Werror"],
[
WERROR=""
AS_CASE([$enable_fatal_warnings],
[$REQUIRED], [AC_MSG_ERROR([Compiler does not support fatal warnings])],
[$OPTIONAL], [enable_fatal_warnings=$DISABLED])
])
dnl We use md5.c from gnulib, which has its own m4 macros. Per its docs:
dnl "The macro gl_EARLY must be called as soon as possible after verifying that
dnl the C compiler is working. ... The core part of the gnulib checks are done
dnl by the macro gl_INIT." In addition, prevent gnulib from introducing OpenSSL
dnl as a dependency.
gl_EARLY
gl_SET_CRYPTO_CHECK_DEFAULT([no])
gl_INIT
AC_CHECK_SIZEOF(long)
dnl ==============================================
dnl Linker checks
dnl ==============================================
# Check whether linker supports --enable-new-dtags to use RUNPATH instead of
# RPATH. It is necessary to do this before libtool does linker detection.
# See also: https://github.com/kronosnet/kronosnet/issues/107
AX_CHECK_LINK_FLAG([-Wl,--enable-new-dtags],
[AM_LDFLAGS=-Wl,--enable-new-dtags],
[AC_MSG_ERROR(["Linker support for --enable-new-dtags is required"])])
AC_SUBST([AM_LDFLAGS])
saved_LDFLAGS="$LDFLAGS"
LDFLAGS="$AM_LDFLAGS $LDFLAGS"
LT_INIT([dlopen])
LDFLAGS="$saved_LDFLAGS"
LTDL_INIT([convenience])
dnl ==============================================
dnl Define configure options
dnl ==============================================
# yes_no_try <user-response> <default>
# Map a yes/no/try user selection to $REQUIRED for yes, $DISABLED for no, and
# $OPTIONAL for try.
DISABLED=0
REQUIRED=1
OPTIONAL=2
yes_no_try() {
local value
AS_IF([test x"$1" = x""], [value="$2"], [value="$1"])
AS_CASE(["`echo "$value" | tr '[A-Z]' '[a-z]'`"],
[0|no|false|disable], [return $DISABLED],
[1|yes|true|enable], [return $REQUIRED],
[try|check], [return $OPTIONAL]
)
AC_MSG_ERROR([Invalid option value "$value"])
}
#
# Fix the defaults of certain built-in variables so they can be used in the
# defaults for our custom arguments
#
AC_MSG_NOTICE([Sanitizing prefix: ${prefix}])
AS_IF([test x"$prefix" = x"NONE"],
[
prefix=/usr
dnl Fix default variables - "prefix" variable if not specified
AS_IF([test x"$localstatedir" = x"\${prefix}/var"],
[localstatedir="/var"])
AS_IF([test x"$sysconfdir" = x"\${prefix}/etc"],
[sysconfdir="/etc"])
])
AC_MSG_NOTICE([Sanitizing exec_prefix: ${exec_prefix}])
AS_CASE([$exec_prefix],
[prefix|NONE], [exec_prefix=$prefix])
AC_MSG_NOTICE([Sanitizing libdir: ${libdir}])
AS_CASE([$libdir],
[prefix|NONE], [
AC_MSG_CHECKING([which lib directory to use])
for aDir in lib64 lib
do
trydir="${exec_prefix}/${aDir}"
AS_IF([test -d ${trydir}],
[
libdir=${trydir}
break
])
done
AC_MSG_RESULT([$libdir])
])
# Start a list of optional features this build supports
PCMK_FEATURES=""
dnl This section should include only the definition of configure script
dnl options and determining their values. Processing should be done later when
dnl possible, other than what's needed to determine values and defaults.
dnl Per the autoconf docs, --enable-*/--disable-* options should control
dnl features inherent to Pacemaker, while --with-*/--without-* options should
dnl control the use of external software. However, --enable-*/--disable-* may
dnl implicitly require additional external dependencies, and
dnl --with-*/--without-* may implicitly enable or disable features, so the
dnl line is blurry.
dnl
dnl We also use --with-* options for custom file, directory, and path
dnl locations, since autoconf does not provide an option type for those.
dnl --enable-* options: build process
AC_ARG_ENABLE([quiet],
[AS_HELP_STRING([--enable-quiet],
[suppress make output unless there is an error @<:@no@:>@])]
)
yes_no_try "$enable_quiet" "no"
enable_quiet=$?
AC_ARG_ENABLE([fatal-warnings],
[AS_HELP_STRING([--enable-fatal-warnings],
[enable pedantic and fatal warnings for gcc @<:@try@:>@])],
)
yes_no_try "$enable_fatal_warnings" "try"
enable_fatal_warnings=$?
AC_ARG_ENABLE([hardening],
[AS_HELP_STRING([--enable-hardening],
[harden the resulting executables/libraries @<:@try@:>@])]
)
yes_no_try "$enable_hardening" "try"
enable_hardening=$?
dnl --enable-* options: features
AC_ARG_ENABLE([systemd],
[AS_HELP_STRING([--enable-systemd],
[enable support for managing resources via systemd @<:@try@:>@])]
)
yes_no_try "$enable_systemd" "try"
enable_systemd=$?
AC_ARG_ENABLE([upstart],
[AS_HELP_STRING([--enable-upstart],
[enable support for managing resources via Upstart (deprecated) @<:@try@:>@])]
)
yes_no_try "$enable_upstart" "try"
enable_upstart=$?
dnl --enable-* options: features inherent to Pacemaker
AC_ARG_ENABLE([compat-2.0],
[AS_HELP_STRING([--enable-compat-2.0], m4_normalize([
preserve certain output as it was in 2.0; this option will be
available only for the lifetime of the 2.1 series @<:@no@:>@]))]
)
yes_no_try "$enable_compat_2_0" "no"
enable_compat_2_0=$?
# Add an option to create symlinks at the pre-2.0.0 daemon name locations, so
# that users and tools can continue to invoke those names directly (e.g., for
# meta-data). This option will be removed in a future release.
AC_ARG_ENABLE([legacy-links],
[AS_HELP_STRING([--enable-legacy-links],
[add symlinks for old daemon names (deprecated) @<:@no@:>@])]
)
yes_no_try "$enable_legacy_links" "no"
enable_legacy_links=$?
# AM_GNU_GETTEXT calls AM_NLS which defines the nls option, but it defaults
# to enabled. We override the definition of AM_NLS to flip the default and mark
# it as experimental in the help text.
AC_DEFUN([AM_NLS],
[AC_MSG_CHECKING([whether NLS is requested])
AC_ARG_ENABLE([nls],
[AS_HELP_STRING([--enable-nls],
[use Native Language Support (experimental)])],
USE_NLS=$enableval, USE_NLS=no)
AC_MSG_RESULT([$USE_NLS])
AC_SUBST([USE_NLS])]
)
AM_GNU_GETTEXT([external])
AM_GNU_GETTEXT_VERSION([0.18])
dnl --with-* options: external software support, and custom locations
dnl This argument is defined via an M4 macro so default can be a variable
AC_DEFUN([VERSION_ARG],
[AC_ARG_WITH([version],
[AS_HELP_STRING([--with-version=VERSION],
[override package version @<:@$1@:>@])],
[ PACEMAKER_VERSION="$withval" ],
[ PACEMAKER_VERSION="$PACKAGE_VERSION" ])]
)
VERSION_ARG(VERSION_NUMBER)
CRM_DAEMON_USER=""
AC_ARG_WITH([daemon-user],
[AS_HELP_STRING([--with-daemon-user=USER],
[user to run unprivileged Pacemaker daemons as (advanced option: changing this may break other cluster components unless similarly configured) @<:@hacluster@:>@])],
[ CRM_DAEMON_USER="$withval" ]
)
AS_IF([test x"${CRM_DAEMON_USER}" = x""],
[CRM_DAEMON_USER="hacluster"])
CRM_DAEMON_GROUP=""
AC_ARG_WITH([daemon-group],
[AS_HELP_STRING([--with-daemon-group=GROUP],
[group to run unprivileged Pacemaker daemons as (advanced option: changing this may break other cluster components unless similarly configured) @<:@haclient@:>@])],
[ CRM_DAEMON_GROUP="$withval" ]
)
AS_IF([test x"${CRM_DAEMON_GROUP}" = x""],
[CRM_DAEMON_GROUP="haclient"])
BUG_URL=""
AC_ARG_WITH([bug-url],
[AS_HELP_STRING([--with-bug-url=DIR], m4_normalize([
address where users should submit bug reports
@<:@https://bugs.clusterlabs.org/enter_bug.cgi?product=Pacemaker@:>@]))],
[ BUG_URL="$withval" ]
)
AS_IF([test x"${BUG_URL}" = x""],
[BUG_URL="https://bugs.clusterlabs.org/enter_bug.cgi?product=Pacemaker"])
dnl --with-* options: features
AC_ARG_WITH([cibsecrets],
[AS_HELP_STRING([--with-cibsecrets],
[support separate file for CIB secrets @<:@no@:>@])]
)
yes_no_try "$with_cibsecrets" "no"
with_cibsecrets=$?
AC_ARG_WITH([gnutls],
[AS_HELP_STRING([--with-gnutls],
[support Pacemaker Remote and remote-tls-port using GnuTLS @<:@try@:>@])]
)
yes_no_try "$with_gnutls" "try"
with_gnutls=$?
PCMK_GNUTLS_PRIORITIES="NORMAL"
AC_ARG_WITH([gnutls-priorities],
[AS_HELP_STRING([--with-gnutls-priorities],
[default GnuTLS cipher priorities @<:@NORMAL@:>@])],
[ test x"$withval" = x"no" || PCMK_GNUTLS_PRIORITIES="$withval" ]
)
AC_ARG_WITH([concurrent-fencing-default],
[AS_HELP_STRING([--with-concurrent-fencing-default],
[default value for concurrent-fencing cluster option @<:@false@:>@])],
)
AS_CASE([$with_concurrent_fencing_default],
[""], [with_concurrent_fencing_default="false"],
[false], [],
[true], [PCMK_FEATURES="$PCMK_FEATURES default-concurrent-fencing"],
[AC_MSG_ERROR([Invalid value "$with_concurrent_fencing_default" for --with-concurrent-fencing-default])]
)
AC_ARG_WITH([sbd-sync-default],
[AS_HELP_STRING([--with-sbd-sync-default], m4_normalize([
default value used by sbd if SBD_SYNC_RESOURCE_STARTUP
environment variable is not set @<:@false@:>@]))],
)
AS_CASE([$with_sbd_sync_default],
[""], [with_sbd_sync_default=false],
[false], [],
[true], [PCMK_FEATURES="$PCMK_FEATURES default-sbd-sync"],
[AC_MSG_ERROR([Invalid value "$with_sbd_sync_default" for --with-sbd-sync-default])]
)
AC_ARG_WITH([resource-stickiness-default],
[AS_HELP_STRING([--with-resource-stickiness-default],
[If positive, value to add to new CIBs as explicit resource default for resource-stickiness @<:@0@:>@])],
)
errmsg="Invalid value \"$with_resource_stickiness_default\" for --with-resource-stickiness-default"
AS_CASE([$with_resource_stickiness_default],
[0|""], [with_resource_stickiness_default="0"],
[*[[!0-9]]*], [AC_MSG_ERROR([$errmsg])],
[PCMK_FEATURES="$PCMK_FEATURES default-resource-stickiness"]
)
AC_ARG_WITH([corosync],
[AS_HELP_STRING([--with-corosync],
[support the Corosync messaging and membership layer @<:@try@:>@])]
)
yes_no_try "$with_corosync" "try"
with_corosync=$?
dnl Get default from Corosync if possible
PKG_CHECK_VAR([PCMK__COROSYNC_CONF], [corosync], [corosysconfdir],
[PCMK__COROSYNC_CONF="$PCMK__COROSYNC_CONF/corosync.conf"],
[PCMK__COROSYNC_CONF="${sysconfdir}/corosync/corosync.conf"])
AC_ARG_WITH([corosync-conf],
[AS_HELP_STRING([--with-corosync-conf], m4_normalize([
location of Corosync configuration file
@<:@value from Corosync package if available otherwise
SYSCONFDIR/corosync/corosync.conf@:>@]))],
[ PCMK__COROSYNC_CONF="$withval" ]
)
AC_ARG_WITH([nagios],
[AS_HELP_STRING([--with-nagios], [support nagios resources (deprecated)])]
)
yes_no_try "$with_nagios" "try"
with_nagios=$?
dnl --with-* options: directory locations
AC_ARG_WITH([nagios-plugin-dir],
[AS_HELP_STRING([--with-nagios-plugin-dir=DIR],
[directory for nagios plugins (deprecated) @<:@LIBEXECDIR/nagios/plugins@:>@])],
[ NAGIOS_PLUGIN_DIR="$withval" ]
)
AC_ARG_WITH([nagios-metadata-dir],
[AS_HELP_STRING([--with-nagios-metadata-dir=DIR],
[directory for nagios plugins metadata (deprecated) @<:@DATADIR/nagios/plugins-metadata@:>@])],
[ NAGIOS_METADATA_DIR="$withval" ]
)
INITDIR=""
AC_ARG_WITH([initdir],
[AS_HELP_STRING([--with-initdir=DIR],
[directory for init (rc) scripts])],
[ INITDIR="$withval" ]
)
systemdsystemunitdir="${systemdsystemunitdir-}"
AC_ARG_WITH([systemdsystemunitdir],
[AS_HELP_STRING([--with-systemdsystemunitdir=DIR],
[directory for systemd unit files (advanced option: must match what systemd uses)])],
[ systemdsystemunitdir="$withval" ]
)
CONFIGDIR=""
AC_ARG_WITH([configdir],
[AS_HELP_STRING([--with-configdir=DIR],
[directory for Pacemaker configuration file @<:@SYSCONFDIR/sysconfig@:>@])],
[ CONFIGDIR="$withval" ]
)
dnl --runstatedir is available as of autoconf 2.70 (2020-12-08). When users
dnl have an older version, they can use our --with-runstatedir.
pcmk_runstatedir=""
AC_ARG_WITH([runstatedir],
[AS_HELP_STRING([--with-runstatedir=DIR],
[modifiable per-process data @<:@LOCALSTATEDIR/run@:>@ (ignored if --runstatedir is available)])],
[ pcmk_runstatedir="$withval" ]
)
CRM_LOG_DIR=""
AC_ARG_WITH([logdir],
[AS_HELP_STRING([--with-logdir=DIR],
[directory for Pacemaker log file @<:@LOCALSTATEDIR/log/pacemaker@:>@])],
[ CRM_LOG_DIR="$withval" ]
)
CRM_BUNDLE_DIR=""
AC_ARG_WITH([bundledir],
[AS_HELP_STRING([--with-bundledir=DIR],
[directory for Pacemaker bundle logs @<:@LOCALSTATEDIR/log/pacemaker/bundles@:>@])],
[ CRM_BUNDLE_DIR="$withval" ]
)
dnl Get default from resource-agents if possible. Otherwise, the default uses
dnl /usr/lib rather than libdir because it's determined by the OCF project and
dnl not Pacemaker. Even if a user wants to install Pacemaker to /usr/local or
dnl such, the OCF agents will be expected in their usual location. However, we
dnl do give the user the option to override it.
PKG_CHECK_VAR([OCF_ROOT_DIR], [resource-agents], [ocfrootdir], [],
[OCF_ROOT_DIR="/usr/lib/ocf"])
AC_ARG_WITH([ocfdir],
[AS_HELP_STRING([--with-ocfdir=DIR], m4_normalize([
OCF resource agent root directory (advanced option: changing this
may break other cluster components unless similarly configured)
@<:@value from resource-agents package if available otherwise
/usr/lib/ocf@:>@]))],
[ OCF_ROOT_DIR="$withval" ]
)
dnl Get default from resource-agents if possible
PKG_CHECK_VAR([OCF_RA_PATH], [resource-agents], [ocfrapath], [],
[OCF_RA_PATH="$OCF_ROOT_DIR/resource.d"])
AC_ARG_WITH([ocfrapath],
[AS_HELP_STRING([--with-ocfrapath=DIR], m4_normalize([
OCF resource agent directories (colon-separated) to search
@<:@value from resource-agents package if available otherwise
OCFDIR/resource.d@:>@]))],
[ OCF_RA_PATH="$withval" ]
)
OCF_RA_INSTALL_DIR="$OCF_ROOT_DIR/resource.d"
AC_ARG_WITH([ocfrainstalldir],
[AS_HELP_STRING([--with-ocfrainstalldir=DIR], m4_normalize([
OCF installation directory for Pacemakers resource agents
@<:@OCFDIR/resource.d@:>@]))],
[ OCF_RA_INSTALL_DIR="$withval" ]
)
dnl Get default from fence-agents if available
PKG_CHECK_VAR([FA_PREFIX], [fence-agents], [prefix],
[PCMK__FENCE_BINDIR="${FA_PREFIX}/sbin"],
[PCMK__FENCE_BINDIR="$sbindir"])
AC_ARG_WITH([fence-bindir],
[AS_HELP_STRING([--with-fence-bindir=DIR], m4_normalize([
directory for executable fence agents @<:@value from fence-agents
package if available otherwise SBINDIR@:>@]))],
[ PCMK__FENCE_BINDIR="$withval" ]
)
dnl --with-* options: non-production testing
AC_ARG_WITH([profiling],
[AS_HELP_STRING([--with-profiling],
[disable optimizations, for effective profiling @<:@no@:>@])]
)
yes_no_try "$with_profiling" "no"
with_profiling=$?
AC_ARG_WITH([coverage],
[AS_HELP_STRING([--with-coverage],
[disable optimizations, for effective profiling and coverage testing @<:@no@:>@])]
)
yes_no_try "$with_coverage" "no"
with_coverage=$?
AC_ARG_WITH([sanitizers],
[AS_HELP_STRING([--with-sanitizers=...,...],
[enable SANitizer build, do *NOT* use for production. Only ASAN/UBSAN/TSAN are currently supported])],
[ SANITIZERS="$withval" ],
[ SANITIZERS="" ])
dnl Environment variable options
AC_ARG_VAR([CFLAGS_HARDENED_LIB], [extra C compiler flags for hardened libraries])
AC_ARG_VAR([LDFLAGS_HARDENED_LIB], [extra linker flags for hardened libraries])
AC_ARG_VAR([CFLAGS_HARDENED_EXE], [extra C compiler flags for hardened executables])
AC_ARG_VAR([LDFLAGS_HARDENED_EXE], [extra linker flags for hardened executables])
dnl ==============================================
dnl Locate essential tools
dnl ==============================================
PATH="$PATH:/sbin:/usr/sbin:/usr/local/sbin:/usr/local/bin"
export PATH
dnl Pacemaker's executable python scripts will invoke the python specified by
dnl configure's PYTHON variable. If not specified, AM_PATH_PYTHON will check a
dnl built-in list with (unversioned) "python" having precedence. To configure
dnl Pacemaker to use a specific python interpreter version, define PYTHON
dnl when calling configure, for example: ./configure PYTHON=/usr/bin/python3.6
dnl If PYTHON was specified, ensure it is an absolute path
AS_IF([test x"${PYTHON}" != x""], [AC_PATH_PROG([PYTHON], [$PYTHON])])
dnl Require a minimum Python version
AM_PATH_PYTHON([3.4])
AC_PROG_LN_S
AC_PROG_MKDIR_P
AC_PATH_PROG([GIT], [git], [false])
dnl Bash is needed for building man pages and running regression tests.
dnl We set "BASH_PATH" because "BASH" is already an environment variable.
REQUIRE_PROG([BASH_PATH], [bash])
AC_PATH_PROGS(VALGRIND_BIN, valgrind, /usr/bin/valgrind)
AC_DEFINE_UNQUOTED(VALGRIND_BIN, "$VALGRIND_BIN", Valgrind command)
dnl ==============================================
dnl Package and schema versioning
dnl ==============================================
# Redefine PACKAGE_VERSION and VERSION according to PACEMAKER_VERSION in case
# the user used --with-version. Unfortunately, this can only affect the
# substitution variables and later uses in this file, not the config.h
# constants, so we have to be careful to use only PACEMAKER_VERSION in C code.
PACKAGE_VERSION=$PACEMAKER_VERSION
VERSION=$PACEMAKER_VERSION
AC_DEFINE_UNQUOTED(PACEMAKER_VERSION, "$VERSION",
[Version number of this Pacemaker build])
AC_MSG_CHECKING([build version])
AS_IF([test "$GIT" != "false" && test -d .git],
[
BUILD_VERSION=`"$GIT" log --pretty="format:%h" -n 1`
AC_MSG_RESULT([$BUILD_VERSION (git hash)])
],
[
# The current directory name make a reasonable default
# Most generated archives will include the hash or tag
BASE=`basename $PWD`
BUILD_VERSION=`echo $BASE | sed s:.*[[Pp]]acemaker-::`
AC_MSG_RESULT([$BUILD_VERSION (directory name)])
])
AC_DEFINE_UNQUOTED(BUILD_VERSION, "$BUILD_VERSION", Build version)
AC_SUBST(BUILD_VERSION)
# schema_files <schema-dir>
# List all manually edited RNG schemas (as opposed to auto-generated via make)
# in the given directory. Use git if available to list managed RNGs, in case
# there are leftover schema files from an earlier build of a different
# version. Otherwise, check all RNGs.
schema_files() {
local files="$("$GIT" ls-files "$1"/*.rng 2>/dev/null)"
AS_IF([test x"$files" = x""],
[
files="$(ls -1 "$1"/*.rng | grep -E -v \
'/(pacemaker|api-result|crm_mon|versions)[^/]*\.rng')"
])
echo "$files"
}
# latest_schema_version <schema-dir>
# Determine highest RNG version in the given schema directory.
latest_schema_version() {
schema_files "$1" | sed -n -e 's/^.*-\([[0-9]][[0-9.]]*\).rng$/\1/p' dnl
| sort -V | tail -1
}
# schemas_for_make <schema-dir>
# Like schema_files, but suitable for use in make variables.
schemas_for_make() {
local file
for file in $(schema_files "$1"); do
AS_ECHO_N(["\$(top_srcdir)/$file "])
done
}
# Detect highest API schema version
API_VERSION=$(latest_schema_version "xml/api")
AC_DEFINE_UNQUOTED([PCMK__API_VERSION], ["$API_VERSION"],
[Highest API schema version])
# Detect highest CIB schema version
CIB_VERSION=$(latest_schema_version "xml")
AC_SUBST(CIB_VERSION)
# Re-run configure at next make if schema files change, to re-detect versions
cib_schemas="$(schemas_for_make "xml")"
api_schemas="$(schemas_for_make "xml/api")"
CONFIG_STATUS_DEPENDENCIES="$cib_schemas $api_schemas"
AC_SUBST(CONFIG_STATUS_DEPENDENCIES)
dnl ==============================================
dnl Process simple options
dnl ==============================================
AS_IF([test $enable_compat_2_0 -ne $DISABLED],
[
AC_DEFINE_UNQUOTED([PCMK__COMPAT_2_0], [1],
[Keep certain output compatible with 2.0 release series])
PCMK_FEATURES="$PCMK_FEATURES compat-2.0"
]
)
AM_CONDITIONAL([BUILD_LEGACY_LINKS], [test $enable_legacy_links -ne $DISABLED])
AS_IF([test x"$enable_nls" = x"yes"], [PCMK_FEATURES="$PCMK_FEATURES nls"])
AC_DEFINE_UNQUOTED([PCMK__CONCURRENT_FENCING_DEFAULT],
["$with_concurrent_fencing_default"],
[Default value for concurrent-fencing cluster option])
AC_DEFINE_UNQUOTED([PCMK__SBD_SYNC_DEFAULT],
[$with_sbd_sync_default],
[Default value for SBD_SYNC_RESOURCE_STARTUP environment variable])
AC_DEFINE_UNQUOTED([PCMK__RESOURCE_STICKINESS_DEFAULT],
[$with_resource_stickiness_default],
[Default value for resource-stickiness resource meta-attribute])
AS_IF([test x"${PCMK_GNUTLS_PRIORITIES}" != x""], [],
[AC_MSG_ERROR([--with-gnutls-priorities value must not be empty])])
AC_DEFINE_UNQUOTED([PCMK_GNUTLS_PRIORITIES], ["$PCMK_GNUTLS_PRIORITIES"],
[GnuTLS cipher priorities])
AC_SUBST(PCMK_GNUTLS_PRIORITIES)
AC_SUBST(BUG_URL)
AC_DEFINE_UNQUOTED([PCMK__BUG_URL], ["$BUG_URL"],
[Where bugs should be reported])
AC_DEFINE_UNQUOTED([CRM_DAEMON_USER], ["$CRM_DAEMON_USER"],
[User to run Pacemaker daemons as])
AC_SUBST(CRM_DAEMON_USER)
AC_DEFINE_UNQUOTED([CRM_DAEMON_GROUP], ["$CRM_DAEMON_GROUP"],
[Group to run Pacemaker daemons as])
AC_SUBST(CRM_DAEMON_GROUP)
dnl ==============================================
dnl Process file paths
dnl ==============================================
# expand_path_option <path-variable-name> [<default>]
# Given the name of a file path variable, expand any variable references
# inside it, use the specified default if it is not specified, and ensure it
# is a full path.
expand_path_option() {
# The first argument is the variable *name* (not value)
ac_path_varname="$1"
# Get the original value of the variable
ac_path_value=$(eval echo "\${${ac_path_varname}}")
# Expand any literal variable expressions in the value so that we don't
# end up with something like '${prefix}' in #defines etc.
#
# Autoconf deliberately leaves values unexpanded to allow overriding
# the configure script choices in make commands (for example,
# "make exec_prefix=/foo install"). No longer being able to do this seems
# like no great loss.
eval ac_path_value=$(eval echo "${ac_path_value}")
# Use (expanded) default if necessary
AS_IF([test x"${ac_path_value}" = x""],
[eval ac_path_value=$(eval echo "$2")])
# Require a full path
AS_CASE(["$ac_path_value"],
[/*], [eval ${ac_path_varname}="$ac_path_value"],
[*], [AC_MSG_ERROR([$ac_path_varname value "$ac_path_value" is not a full path])]
)
}
AC_MSG_NOTICE([Sanitizing INITDIR: ${INITDIR}])
AS_CASE([$INITDIR],
[prefix], [INITDIR=$prefix],
[""], [
AC_MSG_CHECKING([which init (rc) directory to use])
for initdir in /etc/init.d /etc/rc.d/init.d /sbin/init.d \
/usr/local/etc/rc.d /etc/rc.d
do
AS_IF([test -d $initdir],
[
INITDIR=$initdir
break
])
done
AC_MSG_RESULT([$INITDIR])
])
AC_SUBST(INITDIR)
dnl Expand values of autoconf-provided directory options
expand_path_option prefix
expand_path_option exec_prefix
expand_path_option bindir
expand_path_option sbindir
expand_path_option libexecdir
expand_path_option datarootdir
expand_path_option datadir
expand_path_option sysconfdir
expand_path_option sharedstatedir
expand_path_option localstatedir
expand_path_option libdir
expand_path_option includedir
expand_path_option oldincludedir
expand_path_option infodir
expand_path_option mandir
AC_DEFUN([AC_DATAROOTDIR_CHECKED])
dnl Expand values of custom directory options
expand_path_option localedir "${datadir}/locale"
AC_DEFINE_UNQUOTED([PCMK__LOCALE_DIR],["$localedir"],
[Base directory for message catalogs])
AS_IF([test x"${runstatedir}" = x""], [runstatedir="${pcmk_runstatedir}"])
expand_path_option runstatedir "${localstatedir}/run"
AC_DEFINE_UNQUOTED([PCMK_RUN_DIR], ["$runstatedir"],
[Location for modifiable per-process data])
AC_SUBST(runstatedir)
expand_path_option INITDIR
AC_DEFINE_UNQUOTED([PCMK__LSB_INIT_DIR], ["$INITDIR"],
[Location for LSB init scripts])
expand_path_option docdir "${datadir}/doc/${PACKAGE}-${VERSION}"
AC_SUBST(docdir)
expand_path_option CONFIGDIR "${sysconfdir}/sysconfig"
AC_SUBST(CONFIGDIR)
expand_path_option PCMK__COROSYNC_CONF "${sysconfdir}/corosync/corosync.conf"
AC_SUBST(PCMK__COROSYNC_CONF)
expand_path_option CRM_LOG_DIR "${localstatedir}/log/pacemaker"
AC_DEFINE_UNQUOTED([CRM_LOG_DIR], ["$CRM_LOG_DIR"],
[Location for Pacemaker log file])
AC_SUBST(CRM_LOG_DIR)
expand_path_option CRM_BUNDLE_DIR "${localstatedir}/log/pacemaker/bundles"
AC_DEFINE_UNQUOTED([CRM_BUNDLE_DIR], ["$CRM_BUNDLE_DIR"],
[Location for Pacemaker bundle logs])
AC_SUBST(CRM_BUNDLE_DIR)
expand_path_option PCMK__FENCE_BINDIR
AC_SUBST(PCMK__FENCE_BINDIR)
AC_DEFINE_UNQUOTED([PCMK__FENCE_BINDIR], ["$PCMK__FENCE_BINDIR"],
[Location for executable fence agents])
expand_path_option OCF_ROOT_DIR
AC_SUBST(OCF_ROOT_DIR)
AC_DEFINE_UNQUOTED([OCF_ROOT_DIR], ["$OCF_ROOT_DIR"],
[OCF root directory for resource agents and libraries])
expand_path_option OCF_RA_PATH
AC_SUBST(OCF_RA_PATH)
AC_DEFINE_UNQUOTED([OCF_RA_PATH], ["$OCF_RA_PATH"],
[OCF directories to search for resource agents ])
expand_path_option OCF_RA_INSTALL_DIR
AC_SUBST(OCF_RA_INSTALL_DIR)
# Derived paths
CRM_SCHEMA_DIRECTORY="${datadir}/pacemaker"
AC_DEFINE_UNQUOTED([CRM_SCHEMA_DIRECTORY], ["$CRM_SCHEMA_DIRECTORY"],
[Location for the Pacemaker Relax-NG Schema])
AC_SUBST(CRM_SCHEMA_DIRECTORY)
CRM_CORE_DIR="${localstatedir}/lib/pacemaker/cores"
AC_DEFINE_UNQUOTED([CRM_CORE_DIR], ["$CRM_CORE_DIR"],
[Directory Pacemaker daemons should change to (without systemd, core files will go here)])
AC_SUBST(CRM_CORE_DIR)
CRM_PACEMAKER_DIR="${localstatedir}/lib/pacemaker"
AC_DEFINE_UNQUOTED([CRM_PACEMAKER_DIR], ["$CRM_PACEMAKER_DIR"],
[Location to store directory produced by Pacemaker daemons])
AC_SUBST(CRM_PACEMAKER_DIR)
CRM_BLACKBOX_DIR="${localstatedir}/lib/pacemaker/blackbox"
AC_DEFINE_UNQUOTED([CRM_BLACKBOX_DIR], ["$CRM_BLACKBOX_DIR"],
[Where to keep blackbox dumps])
AC_SUBST(CRM_BLACKBOX_DIR)
PE_STATE_DIR="${localstatedir}/lib/pacemaker/pengine"
AC_DEFINE_UNQUOTED([PE_STATE_DIR], ["$PE_STATE_DIR"],
[Where to keep scheduler outputs])
AC_SUBST(PE_STATE_DIR)
CRM_CONFIG_DIR="${localstatedir}/lib/pacemaker/cib"
AC_DEFINE_UNQUOTED([CRM_CONFIG_DIR], ["$CRM_CONFIG_DIR"],
[Where to keep configuration files])
AC_SUBST(CRM_CONFIG_DIR)
CRM_DAEMON_DIR="${libexecdir}/pacemaker"
AC_DEFINE_UNQUOTED([CRM_DAEMON_DIR], ["$CRM_DAEMON_DIR"],
[Location for Pacemaker daemons])
AC_SUBST(CRM_DAEMON_DIR)
CRM_STATE_DIR="${runstatedir}/crm"
AC_DEFINE_UNQUOTED([CRM_STATE_DIR], ["$CRM_STATE_DIR"],
[Where to keep state files and sockets])
AC_SUBST(CRM_STATE_DIR)
CRM_RSCTMP_DIR="${runstatedir}/resource-agents"
AC_DEFINE_UNQUOTED([CRM_RSCTMP_DIR], ["$CRM_RSCTMP_DIR"],
[Where resource agents should keep state files])
AC_SUBST(CRM_RSCTMP_DIR)
PACEMAKER_CONFIG_DIR="${sysconfdir}/pacemaker"
AC_DEFINE_UNQUOTED([PACEMAKER_CONFIG_DIR], ["$PACEMAKER_CONFIG_DIR"],
[Where to keep configuration files like authkey])
AC_SUBST(PACEMAKER_CONFIG_DIR)
AC_DEFINE_UNQUOTED([SBIN_DIR], ["$sbindir"], [Location for system binaries])
# Warn about any directories that don't exist (which may be OK)
for j in prefix exec_prefix bindir sbindir libexecdir datadir sysconfdir \
sharedstatedir localstatedir libdir includedir oldincludedir infodir \
mandir INITDIR docdir CONFIGDIR localedir
do
dirname=`eval echo '${'${j}'}'`
AS_IF([test ! -d "$dirname"],
[AC_MSG_WARN([$j directory ($dirname) does not exist (yet)])])
done
dnl ===============================================
dnl General Processing
dnl ===============================================
us_auth=
AC_CHECK_HEADER([sys/socket.h], [
AC_CHECK_DECL([SO_PEERCRED], [
# Linux
AC_CHECK_TYPE([struct ucred], [
us_auth=peercred_ucred;
AC_DEFINE([HAVE_UCRED], [1],
[Define if Unix socket auth method is
getsockopt(s, SO_PEERCRED, &ucred, ...)])
], [
# OpenBSD
AC_CHECK_TYPE([struct sockpeercred], [
us_auth=localpeercred_sockepeercred;
AC_DEFINE([HAVE_SOCKPEERCRED], [1],
[Define if Unix socket auth method is
getsockopt(s, SO_PEERCRED, &sockpeercred, ...)])
], [], [[#include <sys/socket.h>]])
], [[#define _GNU_SOURCE
#include <sys/socket.h>]])
], [], [[#include <sys/socket.h>]])
])
AS_IF([test -z "${us_auth}"], [
# FreeBSD
AC_CHECK_DECL([getpeereid], [
us_auth=getpeereid;
AC_DEFINE([HAVE_GETPEEREID], [1],
[Define if Unix socket auth method is
getpeereid(s, &uid, &gid)])
], [
# Solaris/OpenIndiana
AC_CHECK_DECL([getpeerucred], [
us_auth=getpeerucred;
AC_DEFINE([HAVE_GETPEERUCRED], [1],
[Define if Unix socket auth method is
getpeercred(s, &ucred)])
], [
AC_MSG_FAILURE([No way to authenticate a Unix socket peer])
], [[#include <ucred.h>]])
])
])
dnl OS-based decision-making is poor autotools practice; feature-based
dnl mechanisms are strongly preferred. Keep this section to a bare minimum;
dnl regard as a "necessary evil".
dnl Set host_os and host_cpu
AC_CANONICAL_HOST
INIT_EXT=""
PROCFS=0
dnl Solaris and some *BSD versions support procfs but not files we need
AS_CASE(["$host_os"],
[*bsd*], [INIT_EXT=".sh"],
[*linux*], [PROCFS=1],
[darwin*], [
LIBS="$LIBS -L${prefix}/lib"
CFLAGS="$CFLAGS -I${prefix}/include"
])
AC_SUBST(INIT_EXT)
AM_CONDITIONAL([SUPPORT_PROCFS], [test $PROCFS -eq 1])
AC_DEFINE_UNQUOTED([HAVE_LINUX_PROCFS], [$PROCFS],
[Define to 1 if procfs is supported])
AS_CASE(["$host_cpu"],
[ppc64|powerpc64], [
AS_CASE([$CFLAGS],
[*powerpc64*], [],
[*], [AS_IF([test x"$GCC" = x"yes"], [CFLAGS="$CFLAGS -m64"])
])
])
dnl ==============================================
dnl Documentation build dependencies and checks
dnl ==============================================
AC_PATH_PROGS([ASCIIDOC_CONV], [asciidoc asciidoctor])
AC_PATH_PROG([HELP2MAN], [help2man])
AC_PATH_PROG([SPHINX], [sphinx-build])
AC_PATH_PROG([INKSCAPE], [inkscape])
AC_PATH_PROG([XSLTPROC], [xsltproc])
AC_PATH_PROG([XMLCATALOG], [xmlcatalog])
AM_CONDITIONAL(BUILD_HELP, test x"${HELP2MAN}" != x"")
AS_IF([test x"${HELP2MAN}" != x""],
[PCMK_FEATURES="$PCMK_FEATURES generated-manpages"])
MANPAGE_XSLT=""
AS_IF([test x"${XSLTPROC}" != x""],
[
AC_MSG_CHECKING([for DocBook-to-manpage transform])
# first try to figure out correct template using xmlcatalog query,
# resort to extensive (semi-deterministic) file search if that fails
DOCBOOK_XSL_URI='http://docbook.sourceforge.net/release/xsl/current'
DOCBOOK_XSL_PATH='manpages/docbook.xsl'
MANPAGE_XSLT=$(${XMLCATALOG} "" ${DOCBOOK_XSL_URI}/${DOCBOOK_XSL_PATH} \
| sed -n 's|^file://||p;q')
AS_IF([test x"${MANPAGE_XSLT}" = x""],
[
DIRS=$(find "${datadir}" -name $(basename $(dirname ${DOCBOOK_XSL_PATH})) \
-type d 2>/dev/null | LC_ALL=C sort)
XSLT=$(basename ${DOCBOOK_XSL_PATH})
for d in ${DIRS}
do
AS_IF([test -f "${d}/${XSLT}"],
[
MANPAGE_XSLT="${d}/${XSLT}"
break
])
done
])
])
AC_MSG_RESULT([$MANPAGE_XSLT])
AC_SUBST(MANPAGE_XSLT)
AM_CONDITIONAL(BUILD_XML_HELP, test x"${MANPAGE_XSLT}" != x"")
AS_IF([test x"${MANPAGE_XSLT}" != x""],
[PCMK_FEATURES="$PCMK_FEATURES agent-manpages"])
AM_CONDITIONAL([IS_ASCIIDOC], [echo "${ASCIIDOC_CONV}" | grep -Eq 'asciidoc$'])
AM_CONDITIONAL([BUILD_ASCIIDOC], [test "x${ASCIIDOC_CONV}" != x])
AS_IF([test x"${ASCIIDOC_CONV}" != x""],
[PCMK_FEATURES="$PCMK_FEATURES ascii-docs"])
AM_CONDITIONAL([BUILD_SPHINX_DOCS],
[test x"${SPHINX}" != x"" && test x"${INKSCAPE}" != x""])
AM_COND_IF([BUILD_SPHINX_DOCS], [PCMK_FEATURES="$PCMK_FEATURES books"])
dnl Pacemaker's shell scripts (and thus man page builders) rely on GNU getopt
AC_MSG_CHECKING([for GNU-compatible getopt])
IFS_orig=$IFS
IFS=:
for PATH_DIR in $PATH
do
IFS=$IFS_orig
GETOPT_PATH="${PATH_DIR}/getopt"
AS_IF([test -f "$GETOPT_PATH" && test -x "$GETOPT_PATH"],
[
$GETOPT_PATH -T >/dev/null 2>/dev/null
AS_IF([test $? -eq 4], [break])
])
GETOPT_PATH=""
done
IFS=$IFS_orig
AS_IF([test -n "$GETOPT_PATH"], [AC_MSG_RESULT([$GETOPT_PATH])],
[
AC_MSG_RESULT([no])
AC_MSG_ERROR([Could not find required build tool GNU-compatible getopt])
])
AC_SUBST([GETOPT_PATH])
dnl ===============================================
dnl Libraries
dnl ===============================================
AC_CHECK_LIB(socket, socket) dnl -lsocket
AC_CHECK_LIB(c, dlopen) dnl if dlopen is in libc...
AC_CHECK_LIB(dl, dlopen) dnl -ldl (for Linux)
AC_CHECK_LIB(rt, sched_getscheduler) dnl -lrt (for Tru64)
AC_CHECK_LIB(gnugetopt, getopt_long) dnl -lgnugetopt ( if available )
AC_CHECK_LIB(pam, pam_start) dnl -lpam (if available)
PKG_CHECK_MODULES([UUID], [uuid],
[CPPFLAGS="${CPPFLAGS} ${UUID_CFLAGS}"
LIBS="${LIBS} ${UUID_LIBS}"])
AC_CHECK_FUNCS([sched_setscheduler])
AS_IF([test x"$ac_cv_func_sched_setscheduler" != x"yes"],
[PC_LIBS_RT=""],
[PC_LIBS_RT="-lrt"])
AC_SUBST(PC_LIBS_RT)
# Require minimum glib version
PKG_CHECK_MODULES([GLIB], [glib-2.0 >= 2.42.0],
[CPPFLAGS="${CPPFLAGS} ${GLIB_CFLAGS}"
LIBS="${LIBS} ${GLIB_LIBS}"])
# Check whether high-resolution sleep function is available
AC_CHECK_FUNCS([nanosleep usleep])
#
# Where is dlopen?
#
AS_IF([test x"$ac_cv_lib_c_dlopen" = x"yes"],
[LIBADD_DL=""],
[test x"$ac_cv_lib_dl_dlopen" = x"yes"],
[LIBADD_DL=-ldl],
[LIBADD_DL=${lt_cv_dlopen_libs}])
-PKG_CHECK_MODULES(LIBXML2, [libxml-2.0],
+PKG_CHECK_MODULES(LIBXML2, [libxml-2.0 >= 2.6.0],
[CPPFLAGS="${CPPFLAGS} ${LIBXML2_CFLAGS}"
LIBS="${LIBS} ${LIBXML2_LIBS}"])
REQUIRE_LIB([xslt], [xsltApplyStylesheet])
AC_MSG_CHECKING([whether __progname and __progname_full are available])
AC_LINK_IFELSE([AC_LANG_PROGRAM([[extern char *__progname, *__progname_full;]],
[[__progname = "foo";
__progname_full = "foo bar";]])],
[
have_progname="yes"
AC_DEFINE(HAVE_PROGNAME, 1,
[Define to 1 if processes can change their name])
],
[have_progname="no"])
AC_MSG_RESULT([$have_progname])
dnl ========================================================================
dnl Headers
dnl ========================================================================
# Some distributions insert #warnings into deprecated headers. If we will
# enable fatal warnings for the build, then enable them for the header checks
# as well, otherwise the build could fail even though the header check
# succeeds. (We should probably be doing this in more places.)
cc_temp_flags "$CFLAGS $WERROR"
# Optional headers (inclusion of these should be conditional in C code)
AC_CHECK_HEADERS([linux/swab.h])
AC_CHECK_HEADERS([stddef.h])
AC_CHECK_HEADERS([sys/signalfd.h])
AC_CHECK_HEADERS([uuid/uuid.h])
AC_CHECK_HEADERS([security/pam_appl.h pam/pam_appl.h])
# Required headers
REQUIRE_HEADER([arpa/inet.h])
REQUIRE_HEADER([ctype.h])
REQUIRE_HEADER([dirent.h])
REQUIRE_HEADER([dlfcn.h])
REQUIRE_HEADER([errno.h])
REQUIRE_HEADER([fcntl.h])
REQUIRE_HEADER([float.h])
REQUIRE_HEADER([glib.h])
REQUIRE_HEADER([grp.h])
REQUIRE_HEADER([inttypes.h])
REQUIRE_HEADER([libgen.h])
REQUIRE_HEADER([limits.h])
REQUIRE_HEADER([locale.h])
REQUIRE_HEADER([netdb.h])
REQUIRE_HEADER([netinet/in.h])
REQUIRE_HEADER([netinet/ip.h], [
#include <sys/types.h>
#include <netinet/in.h>
])
REQUIRE_HEADER([netinet/tcp.h])
REQUIRE_HEADER([pwd.h])
REQUIRE_HEADER([regex.h])
REQUIRE_HEADER([sched.h])
REQUIRE_HEADER([signal.h])
REQUIRE_HEADER([stdarg.h])
REQUIRE_HEADER([stdbool.h])
REQUIRE_HEADER([stdint.h])
REQUIRE_HEADER([stdio.h])
REQUIRE_HEADER([stdlib.h])
REQUIRE_HEADER([string.h])
REQUIRE_HEADER([strings.h])
REQUIRE_HEADER([sys/ioctl.h])
REQUIRE_HEADER([sys/param.h])
REQUIRE_HEADER([sys/reboot.h])
REQUIRE_HEADER([sys/resource.h])
REQUIRE_HEADER([sys/socket.h])
REQUIRE_HEADER([sys/stat.h])
REQUIRE_HEADER([sys/time.h])
REQUIRE_HEADER([sys/types.h])
REQUIRE_HEADER([sys/uio.h])
REQUIRE_HEADER([sys/utsname.h])
REQUIRE_HEADER([sys/wait.h])
REQUIRE_HEADER([termios.h])
REQUIRE_HEADER([time.h])
REQUIRE_HEADER([unistd.h])
REQUIRE_HEADER([libxml/xpath.h])
REQUIRE_HEADER([libxslt/xslt.h])
cc_restore_flags
dnl ========================================================================
dnl Generic declarations
dnl ========================================================================
AC_CHECK_DECLS([CLOCK_MONOTONIC], [PCMK_FEATURES="$PCMK_FEATURES monotonic"], [], [[
#include <time.h>
]])
dnl ========================================================================
dnl Unit test declarations
dnl ========================================================================
AC_CHECK_DECLS([assert_float_equal], [], [], [[
#include <stdarg.h>
#include <stddef.h>
#include <setjmp.h>
#include <cmocka.h>
]])
cc_temp_flags "$CFLAGS -Wl,--wrap=uname"
WRAPPABLE_UNAME="no"
AC_MSG_CHECKING([if uname() can be wrapped])
AC_RUN_IFELSE([AC_LANG_SOURCE([[
#include <sys/utsname.h>
int __wrap_uname(struct utsname *buf) {
return 100;
}
int main(int argc, char **argv) {
struct utsname x;
return uname(&x) == 100 ? 0 : 1;
}
]])],
[ WRAPPABLE_UNAME="yes" ], [ WRAPPABLE_UNAME="no"])
AC_MSG_RESULT([$WRAPPABLE_UNAME])
AM_CONDITIONAL([WRAPPABLE_UNAME], [test x"$WRAPPABLE_UNAME" = x"yes"])
cc_restore_flags
dnl ========================================================================
dnl Structures
dnl ========================================================================
AC_CHECK_MEMBERS([struct tm.tm_gmtoff],,,[[#include <time.h>]])
AC_CHECK_MEMBER([struct dirent.d_type],
AC_DEFINE(HAVE_STRUCT_DIRENT_D_TYPE,1,[Define this if struct dirent has d_type]),,
[#include <dirent.h>])
dnl ========================================================================
dnl Functions
dnl ========================================================================
REQUIRE_FUNC([alphasort])
REQUIRE_FUNC([getopt])
REQUIRE_FUNC([scandir])
REQUIRE_FUNC([setenv])
REQUIRE_FUNC([strndup])
REQUIRE_FUNC([strnlen])
REQUIRE_FUNC([unsetenv])
REQUIRE_FUNC([uuid_unparse])
REQUIRE_FUNC([vasprintf])
AC_CHECK_FUNCS([strchrnul])
AC_CHECK_FUNCS([fopen64])
AM_CONDITIONAL([WRAPPABLE_FOPEN64], [test x"$ac_cv_func_fopen64" = x"yes"])
AC_MSG_CHECKING([whether strerror always returns non-NULL])
AC_RUN_IFELSE([AC_LANG_PROGRAM([[
#include <stdio.h>
#include <string.h>
]], [[
return strerror(-1) == NULL;
]])],
[AC_MSG_RESULT([yes])],
[AC_MSG_ERROR([strerror() is not C99-compliant])],
[AC_MSG_ERROR([strerror() is not C99-compliant])])
AC_RUN_IFELSE([AC_LANG_PROGRAM([[#include <stdio.h>]], [[
const char *s = "some-command-line-arg";
char *name = NULL;
int n = sscanf(s, "%ms", &name);
return n != 1;
]])],
[have_sscanf_m="yes"],
[have_sscanf_m="no"],
[have_sscanf_m="no"])
AS_IF([test x"$have_sscanf_m" = x"yes"],
[AC_DEFINE([HAVE_SSCANF_M], [1],
[Define to 1 if sscanf %m modifier is available])])
dnl ========================================================================
dnl bzip2
dnl ========================================================================
REQUIRE_HEADER([bzlib.h])
REQUIRE_LIB([bz2], [BZ2_bzBuffToBuffCompress])
dnl ========================================================================
dnl sighandler_t is missing from Illumos, Solaris11 systems
dnl ========================================================================
AC_MSG_CHECKING([for sighandler_t])
AC_COMPILE_IFELSE([AC_LANG_PROGRAM([[#include <signal.h>]], [[sighandler_t *f;]])],
[
AC_MSG_RESULT([yes])
AC_DEFINE([HAVE_SIGHANDLER_T], [1],
[Define to 1 if sighandler_t is available])
],
[AC_MSG_RESULT([no])])
dnl ========================================================================
dnl ncurses
dnl ========================================================================
dnl
dnl A few OSes (e.g. Linux) deliver a default "ncurses" alongside "curses".
dnl Many non-Linux deliver "curses"; sites may add "ncurses".
dnl
dnl However, the source-code recommendation for both is to #include "curses.h"
dnl (i.e. "ncurses" still wants the include to be simple, no-'n', "curses.h").
dnl
dnl ncurses takes precedence.
dnl
AC_CHECK_HEADERS([curses.h curses/curses.h ncurses.h ncurses/ncurses.h])
dnl Although n-library is preferred, only look for it if the n-header was found.
CURSESLIBS=''
PC_NAME_CURSES=""
PC_LIBS_CURSES=""
AS_IF([test x"$ac_cv_header_ncurses_h" = x"yes"], [
AC_CHECK_LIB(ncurses, printw,
[AC_DEFINE(HAVE_LIBNCURSES,1, have ncurses library)])
CURSESLIBS=`$PKG_CONFIG --libs ncurses` || CURSESLIBS='-lncurses'
PC_NAME_CURSES="ncurses"
])
AS_IF([test x"$ac_cv_header_ncurses_ncurses_h" = x"yes"], [
AC_CHECK_LIB(ncurses, printw,
[AC_DEFINE(HAVE_LIBNCURSES,1, have ncurses library)])
CURSESLIBS=`$PKG_CONFIG --libs ncurses` || CURSESLIBS='-lncurses'
PC_NAME_CURSES="ncurses"
])
dnl Only look for non-n-library if there was no n-library.
AS_IF([test x"$CURSESLIBS" = x"" && test x"$ac_cv_header_curses_h" = x"yes"], [
AC_CHECK_LIB(curses, printw,
[CURSESLIBS='-lcurses'; AC_DEFINE(HAVE_LIBCURSES,1, have curses library)])
PC_LIBS_CURSES="$CURSESLIBS"
])
dnl Only look for non-n-library if there was no n-library.
AS_IF([test x"$CURSESLIBS" = x"" && test x"$ac_cv_header_curses_curses_h" = x"yes"], [
AC_CHECK_LIB(curses, printw,
[CURSESLIBS='-lcurses'; AC_DEFINE(HAVE_LIBCURSES,1, have curses library)])
PC_LIBS_CURSES="$CURSESLIBS"
])
AS_IF([test x"$CURSESLIBS" != x""],
[PCMK_FEATURES="$PCMK_FEATURES ncurses"])
dnl Check for printw() prototype compatibility
AS_IF([test x"$CURSESLIBS" != x"" && cc_supports_flag -Wcast-qual], [
ac_save_LIBS=$LIBS
LIBS="$CURSESLIBS"
# avoid broken test because of hardened build environment in Fedora 23+
# - https://fedoraproject.org/wiki/Changes/Harden_All_Packages
# - https://bugzilla.redhat.com/1297985
AS_IF([cc_supports_flag -fPIC],
[cc_temp_flags "-Wcast-qual $WERROR -fPIC"],
[cc_temp_flags "-Wcast-qual $WERROR"])
AC_MSG_CHECKING([whether curses library is compatible])
AC_LINK_IFELSE(
[AC_LANG_PROGRAM([
#if defined(HAVE_NCURSES_H)
# include <ncurses.h>
#elif defined(HAVE_NCURSES_NCURSES_H)
# include <ncurses/ncurses.h>
#elif defined(HAVE_CURSES_H)
# include <curses.h>
#endif
],
[printw((const char *)"Test");]
)],
[AC_MSG_RESULT([yes])],
[
AC_MSG_RESULT([no])
AC_MSG_WARN(m4_normalize([Disabling curses because the printw()
function of your (n)curses library is old.
If you wish to enable curses, update to a
newer version (ncurses 5.4 or later is
recommended, available from
https://invisible-island.net/ncurses/)
]))
AC_DEFINE([HAVE_INCOMPATIBLE_PRINTW], [1],
[Define to 1 if curses library has incompatible printw()])
]
)
LIBS=$ac_save_LIBS
cc_restore_flags
])
AC_SUBST(CURSESLIBS)
AC_SUBST(PC_NAME_CURSES)
AC_SUBST(PC_LIBS_CURSES)
dnl ========================================================================
dnl Profiling and GProf
dnl ========================================================================
CFLAGS_ORIG="$CFLAGS"
AS_IF([test $with_coverage -ne $DISABLED],
[
with_profiling=$REQUIRED
PCMK_FEATURES="$PCMK_FEATURES coverage"
CFLAGS="$CFLAGS -fprofile-arcs -ftest-coverage"
dnl During linking, make sure to specify -lgcov or -coverage
]
)
AS_IF([test $with_profiling -ne $DISABLED],
[
with_profiling=$REQUIRED
PCMK_FEATURES="$PCMK_FEATURES profile"
dnl Disable various compiler optimizations
CFLAGS="$CFLAGS -fno-omit-frame-pointer -fno-inline -fno-builtin"
dnl CFLAGS="$CFLAGS -fno-inline-functions"
dnl CFLAGS="$CFLAGS -fno-default-inline"
dnl CFLAGS="$CFLAGS -fno-inline-functions-called-once"
dnl CFLAGS="$CFLAGS -fno-optimize-sibling-calls"
dnl Turn off optimization so tools can get accurate line numbers
CFLAGS=`echo $CFLAGS | sed \
-e 's/-O.\ //g' \
-e 's/-Wp,-D_FORTIFY_SOURCE=.\ //g' \
-e 's/-D_FORTIFY_SOURCE=.\ //g'`
CFLAGS="$CFLAGS -O0 -g3 -gdwarf-2"
AC_MSG_NOTICE([CFLAGS before adding profiling options: $CFLAGS_ORIG])
AC_MSG_NOTICE([CFLAGS after: $CFLAGS])
]
)
AC_DEFINE_UNQUOTED([SUPPORT_PROFILING], [$with_profiling], [Support profiling])
AM_CONDITIONAL([BUILD_PROFILING], [test "$with_profiling" = "$REQUIRED"])
dnl ========================================================================
dnl Cluster infrastructure - LibQB
dnl ========================================================================
PKG_CHECK_MODULES(libqb, libqb >= 0.17)
CPPFLAGS="$libqb_CFLAGS $CPPFLAGS"
LIBS="$libqb_LIBS $LIBS"
dnl libqb 2.0.5+ (2022-03)
AC_CHECK_FUNCS([qb_ipcc_connect_async])
dnl libqb 2.0.2+ (2020-10)
AC_CHECK_FUNCS([qb_ipcc_auth_get])
dnl libqb 2.0.0+ (2020-05)
CHECK_ENUM_VALUE([qb/qblog.h],[qb_log_conf],[QB_LOG_CONF_MAX_LINE_LEN])
CHECK_ENUM_VALUE([qb/qblog.h],[qb_log_conf],[QB_LOG_CONF_ELLIPSIS])
dnl Support Linux-HA fence agents if available
AS_IF([test x"$cross_compiling" != x"yes"],
[CPPFLAGS="$CPPFLAGS -I${prefix}/include/heartbeat"])
AC_CHECK_HEADERS([stonith/stonith.h],
[
AC_CHECK_LIB([pils], [PILLoadPlugin])
AC_CHECK_LIB([plumb], [G_main_add_IPC_Channel])
PCMK_FEATURES="$PCMK_FEATURES lha"
])
AM_CONDITIONAL([BUILD_LHA_SUPPORT], [test x"$ac_cv_header_stonith_stonith_h" = x"yes"])
dnl ===============================================
dnl Detect DBus, systemd, and Upstart support
dnl ===============================================
HAVE_dbus=1
PKG_CHECK_MODULES([DBUS], [dbus-1],
[CPPFLAGS="${CPPFLAGS} ${DBUS_CFLAGS}"],
[HAVE_dbus=0])
AC_DEFINE_UNQUOTED(HAVE_DBUS, $HAVE_dbus, Support dbus)
AM_CONDITIONAL(BUILD_DBUS, test $HAVE_dbus = 1)
dnl libdbus 1.5.12+ (2012-03) / 1.6.0+ (2012-06)
AC_CHECK_TYPES([DBusBasicValue],,,[[#include <dbus/dbus.h>]])
AS_IF([test $HAVE_dbus = 0],
[PC_NAME_DBUS=""],
[PC_NAME_DBUS="dbus-1"])
AC_SUBST(PC_NAME_DBUS)
check_systemdsystemunitdir() {
AC_MSG_CHECKING([which system unit file directory to use])
PKG_CHECK_VAR([systemdsystemunitdir], [systemd], [systemdsystemunitdir])
AC_MSG_RESULT([${systemdsystemunitdir}])
test x"$systemdsystemunitdir" != x""
return $?
}
AS_CASE([$enable_systemd],
[$REQUIRED], [
AS_IF([test $HAVE_dbus = 0],
[AC_MSG_FAILURE([Cannot support systemd resources without DBus])])
AS_IF([test "$ac_cv_have_decl_CLOCK_MONOTONIC" = "no"],
[AC_MSG_FAILURE([Cannot support systemd resources without monotonic clock])])
AS_IF([check_systemdsystemunitdir], [],
[AC_MSG_FAILURE([Cannot support systemd resources without systemdsystemunitdir])])
],
[$OPTIONAL], [
AS_IF([test $HAVE_dbus = 0 \
|| test x"$ac_cv_have_decl_CLOCK_MONOTONIC" = x"no"],
[enable_systemd=$DISABLED],
[
AC_MSG_CHECKING([for systemd version (using dbus-send)])
ret=$({ dbus-send --system --print-reply \
--dest=org.freedesktop.systemd1 \
/org/freedesktop/systemd1 \
org.freedesktop.DBus.Properties.Get \
string:org.freedesktop.systemd1.Manager \
string:Version 2>/dev/null \
|| echo "version unavailable"; } | tail -n1)
# sanitize output a bit (interested just in value, not type),
# ret is intentionally unenquoted so as to normalize whitespace
ret=$(echo ${ret} | cut -d' ' -f2-)
AC_MSG_RESULT([${ret}])
AS_IF([test x"$ret" != x"unavailable" \
|| systemctl --version 2>/dev/null | grep -q systemd],
[
AS_IF([check_systemdsystemunitdir],
[enable_systemd=$REQUIRED],
[enable_systemd=$DISABLED])
],
[enable_systemd=$DISABLED]
)
])
],
)
AC_MSG_CHECKING([whether to enable support for managing resources via systemd])
AS_IF([test $enable_systemd -eq $DISABLED], [AC_MSG_RESULT([no])],
[
AC_MSG_RESULT([yes])
PCMK_FEATURES="$PCMK_FEATURES systemd"
]
)
AC_SUBST([systemdsystemunitdir])
AC_DEFINE_UNQUOTED([SUPPORT_SYSTEMD], [$enable_systemd],
[Support systemd resources])
AM_CONDITIONAL([BUILD_SYSTEMD], [test $enable_systemd = $REQUIRED])
AC_SUBST(SUPPORT_SYSTEMD)
AS_CASE([$enable_upstart],
[$REQUIRED], [
AS_IF([test $HAVE_dbus = 0],
[AC_MSG_FAILURE([Cannot support Upstart resources without DBus])])
],
[$OPTIONAL], [
AS_IF([test $HAVE_dbus = 0], [enable_upstart=$DISABLED],
[
AC_MSG_CHECKING([for Upstart version (using dbus-send)])
ret=$({ dbus-send --system --print-reply \
--dest=com.ubuntu.Upstart \
/com/ubuntu/Upstart org.freedesktop.DBus.Properties.Get \
string:com.ubuntu.Upstart0_6 string:version 2>/dev/null \
|| echo "version unavailable"; } | tail -n1)
# sanitize output a bit (interested just in value, not type),
# ret is intentionally unenquoted so as to normalize whitespace
ret=$(echo ${ret} | cut -d' ' -f2-)
AC_MSG_RESULT([${ret}])
AS_IF([test x"$ret" != x"unavailable" \
|| initctl --version 2>/dev/null | grep -q upstart],
[enable_upstart=$REQUIRED],
[enable_upstart=$DISABLED]
)
])
],
)
AC_MSG_CHECKING([whether to enable support for managing resources via Upstart])
AS_IF([test $enable_upstart -eq $DISABLED], [AC_MSG_RESULT([no])],
[
AC_MSG_RESULT([yes])
PCMK_FEATURES="$PCMK_FEATURES upstart"
]
)
AC_DEFINE_UNQUOTED([SUPPORT_UPSTART], [$enable_upstart],
[Support Upstart resources])
AM_CONDITIONAL([BUILD_UPSTART], [test $enable_upstart -eq $REQUIRED])
AC_SUBST(SUPPORT_UPSTART)
dnl ========================================================================
dnl Detect Nagios support
dnl ========================================================================
AS_CASE([$with_nagios],
[$REQUIRED], [
AS_IF([test x"$ac_cv_have_decl_CLOCK_MONOTONIC" = x"no"],
[AC_MSG_FAILURE([Cannot support nagios resources without monotonic clock])])
],
[$OPTIONAL], [
AS_IF([test x"$ac_cv_have_decl_CLOCK_MONOTONIC" = x"no"],
[with_nagios=$DISABLED], [with_nagios=$REQUIRED])
]
)
AS_IF([test $with_nagios -eq $REQUIRED], [PCMK_FEATURES="$PCMK_FEATURES nagios"])
AC_DEFINE_UNQUOTED([SUPPORT_NAGIOS], [$with_nagios], [Support nagios plugins])
AM_CONDITIONAL([BUILD_NAGIOS], [test $with_nagios -eq $REQUIRED])
AS_IF([test x"$NAGIOS_PLUGIN_DIR" = x""],
[NAGIOS_PLUGIN_DIR="${libexecdir}/nagios/plugins"])
AC_DEFINE_UNQUOTED(NAGIOS_PLUGIN_DIR, "$NAGIOS_PLUGIN_DIR", Directory for nagios plugins)
AC_SUBST(NAGIOS_PLUGIN_DIR)
AS_IF([test x"$NAGIOS_METADATA_DIR" = x""],
[NAGIOS_METADATA_DIR="${datadir}/nagios/plugins-metadata"])
AC_DEFINE_UNQUOTED(NAGIOS_METADATA_DIR, "$NAGIOS_METADATA_DIR", Directory for nagios plugins metadata)
AC_SUBST(NAGIOS_METADATA_DIR)
STACKS=""
CLUSTERLIBS=""
PC_NAME_CLUSTER=""
dnl ========================================================================
dnl Cluster stack - Corosync
dnl ========================================================================
COROSYNC_LIBS=""
AS_CASE([$with_corosync],
[$REQUIRED], [
# These will be fatal if unavailable
PKG_CHECK_MODULES([cpg], [libcpg])
PKG_CHECK_MODULES([cfg], [libcfg])
PKG_CHECK_MODULES([cmap], [libcmap])
PKG_CHECK_MODULES([quorum], [libquorum])
PKG_CHECK_MODULES([libcorosync_common], [libcorosync_common])
]
[$OPTIONAL], [
PKG_CHECK_MODULES([cpg], [libcpg], [], [with_corosync=$DISABLED])
PKG_CHECK_MODULES([cfg], [libcfg], [], [with_corosync=$DISABLED])
PKG_CHECK_MODULES([cmap], [libcmap], [], [with_corosync=$DISABLED])
PKG_CHECK_MODULES([quorum], [libquorum], [], [with_corosync=$DISABLED])
PKG_CHECK_MODULES([libcorosync_common], [libcorosync_common], [], [with_corosync=$DISABLED])
AS_IF([test $with_corosync -ne $DISABLED], [with_corosync=$REQUIRED])
]
)
AS_IF([test $with_corosync -ne $DISABLED],
[
AC_MSG_CHECKING([for Corosync 2 or later])
AC_MSG_RESULT([yes])
CFLAGS="$CFLAGS $libqb_CFLAGS $cpg_CFLAGS $cfg_CFLAGS $cmap_CFLAGS $quorum_CFLAGS $libcorosync_common_CFLAGS"
CPPFLAGS="$CPPFLAGS `$PKG_CONFIG --cflags-only-I corosync`"
COROSYNC_LIBS="$COROSYNC_LIBS $cpg_LIBS $cfg_LIBS $cmap_LIBS $quorum_LIBS $libcorosync_common_LIBS"
CLUSTERLIBS="$CLUSTERLIBS $COROSYNC_LIBS"
PC_NAME_CLUSTER="$PC_CLUSTER_NAME libcfg libcmap libcorosync_common libcpg libquorum"
STACKS="$STACKS corosync-ge-2"
dnl Shutdown tracking added (back) to corosync Jan 2021
saved_LIBS="$LIBS"
LIBS="$LIBS $COROSYNC_LIBS"
AC_CHECK_FUNCS([corosync_cfg_trackstart])
LIBS="$saved_LIBS"
]
)
AC_DEFINE_UNQUOTED([SUPPORT_COROSYNC], [$with_corosync],
[Support the Corosync messaging and membership layer])
AM_CONDITIONAL([BUILD_CS_SUPPORT], [test $with_corosync -eq $REQUIRED])
AC_SUBST([SUPPORT_COROSYNC])
dnl
dnl Cluster stack - Sanity
dnl
AS_IF([test x"$STACKS" != x""], [AC_MSG_NOTICE([Supported stacks:${STACKS}])],
[AC_MSG_FAILURE([At least one cluster stack must be supported])])
PCMK_FEATURES="${PCMK_FEATURES}${STACKS}"
AC_SUBST(CLUSTERLIBS)
AC_SUBST(PC_NAME_CLUSTER)
dnl ========================================================================
dnl CIB secrets
dnl ========================================================================
AS_IF([test $with_cibsecrets -ne $DISABLED],
[
with_cibsecrets=$REQUIRED
PCMK_FEATURES="$PCMK_FEATURES cibsecrets"
LRM_CIBSECRETS_DIR="${localstatedir}/lib/pacemaker/lrm/secrets"
AC_DEFINE_UNQUOTED([LRM_CIBSECRETS_DIR], ["$LRM_CIBSECRETS_DIR"],
[Location for CIB secrets])
AC_SUBST([LRM_CIBSECRETS_DIR])
]
)
AC_DEFINE_UNQUOTED([SUPPORT_CIBSECRETS], [$with_cibsecrets], [Support CIB secrets])
AM_CONDITIONAL([BUILD_CIBSECRETS], [test $with_cibsecrets -eq $REQUIRED])
dnl ========================================================================
dnl GnuTLS
dnl ========================================================================
dnl Require GnuTLS >=2.12.0 (2011-03) for Pacemaker Remote support
PC_NAME_GNUTLS=""
AS_CASE([$with_gnutls],
[$REQUIRED], [
REQUIRE_LIB([gnutls], [gnutls_sec_param_to_pk_bits])
REQUIRE_HEADER([gnutls/gnutls.h])
],
[$OPTIONAL], [
AC_CHECK_LIB([gnutls], [gnutls_sec_param_to_pk_bits],
[], [with_gnutls=$DISABLED])
AC_CHECK_HEADERS([gnutls/gnutls.h], [], [with_gnutls=$DISABLED])
]
)
AS_IF([test $with_gnutls -ne $DISABLED],
[
PC_NAME_GNUTLS="gnutls"
PCMK_FEATURES="$PCMK_FEATURES remote"
]
)
AC_SUBST([PC_NAME_GNUTLS])
AM_CONDITIONAL([BUILD_REMOTE], [test $with_gnutls -ne $DISABLED])
# --- ASAN/UBSAN/TSAN (see man gcc) ---
# when using SANitizers, we need to pass the -fsanitize..
# to both CFLAGS and LDFLAGS. The CFLAGS/LDFLAGS must be
# specified as first in the list or there will be runtime
# issues (for example user has to LD_PRELOAD asan for it to work
# properly).
AS_IF([test -n "${SANITIZERS}"], [
SANITIZERS=$(echo $SANITIZERS | sed -e 's/,/ /g')
for SANITIZER in $SANITIZERS
do
AS_CASE([$SANITIZER],
[asan|ASAN], [
SANITIZERS_CFLAGS="$SANITIZERS_CFLAGS -fsanitize=address"
SANITIZERS_LDFLAGS="$SANITIZERS_LDFLAGS -fsanitize=address -lasan"
PCMK_FEATURES="$PCMK_FEATURES asan"
REQUIRE_LIB([asan],[main])
],
[ubsan|UBSAN], [
SANITIZERS_CFLAGS="$SANITIZERS_CFLAGS -fsanitize=undefined"
SANITIZERS_LDFLAGS="$SANITIZERS_LDFLAGS -fsanitize=undefined -lubsan"
PCMK_FEATURES="$PCMK_FEATURES ubsan"
REQUIRE_LIB([ubsan],[main])
],
[tsan|TSAN], [
SANITIZERS_CFLAGS="$SANITIZERS_CFLAGS -fsanitize=thread"
SANITIZERS_LDFLAGS="$SANITIZERS_LDFLAGS -fsanitize=thread -ltsan"
PCMK_FEATURES="$PCMK_FEATURES tsan"
REQUIRE_LIB([tsan],[main])
])
done
])
dnl ========================================================================
dnl Compiler flags
dnl ========================================================================
dnl Make sure that CFLAGS is not exported. If the user did
dnl not have CFLAGS in their environment then this should have
dnl no effect. However if CFLAGS was exported from the user's
dnl environment, then the new CFLAGS will also be exported
dnl to sub processes.
AS_IF([export | fgrep " CFLAGS=" > /dev/null],
[
SAVED_CFLAGS="$CFLAGS"
unset CFLAGS
CFLAGS="$SAVED_CFLAGS"
unset SAVED_CFLAGS
])
CC_EXTRAS=""
AS_IF([test x"$GCC" != x"yes"], [CFLAGS="$CFLAGS -g"], [
CFLAGS="$CFLAGS -ggdb"
dnl When we don't have diagnostic push / pull, we can't explicitly disable
dnl checking for nonliteral formats in the places where they occur on purpose
dnl thus we disable nonliteral format checking globally as we are aborting
dnl on warnings.
dnl what makes the things really ugly is that nonliteral format checking is
dnl obviously available as an extra switch in very modern gcc but for older
dnl gcc this is part of -Wformat=2
dnl so if we have push/pull we can enable -Wformat=2 -Wformat-nonliteral
dnl if we don't have push/pull but -Wformat-nonliteral we can enable -Wformat=2
dnl otherwise none of both
gcc_diagnostic_push_pull=no
cc_temp_flags "$CFLAGS $WERROR"
AC_MSG_CHECKING([for gcc diagnostic push / pull])
AC_COMPILE_IFELSE([AC_LANG_PROGRAM([[
#pragma GCC diagnostic push
#pragma GCC diagnostic pop
]])],
[
AC_MSG_RESULT([yes])
gcc_diagnostic_push_pull=yes
], AC_MSG_RESULT([no]))
cc_restore_flags
AS_IF([cc_supports_flag "-Wformat-nonliteral"],
[gcc_format_nonliteral=yes],
[gcc_format_nonliteral=no])
# We had to eliminate -Wnested-externs because of libtool changes
# Make sure to order options so that the former stand for prerequisites
# of the latter (e.g., -Wformat-nonliteral requires -Wformat).
EXTRA_FLAGS="-fgnu89-inline"
EXTRA_FLAGS="$EXTRA_FLAGS -Wall"
EXTRA_FLAGS="$EXTRA_FLAGS -Waggregate-return"
EXTRA_FLAGS="$EXTRA_FLAGS -Wbad-function-cast"
EXTRA_FLAGS="$EXTRA_FLAGS -Wcast-align"
EXTRA_FLAGS="$EXTRA_FLAGS -Wdeclaration-after-statement"
EXTRA_FLAGS="$EXTRA_FLAGS -Wendif-labels"
EXTRA_FLAGS="$EXTRA_FLAGS -Wfloat-equal"
EXTRA_FLAGS="$EXTRA_FLAGS -Wformat-security"
EXTRA_FLAGS="$EXTRA_FLAGS -Wimplicit-fallthrough"
EXTRA_FLAGS="$EXTRA_FLAGS -Wmissing-prototypes"
EXTRA_FLAGS="$EXTRA_FLAGS -Wmissing-declarations"
EXTRA_FLAGS="$EXTRA_FLAGS -Wnested-externs"
EXTRA_FLAGS="$EXTRA_FLAGS -Wno-long-long"
EXTRA_FLAGS="$EXTRA_FLAGS -Wno-strict-aliasing"
EXTRA_FLAGS="$EXTRA_FLAGS -Wpointer-arith"
EXTRA_FLAGS="$EXTRA_FLAGS -Wstrict-prototypes"
EXTRA_FLAGS="$EXTRA_FLAGS -Wwrite-strings"
EXTRA_FLAGS="$EXTRA_FLAGS -Wunused-but-set-variable"
EXTRA_FLAGS="$EXTRA_FLAGS -Wunsigned-char"
AS_IF([test x"$gcc_diagnostic_push_pull" = x"yes"],
[
AC_DEFINE([HAVE_FORMAT_NONLITERAL], [],
[gcc can complain about nonliterals in format])
EXTRA_FLAGS="$EXTRA_FLAGS -Wformat=2 -Wformat-nonliteral"
],
[test x"$gcc_format_nonliteral" = x"yes"],
[EXTRA_FLAGS="$EXTRA_FLAGS -Wformat=2"])
# Additional warnings it might be nice to enable one day
# -Wshadow
# -Wunreachable-code
for j in $EXTRA_FLAGS
do
AS_IF([cc_supports_flag $CC_EXTRAS $j], [CC_EXTRAS="$CC_EXTRAS $j"])
done
AC_MSG_NOTICE([Using additional gcc flags: ${CC_EXTRAS}])
])
dnl
dnl Hardening flags
dnl
dnl The prime control of whether to apply (targeted) hardening build flags and
dnl which ones is --{enable,disable}-hardening option passed to ./configure:
dnl
dnl --enable-hardening=try (default):
dnl depending on whether any of CFLAGS_HARDENED_EXE, LDFLAGS_HARDENED_EXE,
dnl CFLAGS_HARDENED_LIB or LDFLAGS_HARDENED_LIB environment variables
dnl (see below) is set and non-null, all these custom flags (even if not
dnl set) are used as are, otherwise the best effort is made to offer
dnl reasonably strong hardening in several categories (RELRO, PIE,
dnl "bind now", stack protector) according to what the selected toolchain
dnl can offer
dnl
dnl --enable-hardening:
dnl same effect as --enable-hardening=try when the environment variables
dnl in question are suppressed
dnl
dnl --disable-hardening:
dnl do not apply any targeted hardening measures at all
dnl
dnl The user-injected environment variables that regulate the hardening in
dnl default case are as follows:
dnl
dnl * CFLAGS_HARDENED_EXE, LDFLAGS_HARDENED_EXE
dnl compiler and linker flags (respectively) for daemon programs
dnl (pacemakerd, pacemaker-attrd, pacemaker-controld, pacemaker-execd,
dnl pacemaker-based, pacemaker-fenced, pacemaker-remoted,
dnl pacemaker-schedulerd)
dnl
dnl * CFLAGS_HARDENED_LIB, LDFLAGS_HARDENED_LIB
dnl compiler and linker flags (respectively) for libraries linked
dnl with the daemon programs
dnl
dnl Note that these are purposedly targeted variables (addressing particular
dnl targets all over the scattered Makefiles) and have no effect outside of
dnl the predestined scope (e.g., CLI utilities). For a global reach,
dnl use CFLAGS, LDFLAGS, etc. as usual.
dnl
dnl For guidance on the suitable flags consult, for instance:
dnl https://fedoraproject.org/wiki/Changes/Harden_All_Packages#Detailed_Harden_Flags_Description
dnl https://owasp.org/index.php/C-Based_Toolchain_Hardening#GCC.2FBinutils
dnl
AS_IF([test $enable_hardening -eq $OPTIONAL],
[
AS_IF([test "$(env | grep -Ec '^(C|LD)FLAGS_HARDENED_(EXE|LIB)=.')" = 0],
[enable_hardening=$REQUIRED],
[AC_MSG_NOTICE([Hardening: using custom flags from environment])]
)
],
[
unset CFLAGS_HARDENED_EXE
unset CFLAGS_HARDENED_LIB
unset LDFLAGS_HARDENED_EXE
unset LDFLAGS_HARDENED_LIB
]
)
AS_CASE([$enable_hardening],
[$DISABLED], [AC_MSG_NOTICE([Hardening: explicitly disabled])],
[$REQUIRED], [
CFLAGS_HARDENED_EXE=
CFLAGS_HARDENED_LIB=
LDFLAGS_HARDENED_EXE=
LDFLAGS_HARDENED_LIB=
relro=0
pie=0
bindnow=0
stackprot="none"
# daemons incl. libs: partial RELRO
flag="-Wl,-z,relro"
CC_CHECK_LDFLAGS(["${flag}"],
[
LDFLAGS_HARDENED_EXE="${LDFLAGS_HARDENED_EXE} ${flag}"
LDFLAGS_HARDENED_LIB="${LDFLAGS_HARDENED_LIB} ${flag}"
relro=1
])
# daemons: PIE for both CFLAGS and LDFLAGS
AS_IF([cc_supports_flag -fPIE],
[
flag="-pie"
CC_CHECK_LDFLAGS(["${flag}"],
[
CFLAGS_HARDENED_EXE="${CFLAGS_HARDENED_EXE} -fPIE"
LDFLAGS_HARDENED_EXE="${LDFLAGS_HARDENED_EXE} ${flag}"
pie=1
])
]
)
# daemons incl. libs: full RELRO if sensible + as-needed linking
# so as to possibly mitigate startup performance
# hit caused by excessive linking with unneeded
# libraries
AS_IF([test "${relro}" = 1 && test "${pie}" = 1],
[
flag="-Wl,-z,now"
CC_CHECK_LDFLAGS(["${flag}"],
[
LDFLAGS_HARDENED_EXE="${LDFLAGS_HARDENED_EXE} ${flag}"
LDFLAGS_HARDENED_LIB="${LDFLAGS_HARDENED_LIB} ${flag}"
bindnow=1
])
]
)
AS_IF([test "${bindnow}" = 1],
[
flag="-Wl,--as-needed"
CC_CHECK_LDFLAGS(["${flag}"],
[
LDFLAGS_HARDENED_EXE="${LDFLAGS_HARDENED_EXE} ${flag}"
LDFLAGS_HARDENED_LIB="${LDFLAGS_HARDENED_LIB} ${flag}"
])
])
# universal: prefer strong > all > default stack protector if possible
flag=
AS_IF([cc_supports_flag -fstack-protector-strong],
[
flag="-fstack-protector-strong"
stackprot="strong"
],
[cc_supports_flag -fstack-protector-all],
[
flag="-fstack-protector-all"
stackprot="all"
],
[cc_supports_flag -fstack-protector],
[
flag="-fstack-protector"
stackprot="default"
]
)
AS_IF([test -n "${flag}"], [CC_EXTRAS="${CC_EXTRAS} ${flag}"])
# universal: enable stack clash protection if possible
AS_IF([cc_supports_flag -fstack-clash-protection],
[
CC_EXTRAS="${CC_EXTRAS} -fstack-clash-protection"
AS_IF([test "${stackprot}" = "none"],
[stackprot="clash-only"],
[stackprot="${stackprot}+clash"]
)
]
)
# Log a summary
AS_IF([test "${relro}" = 1 || test "${pie}" = 1 || test x"${stackprot}" != x"none"],
[AC_MSG_NOTICE(m4_normalize([Hardening:
relro=${relro}
pie=${pie}
bindnow=${bindnow}
stackprot=${stackprot}]))
],
[AC_MSG_WARN([Hardening: no suitable features in the toolchain detected])]
)
],
)
CFLAGS="$SANITIZERS_CFLAGS $CFLAGS $CC_EXTRAS"
LDFLAGS="$SANITIZERS_LDFLAGS $LDFLAGS"
CFLAGS_HARDENED_EXE="$SANITIZERS_CFLAGS $CFLAGS_HARDENED_EXE"
LDFLAGS_HARDENED_EXE="$SANITIZERS_LDFLAGS $LDFLAGS_HARDENED_EXE"
NON_FATAL_CFLAGS="$CFLAGS"
AC_SUBST(NON_FATAL_CFLAGS)
dnl
dnl We reset CFLAGS to include our warnings *after* all function
dnl checking goes on, so that our warning flags don't keep the
dnl AC_*FUNCS() calls above from working. In particular, -Werror will
dnl *always* cause us troubles if we set it before here.
dnl
dnl
AS_IF([test $enable_fatal_warnings -ne $DISABLED], [
AC_MSG_NOTICE([Enabling fatal compiler warnings])
CFLAGS="$CFLAGS $WERROR"
])
AC_SUBST(CFLAGS)
dnl This is useful for use in Makefiles that need to remove one specific flag
CFLAGS_COPY="$CFLAGS"
AC_SUBST(CFLAGS_COPY)
AC_SUBST(LIBADD_DL) dnl extra flags for dynamic linking libraries
AC_SUBST(LOCALE)
dnl Options for cleaning up the compiler output
AS_IF([test $enable_quiet -ne $DISABLED],
[
AC_MSG_NOTICE([Suppressing make details])
QUIET_LIBTOOL_OPTS="--silent"
QUIET_MAKE_OPTS="-s" # POSIX compliant
],
[
QUIET_LIBTOOL_OPTS=""
QUIET_MAKE_OPTS=""
]
)
dnl Put the above variables to use
LIBTOOL="${LIBTOOL} --tag=CC \$(QUIET_LIBTOOL_OPTS)"
MAKEFLAGS="${MAKEFLAGS} ${QUIET_MAKE_OPTS}"
# Make features list available (sorted alphabetically, without leading space)
PCMK_FEATURES=`echo "$PCMK_FEATURES" | sed -e 's/^ //' -e 's/ /\n/g' | sort | xargs`
AC_DEFINE_UNQUOTED(CRM_FEATURES, "$PCMK_FEATURES", Set of enabled features)
AC_SUBST(PCMK_FEATURES)
AC_SUBST(CC)
AC_SUBST(MAKEFLAGS)
AC_SUBST(LIBTOOL)
AC_SUBST(QUIET_LIBTOOL_OPTS)
dnl Files we output that need to be executable
CONFIG_FILES_EXEC([agents/ocf/ClusterMon],
[agents/ocf/Dummy],
[agents/ocf/HealthCPU],
[agents/ocf/HealthIOWait],
[agents/ocf/HealthSMART],
[agents/ocf/Stateful],
[agents/ocf/SysInfo],
[agents/ocf/attribute],
[agents/ocf/controld],
[agents/ocf/ifspeed],
[agents/ocf/o2cb],
[agents/ocf/ping],
[agents/ocf/remote],
[agents/stonith/fence_legacy],
[agents/stonith/fence_watchdog],
[cts/cluster_test],
[cts/cts],
[cts/cts-attrd],
[cts/cts-cli],
[cts/cts-exec],
[cts/cts-fencing],
[cts/cts-lab],
[cts/cts-log-watcher],
[cts/cts-regression],
[cts/cts-scheduler],
[cts/benchmark/clubench],
[cts/support/LSBDummy],
[cts/support/cts-support],
[cts/support/fence_dummy],
[cts/support/pacemaker-cts-dummyd],
[doc/abi-check],
[maint/bumplibs],
[tools/cluster-clean],
[tools/cluster-helper],
[tools/crm_failcount],
[tools/crm_master],
[tools/crm_report],
[tools/crm_standby],
[tools/cibsecret],
[tools/pcmk_simtimes],
[xml/version-diff.sh])
dnl Other files we output
AC_CONFIG_FILES(Makefile \
agents/Makefile \
agents/alerts/Makefile \
agents/ocf/Makefile \
agents/stonith/Makefile \
cts/Makefile \
cts/benchmark/Makefile \
cts/scheduler/Makefile \
cts/scheduler/dot/Makefile \
cts/scheduler/exp/Makefile \
cts/scheduler/scores/Makefile \
cts/scheduler/stderr/Makefile \
cts/scheduler/summary/Makefile \
cts/scheduler/xml/Makefile \
cts/support/Makefile \
cts/support/pacemaker-cts-dummyd@.service \
daemons/Makefile \
daemons/attrd/Makefile \
daemons/based/Makefile \
daemons/controld/Makefile \
daemons/execd/Makefile \
daemons/execd/pacemaker_remote \
daemons/execd/pacemaker_remote.service \
daemons/fenced/Makefile \
daemons/pacemakerd/Makefile \
daemons/pacemakerd/pacemaker.combined.upstart \
daemons/pacemakerd/pacemaker.service \
daemons/pacemakerd/pacemaker.upstart \
daemons/schedulerd/Makefile \
devel/Makefile \
doc/Doxyfile \
doc/Makefile \
doc/sphinx/Makefile \
etc/Makefile \
etc/init.d/pacemaker \
etc/logrotate.d/pacemaker \
etc/sysconfig/pacemaker \
include/Makefile \
include/crm/Makefile \
include/crm/cib/Makefile \
include/crm/common/Makefile \
include/crm/cluster/Makefile \
include/crm/fencing/Makefile \
include/crm/pengine/Makefile \
include/pcmki/Makefile \
lib/Makefile \
lib/cib/Makefile \
lib/cluster/Makefile \
lib/common/Makefile \
lib/common/tests/Makefile \
lib/common/tests/acl/Makefile \
lib/common/tests/actions/Makefile \
lib/common/tests/agents/Makefile \
lib/common/tests/cmdline/Makefile \
lib/common/tests/flags/Makefile \
lib/common/tests/health/Makefile \
lib/common/tests/io/Makefile \
lib/common/tests/iso8601/Makefile \
lib/common/tests/lists/Makefile \
lib/common/tests/nvpair/Makefile \
lib/common/tests/options/Makefile \
lib/common/tests/output/Makefile \
lib/common/tests/procfs/Makefile \
lib/common/tests/results/Makefile \
lib/common/tests/schemas/Makefile \
lib/common/tests/scores/Makefile \
lib/common/tests/strings/Makefile \
lib/common/tests/utils/Makefile \
lib/common/tests/xml/Makefile \
lib/common/tests/xpath/Makefile \
lib/fencing/Makefile \
lib/gnu/Makefile \
lib/libpacemaker.pc \
lib/lrmd/Makefile \
lib/pacemaker/Makefile \
lib/pacemaker.pc \
lib/pacemaker-cib.pc \
lib/pacemaker-cluster.pc \
lib/pacemaker-fencing.pc \
lib/pacemaker-lrmd.pc \
lib/pacemaker-service.pc \
lib/pacemaker-pe_rules.pc \
lib/pacemaker-pe_status.pc \
lib/pengine/Makefile \
lib/pengine/tests/Makefile \
lib/pengine/tests/native/Makefile \
lib/pengine/tests/rules/Makefile \
lib/pengine/tests/status/Makefile \
lib/pengine/tests/unpack/Makefile \
lib/pengine/tests/utils/Makefile \
lib/services/Makefile \
maint/Makefile \
po/Makefile.in \
python/Makefile \
python/setup.py \
python/pacemaker/Makefile \
python/pacemaker/_cts/Makefile \
python/pacemaker/_cts/tests/Makefile \
python/pacemaker/buildoptions.py \
python/tests/Makefile \
rpm/Makefile \
tests/Makefile \
tools/Makefile \
tools/crm_mon.service \
tools/crm_mon.upstart \
tools/report.collector \
tools/report.common \
xml/Makefile \
xml/pacemaker-schemas.pc \
)
dnl Now process the entire list of files added by previous
dnl calls to AC_CONFIG_FILES()
AC_OUTPUT()
dnl *****************
dnl Configure summary
dnl *****************
AC_MSG_NOTICE([])
AC_MSG_NOTICE([$PACKAGE configuration:])
AC_MSG_NOTICE([ Version = ${VERSION} (Build: $BUILD_VERSION)])
AC_MSG_NOTICE([ Features = ${PCMK_FEATURES}])
AC_MSG_NOTICE([])
AC_MSG_NOTICE([ Prefix = ${prefix}])
AC_MSG_NOTICE([ Executables = ${sbindir}])
AC_MSG_NOTICE([ Man pages = ${mandir}])
AC_MSG_NOTICE([ Libraries = ${libdir}])
AC_MSG_NOTICE([ Header files = ${includedir}])
AC_MSG_NOTICE([ Arch-independent files = ${datadir}])
AC_MSG_NOTICE([ State information = ${localstatedir}])
AC_MSG_NOTICE([ System configuration = ${sysconfdir}])
AC_MSG_NOTICE([ OCF agents = ${OCF_ROOT_DIR}])
AC_MSG_NOTICE([])
AC_MSG_NOTICE([ HA group name = ${CRM_DAEMON_GROUP}])
AC_MSG_NOTICE([ HA user name = ${CRM_DAEMON_USER}])
AC_MSG_NOTICE([])
AC_MSG_NOTICE([ CFLAGS = ${CFLAGS}])
AC_MSG_NOTICE([ CFLAGS_HARDENED_EXE = ${CFLAGS_HARDENED_EXE}])
AC_MSG_NOTICE([ CFLAGS_HARDENED_LIB = ${CFLAGS_HARDENED_LIB}])
AC_MSG_NOTICE([ LDFLAGS_HARDENED_EXE = ${LDFLAGS_HARDENED_EXE}])
AC_MSG_NOTICE([ LDFLAGS_HARDENED_LIB = ${LDFLAGS_HARDENED_LIB}])
AC_MSG_NOTICE([ Libraries = ${LIBS}])
AC_MSG_NOTICE([ Stack Libraries = ${CLUSTERLIBS}])
AC_MSG_NOTICE([ Unix socket auth method = ${us_auth}])
diff --git a/cts/cli/regression.daemons.exp b/cts/cli/regression.daemons.exp
index 7b784b49e1..b34fba8070 100644
--- a/cts/cli/regression.daemons.exp
+++ b/cts/cli/regression.daemons.exp
@@ -1,451 +1,456 @@
=#=#=#= Begin test: Get CIB manager metadata =#=#=#=
<?xml version=""?>
<resource-agent name="pacemaker-based" version="">
<version>1.1</version>
<longdesc lang="en">Cluster options used by Pacemaker&apos;s Cluster Information Base manager</longdesc>
<shortdesc lang="en">Cluster Information Base manager options</shortdesc>
<parameters>
<parameter name="enable-acl">
<longdesc lang="en">Enable Access Control Lists (ACLs) for the CIB</longdesc>
<shortdesc lang="en">Enable Access Control Lists (ACLs) for the CIB</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="cluster-ipc-limit">
<longdesc lang="en">Raise this if log has &quot;Evicting client&quot; messages for cluster daemon PIDs (a good value is the number of resources in the cluster multiplied by the number of nodes).</longdesc>
<shortdesc lang="en">Maximum IPC message backlog before disconnecting a cluster daemon</shortdesc>
<content type="integer" default=""/>
</parameter>
</parameters>
</resource-agent>
=#=#=#= End test: Get CIB manager metadata - OK (0) =#=#=#=
* Passed: pacemaker-based - Get CIB manager metadata
=#=#=#= Begin test: Get controller metadata =#=#=#=
<?xml version=""?>
<resource-agent name="pacemaker-controld" version="">
<version>1.1</version>
<longdesc lang="en">Cluster options used by Pacemaker&apos;s controller</longdesc>
<shortdesc lang="en">Pacemaker controller options</shortdesc>
<parameters>
<parameter name="dc-version">
<longdesc lang="en">Includes a hash which identifies the exact changeset the code was built from. Used for diagnostic purposes.</longdesc>
<shortdesc lang="en">Pacemaker version on cluster node elected Designated Controller (DC)</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="cluster-infrastructure">
<longdesc lang="en">Used for informational and diagnostic purposes.</longdesc>
<shortdesc lang="en">The messaging stack on which Pacemaker is currently running</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="cluster-name">
<longdesc lang="en">This optional value is mostly for users&apos; convenience as desired in administration, but may also be used in Pacemaker configuration rules via the #cluster-name node attribute, and by higher-level tools and resource agents.</longdesc>
<shortdesc lang="en">An arbitrary name for the cluster</shortdesc>
<content type="string"/>
</parameter>
<parameter name="dc-deadtime">
<longdesc lang="en">The optimal value will depend on the speed and load of your network and the type of switches used.</longdesc>
<shortdesc lang="en">How long to wait for a response from other nodes during start-up</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="cluster-recheck-interval">
<longdesc lang="en">Pacemaker is primarily event-driven, and looks ahead to know when to recheck cluster state for failure timeouts and most time-based rules. However, it will also recheck the cluster after this amount of inactivity, to evaluate rules with date specifications and serve as a fail-safe for certain types of scheduler bugs. Allowed values: Zero disables polling, while positive values are an interval in seconds(unless other units are specified, for example "5min")</longdesc>
<shortdesc lang="en">Polling interval to recheck cluster state and evaluate rules with date specifications</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="load-threshold">
<longdesc lang="en">The cluster will slow down its recovery process when the amount of system resources used (currently CPU) approaches this limit</longdesc>
<shortdesc lang="en">Maximum amount of system load that should be used by cluster nodes</shortdesc>
<content type="percentage" default=""/>
</parameter>
<parameter name="node-action-limit">
<longdesc lang="en">Maximum number of jobs that can be scheduled per node (defaults to 2x cores)</longdesc>
<shortdesc lang="en">Maximum number of jobs that can be scheduled per node (defaults to 2x cores)</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="fence-reaction">
<longdesc lang="en">A cluster node may receive notification of its own fencing if fencing is misconfigured, or if fabric fencing is in use that doesn&apos;t cut cluster communication. Allowed values are &quot;stop&quot; to attempt to immediately stop Pacemaker and stay stopped, or &quot;panic&quot; to attempt to immediately reboot the local node, falling back to stop on failure.</longdesc>
<shortdesc lang="en">How a cluster node should react if notified of its own fencing</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="election-timeout">
<longdesc lang="en">Declare an election failed if it is not decided within this much time. If you need to adjust this value, it probably indicates the presence of a bug.</longdesc>
<shortdesc lang="en">*** Advanced Use Only ***</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="shutdown-escalation">
<longdesc lang="en">Exit immediately if shutdown does not complete within this much time. If you need to adjust this value, it probably indicates the presence of a bug.</longdesc>
<shortdesc lang="en">*** Advanced Use Only ***</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="join-integration-timeout">
<longdesc lang="en">If you need to adjust this value, it probably indicates the presence of a bug.</longdesc>
<shortdesc lang="en">*** Advanced Use Only ***</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="join-finalization-timeout">
<longdesc lang="en">If you need to adjust this value, it probably indicates the presence of a bug.</longdesc>
<shortdesc lang="en">*** Advanced Use Only ***</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="transition-delay">
<longdesc lang="en">Delay cluster recovery for this much time to allow for additional events to occur. Useful if your configuration is sensitive to the order in which ping updates arrive.</longdesc>
<shortdesc lang="en">*** Advanced Use Only *** Enabling this option will slow down cluster recovery under all conditions</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="stonith-watchdog-timeout">
<longdesc lang="en">If this is set to a positive value, lost nodes are assumed to self-fence using watchdog-based SBD within this much time. This does not require a fencing resource to be explicitly configured, though a fence_watchdog resource can be configured, to limit use to specific nodes. If this is set to 0 (the default), the cluster will never assume watchdog-based self-fencing. If this is set to a negative value, the cluster will use twice the local value of the `SBD_WATCHDOG_TIMEOUT` environment variable if that is positive, or otherwise treat this as 0. WARNING: When used, this timeout must be larger than `SBD_WATCHDOG_TIMEOUT` on all nodes that use watchdog-based SBD, and Pacemaker will refuse to start on any of those nodes where this is not true for the local value or SBD is not active. When this is set to a negative value, `SBD_WATCHDOG_TIMEOUT` must be set to the same value on all nodes that use SBD, otherwise data corruption or loss could occur.</longdesc>
<shortdesc lang="en">How long before nodes can be assumed to be safely down when watchdog-based self-fencing via SBD is in use</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="stonith-max-attempts">
<longdesc lang="en">How many times fencing can fail before it will no longer be immediately re-attempted on a target</longdesc>
<shortdesc lang="en">How many times fencing can fail before it will no longer be immediately re-attempted on a target</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="no-quorum-policy">
<longdesc lang="en">What to do when the cluster does not have quorum Allowed values: stop, freeze, ignore, demote, suicide</longdesc>
<shortdesc lang="en">What to do when the cluster does not have quorum</shortdesc>
<content type="select" default="">
<option value="stop" />
<option value="freeze" />
<option value="ignore" />
<option value="demote" />
<option value="suicide" />
</content>
</parameter>
<parameter name="shutdown-lock">
<longdesc lang="en">When true, resources active on a node when it is cleanly shut down are kept &quot;locked&quot; to that node (not allowed to run elsewhere) until they start again on that node after it rejoins (or for at most shutdown-lock-limit, if set). Stonith resources and Pacemaker Remote connections are never locked. Clone and bundle instances and the promoted role of promotable clones are currently never locked, though support could be added in a future release.</longdesc>
<shortdesc lang="en">Whether to lock resources to a cleanly shut down node</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="shutdown-lock-limit">
<longdesc lang="en">If shutdown-lock is true and this is set to a nonzero time duration, shutdown locks will expire after this much time has passed since the shutdown was initiated, even if the node has not rejoined.</longdesc>
<shortdesc lang="en">Do not lock resources to a cleanly shut down node longer than this</shortdesc>
<content type="time" default=""/>
</parameter>
+ <parameter name="node-pending-timeout">
+ <longdesc lang="en">Fence nodes that do not join the controller process group within this much time after joining the cluster, to allow the cluster to continue managing resources. A value of 0 means never fence pending nodes. Setting the value to 2h means fence nodes after 2 hours.</longdesc>
+ <shortdesc lang="en">How long to wait for a node that has joined the cluster to join the controller process group</shortdesc>
+ <content type="time" default=""/>
+ </parameter>
</parameters>
</resource-agent>
=#=#=#= End test: Get controller metadata - OK (0) =#=#=#=
* Passed: pacemaker-controld - Get controller metadata
=#=#=#= Begin test: Get fencer metadata =#=#=#=
<?xml version=""?>
<resource-agent name="pacemaker-fenced" version="">
<version>1.1</version>
<longdesc lang="en">Instance attributes available for all &quot;stonith&quot;-class resources and used by Pacemaker&apos;s fence daemon, formerly known as stonithd</longdesc>
<shortdesc lang="en">Instance attributes available for all &quot;stonith&quot;-class resources</shortdesc>
<parameters>
<parameter name="pcmk_host_argument">
<longdesc lang="en">some devices do not support the standard &apos;port&apos; parameter or may provide additional ones. Use this to specify an alternate, device-specific, parameter that should indicate the machine to be fenced. A value of none can be used to tell the cluster not to supply any additional parameters.</longdesc>
<shortdesc lang="en">Advanced use only: An alternate parameter to supply instead of &apos;port&apos;</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="pcmk_host_map">
<longdesc lang="en">Eg. node1:1;node2:2,3 would tell the cluster to use port 1 for node1 and ports 2 and 3 for node2</longdesc>
<shortdesc lang="en">A mapping of host names to ports numbers for devices that do not support host names.</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="pcmk_host_list">
<longdesc lang="en">A list of machines controlled by this device (Optional unless pcmk_host_list=static-list)</longdesc>
<shortdesc lang="en">Eg. node1,node2,node3</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="pcmk_host_check">
<longdesc lang="en">Allowed values: dynamic-list (query the device via the &apos;list&apos; command), static-list (check the pcmk_host_list attribute), status (query the device via the &apos;status&apos; command), none (assume every device can fence every machine)</longdesc>
<shortdesc lang="en">How to determine which machines are controlled by the device.</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="pcmk_delay_max">
<longdesc lang="en">Enable a delay of no more than the time specified before executing fencing actions. Pacemaker derives the overall delay by taking the value of pcmk_delay_base and adding a random delay value such that the sum is kept below this maximum.</longdesc>
<shortdesc lang="en">Enable a base delay for fencing actions and specify base delay value.</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="pcmk_delay_base">
<longdesc lang="en">This enables a static delay for fencing actions, which can help avoid &quot;death matches&quot; where two nodes try to fence each other at the same time. If pcmk_delay_max is also used, a random delay will be added such that the total delay is kept below that value.This can be set to a single time value to apply to any node targeted by this device (useful if a separate device is configured for each target), or to a node map (for example, &quot;node1:1s;node2:5&quot;) to set a different value per target.</longdesc>
<shortdesc lang="en">Enable a base delay for fencing actions and specify base delay value.</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="pcmk_action_limit">
<longdesc lang="en">Cluster property concurrent-fencing=true needs to be configured first.Then use this to specify the maximum number of actions can be performed in parallel on this device. -1 is unlimited.</longdesc>
<shortdesc lang="en">The maximum number of actions can be performed in parallel on this device</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="pcmk_reboot_action">
<longdesc lang="en">Some devices do not support the standard commands or may provide additional ones.\nUse this to specify an alternate, device-specific, command that implements the &apos;reboot&apos; action.</longdesc>
<shortdesc lang="en">Advanced use only: An alternate command to run instead of &apos;reboot&apos;</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="pcmk_reboot_timeout">
<longdesc lang="en">Some devices need much more/less time to complete than normal.Use this to specify an alternate, device-specific, timeout for &apos;reboot&apos; actions.</longdesc>
<shortdesc lang="en">Advanced use only: Specify an alternate timeout to use for reboot actions instead of stonith-timeout</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="pcmk_reboot_retries">
<longdesc lang="en">Some devices do not support multiple connections. Operations may &apos;fail&apos; if the device is busy with another task so Pacemaker will automatically retry the operation, if there is time remaining. Use this option to alter the number of times Pacemaker retries &apos;reboot&apos; actions before giving up.</longdesc>
<shortdesc lang="en">Advanced use only: The maximum number of times to retry the &apos;reboot&apos; command within the timeout period</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="pcmk_off_action">
<longdesc lang="en">Some devices do not support the standard commands or may provide additional ones.Use this to specify an alternate, device-specific, command that implements the &apos;off&apos; action.</longdesc>
<shortdesc lang="en">Advanced use only: An alternate command to run instead of &apos;off&apos;</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="pcmk_off_timeout">
<longdesc lang="en">Some devices need much more/less time to complete than normal.Use this to specify an alternate, device-specific, timeout for &apos;off&apos; actions.</longdesc>
<shortdesc lang="en">Advanced use only: Specify an alternate timeout to use for off actions instead of stonith-timeout</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="pcmk_off_retries">
<longdesc lang="en">Some devices do not support multiple connections. Operations may &apos;fail&apos; if the device is busy with another task so Pacemaker will automatically retry the operation, if there is time remaining. Use this option to alter the number of times Pacemaker retries &apos;off&apos; actions before giving up.</longdesc>
<shortdesc lang="en">Advanced use only: The maximum number of times to retry the &apos;off&apos; command within the timeout period</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="pcmk_on_action">
<longdesc lang="en">Some devices do not support the standard commands or may provide additional ones.Use this to specify an alternate, device-specific, command that implements the &apos;on&apos; action.</longdesc>
<shortdesc lang="en">Advanced use only: An alternate command to run instead of &apos;on&apos;</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="pcmk_on_timeout">
<longdesc lang="en">Some devices need much more/less time to complete than normal.Use this to specify an alternate, device-specific, timeout for &apos;on&apos; actions.</longdesc>
<shortdesc lang="en">Advanced use only: Specify an alternate timeout to use for on actions instead of stonith-timeout</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="pcmk_on_retries">
<longdesc lang="en">Some devices do not support multiple connections. Operations may &apos;fail&apos; if the device is busy with another task so Pacemaker will automatically retry the operation, if there is time remaining. Use this option to alter the number of times Pacemaker retries &apos;on&apos; actions before giving up.</longdesc>
<shortdesc lang="en">Advanced use only: The maximum number of times to retry the &apos;on&apos; command within the timeout period</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="pcmk_list_action">
<longdesc lang="en">Some devices do not support the standard commands or may provide additional ones.Use this to specify an alternate, device-specific, command that implements the &apos;list&apos; action.</longdesc>
<shortdesc lang="en">Advanced use only: An alternate command to run instead of &apos;list&apos;</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="pcmk_list_timeout">
<longdesc lang="en">Some devices need much more/less time to complete than normal.Use this to specify an alternate, device-specific, timeout for &apos;list&apos; actions.</longdesc>
<shortdesc lang="en">Advanced use only: Specify an alternate timeout to use for list actions instead of stonith-timeout</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="pcmk_list_retries">
<longdesc lang="en">Some devices do not support multiple connections. Operations may &apos;fail&apos; if the device is busy with another task so Pacemaker will automatically retry the operation, if there is time remaining. Use this option to alter the number of times Pacemaker retries &apos;list&apos; actions before giving up.</longdesc>
<shortdesc lang="en">Advanced use only: The maximum number of times to retry the &apos;list&apos; command within the timeout period</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="pcmk_monitor_action">
<longdesc lang="en">Some devices do not support the standard commands or may provide additional ones.Use this to specify an alternate, device-specific, command that implements the &apos;monitor&apos; action.</longdesc>
<shortdesc lang="en">Advanced use only: An alternate command to run instead of &apos;monitor&apos;</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="pcmk_monitor_timeout">
<longdesc lang="en">Some devices need much more/less time to complete than normal.\nUse this to specify an alternate, device-specific, timeout for &apos;monitor&apos; actions.</longdesc>
<shortdesc lang="en">Advanced use only: Specify an alternate timeout to use for monitor actions instead of stonith-timeout</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="pcmk_monitor_retries">
<longdesc lang="en">Some devices do not support multiple connections. Operations may &apos;fail&apos; if the device is busy with another task so Pacemaker will automatically retry the operation, if there is time remaining. Use this option to alter the number of times Pacemaker retries &apos;monitor&apos; actions before giving up.</longdesc>
<shortdesc lang="en">Advanced use only: The maximum number of times to retry the &apos;monitor&apos; command within the timeout period</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="pcmk_status_action">
<longdesc lang="en">Some devices do not support the standard commands or may provide additional ones.Use this to specify an alternate, device-specific, command that implements the &apos;status&apos; action.</longdesc>
<shortdesc lang="en">Advanced use only: An alternate command to run instead of &apos;status&apos;</shortdesc>
<content type="string" default=""/>
</parameter>
<parameter name="pcmk_status_timeout">
<longdesc lang="en">Some devices need much more/less time to complete than normal.Use this to specify an alternate, device-specific, timeout for &apos;status&apos; actions.</longdesc>
<shortdesc lang="en">Advanced use only: Specify an alternate timeout to use for status actions instead of stonith-timeout</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="pcmk_status_retries">
<longdesc lang="en">Some devices do not support multiple connections. Operations may &apos;fail&apos; if the device is busy with another task so Pacemaker will automatically retry the operation, if there is time remaining. Use this option to alter the number of times Pacemaker retries &apos;status&apos; actions before giving up.</longdesc>
<shortdesc lang="en">Advanced use only: The maximum number of times to retry the &apos;status&apos; command within the timeout period</shortdesc>
<content type="integer" default=""/>
</parameter>
</parameters>
</resource-agent>
=#=#=#= End test: Get fencer metadata - OK (0) =#=#=#=
* Passed: pacemaker-fenced - Get fencer metadata
=#=#=#= Begin test: Get scheduler metadata =#=#=#=
<?xml version=""?>
<resource-agent name="pacemaker-schedulerd" version="">
<version>1.1</version>
<longdesc lang="en">Cluster options used by Pacemaker&apos;s scheduler</longdesc>
<shortdesc lang="en">Pacemaker scheduler options</shortdesc>
<parameters>
<parameter name="no-quorum-policy">
<longdesc lang="en">What to do when the cluster does not have quorum Allowed values: stop, freeze, ignore, demote, suicide</longdesc>
<shortdesc lang="en">What to do when the cluster does not have quorum</shortdesc>
<content type="select" default="">
<option value="stop" />
<option value="freeze" />
<option value="ignore" />
<option value="demote" />
<option value="suicide" />
</content>
</parameter>
<parameter name="symmetric-cluster">
<longdesc lang="en">Whether resources can run on any node by default</longdesc>
<shortdesc lang="en">Whether resources can run on any node by default</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="maintenance-mode">
<longdesc lang="en">Whether the cluster should refrain from monitoring, starting, and stopping resources</longdesc>
<shortdesc lang="en">Whether the cluster should refrain from monitoring, starting, and stopping resources</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="start-failure-is-fatal">
<longdesc lang="en">When true, the cluster will immediately ban a resource from a node if it fails to start there. When false, the cluster will instead check the resource&apos;s fail count against its migration-threshold.</longdesc>
<shortdesc lang="en">Whether a start failure should prevent a resource from being recovered on the same node</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="enable-startup-probes">
<longdesc lang="en">Whether the cluster should check for active resources during start-up</longdesc>
<shortdesc lang="en">Whether the cluster should check for active resources during start-up</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="shutdown-lock">
<longdesc lang="en">When true, resources active on a node when it is cleanly shut down are kept &quot;locked&quot; to that node (not allowed to run elsewhere) until they start again on that node after it rejoins (or for at most shutdown-lock-limit, if set). Stonith resources and Pacemaker Remote connections are never locked. Clone and bundle instances and the promoted role of promotable clones are currently never locked, though support could be added in a future release.</longdesc>
<shortdesc lang="en">Whether to lock resources to a cleanly shut down node</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="shutdown-lock-limit">
<longdesc lang="en">If shutdown-lock is true and this is set to a nonzero time duration, shutdown locks will expire after this much time has passed since the shutdown was initiated, even if the node has not rejoined.</longdesc>
<shortdesc lang="en">Do not lock resources to a cleanly shut down node longer than this</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="stonith-enabled">
<longdesc lang="en">If false, unresponsive nodes are immediately assumed to be harmless, and resources that were active on them may be recovered elsewhere. This can result in a &quot;split-brain&quot; situation, potentially leading to data loss and/or service unavailability.</longdesc>
<shortdesc lang="en">*** Advanced Use Only *** Whether nodes may be fenced as part of recovery</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="stonith-action">
<longdesc lang="en">Action to send to fence device when a node needs to be fenced (&quot;poweroff&quot; is a deprecated alias for &quot;off&quot;) Allowed values: reboot, off, poweroff</longdesc>
<shortdesc lang="en">Action to send to fence device when a node needs to be fenced (&quot;poweroff&quot; is a deprecated alias for &quot;off&quot;)</shortdesc>
<content type="select" default="">
<option value="reboot" />
<option value="off" />
<option value="poweroff" />
</content>
</parameter>
<parameter name="stonith-timeout">
<longdesc lang="en">This value is not used by Pacemaker, but is kept for backward compatibility, and certain legacy fence agents might use it.</longdesc>
<shortdesc lang="en">*** Advanced Use Only *** Unused by Pacemaker</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="have-watchdog">
<longdesc lang="en">This is set automatically by the cluster according to whether SBD is detected to be in use. User-configured values are ignored. The value `true` is meaningful if diskless SBD is used and `stonith-watchdog-timeout` is nonzero. In that case, if fencing is required, watchdog-based self-fencing will be performed via SBD without requiring a fencing resource explicitly configured.</longdesc>
<shortdesc lang="en">Whether watchdog integration is enabled</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="concurrent-fencing">
<longdesc lang="en">Allow performing fencing operations in parallel</longdesc>
<shortdesc lang="en">Allow performing fencing operations in parallel</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="startup-fencing">
<longdesc lang="en">Setting this to false may lead to a &quot;split-brain&quot; situation,potentially leading to data loss and/or service unavailability.</longdesc>
<shortdesc lang="en">*** Advanced Use Only *** Whether to fence unseen nodes at start-up</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="priority-fencing-delay">
<longdesc lang="en">Apply specified delay for the fencings that are targeting the lost nodes with the highest total resource priority in case we don&apos;t have the majority of the nodes in our cluster partition, so that the more significant nodes potentially win any fencing match, which is especially meaningful under split-brain of 2-node cluster. A promoted resource instance takes the base priority + 1 on calculation if the base priority is not 0. Any static/random delays that are introduced by `pcmk_delay_base/max` configured for the corresponding fencing resources will be added to this delay. This delay should be significantly greater than, safely twice, the maximum `pcmk_delay_base/max`. By default, priority fencing delay is disabled.</longdesc>
<shortdesc lang="en">Apply fencing delay targeting the lost nodes with the highest total resource priority</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="node-pending-timeout">
- <longdesc lang="en">Fence nodes that do not join the controller process group within this much time after joining the cluster, to allow the cluster to continue managing resources. A value of 0 means never fence pending nodes.</longdesc>
+ <longdesc lang="en">Fence nodes that do not join the controller process group within this much time after joining the cluster, to allow the cluster to continue managing resources. A value of 0 means never fence pending nodes. Setting the value to 2h means fence nodes after 2 hours.</longdesc>
<shortdesc lang="en">How long to wait for a node that has joined the cluster to join the controller process group</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="cluster-delay">
<longdesc lang="en">The node elected Designated Controller (DC) will consider an action failed if it does not get a response from the node executing the action within this time (after considering the action&apos;s own timeout). The &quot;correct&quot; value will depend on the speed and load of your network and cluster nodes.</longdesc>
<shortdesc lang="en">Maximum time for node-to-node communication</shortdesc>
<content type="time" default=""/>
</parameter>
<parameter name="batch-limit">
<longdesc lang="en">The &quot;correct&quot; value will depend on the speed and load of your network and cluster nodes. If set to 0, the cluster will impose a dynamically calculated limit when any node has a high load.</longdesc>
<shortdesc lang="en">Maximum number of jobs that the cluster may execute in parallel across all nodes</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="migration-limit">
<longdesc lang="en">The number of live migration actions that the cluster is allowed to execute in parallel on a node (-1 means no limit)</longdesc>
<shortdesc lang="en">The number of live migration actions that the cluster is allowed to execute in parallel on a node (-1 means no limit)</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="stop-all-resources">
<longdesc lang="en">Whether the cluster should stop all active resources</longdesc>
<shortdesc lang="en">Whether the cluster should stop all active resources</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="stop-orphan-resources">
<longdesc lang="en">Whether to stop resources that were removed from the configuration</longdesc>
<shortdesc lang="en">Whether to stop resources that were removed from the configuration</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="stop-orphan-actions">
<longdesc lang="en">Whether to cancel recurring actions removed from the configuration</longdesc>
<shortdesc lang="en">Whether to cancel recurring actions removed from the configuration</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="remove-after-stop">
<longdesc lang="en">Values other than default are poorly tested and potentially dangerous. This option will be removed in a future release.</longdesc>
<shortdesc lang="en">*** Deprecated *** Whether to remove stopped resources from the executor</shortdesc>
<content type="boolean" default=""/>
</parameter>
<parameter name="pe-error-series-max">
<longdesc lang="en">Zero to disable, -1 to store unlimited.</longdesc>
<shortdesc lang="en">The number of scheduler inputs resulting in errors to save</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="pe-warn-series-max">
<longdesc lang="en">Zero to disable, -1 to store unlimited.</longdesc>
<shortdesc lang="en">The number of scheduler inputs resulting in warnings to save</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="pe-input-series-max">
<longdesc lang="en">Zero to disable, -1 to store unlimited.</longdesc>
<shortdesc lang="en">The number of scheduler inputs without errors or warnings to save</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="node-health-strategy">
<longdesc lang="en">Requires external entities to create node attributes (named with the prefix &quot;#health&quot;) with values &quot;red&quot;, &quot;yellow&quot;, or &quot;green&quot;. Allowed values: none, migrate-on-red, only-green, progressive, custom</longdesc>
<shortdesc lang="en">How cluster should react to node health attributes</shortdesc>
<content type="select" default="">
<option value="none" />
<option value="migrate-on-red" />
<option value="only-green" />
<option value="progressive" />
<option value="custom" />
</content>
</parameter>
<parameter name="node-health-base">
<longdesc lang="en">Only used when &quot;node-health-strategy&quot; is set to &quot;progressive&quot;.</longdesc>
<shortdesc lang="en">Base health score assigned to a node</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="node-health-green">
<longdesc lang="en">Only used when &quot;node-health-strategy&quot; is set to &quot;custom&quot; or &quot;progressive&quot;.</longdesc>
<shortdesc lang="en">The score to use for a node health attribute whose value is &quot;green&quot;</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="node-health-yellow">
<longdesc lang="en">Only used when &quot;node-health-strategy&quot; is set to &quot;custom&quot; or &quot;progressive&quot;.</longdesc>
<shortdesc lang="en">The score to use for a node health attribute whose value is &quot;yellow&quot;</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="node-health-red">
<longdesc lang="en">Only used when &quot;node-health-strategy&quot; is set to &quot;custom&quot; or &quot;progressive&quot;.</longdesc>
<shortdesc lang="en">The score to use for a node health attribute whose value is &quot;red&quot;</shortdesc>
<content type="integer" default=""/>
</parameter>
<parameter name="placement-strategy">
<longdesc lang="en">How the cluster should allocate resources to nodes Allowed values: default, utilization, minimal, balanced</longdesc>
<shortdesc lang="en">How the cluster should allocate resources to nodes</shortdesc>
<content type="select" default="">
<option value="default" />
<option value="utilization" />
<option value="minimal" />
<option value="balanced" />
</content>
</parameter>
</parameters>
</resource-agent>
=#=#=#= End test: Get scheduler metadata - OK (0) =#=#=#=
* Passed: pacemaker-schedulerd - Get scheduler metadata
diff --git a/daemons/attrd/attrd_cib.c b/daemons/attrd/attrd_cib.c
index 95c9e1366f..3f71691117 100644
--- a/daemons/attrd/attrd_cib.c
+++ b/daemons/attrd/attrd_cib.c
@@ -1,685 +1,685 @@
/*
* Copyright 2013-2023 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU General Public License version 2
* or later (GPLv2+) WITHOUT ANY WARRANTY.
*/
#include <crm_internal.h>
#include <errno.h>
#include <inttypes.h> // PRIu32
#include <stdbool.h>
#include <stdlib.h>
#include <glib.h>
#include <crm/msg_xml.h>
#include <crm/common/logging.h>
#include <crm/common/results.h>
#include <crm/common/strings_internal.h>
#include <crm/common/xml.h>
#include "pacemaker-attrd.h"
static int last_cib_op_done = 0;
static void write_attribute(attribute_t *a, bool ignore_delay);
static void
attrd_cib_destroy_cb(gpointer user_data)
{
cib_t *cib = user_data;
cib->cmds->signoff(cib);
if (attrd_shutting_down(false)) {
crm_info("Disconnected from the CIB manager");
} else {
// @TODO This should trigger a reconnect, not a shutdown
crm_crit("Lost connection to the CIB manager, shutting down");
attrd_exit_status = CRM_EX_DISCONNECT;
attrd_shutdown(0);
}
}
static void
attrd_cib_updated_cb(const char *event, xmlNode *msg)
{
const xmlNode *patchset = NULL;
const char *client_name = NULL;
if (attrd_shutting_down(true)) {
return;
}
if (cib__get_notify_patchset(msg, &patchset) != pcmk_rc_ok) {
return;
}
if (cib__element_in_patchset(patchset, XML_CIB_TAG_ALERTS)) {
mainloop_set_trigger(attrd_config_read);
}
if (!attrd_election_won()) {
// Don't write attributes if we're not the writer
return;
}
client_name = crm_element_value(msg, F_CIB_CLIENTNAME);
if (!cib__client_triggers_refresh(client_name)) {
// The CIB is still accurate
return;
}
if (cib__element_in_patchset(patchset, XML_CIB_TAG_NODES)
|| cib__element_in_patchset(patchset, XML_CIB_TAG_STATUS)) {
/* An unsafe client modified the nodes or status section. Write
* transient attributes to ensure they're up-to-date in the CIB.
*/
if (client_name == NULL) {
client_name = crm_element_value(msg, F_CIB_CLIENTID);
}
crm_notice("Updating all attributes after %s event triggered by %s",
event, pcmk__s(client_name, "(unidentified client)"));
attrd_write_attributes(attrd_write_all);
}
}
int
attrd_cib_connect(int max_retry)
{
static int attempts = 0;
int rc = -ENOTCONN;
the_cib = cib_new();
if (the_cib == NULL) {
return -ENOTCONN;
}
do {
if (attempts > 0) {
sleep(attempts);
}
attempts++;
crm_debug("Connection attempt %d to the CIB manager", attempts);
rc = the_cib->cmds->signon(the_cib, T_ATTRD, cib_command);
} while ((rc != pcmk_ok) && (attempts < max_retry));
if (rc != pcmk_ok) {
crm_err("Connection to the CIB manager failed: %s " CRM_XS " rc=%d",
pcmk_strerror(rc), rc);
goto cleanup;
}
crm_debug("Connected to the CIB manager after %d attempts", attempts);
rc = the_cib->cmds->set_connection_dnotify(the_cib, attrd_cib_destroy_cb);
if (rc != pcmk_ok) {
crm_err("Could not set disconnection callback");
goto cleanup;
}
rc = the_cib->cmds->add_notify_callback(the_cib, T_CIB_DIFF_NOTIFY,
attrd_cib_updated_cb);
if (rc != pcmk_ok) {
crm_err("Could not set CIB notification callback");
goto cleanup;
}
return pcmk_ok;
cleanup:
cib__clean_up_connection(&the_cib);
return -ENOTCONN;
}
void
attrd_cib_disconnect(void)
{
CRM_CHECK(the_cib != NULL, return);
the_cib->cmds->del_notify_callback(the_cib, T_CIB_DIFF_NOTIFY,
attrd_cib_updated_cb);
cib__clean_up_connection(&the_cib);
}
static void
attrd_erase_cb(xmlNode *msg, int call_id, int rc, xmlNode *output,
void *user_data)
{
do_crm_log_unlikely(((rc != pcmk_ok)? LOG_NOTICE : LOG_DEBUG),
"Cleared transient attributes: %s "
CRM_XS " xpath=%s rc=%d",
pcmk_strerror(rc), (char *) user_data, rc);
}
#define XPATH_TRANSIENT "//node_state[@uname='%s']/" XML_TAG_TRANSIENT_NODEATTRS
/*!
* \internal
* \brief Wipe all transient attributes for this node from the CIB
*
* Clear any previous transient node attributes from the CIB. This is
* normally done by the DC's controller when this node leaves the cluster, but
* this handles the case where the node restarted so quickly that the
* cluster layer didn't notice.
*
- * \todo If pacemaker-attrd respawns after crashing (see PCMK_respawned),
+ * \todo If pacemaker-attrd respawns after crashing (see PCMK_ENV_RESPAWNED),
* ideally we'd skip this and sync our attributes from the writer.
* However, currently we reject any values for us that the writer has, in
* attrd_peer_update().
*/
static void
attrd_erase_attrs(void)
{
int call_id = 0;
char *xpath = crm_strdup_printf(XPATH_TRANSIENT, attrd_cluster->uname);
crm_info("Clearing transient attributes from CIB " CRM_XS " xpath=%s",
xpath);
call_id = the_cib->cmds->remove(the_cib, xpath, NULL, cib_xpath);
the_cib->cmds->register_callback_full(the_cib, call_id, 120, FALSE, xpath,
"attrd_erase_cb", attrd_erase_cb,
free);
}
/*!
* \internal
* \brief Prepare the CIB after cluster is connected
*/
void
attrd_cib_init(void)
{
// We have no attribute values in memory, wipe the CIB to match
attrd_erase_attrs();
// Set a trigger for reading the CIB (for the alerts section)
attrd_config_read = mainloop_add_trigger(G_PRIORITY_HIGH, attrd_read_options, NULL);
// Always read the CIB at start-up
mainloop_set_trigger(attrd_config_read);
}
static gboolean
attribute_timer_cb(gpointer data)
{
attribute_t *a = data;
crm_trace("Dampen interval expired for %s", a->id);
attrd_write_or_elect_attribute(a);
return FALSE;
}
static void
attrd_cib_callback(xmlNode *msg, int call_id, int rc, xmlNode *output, void *user_data)
{
int level = LOG_ERR;
GHashTableIter iter;
const char *peer = NULL;
attribute_value_t *v = NULL;
char *name = user_data;
attribute_t *a = g_hash_table_lookup(attributes, name);
if(a == NULL) {
crm_info("Attribute %s no longer exists", name);
return;
}
a->update = 0;
if (rc == pcmk_ok && call_id < 0) {
rc = call_id;
}
switch (rc) {
case pcmk_ok:
level = LOG_INFO;
last_cib_op_done = call_id;
if (a->timer && !a->timeout_ms) {
// Remove temporary dampening for failed writes
mainloop_timer_del(a->timer);
a->timer = NULL;
}
break;
case -pcmk_err_diff_failed: /* When an attr changes while the CIB is syncing */
case -ETIME: /* When an attr changes while there is a DC election */
case -ENXIO: /* When an attr changes while the CIB is syncing a
* newer config from a node that just came up
*/
level = LOG_WARNING;
break;
}
do_crm_log(level, "CIB update %d result for %s: %s " CRM_XS " rc=%d",
call_id, a->id, pcmk_strerror(rc), rc);
g_hash_table_iter_init(&iter, a->values);
while (g_hash_table_iter_next(&iter, (gpointer *) & peer, (gpointer *) & v)) {
do_crm_log(level, "* %s[%s]=%s", a->id, peer, v->requested);
free(v->requested);
v->requested = NULL;
if (rc != pcmk_ok) {
a->changed = true; /* Attempt write out again */
}
}
if (a->changed && attrd_election_won()) {
if (rc == pcmk_ok) {
/* We deferred a write of a new update because this update was in
* progress. Write out the new value without additional delay.
*/
write_attribute(a, false);
/* We're re-attempting a write because the original failed; delay
* the next attempt so we don't potentially flood the CIB manager
* and logs with a zillion attempts per second.
*
* @TODO We could elect a new writer instead. However, we'd have to
* somehow downgrade our vote, and we'd still need something like this
* if all peers similarly fail to write this attribute (which may
* indicate a corrupted attribute entry rather than a CIB issue).
*/
} else if (a->timer) {
// Attribute has a dampening value, so use that as delay
if (!mainloop_timer_running(a->timer)) {
crm_trace("Delayed re-attempted write for %s by %s",
name, pcmk__readable_interval(a->timeout_ms));
mainloop_timer_start(a->timer);
}
} else {
/* Set a temporary dampening of 2 seconds (timer will continue
* to exist until the attribute's dampening gets set or the
* write succeeds).
*/
a->timer = attrd_add_timer(a->id, 2000, a);
mainloop_timer_start(a->timer);
}
}
}
/*!
* \internal
* \brief Add a set-attribute update request to the current CIB transaction
*
* \param[in] attr Attribute to update
* \param[in] attr_id ID of attribute to update
* \param[in] node_id ID of node for which to update attribute value
* \param[in] set_id ID of attribute set
* \param[in] value New value for attribute
*
* \return Standard Pacemaker return code
*/
static int
add_set_attr_update(const attribute_t *attr, const char *attr_id,
const char *node_id, const char *set_id, const char *value)
{
xmlNode *update = create_xml_node(NULL, XML_CIB_TAG_STATE);
xmlNode *child = update;
int rc = ENOMEM;
if (child == NULL) {
goto done;
}
crm_xml_add(child, XML_ATTR_ID, node_id);
child = create_xml_node(child, XML_TAG_TRANSIENT_NODEATTRS);
if (child == NULL) {
goto done;
}
crm_xml_add(child, XML_ATTR_ID, node_id);
child = create_xml_node(child, attr->set_type);
if (child == NULL) {
goto done;
}
crm_xml_add(child, XML_ATTR_ID, set_id);
child = create_xml_node(child, XML_CIB_TAG_NVPAIR);
if (child == NULL) {
goto done;
}
crm_xml_add(child, XML_ATTR_ID, attr_id);
crm_xml_add(child, XML_NVPAIR_ATTR_NAME, attr->id);
crm_xml_add(child, XML_NVPAIR_ATTR_VALUE, value);
rc = the_cib->cmds->modify(the_cib, XML_CIB_TAG_STATUS, update,
cib_can_create|cib_transaction);
rc = pcmk_legacy2rc(rc);
done:
free_xml(update);
return rc;
}
/*!
* \internal
* \brief Add an unset-attribute update request to the current CIB transaction
*
* \param[in] attr Attribute to update
* \param[in] attr_id ID of attribute to update
* \param[in] node_id ID of node for which to update attribute value
* \param[in] set_id ID of attribute set
*
* \return Standard Pacemaker return code
*/
static int
add_unset_attr_update(const attribute_t *attr, const char *attr_id,
const char *node_id, const char *set_id)
{
char *xpath = crm_strdup_printf("/" XML_CIB_TAG_STATUS
"/" XML_CIB_TAG_STATE
"[@" XML_ATTR_ID "='%s']"
"/" XML_TAG_TRANSIENT_NODEATTRS
"[@" XML_ATTR_ID "='%s']"
"/%s[@" XML_ATTR_ID "='%s']"
"/" XML_CIB_TAG_NVPAIR
"[@" XML_ATTR_ID "='%s' "
"and @" XML_NVPAIR_ATTR_NAME "='%s']",
node_id, node_id, attr->set_type, set_id,
attr_id, attr->id);
int rc = the_cib->cmds->remove(the_cib, xpath, NULL,
cib_xpath|cib_transaction);
free(xpath);
return pcmk_legacy2rc(rc);
}
/*!
* \internal
* \brief Add an attribute update request to the current CIB transaction
*
* \param[in] attr Attribute to update
* \param[in] value New value for attribute
* \param[in] node_id ID of node for which to update attribute value
*
* \return Standard Pacemaker return code
*/
static int
add_attr_update(const attribute_t *attr, const char *value, const char *node_id)
{
char *set_id = NULL;
char *attr_id = NULL;
int rc = pcmk_rc_ok;
if (attr->set_id != NULL) {
pcmk__str_update(&set_id, attr->set_id);
} else {
set_id = crm_strdup_printf("%s-%s", XML_CIB_TAG_STATUS, node_id);
}
crm_xml_sanitize_id(set_id);
if (attr->uuid != NULL) {
pcmk__str_update(&attr_id, attr->uuid);
} else {
attr_id = crm_strdup_printf("%s-%s", set_id, attr->id);
}
crm_xml_sanitize_id(attr_id);
if (value != NULL) {
rc = add_set_attr_update(attr, attr_id, node_id, set_id, value);
} else {
rc = add_unset_attr_update(attr, attr_id, node_id, set_id);
}
free(set_id);
free(attr_id);
return rc;
}
static void
send_alert_attributes_value(attribute_t *a, GHashTable *t)
{
int rc = 0;
attribute_value_t *at = NULL;
GHashTableIter vIter;
g_hash_table_iter_init(&vIter, t);
while (g_hash_table_iter_next(&vIter, NULL, (gpointer *) & at)) {
rc = attrd_send_attribute_alert(at->nodename, at->nodeid,
a->id, at->current);
crm_trace("Sent alerts for %s[%s]=%s: nodeid=%d rc=%d",
a->id, at->nodename, at->current, at->nodeid, rc);
}
}
static void
set_alert_attribute_value(GHashTable *t, attribute_value_t *v)
{
attribute_value_t *a_v = NULL;
a_v = calloc(1, sizeof(attribute_value_t));
CRM_ASSERT(a_v != NULL);
a_v->nodeid = v->nodeid;
a_v->nodename = strdup(v->nodename);
pcmk__str_update(&a_v->current, v->current);
g_hash_table_replace(t, a_v->nodename, a_v);
}
mainloop_timer_t *
attrd_add_timer(const char *id, int timeout_ms, attribute_t *attr)
{
return mainloop_timer_add(id, timeout_ms, FALSE, attribute_timer_cb, attr);
}
/*!
* \internal
* \brief Write an attribute's values to the CIB if appropriate
*
* \param[in,out] a Attribute to write
* \param[in] ignore_delay If true, write attribute now regardless of any
* configured delay
*/
static void
write_attribute(attribute_t *a, bool ignore_delay)
{
int private_updates = 0, cib_updates = 0;
attribute_value_t *v = NULL;
GHashTableIter iter;
GHashTable *alert_attribute_value = NULL;
int rc = pcmk_ok;
if (a == NULL) {
return;
}
/* If this attribute will be written to the CIB ... */
if (!stand_alone && !a->is_private) {
/* Defer the write if now's not a good time */
if (a->update && (a->update < last_cib_op_done)) {
crm_info("Write out of '%s' continuing: update %d considered lost",
a->id, a->update);
a->update = 0; // Don't log this message again
} else if (a->update) {
crm_info("Write out of '%s' delayed: update %d in progress",
a->id, a->update);
goto done;
} else if (mainloop_timer_running(a->timer)) {
if (ignore_delay) {
mainloop_timer_stop(a->timer);
crm_debug("Overriding '%s' write delay", a->id);
} else {
crm_info("Delaying write of '%s'", a->id);
goto done;
}
}
// Initiate a transaction for all the peer value updates
CRM_CHECK(the_cib != NULL, goto done);
the_cib->cmds->set_user(the_cib, a->user);
rc = the_cib->cmds->init_transaction(the_cib);
if (rc != pcmk_ok) {
crm_err("Failed to write %s (id %s, set %s): Could not initiate "
"CIB transaction",
a->id, pcmk__s(a->uuid, "n/a"), pcmk__s(a->set_id, "n/a"));
goto done;
}
}
/* Attribute will be written shortly, so clear changed flag */
a->changed = false;
/* We will check all peers' uuids shortly, so initialize this to false */
a->unknown_peer_uuids = false;
/* Attribute will be written shortly, so clear forced write flag */
a->force_write = FALSE;
/* Make the table for the attribute trap */
alert_attribute_value = pcmk__strikey_table(NULL,
attrd_free_attribute_value);
/* Iterate over each peer value of this attribute */
g_hash_table_iter_init(&iter, a->values);
while (g_hash_table_iter_next(&iter, NULL, (gpointer *) &v)) {
crm_node_t *peer = crm_get_peer_full(v->nodeid, v->nodename,
CRM_GET_PEER_ANY);
/* If the value's peer info does not correspond to a peer, ignore it */
if (peer == NULL) {
crm_notice("Cannot update %s[%s]=%s because peer not known",
a->id, v->nodename, v->current);
continue;
}
/* If we're just learning the peer's node id, remember it */
if (peer->id && (v->nodeid == 0)) {
crm_trace("Learned ID %u for node %s", peer->id, v->nodename);
v->nodeid = peer->id;
}
/* If this is a private attribute, no update needs to be sent */
if (stand_alone || a->is_private) {
private_updates++;
continue;
}
/* If the peer is found, but its uuid is unknown, defer write */
if (peer->uuid == NULL) {
a->unknown_peer_uuids = true;
crm_notice("Cannot update %s[%s]=%s because peer UUID not known "
"(will retry if learned)",
a->id, v->nodename, v->current);
continue;
}
// Update this value as part of the CIB transaction we're building
rc = add_attr_update(a, v->current, peer->uuid);
if (rc != pcmk_rc_ok) {
crm_err("Failed to update %s[%s]=%s (peer known as %s, UUID %s, "
"ID %" PRIu32 "/%" PRIu32 "): %s",
a->id, v->nodename, v->current, peer->uname, peer->uuid,
peer->id, v->nodeid, pcmk_rc_str(rc));
continue;
}
crm_debug("Updating %s[%s]=%s (peer known as %s, UUID %s, ID "
"%" PRIu32 "/%" PRIu32 ")",
a->id, v->nodename, v->current,
peer->uname, peer->uuid, peer->id, v->nodeid);
cib_updates++;
/* Preservation of the attribute to transmit alert */
set_alert_attribute_value(alert_attribute_value, v);
free(v->requested);
v->requested = NULL;
if (v->current) {
v->requested = strdup(v->current);
}
}
if (private_updates) {
crm_info("Processed %d private change%s for %s, id=%s, set=%s",
private_updates, pcmk__plural_s(private_updates),
a->id, pcmk__s(a->uuid, "n/a"), pcmk__s(a->set_id, "n/a"));
}
if (cib_updates > 0) {
char *id = NULL;
// Commit transaction
a->update = the_cib->cmds->end_transaction(the_cib, true, cib_none);
crm_info("Sent CIB request %d with %d change%s for %s (id %s, set %s)",
a->update, cib_updates, pcmk__plural_s(cib_updates),
a->id, pcmk__s(a->uuid, "n/a"), pcmk__s(a->set_id, "n/a"));
pcmk__str_update(&id, a->id);
if (the_cib->cmds->register_callback_full(the_cib, a->update,
CIB_OP_TIMEOUT_S, FALSE, id,
"attrd_cib_callback",
attrd_cib_callback, free)) {
// Transmit alert of the attribute
send_alert_attributes_value(a, alert_attribute_value);
}
}
done:
// Discard transaction (if any)
if (the_cib != NULL) {
the_cib->cmds->end_transaction(the_cib, false, cib_none);
the_cib->cmds->set_user(the_cib, NULL);
}
if (alert_attribute_value != NULL) {
g_hash_table_destroy(alert_attribute_value);
}
}
/*!
* \internal
* \brief Write out attributes
*
* \param[in] options Group of enum attrd_write_options
*/
void
attrd_write_attributes(uint32_t options)
{
GHashTableIter iter;
attribute_t *a = NULL;
crm_debug("Writing out %s attributes",
pcmk_is_set(options, attrd_write_all)? "all" : "changed");
g_hash_table_iter_init(&iter, attributes);
while (g_hash_table_iter_next(&iter, NULL, (gpointer *) & a)) {
if (!pcmk_is_set(options, attrd_write_all) && a->unknown_peer_uuids) {
// Try writing this attribute again, in case peer ID was learned
a->changed = true;
} else if (a->force_write) {
/* If the force_write flag is set, write the attribute. */
a->changed = true;
}
if (pcmk_is_set(options, attrd_write_all) || a->changed) {
bool ignore_delay = pcmk_is_set(options, attrd_write_no_delay);
if (a->force_write) {
// Always ignore delay when forced write flag is set
ignore_delay = true;
}
write_attribute(a, ignore_delay);
} else {
crm_trace("Skipping unchanged attribute %s", a->id);
}
}
}
void
attrd_write_or_elect_attribute(attribute_t *a)
{
if (attrd_election_won()) {
write_attribute(a, false);
} else {
attrd_start_election_if_needed();
}
}
diff --git a/daemons/controld/controld_cib.c b/daemons/controld/controld_cib.c
index 822c491977..865e41f082 100644
--- a/daemons/controld/controld_cib.c
+++ b/daemons/controld/controld_cib.c
@@ -1,1069 +1,1070 @@
/*
* Copyright 2004-2023 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU General Public License version 2
* or later (GPLv2+) WITHOUT ANY WARRANTY.
*/
#include <crm_internal.h>
#include <unistd.h> /* sleep */
#include <crm/common/alerts_internal.h>
#include <crm/common/xml.h>
#include <crm/crm.h>
#include <crm/msg_xml.h>
#include <crm/lrmd_internal.h>
#include <pacemaker-controld.h>
// Call ID of the most recent in-progress CIB resource update (or 0 if none)
static int pending_rsc_update = 0;
/*!
* \internal
* \brief Respond to a dropped CIB connection
*
* \param[in] user_data CIB connection that dropped
*/
static void
handle_cib_disconnect(gpointer user_data)
{
CRM_LOG_ASSERT(user_data == controld_globals.cib_conn);
controld_trigger_fsa();
controld_globals.cib_conn->state = cib_disconnected;
if (pcmk_is_set(controld_globals.fsa_input_register, R_CIB_CONNECTED)) {
// @TODO This should trigger a reconnect, not a shutdown
crm_crit("Lost connection to the CIB manager, shutting down");
register_fsa_input(C_FSA_INTERNAL, I_ERROR, NULL);
controld_clear_fsa_input_flags(R_CIB_CONNECTED);
} else { // Expected
crm_info("Disconnected from the CIB manager");
}
}
static void
do_cib_updated(const char *event, xmlNode * msg)
{
const xmlNode *patchset = NULL;
const char *client_name = NULL;
crm_debug("Received CIB diff notification: DC=%s", pcmk__btoa(AM_I_DC));
if (cib__get_notify_patchset(msg, &patchset) != pcmk_rc_ok) {
return;
}
if (cib__element_in_patchset(patchset, XML_CIB_TAG_ALERTS)
|| cib__element_in_patchset(patchset, XML_CIB_TAG_CRMCONFIG)) {
controld_trigger_config();
}
if (!AM_I_DC) {
// We're not in control of the join sequence
return;
}
client_name = crm_element_value(msg, F_CIB_CLIENTNAME);
if (!cib__client_triggers_refresh(client_name)) {
// The CIB is still accurate
return;
}
if (cib__element_in_patchset(patchset, XML_CIB_TAG_NODES)
|| cib__element_in_patchset(patchset, XML_CIB_TAG_STATUS)) {
/* An unsafe client modified the nodes or status section. Ensure the
* node list is up-to-date, and start the join process again so we get
* everyone's current resource history.
*/
if (client_name == NULL) {
client_name = crm_element_value(msg, F_CIB_CLIENTID);
}
crm_notice("Populating nodes and starting an election after %s event "
"triggered by %s",
event, pcmk__s(client_name, "(unidentified client)"));
populate_cib_nodes(node_update_quick|node_update_all, __func__);
register_fsa_input(C_FSA_INTERNAL, I_ELECTION, NULL);
}
}
void
controld_disconnect_cib_manager(void)
{
cib_t *cib_conn = controld_globals.cib_conn;
CRM_ASSERT(cib_conn != NULL);
crm_debug("Disconnecting from the CIB manager");
controld_clear_fsa_input_flags(R_CIB_CONNECTED);
cib_conn->cmds->del_notify_callback(cib_conn, T_CIB_DIFF_NOTIFY,
do_cib_updated);
cib_free_callbacks(cib_conn);
if (cib_conn->state != cib_disconnected) {
cib_conn->cmds->set_secondary(cib_conn,
cib_scope_local|cib_discard_reply);
cib_conn->cmds->signoff(cib_conn);
}
}
/* A_CIB_STOP, A_CIB_START, O_CIB_RESTART */
void
do_cib_control(long long action,
enum crmd_fsa_cause cause,
enum crmd_fsa_state cur_state,
enum crmd_fsa_input current_input, fsa_data_t * msg_data)
{
static int cib_retries = 0;
cib_t *cib_conn = controld_globals.cib_conn;
void (*dnotify_fn) (gpointer user_data) = handle_cib_disconnect;
void (*update_cb) (const char *event, xmlNodePtr msg) = do_cib_updated;
int rc = pcmk_ok;
CRM_ASSERT(cib_conn != NULL);
if (pcmk_is_set(action, A_CIB_STOP)) {
if ((cib_conn->state != cib_disconnected)
&& (pending_rsc_update != 0)) {
crm_info("Waiting for resource update %d to complete",
pending_rsc_update);
crmd_fsa_stall(FALSE);
return;
}
controld_disconnect_cib_manager();
}
if (!pcmk_is_set(action, A_CIB_START)) {
return;
}
if (cur_state == S_STOPPING) {
crm_err("Ignoring request to connect to the CIB manager after "
"shutdown");
return;
}
rc = cib_conn->cmds->signon(cib_conn, CRM_SYSTEM_CRMD,
cib_command_nonblocking);
if (rc != pcmk_ok) {
// A short wait that usually avoids stalling the FSA
sleep(1);
rc = cib_conn->cmds->signon(cib_conn, CRM_SYSTEM_CRMD,
cib_command_nonblocking);
}
if (rc != pcmk_ok) {
crm_info("Could not connect to the CIB manager: %s", pcmk_strerror(rc));
} else if (cib_conn->cmds->set_connection_dnotify(cib_conn,
dnotify_fn) != pcmk_ok) {
crm_err("Could not set dnotify callback");
} else if (cib_conn->cmds->add_notify_callback(cib_conn,
T_CIB_DIFF_NOTIFY,
update_cb) != pcmk_ok) {
crm_err("Could not set CIB notification callback (update)");
} else {
controld_set_fsa_input_flags(R_CIB_CONNECTED);
cib_retries = 0;
}
if (!pcmk_is_set(controld_globals.fsa_input_register, R_CIB_CONNECTED)) {
cib_retries++;
if (cib_retries < 30) {
crm_warn("Couldn't complete CIB registration %d times... "
"pause and retry", cib_retries);
controld_start_wait_timer();
crmd_fsa_stall(FALSE);
} else {
crm_err("Could not complete CIB registration %d times... "
"hard error", cib_retries);
register_fsa_error(C_FSA_INTERNAL, I_ERROR, NULL);
}
}
}
#define MIN_CIB_OP_TIMEOUT (30)
/*!
* \internal
* \brief Get the timeout (in seconds) that should be used with CIB operations
*
* \return The maximum of 30 seconds, the value of the PCMK_cib_timeout
* environment variable, or 10 seconds times one more than the number of
* nodes in the cluster.
*/
unsigned int
cib_op_timeout(void)
{
+ // @COMPAT: Drop env_timeout at 3.0.0
static int env_timeout = -1;
unsigned int calculated_timeout = 0;
if (env_timeout == -1) {
const char *env = pcmk__env_option(PCMK__ENV_CIB_TIMEOUT);
pcmk__scan_min_int(env, &env_timeout, MIN_CIB_OP_TIMEOUT);
crm_trace("Minimum CIB op timeout: %ds (environment: %s)",
env_timeout, (env? env : "none"));
}
calculated_timeout = 1 + crm_active_peers();
if (crm_remote_peer_cache) {
calculated_timeout += g_hash_table_size(crm_remote_peer_cache);
}
calculated_timeout *= 10;
calculated_timeout = QB_MAX(calculated_timeout, env_timeout);
crm_trace("Calculated timeout: %us", calculated_timeout);
if (controld_globals.cib_conn) {
controld_globals.cib_conn->call_timeout = calculated_timeout;
}
return calculated_timeout;
}
/*!
* \internal
* \brief Get CIB call options to use local scope if primary is unavailable
*
* \return CIB call options
*/
int
crmd_cib_smart_opt(void)
{
int call_opt = cib_none;
if ((controld_globals.fsa_state == S_ELECTION)
|| (controld_globals.fsa_state == S_PENDING)) {
crm_info("Sending update to local CIB in state: %s",
fsa_state2string(controld_globals.fsa_state));
cib__set_call_options(call_opt, "update", cib_scope_local);
}
return call_opt;
}
static void
cib_delete_callback(xmlNode *msg, int call_id, int rc, xmlNode *output,
void *user_data)
{
char *desc = user_data;
if (rc == 0) {
crm_debug("Deletion of %s (via CIB call %d) succeeded", desc, call_id);
} else {
crm_warn("Deletion of %s (via CIB call %d) failed: %s " CRM_XS " rc=%d",
desc, call_id, pcmk_strerror(rc), rc);
}
}
// Searches for various portions of node_state to delete
// Match a particular node's node_state (takes node name 1x)
#define XPATH_NODE_STATE "//" XML_CIB_TAG_STATE "[@" XML_ATTR_UNAME "='%s']"
// Node's lrm section (name 1x)
#define XPATH_NODE_LRM XPATH_NODE_STATE "/" XML_CIB_TAG_LRM
/* Node's lrm_rsc_op entries and lrm_resource entries without unexpired lock
* (name 2x, (seconds_since_epoch - XML_CONFIG_ATTR_SHUTDOWN_LOCK_LIMIT) 1x)
*/
#define XPATH_NODE_LRM_UNLOCKED XPATH_NODE_STATE "//" XML_LRM_TAG_RSC_OP \
"|" XPATH_NODE_STATE \
"//" XML_LRM_TAG_RESOURCE \
"[not(@" XML_CONFIG_ATTR_SHUTDOWN_LOCK ") " \
"or " XML_CONFIG_ATTR_SHUTDOWN_LOCK "<%lld]"
// Node's transient_attributes section (name 1x)
#define XPATH_NODE_ATTRS XPATH_NODE_STATE "/" XML_TAG_TRANSIENT_NODEATTRS
// Everything under node_state (name 1x)
#define XPATH_NODE_ALL XPATH_NODE_STATE "/*"
/* Unlocked history + transient attributes
* (name 2x, (seconds_since_epoch - XML_CONFIG_ATTR_SHUTDOWN_LOCK_LIMIT) 1x,
* name 1x)
*/
#define XPATH_NODE_ALL_UNLOCKED XPATH_NODE_LRM_UNLOCKED "|" XPATH_NODE_ATTRS
/*!
* \internal
* \brief Get the XPath and description of a node state section to be deleted
*
* \param[in] uname Desired node
* \param[in] section Subsection of node_state to be deleted
* \param[out] xpath Where to store XPath of \p section
* \param[out] desc If not \c NULL, where to store description of \p section
*/
void
controld_node_state_deletion_strings(const char *uname,
enum controld_section_e section,
char **xpath, char **desc)
{
const char *desc_pre = NULL;
// Shutdown locks that started before this time are expired
long long expire = (long long) time(NULL)
- controld_globals.shutdown_lock_limit;
switch (section) {
case controld_section_lrm:
*xpath = crm_strdup_printf(XPATH_NODE_LRM, uname);
desc_pre = "resource history";
break;
case controld_section_lrm_unlocked:
*xpath = crm_strdup_printf(XPATH_NODE_LRM_UNLOCKED,
uname, uname, expire);
desc_pre = "resource history (other than shutdown locks)";
break;
case controld_section_attrs:
*xpath = crm_strdup_printf(XPATH_NODE_ATTRS, uname);
desc_pre = "transient attributes";
break;
case controld_section_all:
*xpath = crm_strdup_printf(XPATH_NODE_ALL, uname);
desc_pre = "all state";
break;
case controld_section_all_unlocked:
*xpath = crm_strdup_printf(XPATH_NODE_ALL_UNLOCKED,
uname, uname, expire, uname);
desc_pre = "all state (other than shutdown locks)";
break;
default:
// We called this function incorrectly
CRM_ASSERT(false);
break;
}
if (desc != NULL) {
*desc = crm_strdup_printf("%s for node %s", desc_pre, uname);
}
}
/*!
* \internal
* \brief Delete subsection of a node's CIB node_state
*
* \param[in] uname Desired node
* \param[in] section Subsection of node_state to delete
* \param[in] options CIB call options to use
*/
void
controld_delete_node_state(const char *uname, enum controld_section_e section,
int options)
{
cib_t *cib = controld_globals.cib_conn;
char *xpath = NULL;
char *desc = NULL;
int cib_rc = pcmk_ok;
CRM_ASSERT((uname != NULL) && (cib != NULL));
controld_node_state_deletion_strings(uname, section, &xpath, &desc);
cib__set_call_options(options, "node state deletion",
cib_xpath|cib_multiple);
cib_rc = cib->cmds->remove(cib, xpath, NULL, options);
fsa_register_cib_callback(cib_rc, desc, cib_delete_callback);
crm_info("Deleting %s (via CIB call %d) " CRM_XS " xpath=%s",
desc, cib_rc, xpath);
// CIB library handles freeing desc
free(xpath);
}
// Takes node name and resource ID
#define XPATH_RESOURCE_HISTORY "//" XML_CIB_TAG_STATE \
"[@" XML_ATTR_UNAME "='%s']/" \
XML_CIB_TAG_LRM "/" XML_LRM_TAG_RESOURCES \
"/" XML_LRM_TAG_RESOURCE \
"[@" XML_ATTR_ID "='%s']"
// @TODO could add "and @XML_CONFIG_ATTR_SHUTDOWN_LOCK" to limit to locks
/*!
* \internal
* \brief Clear resource history from CIB for a given resource and node
*
* \param[in] rsc_id ID of resource to be cleared
* \param[in] node Node whose resource history should be cleared
* \param[in] user_name ACL user name to use
* \param[in] call_options CIB call options
*
* \return Standard Pacemaker return code
*/
int
controld_delete_resource_history(const char *rsc_id, const char *node,
const char *user_name, int call_options)
{
char *desc = NULL;
char *xpath = NULL;
int rc = pcmk_rc_ok;
cib_t *cib = controld_globals.cib_conn;
CRM_CHECK((rsc_id != NULL) && (node != NULL), return EINVAL);
desc = crm_strdup_printf("resource history for %s on %s", rsc_id, node);
if (cib == NULL) {
crm_err("Unable to clear %s: no CIB connection", desc);
free(desc);
return ENOTCONN;
}
// Ask CIB to delete the entry
xpath = crm_strdup_printf(XPATH_RESOURCE_HISTORY, node, rsc_id);
cib->cmds->set_user(cib, user_name);
rc = cib->cmds->remove(cib, xpath, NULL, call_options|cib_xpath);
cib->cmds->set_user(cib, NULL);
if (rc < 0) {
rc = pcmk_legacy2rc(rc);
crm_err("Could not delete resource status of %s on %s%s%s: %s "
CRM_XS " rc=%d", rsc_id, node,
(user_name? " for user " : ""), (user_name? user_name : ""),
pcmk_rc_str(rc), rc);
free(desc);
free(xpath);
return rc;
}
if (pcmk_is_set(call_options, cib_sync_call)) {
if (pcmk_is_set(call_options, cib_dryrun)) {
crm_debug("Deletion of %s would succeed", desc);
} else {
crm_debug("Deletion of %s succeeded", desc);
}
free(desc);
} else {
crm_info("Clearing %s (via CIB call %d) " CRM_XS " xpath=%s",
desc, rc, xpath);
fsa_register_cib_callback(rc, desc, cib_delete_callback);
// CIB library handles freeing desc
}
free(xpath);
return pcmk_rc_ok;
}
/*!
* \internal
* \brief Build XML and string of parameters meeting some criteria, for digest
*
* \param[in] op Executor event with parameter table to use
* \param[in] metadata Parsed meta-data for executed resource agent
* \param[in] param_type Flag used for selection criteria
* \param[out] result Will be set to newly created XML with selected
* parameters as attributes
*
* \return Newly allocated space-separated string of parameter names
* \note Selection criteria varies by param_type: for the restart digest, we
* want parameters that are *not* marked reloadable (OCF 1.1) or that
* *are* marked unique (pre-1.1), for both string and XML results; for the
* secure digest, we want parameters that *are* marked private for the
* string, but parameters that are *not* marked private for the XML.
* \note It is the caller's responsibility to free the string return value with
* \p g_string_free() and the XML result with \p free_xml().
*/
static GString *
build_parameter_list(const lrmd_event_data_t *op,
const struct ra_metadata_s *metadata,
enum ra_param_flags_e param_type, xmlNode **result)
{
GString *list = NULL;
*result = create_xml_node(NULL, XML_TAG_PARAMS);
/* Consider all parameters only except private ones to be consistent with
* what scheduler does with calculate_secure_digest().
*/
if (param_type == ra_param_private
&& compare_version(controld_globals.dc_version, "3.16.0") >= 0) {
g_hash_table_foreach(op->params, hash2field, *result);
pcmk__filter_op_for_digest(*result);
}
for (GList *iter = metadata->ra_params; iter != NULL; iter = iter->next) {
struct ra_param_s *param = (struct ra_param_s *) iter->data;
bool accept_for_list = false;
bool accept_for_xml = false;
switch (param_type) {
case ra_param_reloadable:
accept_for_list = !pcmk_is_set(param->rap_flags, param_type);
accept_for_xml = accept_for_list;
break;
case ra_param_unique:
accept_for_list = pcmk_is_set(param->rap_flags, param_type);
accept_for_xml = accept_for_list;
break;
case ra_param_private:
accept_for_list = pcmk_is_set(param->rap_flags, param_type);
accept_for_xml = !accept_for_list;
break;
}
if (accept_for_list) {
crm_trace("Attr %s is %s", param->rap_name, ra_param_flag2text(param_type));
if (list == NULL) {
// We will later search for " WORD ", so start list with a space
pcmk__add_word(&list, 256, " ");
}
pcmk__add_word(&list, 0, param->rap_name);
} else {
crm_trace("Rejecting %s for %s", param->rap_name, ra_param_flag2text(param_type));
}
if (accept_for_xml) {
const char *v = g_hash_table_lookup(op->params, param->rap_name);
if (v != NULL) {
crm_trace("Adding attr %s=%s to the xml result", param->rap_name, v);
crm_xml_add(*result, param->rap_name, v);
}
} else {
crm_trace("Removing attr %s from the xml result", param->rap_name);
xml_remove_prop(*result, param->rap_name);
}
}
if (list != NULL) {
// We will later search for " WORD ", so end list with a space
pcmk__add_word(&list, 0, " ");
}
return list;
}
static void
append_restart_list(lrmd_event_data_t *op, struct ra_metadata_s *metadata,
xmlNode *update, const char *version)
{
GString *list = NULL;
char *digest = NULL;
xmlNode *restart = NULL;
CRM_LOG_ASSERT(op->params != NULL);
if (op->interval_ms > 0) {
/* monitors are not reloadable */
return;
}
if (pcmk_is_set(metadata->ra_flags, ra_supports_reload_agent)) {
// Add parameters not marked reloadable to the "op-force-restart" list
list = build_parameter_list(op, metadata, ra_param_reloadable,
&restart);
} else if (pcmk_is_set(metadata->ra_flags, ra_supports_legacy_reload)) {
/* @COMPAT pre-OCF-1.1 resource agents
*
* Before OCF 1.1, Pacemaker abused "unique=0" to indicate
* reloadability. Add any parameters with unique="1" to the
* "op-force-restart" list.
*/
list = build_parameter_list(op, metadata, ra_param_unique, &restart);
} else {
// Resource does not support agent reloads
return;
}
digest = calculate_operation_digest(restart, version);
/* Add "op-force-restart" and "op-restart-digest" to indicate the resource supports reload,
* no matter if it actually supports any parameters with unique="1"). */
crm_xml_add(update, XML_LRM_ATTR_OP_RESTART,
(list == NULL)? "" : (const char *) list->str);
crm_xml_add(update, XML_LRM_ATTR_RESTART_DIGEST, digest);
if ((list != NULL) && (list->len > 0)) {
crm_trace("%s: %s, %s", op->rsc_id, digest, (const char *) list->str);
} else {
crm_trace("%s: %s", op->rsc_id, digest);
}
if (list != NULL) {
g_string_free(list, TRUE);
}
free_xml(restart);
free(digest);
}
static void
append_secure_list(lrmd_event_data_t *op, struct ra_metadata_s *metadata,
xmlNode *update, const char *version)
{
GString *list = NULL;
char *digest = NULL;
xmlNode *secure = NULL;
CRM_LOG_ASSERT(op->params != NULL);
/*
* To keep XML_LRM_ATTR_OP_SECURE short, we want it to contain the
* secure parameters but XML_LRM_ATTR_SECURE_DIGEST to be based on
* the insecure ones
*/
list = build_parameter_list(op, metadata, ra_param_private, &secure);
if (list != NULL) {
digest = calculate_operation_digest(secure, version);
crm_xml_add(update, XML_LRM_ATTR_OP_SECURE, (const char *) list->str);
crm_xml_add(update, XML_LRM_ATTR_SECURE_DIGEST, digest);
crm_trace("%s: %s, %s", op->rsc_id, digest, (const char *) list->str);
g_string_free(list, TRUE);
} else {
crm_trace("%s: no secure parameters", op->rsc_id);
}
free_xml(secure);
free(digest);
}
/*!
* \internal
* \brief Create XML for a resource history entry
*
* \param[in] func Function name of caller
* \param[in,out] parent XML to add entry to
* \param[in] rsc Affected resource
* \param[in,out] op Action to add an entry for (or NULL to do nothing)
* \param[in] node_name Node where action occurred
*/
void
controld_add_resource_history_xml_as(const char *func, xmlNode *parent,
const lrmd_rsc_info_t *rsc,
lrmd_event_data_t *op,
const char *node_name)
{
int target_rc = 0;
xmlNode *xml_op = NULL;
struct ra_metadata_s *metadata = NULL;
const char *caller_version = NULL;
lrm_state_t *lrm_state = NULL;
if (op == NULL) {
return;
}
target_rc = rsc_op_expected_rc(op);
caller_version = g_hash_table_lookup(op->params, XML_ATTR_CRM_VERSION);
CRM_CHECK(caller_version != NULL, caller_version = CRM_FEATURE_SET);
xml_op = pcmk__create_history_xml(parent, op, caller_version, target_rc,
controld_globals.our_nodename, func);
if (xml_op == NULL) {
return;
}
if ((rsc == NULL) || (op->params == NULL)
|| !crm_op_needs_metadata(rsc->standard, op->op_type)) {
crm_trace("No digests needed for %s action on %s (params=%p rsc=%p)",
op->op_type, op->rsc_id, op->params, rsc);
return;
}
lrm_state = lrm_state_find(node_name);
if (lrm_state == NULL) {
crm_warn("Cannot calculate digests for operation " PCMK__OP_FMT
" because we have no connection to executor for %s",
op->rsc_id, op->op_type, op->interval_ms, node_name);
return;
}
/* Ideally the metadata is cached, and the agent is just a fallback.
*
* @TODO Go through all callers and ensure they get metadata asynchronously
* first.
*/
metadata = controld_get_rsc_metadata(lrm_state, rsc,
controld_metadata_from_agent
|controld_metadata_from_cache);
if (metadata == NULL) {
return;
}
crm_trace("Including additional digests for %s:%s:%s",
rsc->standard, rsc->provider, rsc->type);
append_restart_list(op, metadata, xml_op, caller_version);
append_secure_list(op, metadata, xml_op, caller_version);
return;
}
/*!
* \internal
* \brief Record an action as pending in the CIB, if appropriate
*
* \param[in] node_name Node where the action is pending
* \param[in] rsc Resource that action is for
* \param[in,out] op Pending action
*
* \return true if action was recorded in CIB, otherwise false
*/
bool
controld_record_pending_op(const char *node_name, const lrmd_rsc_info_t *rsc,
lrmd_event_data_t *op)
{
const char *record_pending = NULL;
CRM_CHECK((node_name != NULL) && (rsc != NULL) && (op != NULL),
return false);
// Never record certain operation types as pending
if ((op->op_type == NULL) || (op->params == NULL)
|| !controld_action_is_recordable(op->op_type)) {
return false;
}
// Check action's record-pending meta-attribute (defaults to true)
record_pending = crm_meta_value(op->params, XML_OP_ATTR_PENDING);
if ((record_pending != NULL) && !crm_is_true(record_pending)) {
return false;
}
op->call_id = -1;
op->t_run = time(NULL);
op->t_rcchange = op->t_run;
lrmd__set_result(op, PCMK_OCF_UNKNOWN, PCMK_EXEC_PENDING, NULL);
crm_debug("Recording pending %s-interval %s for %s on %s in the CIB",
pcmk__readable_interval(op->interval_ms), op->op_type, op->rsc_id,
node_name);
controld_update_resource_history(node_name, rsc, op, 0);
return true;
}
static void
cib_rsc_callback(xmlNode * msg, int call_id, int rc, xmlNode * output, void *user_data)
{
switch (rc) {
case pcmk_ok:
case -pcmk_err_diff_failed:
case -pcmk_err_diff_resync:
crm_trace("Resource history update completed (call=%d rc=%d)",
call_id, rc);
break;
default:
if (call_id > 0) {
crm_warn("Resource history update %d failed: %s "
CRM_XS " rc=%d", call_id, pcmk_strerror(rc), rc);
} else {
crm_warn("Resource history update failed: %s " CRM_XS " rc=%d",
pcmk_strerror(rc), rc);
}
}
if (call_id == pending_rsc_update) {
pending_rsc_update = 0;
controld_trigger_fsa();
}
}
/* Only successful stops, and probes that found the resource inactive, get locks
* recorded in the history. This ensures the resource stays locked to the node
* until it is active there again after the node comes back up.
*/
static bool
should_preserve_lock(lrmd_event_data_t *op)
{
if (!pcmk_is_set(controld_globals.flags, controld_shutdown_lock_enabled)) {
return false;
}
if (!strcmp(op->op_type, PCMK_ACTION_STOP) && (op->rc == PCMK_OCF_OK)) {
return true;
}
if (!strcmp(op->op_type, PCMK_ACTION_MONITOR)
&& (op->rc == PCMK_OCF_NOT_RUNNING)) {
return true;
}
return false;
}
/*!
* \internal
* \brief Request a CIB update
*
* \param[in] section Section of CIB to update
* \param[in] data New XML of CIB section to update
* \param[in] options CIB call options
* \param[in] callback If not \c NULL, set this as the operation callback
*
* \return Standard Pacemaker return code
*
* \note If \p callback is \p cib_rsc_callback(), the CIB update's call ID is
* stored in \p pending_rsc_update on success.
*/
int
controld_update_cib(const char *section, xmlNode *data, int options,
void (*callback)(xmlNode *, int, int, xmlNode *, void *))
{
cib_t *cib = controld_globals.cib_conn;
int cib_rc = -ENOTCONN;
CRM_ASSERT(data != NULL);
if (cib != NULL) {
cib_rc = cib->cmds->modify(cib, section, data, options);
if (cib_rc >= 0) {
crm_debug("Submitted CIB update %d for %s section",
cib_rc, section);
}
}
if (callback == NULL) {
if (cib_rc < 0) {
crm_err("Failed to update CIB %s section: %s",
section, pcmk_rc_str(pcmk_legacy2rc(cib_rc)));
}
} else {
if ((cib_rc >= 0) && (callback == cib_rsc_callback)) {
/* Checking for a particular callback is a little hacky, but it
* didn't seem worth adding an output argument for cib_rc for just
* one use case.
*/
pending_rsc_update = cib_rc;
}
fsa_register_cib_callback(cib_rc, NULL, callback);
}
return (cib_rc >= 0)? pcmk_rc_ok : pcmk_legacy2rc(cib_rc);
}
/*!
* \internal
* \brief Update resource history entry in CIB
*
* \param[in] node_name Node where action occurred
* \param[in] rsc Resource that action is for
* \param[in,out] op Action to record
* \param[in] lock_time If nonzero, when resource was locked to node
*
* \note On success, the CIB update's call ID will be stored in
* pending_rsc_update.
*/
void
controld_update_resource_history(const char *node_name,
const lrmd_rsc_info_t *rsc,
lrmd_event_data_t *op, time_t lock_time)
{
xmlNode *update = NULL;
xmlNode *xml = NULL;
int call_opt = crmd_cib_smart_opt();
const char *node_id = NULL;
const char *container = NULL;
CRM_CHECK((node_name != NULL) && (op != NULL), return);
if (rsc == NULL) {
crm_warn("Resource %s no longer exists in the executor", op->rsc_id);
controld_ack_event_directly(NULL, NULL, rsc, op, op->rsc_id);
return;
}
// <status>
update = create_xml_node(NULL, XML_CIB_TAG_STATUS);
// <node_state ...>
xml = create_xml_node(update, XML_CIB_TAG_STATE);
if (pcmk__str_eq(node_name, controld_globals.our_nodename,
pcmk__str_casei)) {
node_id = controld_globals.our_uuid;
} else {
node_id = node_name;
pcmk__xe_set_bool_attr(xml, XML_NODE_IS_REMOTE, true);
}
crm_xml_add(xml, XML_ATTR_ID, node_id);
crm_xml_add(xml, XML_ATTR_UNAME, node_name);
crm_xml_add(xml, XML_ATTR_ORIGIN, __func__);
// <lrm ...>
xml = create_xml_node(xml, XML_CIB_TAG_LRM);
crm_xml_add(xml, XML_ATTR_ID, node_id);
// <lrm_resources>
xml = create_xml_node(xml, XML_LRM_TAG_RESOURCES);
// <lrm_resource ...>
xml = create_xml_node(xml, XML_LRM_TAG_RESOURCE);
crm_xml_add(xml, XML_ATTR_ID, op->rsc_id);
crm_xml_add(xml, XML_AGENT_ATTR_CLASS, rsc->standard);
crm_xml_add(xml, XML_AGENT_ATTR_PROVIDER, rsc->provider);
crm_xml_add(xml, XML_ATTR_TYPE, rsc->type);
if (lock_time != 0) {
/* Actions on a locked resource should either preserve the lock by
* recording it with the action result, or clear it.
*/
if (!should_preserve_lock(op)) {
lock_time = 0;
}
crm_xml_add_ll(xml, XML_CONFIG_ATTR_SHUTDOWN_LOCK,
(long long) lock_time);
}
if (op->params != NULL) {
container = g_hash_table_lookup(op->params,
CRM_META "_" XML_RSC_ATTR_CONTAINER);
if (container != NULL) {
crm_trace("Resource %s is a part of container resource %s",
op->rsc_id, container);
crm_xml_add(xml, XML_RSC_ATTR_CONTAINER, container);
}
}
// <lrm_resource_op ...> (possibly more than one)
controld_add_resource_history_xml(xml, rsc, op, node_name);
/* Update CIB asynchronously. Even if it fails, the resource state should be
* discovered during the next election. Worst case, the node is wrongly
* fenced for running a resource it isn't.
*/
crm_log_xml_trace(update, __func__);
controld_update_cib(XML_CIB_TAG_STATUS, update, call_opt, cib_rsc_callback);
free_xml(update);
}
/*!
* \internal
* \brief Erase an LRM history entry from the CIB, given the operation data
*
* \param[in] op Operation whose history should be deleted
*/
void
controld_delete_action_history(const lrmd_event_data_t *op)
{
xmlNode *xml_top = NULL;
CRM_CHECK(op != NULL, return);
xml_top = create_xml_node(NULL, XML_LRM_TAG_RSC_OP);
crm_xml_add_int(xml_top, XML_LRM_ATTR_CALLID, op->call_id);
crm_xml_add(xml_top, XML_ATTR_TRANSITION_KEY, op->user_data);
if (op->interval_ms > 0) {
char *op_id = pcmk__op_key(op->rsc_id, op->op_type, op->interval_ms);
/* Avoid deleting last_failure too (if it was a result of this recurring op failing) */
crm_xml_add(xml_top, XML_ATTR_ID, op_id);
free(op_id);
}
crm_debug("Erasing resource operation history for " PCMK__OP_FMT " (call=%d)",
op->rsc_id, op->op_type, op->interval_ms, op->call_id);
controld_globals.cib_conn->cmds->remove(controld_globals.cib_conn,
XML_CIB_TAG_STATUS, xml_top,
cib_none);
crm_log_xml_trace(xml_top, "op:cancel");
free_xml(xml_top);
}
/* Define xpath to find LRM resource history entry by node and resource */
#define XPATH_HISTORY \
"/" XML_TAG_CIB "/" XML_CIB_TAG_STATUS \
"/" XML_CIB_TAG_STATE "[@" XML_ATTR_UNAME "='%s']" \
"/" XML_CIB_TAG_LRM "/" XML_LRM_TAG_RESOURCES \
"/" XML_LRM_TAG_RESOURCE "[@" XML_ATTR_ID "='%s']" \
"/" XML_LRM_TAG_RSC_OP
/* ... and also by operation key */
#define XPATH_HISTORY_ID XPATH_HISTORY \
"[@" XML_ATTR_ID "='%s']"
/* ... and also by operation key and operation call ID */
#define XPATH_HISTORY_CALL XPATH_HISTORY \
"[@" XML_ATTR_ID "='%s' and @" XML_LRM_ATTR_CALLID "='%d']"
/* ... and also by operation key and original operation key */
#define XPATH_HISTORY_ORIG XPATH_HISTORY \
"[@" XML_ATTR_ID "='%s' and @" XML_LRM_ATTR_TASK_KEY "='%s']"
/*!
* \internal
* \brief Delete a last_failure resource history entry from the CIB
*
* \param[in] rsc_id Name of resource to clear history for
* \param[in] node Name of node to clear history for
* \param[in] action If specified, delete only if this was failed action
* \param[in] interval_ms If \p action is specified, it has this interval
*/
void
controld_cib_delete_last_failure(const char *rsc_id, const char *node,
const char *action, guint interval_ms)
{
char *xpath = NULL;
char *last_failure_key = NULL;
CRM_CHECK((rsc_id != NULL) && (node != NULL), return);
// Generate XPath to match desired entry
last_failure_key = pcmk__op_key(rsc_id, "last_failure", 0);
if (action == NULL) {
xpath = crm_strdup_printf(XPATH_HISTORY_ID, node, rsc_id,
last_failure_key);
} else {
char *action_key = pcmk__op_key(rsc_id, action, interval_ms);
xpath = crm_strdup_printf(XPATH_HISTORY_ORIG, node, rsc_id,
last_failure_key, action_key);
free(action_key);
}
free(last_failure_key);
controld_globals.cib_conn->cmds->remove(controld_globals.cib_conn, xpath,
NULL, cib_xpath);
free(xpath);
}
/*!
* \internal
* \brief Delete resource history entry from the CIB, given operation key
*
* \param[in] rsc_id Name of resource to clear history for
* \param[in] node Name of node to clear history for
* \param[in] key Operation key of operation to clear history for
* \param[in] call_id If specified, delete entry only if it has this call ID
*/
void
controld_delete_action_history_by_key(const char *rsc_id, const char *node,
const char *key, int call_id)
{
char *xpath = NULL;
CRM_CHECK((rsc_id != NULL) && (node != NULL) && (key != NULL), return);
if (call_id > 0) {
xpath = crm_strdup_printf(XPATH_HISTORY_CALL, node, rsc_id, key,
call_id);
} else {
xpath = crm_strdup_printf(XPATH_HISTORY_ID, node, rsc_id, key);
}
controld_globals.cib_conn->cmds->remove(controld_globals.cib_conn, xpath,
NULL, cib_xpath);
free(xpath);
}
diff --git a/daemons/controld/controld_control.c b/daemons/controld/controld_control.c
index d5c97e2bff..644d686bb1 100644
--- a/daemons/controld/controld_control.c
+++ b/daemons/controld/controld_control.c
@@ -1,853 +1,864 @@
/*
* Copyright 2004-2023 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU General Public License version 2
* or later (GPLv2+) WITHOUT ANY WARRANTY.
*/
#include <crm_internal.h>
#include <sys/param.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <crm/crm.h>
#include <crm/msg_xml.h>
#include <crm/pengine/rules.h>
#include <crm/cluster/internal.h>
#include <crm/cluster/election_internal.h>
#include <crm/common/ipc_internal.h>
#include <pacemaker-controld.h>
static qb_ipcs_service_t *ipcs = NULL;
static crm_trigger_t *config_read_trigger = NULL;
#if SUPPORT_COROSYNC
extern gboolean crm_connect_corosync(crm_cluster_t * cluster);
#endif
void crm_shutdown(int nsig);
static gboolean crm_read_options(gpointer user_data);
/* A_HA_CONNECT */
void
do_ha_control(long long action,
enum crmd_fsa_cause cause,
enum crmd_fsa_state cur_state,
enum crmd_fsa_input current_input, fsa_data_t * msg_data)
{
gboolean registered = FALSE;
static crm_cluster_t *cluster = NULL;
if (cluster == NULL) {
cluster = pcmk_cluster_new();
}
if (action & A_HA_DISCONNECT) {
crm_cluster_disconnect(cluster);
crm_info("Disconnected from the cluster");
controld_set_fsa_input_flags(R_HA_DISCONNECTED);
}
if (action & A_HA_CONNECT) {
crm_set_status_callback(&peer_update_callback);
crm_set_autoreap(FALSE);
#if SUPPORT_COROSYNC
if (is_corosync_cluster()) {
registered = crm_connect_corosync(cluster);
}
#endif // SUPPORT_COROSYNC
if (registered) {
controld_election_init(cluster->uname);
controld_globals.our_nodename = cluster->uname;
controld_globals.our_uuid = cluster->uuid;
if(cluster->uuid == NULL) {
crm_err("Could not obtain local uuid");
registered = FALSE;
}
}
if (!registered) {
controld_set_fsa_input_flags(R_HA_DISCONNECTED);
register_fsa_error(C_FSA_INTERNAL, I_ERROR, NULL);
return;
}
populate_cib_nodes(node_update_none, __func__);
controld_clear_fsa_input_flags(R_HA_DISCONNECTED);
crm_info("Connected to the cluster");
}
if (action & ~(A_HA_CONNECT | A_HA_DISCONNECT)) {
crm_err("Unexpected action %s in %s", fsa_action2string(action),
__func__);
}
}
/* A_SHUTDOWN */
void
do_shutdown(long long action,
enum crmd_fsa_cause cause,
enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data)
{
/* just in case */
controld_set_fsa_input_flags(R_SHUTDOWN);
controld_disconnect_fencer(FALSE);
}
/* A_SHUTDOWN_REQ */
void
do_shutdown_req(long long action,
enum crmd_fsa_cause cause,
enum crmd_fsa_state cur_state,
enum crmd_fsa_input current_input, fsa_data_t * msg_data)
{
xmlNode *msg = NULL;
controld_set_fsa_input_flags(R_SHUTDOWN);
//controld_set_fsa_input_flags(R_STAYDOWN);
crm_info("Sending shutdown request to all peers (DC is %s)",
pcmk__s(controld_globals.dc_name, "not set"));
msg = create_request(CRM_OP_SHUTDOWN_REQ, NULL, NULL, CRM_SYSTEM_CRMD, CRM_SYSTEM_CRMD, NULL);
if (send_cluster_message(NULL, crm_msg_crmd, msg, TRUE) == FALSE) {
register_fsa_error(C_FSA_INTERNAL, I_ERROR, NULL);
}
free_xml(msg);
}
void
crmd_fast_exit(crm_exit_t exit_code)
{
if (pcmk_is_set(controld_globals.fsa_input_register, R_STAYDOWN)) {
crm_warn("Inhibiting respawn "CRM_XS" remapping exit code %d to %d",
exit_code, CRM_EX_FATAL);
exit_code = CRM_EX_FATAL;
} else if ((exit_code == CRM_EX_OK)
&& pcmk_is_set(controld_globals.fsa_input_register,
R_IN_RECOVERY)) {
crm_err("Could not recover from internal error");
exit_code = CRM_EX_ERROR;
}
if (controld_globals.logger_out != NULL) {
controld_globals.logger_out->finish(controld_globals.logger_out,
exit_code, true, NULL);
pcmk__output_free(controld_globals.logger_out);
controld_globals.logger_out = NULL;
}
crm_exit(exit_code);
}
crm_exit_t
crmd_exit(crm_exit_t exit_code)
{
GMainLoop *mloop = controld_globals.mainloop;
static bool in_progress = FALSE;
if (in_progress && (exit_code == CRM_EX_OK)) {
crm_debug("Exit is already in progress");
return exit_code;
} else if(in_progress) {
crm_notice("Error during shutdown process, exiting now with status %d (%s)",
exit_code, crm_exit_str(exit_code));
crm_write_blackbox(SIGTRAP, NULL);
crmd_fast_exit(exit_code);
}
in_progress = TRUE;
crm_trace("Preparing to exit with status %d (%s)",
exit_code, crm_exit_str(exit_code));
/* Suppress secondary errors resulting from us disconnecting everything */
controld_set_fsa_input_flags(R_HA_DISCONNECTED);
/* Close all IPC servers and clients to ensure any and all shared memory files are cleaned up */
if(ipcs) {
crm_trace("Closing IPC server");
mainloop_del_ipc_server(ipcs);
ipcs = NULL;
}
controld_close_attrd_ipc();
controld_shutdown_schedulerd_ipc();
controld_disconnect_fencer(TRUE);
if ((exit_code == CRM_EX_OK) && (controld_globals.mainloop == NULL)) {
crm_debug("No mainloop detected");
exit_code = CRM_EX_ERROR;
}
/* On an error, just get out.
*
* Otherwise, make the effort to have mainloop exit gracefully so
* that it (mostly) cleans up after itself and valgrind has less
* to report on - allowing real errors stand out
*/
if (exit_code != CRM_EX_OK) {
crm_notice("Forcing immediate exit with status %d (%s)",
exit_code, crm_exit_str(exit_code));
crm_write_blackbox(SIGTRAP, NULL);
crmd_fast_exit(exit_code);
}
/* Clean up as much memory as possible for valgrind */
for (GList *iter = controld_globals.fsa_message_queue; iter != NULL;
iter = iter->next) {
fsa_data_t *fsa_data = (fsa_data_t *) iter->data;
crm_info("Dropping %s: [ state=%s cause=%s origin=%s ]",
fsa_input2string(fsa_data->fsa_input),
fsa_state2string(controld_globals.fsa_state),
fsa_cause2string(fsa_data->fsa_cause), fsa_data->origin);
delete_fsa_input(fsa_data);
}
controld_clear_fsa_input_flags(R_MEMBERSHIP);
g_list_free(controld_globals.fsa_message_queue);
controld_globals.fsa_message_queue = NULL;
controld_free_node_pending_timers();
controld_election_fini();
/* Tear down the CIB manager connection, but don't free it yet -- it could
* be used when we drain the mainloop later.
*/
controld_disconnect_cib_manager();
verify_stopped(controld_globals.fsa_state, LOG_WARNING);
controld_clear_fsa_input_flags(R_LRM_CONNECTED);
lrm_state_destroy_all();
mainloop_destroy_trigger(config_read_trigger);
config_read_trigger = NULL;
controld_destroy_fsa_trigger();
controld_destroy_transition_trigger();
pcmk__client_cleanup();
crm_peer_destroy();
controld_free_fsa_timers();
te_cleanup_stonith_history_sync(NULL, TRUE);
controld_free_sched_timer();
free(controld_globals.our_nodename);
controld_globals.our_nodename = NULL;
free(controld_globals.our_uuid);
controld_globals.our_uuid = NULL;
free(controld_globals.dc_name);
controld_globals.dc_name = NULL;
free(controld_globals.dc_version);
controld_globals.dc_version = NULL;
free(controld_globals.cluster_name);
controld_globals.cluster_name = NULL;
free(controld_globals.te_uuid);
controld_globals.te_uuid = NULL;
free_max_generation();
controld_destroy_failed_sync_table();
controld_destroy_outside_events_table();
mainloop_destroy_signal(SIGPIPE);
mainloop_destroy_signal(SIGUSR1);
mainloop_destroy_signal(SIGTERM);
mainloop_destroy_signal(SIGTRAP);
/* leave SIGCHLD engaged as we might still want to drain some service-actions */
if (mloop) {
GMainContext *ctx = g_main_loop_get_context(controld_globals.mainloop);
/* Don't re-enter this block */
controld_globals.mainloop = NULL;
/* no signals on final draining anymore */
mainloop_destroy_signal(SIGCHLD);
crm_trace("Draining mainloop %d %d", g_main_loop_is_running(mloop), g_main_context_pending(ctx));
{
int lpc = 0;
while((g_main_context_pending(ctx) && lpc < 10)) {
lpc++;
crm_trace("Iteration %d", lpc);
g_main_context_dispatch(ctx);
}
}
crm_trace("Closing mainloop %d %d", g_main_loop_is_running(mloop), g_main_context_pending(ctx));
g_main_loop_quit(mloop);
/* Won't do anything yet, since we're inside it now */
g_main_loop_unref(mloop);
} else {
mainloop_destroy_signal(SIGCHLD);
}
cib_delete(controld_globals.cib_conn);
controld_globals.cib_conn = NULL;
throttle_fini();
/* Graceful */
crm_trace("Done preparing for exit with status %d (%s)",
exit_code, crm_exit_str(exit_code));
return exit_code;
}
/* A_EXIT_0, A_EXIT_1 */
void
do_exit(long long action,
enum crmd_fsa_cause cause,
enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data)
{
crm_exit_t exit_code = CRM_EX_OK;
if (pcmk_is_set(action, A_EXIT_1)) {
exit_code = CRM_EX_ERROR;
crm_err("Exiting now due to errors");
}
verify_stopped(cur_state, LOG_ERR);
crmd_exit(exit_code);
}
static void sigpipe_ignore(int nsig) { return; }
/* A_STARTUP */
void
do_startup(long long action,
enum crmd_fsa_cause cause,
enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data)
{
crm_debug("Registering Signal Handlers");
mainloop_add_signal(SIGTERM, crm_shutdown);
mainloop_add_signal(SIGPIPE, sigpipe_ignore);
config_read_trigger = mainloop_add_trigger(G_PRIORITY_HIGH,
crm_read_options, NULL);
controld_init_fsa_trigger();
controld_init_transition_trigger();
crm_debug("Creating CIB manager and executor objects");
controld_globals.cib_conn = cib_new();
lrm_state_init_local();
if (controld_init_fsa_timers() == FALSE) {
register_fsa_error(C_FSA_INTERNAL, I_ERROR, NULL);
}
}
// \return libqb error code (0 on success, -errno on error)
static int32_t
accept_controller_client(qb_ipcs_connection_t *c, uid_t uid, gid_t gid)
{
crm_trace("Accepting new IPC client connection");
if (pcmk__new_client(c, uid, gid) == NULL) {
return -EIO;
}
return 0;
}
// \return libqb error code (0 on success, -errno on error)
static int32_t
dispatch_controller_ipc(qb_ipcs_connection_t * c, void *data, size_t size)
{
uint32_t id = 0;
uint32_t flags = 0;
pcmk__client_t *client = pcmk__find_client(c);
xmlNode *msg = pcmk__client_data2xml(client, data, &id, &flags);
if (msg == NULL) {
pcmk__ipc_send_ack(client, id, flags, "ack", NULL, CRM_EX_PROTOCOL);
return 0;
}
pcmk__ipc_send_ack(client, id, flags, "ack", NULL, CRM_EX_INDETERMINATE);
CRM_ASSERT(client->user != NULL);
pcmk__update_acl_user(msg, F_CRM_USER, client->user);
crm_xml_add(msg, F_CRM_SYS_FROM, client->id);
if (controld_authorize_ipc_message(msg, client, NULL)) {
crm_trace("Processing IPC message from client %s",
pcmk__client_name(client));
route_message(C_IPC_MESSAGE, msg);
}
controld_trigger_fsa();
free_xml(msg);
return 0;
}
static int32_t
ipc_client_disconnected(qb_ipcs_connection_t *c)
{
pcmk__client_t *client = pcmk__find_client(c);
if (client) {
crm_trace("Disconnecting %sregistered client %s (%p/%p)",
(client->userdata? "" : "un"), pcmk__client_name(client),
c, client);
free(client->userdata);
pcmk__free_client(client);
controld_trigger_fsa();
}
return 0;
}
static void
ipc_connection_destroyed(qb_ipcs_connection_t *c)
{
crm_trace("Connection %p", c);
ipc_client_disconnected(c);
}
/* A_STOP */
void
do_stop(long long action,
enum crmd_fsa_cause cause,
enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data)
{
crm_trace("Closing IPC server");
mainloop_del_ipc_server(ipcs); ipcs = NULL;
register_fsa_input(C_FSA_INTERNAL, I_TERMINATE, NULL);
}
/* A_STARTED */
void
do_started(long long action,
enum crmd_fsa_cause cause,
enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data)
{
static struct qb_ipcs_service_handlers crmd_callbacks = {
.connection_accept = accept_controller_client,
.connection_created = NULL,
.msg_process = dispatch_controller_ipc,
.connection_closed = ipc_client_disconnected,
.connection_destroyed = ipc_connection_destroyed
};
if (cur_state != S_STARTING) {
crm_err("Start cancelled... %s", fsa_state2string(cur_state));
return;
} else if (!pcmk_is_set(controld_globals.fsa_input_register,
R_MEMBERSHIP)) {
crm_info("Delaying start, no membership data (%.16llx)", R_MEMBERSHIP);
crmd_fsa_stall(TRUE);
return;
} else if (!pcmk_is_set(controld_globals.fsa_input_register,
R_LRM_CONNECTED)) {
crm_info("Delaying start, not connected to executor (%.16llx)", R_LRM_CONNECTED);
crmd_fsa_stall(TRUE);
return;
} else if (!pcmk_is_set(controld_globals.fsa_input_register,
R_CIB_CONNECTED)) {
crm_info("Delaying start, CIB not connected (%.16llx)", R_CIB_CONNECTED);
crmd_fsa_stall(TRUE);
return;
} else if (!pcmk_is_set(controld_globals.fsa_input_register,
R_READ_CONFIG)) {
crm_info("Delaying start, Config not read (%.16llx)", R_READ_CONFIG);
crmd_fsa_stall(TRUE);
return;
} else if (!pcmk_is_set(controld_globals.fsa_input_register, R_PEER_DATA)) {
crm_info("Delaying start, No peer data (%.16llx)", R_PEER_DATA);
crmd_fsa_stall(TRUE);
return;
}
crm_debug("Init server comms");
ipcs = pcmk__serve_controld_ipc(&crmd_callbacks);
if (ipcs == NULL) {
crm_err("Failed to create IPC server: shutting down and inhibiting respawn");
register_fsa_error(C_FSA_INTERNAL, I_ERROR, NULL);
} else {
crm_notice("Pacemaker controller successfully started and accepting connections");
}
controld_set_fsa_input_flags(R_ST_REQUIRED);
controld_timer_fencer_connect(GINT_TO_POINTER(TRUE));
controld_clear_fsa_input_flags(R_STARTING);
register_fsa_input(msg_data->fsa_cause, I_PENDING, NULL);
}
/* A_RECOVER */
void
do_recover(long long action,
enum crmd_fsa_cause cause,
enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data)
{
controld_set_fsa_input_flags(R_IN_RECOVERY);
crm_warn("Fast-tracking shutdown in response to errors");
register_fsa_input(C_FSA_INTERNAL, I_TERMINATE, NULL);
}
static pcmk__cluster_option_t controller_options[] = {
/* name, old name, type, allowed values,
* default value, validator,
* short description,
* long description
*/
{
"dc-version", NULL, "string", NULL, PCMK__VALUE_NONE, NULL,
N_("Pacemaker version on cluster node elected Designated Controller (DC)"),
N_("Includes a hash which identifies the exact changeset the code was "
"built from. Used for diagnostic purposes.")
},
{
"cluster-infrastructure", NULL, "string", NULL, "corosync", NULL,
N_("The messaging stack on which Pacemaker is currently running"),
N_("Used for informational and diagnostic purposes.")
},
{
"cluster-name", NULL, "string", NULL, NULL, NULL,
N_("An arbitrary name for the cluster"),
N_("This optional value is mostly for users' convenience as desired "
"in administration, but may also be used in Pacemaker "
"configuration rules via the #cluster-name node attribute, and "
"by higher-level tools and resource agents.")
},
{
XML_CONFIG_ATTR_DC_DEADTIME, NULL, "time",
NULL, "20s", pcmk__valid_interval_spec,
N_("How long to wait for a response from other nodes during start-up"),
N_("The optimal value will depend on the speed and load of your network "
"and the type of switches used.")
},
{
XML_CONFIG_ATTR_RECHECK, NULL, "time",
N_("Zero disables polling, while positive values are an interval in seconds"
"(unless other units are specified, for example \"5min\")"),
"15min", pcmk__valid_interval_spec,
N_("Polling interval to recheck cluster state and evaluate rules "
"with date specifications"),
N_("Pacemaker is primarily event-driven, and looks ahead to know when to "
"recheck cluster state for failure timeouts and most time-based "
"rules. However, it will also recheck the cluster after this "
"amount of inactivity, to evaluate rules with date specifications "
"and serve as a fail-safe for certain types of scheduler bugs.")
},
{
"load-threshold", NULL, "percentage", NULL,
"80%", pcmk__valid_percentage,
N_("Maximum amount of system load that should be used by cluster nodes"),
N_("The cluster will slow down its recovery process when the amount of "
"system resources used (currently CPU) approaches this limit"),
},
{
"node-action-limit", NULL, "integer", NULL,
"0", pcmk__valid_number,
N_("Maximum number of jobs that can be scheduled per node "
"(defaults to 2x cores)")
},
{ XML_CONFIG_ATTR_FENCE_REACTION, NULL, "string", NULL, "stop", NULL,
N_("How a cluster node should react if notified of its own fencing"),
N_("A cluster node may receive notification of its own fencing if fencing "
"is misconfigured, or if fabric fencing is in use that doesn't cut "
"cluster communication. Allowed values are \"stop\" to attempt to "
"immediately stop Pacemaker and stay stopped, or \"panic\" to attempt "
"to immediately reboot the local node, falling back to stop on failure.")
},
{
XML_CONFIG_ATTR_ELECTION_FAIL, NULL, "time", NULL,
"2min", pcmk__valid_interval_spec,
"*** Advanced Use Only ***",
N_("Declare an election failed if it is not decided within this much "
"time. If you need to adjust this value, it probably indicates "
"the presence of a bug.")
},
{
XML_CONFIG_ATTR_FORCE_QUIT, NULL, "time", NULL,
"20min", pcmk__valid_interval_spec,
"*** Advanced Use Only ***",
N_("Exit immediately if shutdown does not complete within this much "
"time. If you need to adjust this value, it probably indicates "
"the presence of a bug.")
},
{
"join-integration-timeout", "crmd-integration-timeout", "time", NULL,
"3min", pcmk__valid_interval_spec,
"*** Advanced Use Only ***",
N_("If you need to adjust this value, it probably indicates "
"the presence of a bug.")
},
{
"join-finalization-timeout", "crmd-finalization-timeout", "time", NULL,
"30min", pcmk__valid_interval_spec,
"*** Advanced Use Only ***",
N_("If you need to adjust this value, it probably indicates "
"the presence of a bug.")
},
{
"transition-delay", "crmd-transition-delay", "time", NULL,
"0s", pcmk__valid_interval_spec,
N_("*** Advanced Use Only *** Enabling this option will slow down "
"cluster recovery under all conditions"),
N_("Delay cluster recovery for this much time to allow for additional "
"events to occur. Useful if your configuration is sensitive to "
"the order in which ping updates arrive.")
},
{
"stonith-watchdog-timeout", NULL, "time", NULL,
"0", controld_verify_stonith_watchdog_timeout,
N_("How long before nodes can be assumed to be safely down when "
"watchdog-based self-fencing via SBD is in use"),
N_("If this is set to a positive value, lost nodes are assumed to "
"self-fence using watchdog-based SBD within this much time. This "
"does not require a fencing resource to be explicitly configured, "
"though a fence_watchdog resource can be configured, to limit use "
"to specific nodes. If this is set to 0 (the default), the cluster "
"will never assume watchdog-based self-fencing. If this is set to a "
"negative value, the cluster will use twice the local value of the "
"`SBD_WATCHDOG_TIMEOUT` environment variable if that is positive, "
"or otherwise treat this as 0. WARNING: When used, this timeout "
"must be larger than `SBD_WATCHDOG_TIMEOUT` on all nodes that use "
"watchdog-based SBD, and Pacemaker will refuse to start on any of "
"those nodes where this is not true for the local value or SBD is "
"not active. When this is set to a negative value, "
"`SBD_WATCHDOG_TIMEOUT` must be set to the same value on all nodes "
"that use SBD, otherwise data corruption or loss could occur.")
},
{
"stonith-max-attempts", NULL, "integer", NULL,
"10", pcmk__valid_positive_number,
N_("How many times fencing can fail before it will no longer be "
"immediately re-attempted on a target")
},
// Already documented in libpe_status (other values must be kept identical)
{
"no-quorum-policy", NULL, "select",
"stop, freeze, ignore, demote, suicide", "stop", pcmk__valid_quorum,
N_("What to do when the cluster does not have quorum"), NULL
},
{
XML_CONFIG_ATTR_SHUTDOWN_LOCK, NULL, "boolean", NULL,
"false", pcmk__valid_boolean,
N_("Whether to lock resources to a cleanly shut down node"),
N_("When true, resources active on a node when it is cleanly shut down "
"are kept \"locked\" to that node (not allowed to run elsewhere) "
"until they start again on that node after it rejoins (or for at "
"most shutdown-lock-limit, if set). Stonith resources and "
"Pacemaker Remote connections are never locked. Clone and bundle "
"instances and the promoted role of promotable clones are "
"currently never locked, though support could be added in a future "
"release.")
},
{
XML_CONFIG_ATTR_SHUTDOWN_LOCK_LIMIT, NULL, "time", NULL,
"0", pcmk__valid_interval_spec,
N_("Do not lock resources to a cleanly shut down node longer than "
"this"),
N_("If shutdown-lock is true and this is set to a nonzero time "
"duration, shutdown locks will expire after this much time has "
"passed since the shutdown was initiated, even if the node has not "
"rejoined.")
},
+ {
+ XML_CONFIG_ATTR_NODE_PENDING_TIMEOUT, NULL, "time", NULL,
+ "0", pcmk__valid_interval_spec,
+ N_("How long to wait for a node that has joined the cluster to join "
+ "the controller process group"),
+ N_("Fence nodes that do not join the controller process group within "
+ "this much time after joining the cluster, to allow the cluster "
+ "to continue managing resources. A value of 0 means never fence "
+ "pending nodes. Setting the value to 2h means fence nodes after "
+ "2 hours.")
+ },
};
void
crmd_metadata(void)
{
const char *desc_short = "Pacemaker controller options";
const char *desc_long = "Cluster options used by Pacemaker's controller";
gchar *s = pcmk__format_option_metadata("pacemaker-controld", desc_short,
desc_long, controller_options,
PCMK__NELEM(controller_options));
printf("%s", s);
g_free(s);
}
static void
config_query_callback(xmlNode * msg, int call_id, int rc, xmlNode * output, void *user_data)
{
const char *value = NULL;
GHashTable *config_hash = NULL;
crm_time_t *now = crm_time_new(NULL);
xmlNode *crmconfig = NULL;
xmlNode *alerts = NULL;
if (rc != pcmk_ok) {
fsa_data_t *msg_data = NULL;
crm_err("Local CIB query resulted in an error: %s", pcmk_strerror(rc));
register_fsa_error(C_FSA_INTERNAL, I_ERROR, NULL);
if (rc == -EACCES || rc == -pcmk_err_schema_validation) {
crm_err("The cluster is mis-configured - shutting down and staying down");
controld_set_fsa_input_flags(R_STAYDOWN);
}
goto bail;
}
crmconfig = output;
if ((crmconfig != NULL)
&& !pcmk__xe_is(crmconfig, XML_CIB_TAG_CRMCONFIG)) {
crmconfig = first_named_child(crmconfig, XML_CIB_TAG_CRMCONFIG);
}
if (!crmconfig) {
fsa_data_t *msg_data = NULL;
crm_err("Local CIB query for " XML_CIB_TAG_CRMCONFIG " section failed");
register_fsa_error(C_FSA_INTERNAL, I_ERROR, NULL);
goto bail;
}
crm_debug("Call %d : Parsing CIB options", call_id);
config_hash = pcmk__strkey_table(free, free);
pe_unpack_nvpairs(crmconfig, crmconfig, XML_CIB_TAG_PROPSET, NULL,
config_hash, CIB_OPTIONS_FIRST, FALSE, now, NULL);
// Validate all options, and use defaults if not already present in hash
pcmk__validate_cluster_options(config_hash, controller_options,
PCMK__NELEM(controller_options));
value = g_hash_table_lookup(config_hash, "no-quorum-policy");
if (pcmk__str_eq(value, "suicide", pcmk__str_casei) && pcmk__locate_sbd()) {
controld_set_global_flags(controld_no_quorum_suicide);
}
value = g_hash_table_lookup(config_hash, XML_CONFIG_ATTR_SHUTDOWN_LOCK);
if (crm_is_true(value)) {
controld_set_global_flags(controld_shutdown_lock_enabled);
} else {
controld_clear_global_flags(controld_shutdown_lock_enabled);
}
value = g_hash_table_lookup(config_hash,
XML_CONFIG_ATTR_SHUTDOWN_LOCK_LIMIT);
controld_globals.shutdown_lock_limit = crm_parse_interval_spec(value)
/ 1000;
value = g_hash_table_lookup(config_hash,
XML_CONFIG_ATTR_NODE_PENDING_TIMEOUT);
controld_globals.node_pending_timeout = crm_parse_interval_spec(value) / 1000;
value = g_hash_table_lookup(config_hash, "cluster-name");
pcmk__str_update(&(controld_globals.cluster_name), value);
// Let subcomponents initialize their own static variables
controld_configure_election(config_hash);
controld_configure_fencing(config_hash);
controld_configure_fsa_timers(config_hash);
controld_configure_throttle(config_hash);
alerts = first_named_child(output, XML_CIB_TAG_ALERTS);
crmd_unpack_alerts(alerts);
controld_set_fsa_input_flags(R_READ_CONFIG);
controld_trigger_fsa();
g_hash_table_destroy(config_hash);
bail:
crm_time_free(now);
}
/*!
* \internal
* \brief Trigger read and processing of the configuration
*
* \param[in] fn Calling function name
* \param[in] line Line number where call occurred
*/
void
controld_trigger_config_as(const char *fn, int line)
{
if (config_read_trigger != NULL) {
crm_trace("%s:%d - Triggered config processing", fn, line);
mainloop_set_trigger(config_read_trigger);
}
}
gboolean
crm_read_options(gpointer user_data)
{
cib_t *cib_conn = controld_globals.cib_conn;
int call_id = cib_conn->cmds->query(cib_conn,
"//" XML_CIB_TAG_CRMCONFIG
" | //" XML_CIB_TAG_ALERTS,
NULL, cib_xpath|cib_scope_local);
fsa_register_cib_callback(call_id, NULL, config_query_callback);
crm_trace("Querying the CIB... call %d", call_id);
return TRUE;
}
/* A_READCONFIG */
void
do_read_config(long long action,
enum crmd_fsa_cause cause,
enum crmd_fsa_state cur_state,
enum crmd_fsa_input current_input, fsa_data_t * msg_data)
{
throttle_init();
controld_trigger_config();
}
void
crm_shutdown(int nsig)
{
const char *value = NULL;
guint default_period_ms = 0;
if ((controld_globals.mainloop == NULL)
|| !g_main_loop_is_running(controld_globals.mainloop)) {
crmd_exit(CRM_EX_OK);
return;
}
if (pcmk_is_set(controld_globals.fsa_input_register, R_SHUTDOWN)) {
crm_err("Escalating shutdown");
register_fsa_input_before(C_SHUTDOWN, I_ERROR, NULL);
return;
}
controld_set_fsa_input_flags(R_SHUTDOWN);
register_fsa_input(C_SHUTDOWN, I_SHUTDOWN, NULL);
/* If shutdown timer doesn't have a period set, use the default
*
* @TODO: Evaluate whether this is still necessary. As long as
* config_query_callback() has been run at least once, it doesn't look like
* anything could have changed the timer period since then.
*/
value = pcmk__cluster_option(NULL, controller_options,
PCMK__NELEM(controller_options),
XML_CONFIG_ATTR_FORCE_QUIT);
default_period_ms = crm_parse_interval_spec(value);
controld_shutdown_start_countdown(default_period_ms);
}
diff --git a/daemons/execd/remoted_pidone.c b/daemons/execd/remoted_pidone.c
index 96fee90c07..08271bfb2a 100644
--- a/daemons/execd/remoted_pidone.c
+++ b/daemons/execd/remoted_pidone.c
@@ -1,301 +1,302 @@
/*
* Copyright 2017-2023 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU Lesser General Public License
* version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY.
*/
#include <crm_internal.h>
#include <stdio.h>
#include <ctype.h>
#include <stdlib.h>
#include <signal.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <crm/crm.h>
#include "pacemaker-execd.h"
static pid_t main_pid = 0;
static void
sigdone(void)
{
exit(CRM_EX_OK);
}
static void
sigreap(void)
{
pid_t pid = 0;
int status;
do {
/*
* Opinions seem to differ as to what to put here:
* -1, any child process
* 0, any child process whose process group ID is equal to that of the calling process
*/
pid = waitpid(-1, &status, WNOHANG);
if (pid == main_pid) {
/* Exit when pacemaker-remote exits and use the same return code */
if (WIFEXITED(status)) {
exit(WEXITSTATUS(status));
}
exit(CRM_EX_ERROR);
}
} while (pid > 0);
}
static struct {
int sig;
void (*handler)(void);
} sigmap[] = {
{ SIGCHLD, sigreap },
{ SIGINT, sigdone },
};
/*!
* \internal
* \brief Check a line of text for a valid environment variable name
*
* \param[in] line Text to check
* \param[out] first First character of valid name if found, NULL otherwise
* \param[out] last Last character of valid name if found, NULL otherwise
*
* \return TRUE if valid name found, FALSE otherwise
* \note It's reasonable to impose limitations on environment variable names
* beyond what C or setenv() does: We only allow names that contain only
* [a-zA-Z0-9_] characters and do not start with a digit.
*/
static bool
find_env_var_name(char *line, char **first, char **last)
{
// Skip leading whitespace
*first = line;
while (isspace(**first)) {
++*first;
}
if (isalpha(**first) || (**first == '_')) { // Valid first character
*last = *first;
while (isalnum(*(*last + 1)) || (*(*last + 1) == '_')) {
++*last;
}
return TRUE;
}
*first = *last = NULL;
return FALSE;
}
static void
load_env_vars(const char *filename)
{
/* We haven't forked or initialized logging yet, so don't leave any file
* descriptors open, and don't log -- silently ignore errors.
*/
FILE *fp = fopen(filename, "r");
if (fp != NULL) {
char line[LINE_MAX] = { '\0', };
while (fgets(line, LINE_MAX, fp) != NULL) {
char *name = NULL;
char *end = NULL;
char *value = NULL;
char *quote = NULL;
// Look for valid name immediately followed by equals sign
if (find_env_var_name(line, &name, &end) && (*++end == '=')) {
// Null-terminate name, and advance beyond equals sign
*end++ = '\0';
// Check whether value is quoted
if ((*end == '\'') || (*end == '"')) {
quote = end++;
}
value = end;
if (quote) {
/* Value is remaining characters up to next non-backslashed
* matching quote character.
*/
while (((*end != *quote) || (*(end - 1) == '\\'))
&& (*end != '\0')) {
end++;
}
if (*end == *quote) {
// Null-terminate value, and advance beyond close quote
*end++ = '\0';
} else {
// Matching closing quote wasn't found
value = NULL;
}
} else {
/* Value is remaining characters up to next non-backslashed
* whitespace.
*/
while ((!isspace(*end) || (*(end - 1) == '\\'))
&& (*end != '\0')) {
++end;
}
if (end == (line + LINE_MAX - 1)) {
// Line was too long
value = NULL;
}
// Do NOT null-terminate value (yet)
}
/* We have a valid name and value, and end is now the character
* after the closing quote or the first whitespace after the
* unquoted value. Make sure the rest of the line is just
* whitespace or a comment.
*/
if (value) {
char *value_end = end;
while (isspace(*end) && (*end != '\n')) {
++end;
}
if ((*end == '\n') || (*end == '#')) {
if (quote == NULL) {
// Now we can null-terminate an unquoted value
*value_end = '\0';
}
// Don't overwrite (bundle options take precedence)
setenv(name, value, 0);
} else {
value = NULL;
}
}
}
if ((value == NULL) && (strchr(line, '\n') == NULL)) {
// Eat remainder of line beyond LINE_MAX
if (fscanf(fp, "%*[^\n]\n") == EOF) {
value = NULL; // Don't care, make compiler happy
}
}
}
fclose(fp);
}
}
void
remoted_spawn_pidone(int argc, char **argv, char **envp)
{
sigset_t set;
/* This environment variable exists for two purposes:
* - For testing, setting it to "full" enables full PID 1 behavior even
* when PID is not 1
* - Setting to "vars" enables just the loading of environment variables
* from /etc/pacemaker/pcmk-init.env, which could be useful for testing or
* containers with a custom PID 1 script that launches pacemaker-remoted.
*/
- const char *pid1 = "full";
+ const char *pid1 = "default";
if (getpid() != 1) {
pid1 = pcmk__env_option(PCMK__ENV_REMOTE_PID1);
- if (pid1 == NULL) {
+ if (!pcmk__str_any_of(pid1, "full", "vars", NULL)) {
+ // Default, unset, or invalid
return;
}
}
/* When a container is launched, it may be given specific environment
* variables, which for Pacemaker bundles are given in the bundle
* configuration. However, that does not allow for host-specific values.
* To allow for that, look for a special file containing a shell-like syntax
* of name/value pairs, and export those into the environment.
*/
load_env_vars("/etc/pacemaker/pcmk-init.env");
- if (strcmp(pid1, "full")) {
+ if (strcmp(pid1, "vars") == 0) {
return;
}
/* Containers can be expected to have /var/log, but they may not have
* /var/log/pacemaker, so use a different default if no value has been
* explicitly configured in the container's environment.
*/
if (pcmk__env_option(PCMK__ENV_LOGFILE) == NULL) {
pcmk__set_env_option(PCMK__ENV_LOGFILE, "/var/log/pcmk-init.log", true);
}
sigfillset(&set);
sigprocmask(SIG_BLOCK, &set, 0);
main_pid = fork();
switch (main_pid) {
case 0:
sigprocmask(SIG_UNBLOCK, &set, NULL);
setsid();
setpgid(0, 0);
// Child remains as pacemaker-remoted
return;
case -1:
crm_err("fork failed: %s", pcmk_rc_str(errno));
}
/* Parent becomes the reaper of zombie processes */
/* Safe to initialize logging now if needed */
# ifdef HAVE_PROGNAME
/* Differentiate ourselves in the 'ps' output */
{
char *p;
int i, maxlen;
char *LastArgv = NULL;
const char *name = "pcmk-init";
for (i = 0; i < argc; i++) {
if (!i || (LastArgv + 1 == argv[i]))
LastArgv = argv[i] + strlen(argv[i]);
}
for (i = 0; envp[i] != NULL; i++) {
if ((LastArgv + 1) == envp[i]) {
LastArgv = envp[i] + strlen(envp[i]);
}
}
maxlen = (LastArgv - argv[0]) - 2;
i = strlen(name);
/* We can overwrite individual argv[] arguments */
snprintf(argv[0], maxlen, "%s", name);
/* Now zero out everything else */
p = &argv[0][i];
while (p < LastArgv) {
*p++ = '\0';
}
argv[1] = NULL;
}
# endif // HAVE_PROGNAME
while (1) {
int sig;
size_t i;
sigwait(&set, &sig);
for (i = 0; i < PCMK__NELEM(sigmap); i++) {
if (sigmap[i].sig == sig) {
sigmap[i].handler();
break;
}
}
}
}
diff --git a/daemons/pacemakerd/pcmkd_subdaemons.c b/daemons/pacemakerd/pcmkd_subdaemons.c
index 5ac361d203..e3e8abae88 100644
--- a/daemons/pacemakerd/pcmkd_subdaemons.c
+++ b/daemons/pacemakerd/pcmkd_subdaemons.c
@@ -1,897 +1,898 @@
/*
* Copyright 2010-2023 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU General Public License version 2
* or later (GPLv2+) WITHOUT ANY WARRANTY.
*/
#include <crm_internal.h>
#include "pacemakerd.h"
#if SUPPORT_COROSYNC
#include "pcmkd_corosync.h"
#endif
#include <errno.h>
#include <grp.h>
#include <signal.h>
#include <stdbool.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <time.h>
#include <unistd.h>
#include <crm/cluster.h>
#include <crm/msg_xml.h>
enum child_daemon_flags {
child_none = 0,
child_respawn = 1 << 0,
child_needs_cluster = 1 << 1,
child_needs_retry = 1 << 2,
child_active_before_startup = 1 << 3,
};
typedef struct pcmk_child_s {
pid_t pid;
int respawn_count;
const char *name;
const char *uid;
const char *command;
const char *endpoint; /* IPC server name */
int check_count;
uint32_t flags;
} pcmk_child_t;
#define PCMK_PROCESS_CHECK_INTERVAL 1
#define PCMK_PROCESS_CHECK_RETRIES 5
#define SHUTDOWN_ESCALATION_PERIOD 180000 /* 3m */
/* Index into the array below */
#define PCMK_CHILD_CONTROLD 5
static pcmk_child_t pcmk_children[] = {
{
0, 0, "pacemaker-based", CRM_DAEMON_USER,
CRM_DAEMON_DIR "/pacemaker-based", PCMK__SERVER_BASED_RO,
0, child_respawn | child_needs_cluster
},
{
0, 0, "pacemaker-fenced", NULL,
CRM_DAEMON_DIR "/pacemaker-fenced", "stonith-ng",
0, child_respawn | child_needs_cluster
},
{
0, 0, "pacemaker-execd", NULL,
CRM_DAEMON_DIR "/pacemaker-execd", CRM_SYSTEM_LRMD,
0, child_respawn
},
{
0, 0, "pacemaker-attrd", CRM_DAEMON_USER,
CRM_DAEMON_DIR "/pacemaker-attrd", T_ATTRD,
0, child_respawn | child_needs_cluster
},
{
0, 0, "pacemaker-schedulerd", CRM_DAEMON_USER,
CRM_DAEMON_DIR "/pacemaker-schedulerd", CRM_SYSTEM_PENGINE,
0, child_respawn
},
{
0, 0, "pacemaker-controld", CRM_DAEMON_USER,
CRM_DAEMON_DIR "/pacemaker-controld", CRM_SYSTEM_CRMD,
0, child_respawn | child_needs_cluster
},
};
static char *opts_default[] = { NULL, NULL };
static char *opts_vgrind[] = { NULL, NULL, NULL, NULL, NULL };
crm_trigger_t *shutdown_trigger = NULL;
crm_trigger_t *startup_trigger = NULL;
time_t subdaemon_check_progress = 0;
// Whether we need root group access to talk to cluster layer
static bool need_root_group = true;
/* When contacted via pacemakerd-api by a client having sbd in
* the name we assume it is sbd-daemon which wants to know
* if pacemakerd shutdown gracefully.
* Thus when everything is shutdown properly pacemakerd
* waits till it has reported the graceful completion of
* shutdown to sbd and just when sbd-client closes the
* connection we can assume that the report has arrived
* properly so that pacemakerd can finally exit.
* Following two variables are used to track that handshake.
*/
unsigned int shutdown_complete_state_reported_to = 0;
gboolean shutdown_complete_state_reported_client_closed = FALSE;
/* state we report when asked via pacemakerd-api status-ping */
const char *pacemakerd_state = XML_PING_ATTR_PACEMAKERDSTATE_INIT;
gboolean running_with_sbd = FALSE; /* local copy */
GMainLoop *mainloop = NULL;
static gboolean fatal_error = FALSE;
static int child_liveness(pcmk_child_t *child);
static gboolean escalate_shutdown(gpointer data);
static int start_child(pcmk_child_t * child);
static void pcmk_child_exit(mainloop_child_t * p, pid_t pid, int core, int signo, int exitcode);
static void pcmk_process_exit(pcmk_child_t * child);
static gboolean pcmk_shutdown_worker(gpointer user_data);
static gboolean stop_child(pcmk_child_t * child, int signal);
static bool
pcmkd_cluster_connected(void)
{
#if SUPPORT_COROSYNC
return pcmkd_corosync_connected();
#else
return true;
#endif
}
static gboolean
check_next_subdaemon(gpointer user_data)
{
static int next_child = 0;
int rc = child_liveness(&pcmk_children[next_child]);
crm_trace("Checked %s[%lld]: %s (%d)",
pcmk_children[next_child].name,
(long long) PCMK__SPECIAL_PID_AS_0(pcmk_children[next_child].pid),
pcmk_rc_str(rc), rc);
switch (rc) {
case pcmk_rc_ok:
pcmk_children[next_child].check_count = 0;
subdaemon_check_progress = time(NULL);
break;
case pcmk_rc_ipc_pid_only: // This case: it was previously OK
pcmk_children[next_child].check_count++;
if (pcmk_children[next_child].check_count >= PCMK_PROCESS_CHECK_RETRIES) {
crm_err("%s[%lld] is unresponsive to ipc after %d tries but "
"we found the pid so have it killed that we can restart",
pcmk_children[next_child].name,
(long long) PCMK__SPECIAL_PID_AS_0(
pcmk_children[next_child].pid),
pcmk_children[next_child].check_count);
stop_child(&pcmk_children[next_child], SIGKILL);
if (pcmk_is_set(pcmk_children[next_child].flags, child_respawn)) {
/* as long as the respawn-limit isn't reached
give it another round of check retries
*/
pcmk_children[next_child].check_count = 0;
}
} else {
crm_notice("%s[%lld] is unresponsive to ipc after %d tries",
pcmk_children[next_child].name,
(long long) PCMK__SPECIAL_PID_AS_0(
pcmk_children[next_child].pid),
pcmk_children[next_child].check_count);
if (pcmk_is_set(pcmk_children[next_child].flags, child_respawn)) {
/* as long as the respawn-limit isn't reached
and we haven't run out of connect retries
we account this as progress we are willing
to tell to sbd
*/
subdaemon_check_progress = time(NULL);
}
}
/* go to the next child and see if
we can make progress there
*/
break;
case pcmk_rc_ipc_unresponsive:
if (!pcmk_is_set(pcmk_children[next_child].flags, child_respawn)) {
/* if a subdaemon is down and we don't want it
to be restarted this is a success during
shutdown. if it isn't restarted anymore
due to MAX_RESPAWN it is
rather no success.
*/
if (pcmk_children[next_child].respawn_count <= MAX_RESPAWN) {
subdaemon_check_progress = time(NULL);
}
}
if (!pcmk_is_set(pcmk_children[next_child].flags, child_active_before_startup)) {
crm_trace("found %s[%lld] missing - signal-handler "
"will take care of it",
pcmk_children[next_child].name,
(long long) PCMK__SPECIAL_PID_AS_0(
pcmk_children[next_child].pid));
break;
}
if (pcmk_is_set(pcmk_children[next_child].flags, child_respawn)) {
crm_err("%s[%lld] terminated",
pcmk_children[next_child].name,
(long long) PCMK__SPECIAL_PID_AS_0(
pcmk_children[next_child].pid));
} else {
/* orderly shutdown */
crm_notice("%s[%lld] terminated",
pcmk_children[next_child].name,
(long long) PCMK__SPECIAL_PID_AS_0(
pcmk_children[next_child].pid));
}
pcmk_process_exit(&(pcmk_children[next_child]));
break;
default:
crm_exit(CRM_EX_FATAL);
break; /* static analysis/noreturn */
}
next_child++;
if (next_child >= PCMK__NELEM(pcmk_children)) {
next_child = 0;
}
return G_SOURCE_CONTINUE;
}
static gboolean
escalate_shutdown(gpointer data)
{
pcmk_child_t *child = data;
if (child->pid == PCMK__SPECIAL_PID) {
pcmk_process_exit(child);
} else if (child->pid != 0) {
/* Use SIGSEGV instead of SIGKILL to create a core so we can see what it was up to */
crm_err("Child %s not terminating in a timely manner, forcing", child->name);
stop_child(child, SIGSEGV);
}
return FALSE;
}
static void
pcmk_child_exit(mainloop_child_t * p, pid_t pid, int core, int signo, int exitcode)
{
pcmk_child_t *child = mainloop_child_userdata(p);
const char *name = mainloop_child_name(p);
if (signo) {
do_crm_log(((signo == SIGKILL)? LOG_WARNING : LOG_ERR),
"%s[%d] terminated with signal %d (%s)%s",
name, pid, signo, strsignal(signo),
(core? " and dumped core" : ""));
} else {
switch(exitcode) {
case CRM_EX_OK:
crm_info("%s[%d] exited with status %d (%s)",
name, pid, exitcode, crm_exit_str(exitcode));
break;
case CRM_EX_FATAL:
crm_warn("Shutting cluster down because %s[%d] had fatal failure",
name, pid);
child->flags &= ~child_respawn;
fatal_error = TRUE;
pcmk_shutdown(SIGTERM);
break;
case CRM_EX_PANIC:
crm_emerg("%s[%d] instructed the machine to reset", name, pid);
child->flags &= ~child_respawn;
fatal_error = TRUE;
pcmk__panic(__func__);
pcmk_shutdown(SIGTERM);
break;
default:
crm_err("%s[%d] exited with status %d (%s)",
name, pid, exitcode, crm_exit_str(exitcode));
break;
}
}
pcmk_process_exit(child);
}
static void
pcmk_process_exit(pcmk_child_t * child)
{
child->pid = 0;
child->flags &= ~child_active_before_startup;
child->check_count = 0;
child->respawn_count += 1;
if (child->respawn_count > MAX_RESPAWN) {
crm_err("Child respawn count exceeded by %s", child->name);
child->flags &= ~child_respawn;
}
if (shutdown_trigger) {
/* resume step-wise shutdown (returned TRUE yields no parallelizing) */
mainloop_set_trigger(shutdown_trigger);
} else if (!pcmk_is_set(child->flags, child_respawn)) {
/* nothing to do */
} else if (crm_is_true(pcmk__env_option(PCMK__ENV_FAIL_FAST))) {
crm_err("Rebooting system because of %s", child->name);
pcmk__panic(__func__);
} else if (child_liveness(child) == pcmk_rc_ok) {
crm_warn("One-off suppressing strict respawning of a child process %s,"
" appears alright per %s IPC end-point",
child->name, child->endpoint);
} else if (pcmk_is_set(child->flags, child_needs_cluster) && !pcmkd_cluster_connected()) {
crm_notice("Not respawning %s subdaemon until cluster returns",
child->name);
child->flags |= child_needs_retry;
} else {
crm_notice("Respawning %s subdaemon after unexpected exit",
child->name);
start_child(child);
}
}
static gboolean
pcmk_shutdown_worker(gpointer user_data)
{
static int phase = PCMK__NELEM(pcmk_children) - 1;
static time_t next_log = 0;
if (phase == PCMK__NELEM(pcmk_children) - 1) {
crm_notice("Shutting down Pacemaker");
pacemakerd_state = XML_PING_ATTR_PACEMAKERDSTATE_SHUTTINGDOWN;
}
for (; phase >= 0; phase--) {
pcmk_child_t *child = &(pcmk_children[phase]);
if (child->pid != 0) {
time_t now = time(NULL);
if (pcmk_is_set(child->flags, child_respawn)) {
if (child->pid == PCMK__SPECIAL_PID) {
crm_warn("The process behind %s IPC cannot be"
" terminated, so either wait the graceful"
" period of %ld s for its native termination"
" if it vitally depends on some other daemons"
" going down in a controlled way already,"
" or locate and kill the correct %s process"
" on your own; set PCMK_" PCMK__ENV_FAIL_FAST "=1"
" to avoid this altogether next time around",
child->name, (long) SHUTDOWN_ESCALATION_PERIOD,
child->command);
}
next_log = now + 30;
child->flags &= ~child_respawn;
stop_child(child, SIGTERM);
if (phase < PCMK_CHILD_CONTROLD) {
g_timeout_add(SHUTDOWN_ESCALATION_PERIOD,
escalate_shutdown, child);
}
} else if (now >= next_log) {
next_log = now + 30;
crm_notice("Still waiting for %s to terminate "
CRM_XS " pid=%lld",
child->name, (long long) child->pid);
}
return TRUE;
}
/* cleanup */
crm_debug("%s confirmed stopped", child->name);
child->pid = 0;
}
crm_notice("Shutdown complete");
pacemakerd_state = XML_PING_ATTR_PACEMAKERDSTATE_SHUTDOWNCOMPLETE;
if (!fatal_error && running_with_sbd &&
pcmk__get_sbd_sync_resource_startup() &&
!shutdown_complete_state_reported_client_closed) {
crm_notice("Waiting for SBD to pick up shutdown-complete-state.");
return TRUE;
}
+ // @COMPAT Drop shutdown delay at 3.0.0
{
const char *delay = pcmk__env_option(PCMK__ENV_SHUTDOWN_DELAY);
if(delay) {
sync();
pcmk__sleep_ms(crm_get_msec(delay));
}
}
g_main_loop_quit(mainloop);
if (fatal_error) {
crm_notice("Shutting down and staying down after fatal error");
#ifdef SUPPORT_COROSYNC
pcmkd_shutdown_corosync();
#endif
crm_exit(CRM_EX_FATAL);
}
return TRUE;
}
/* TODO once libqb is taught to juggle with IPC end-points carried over as
bare file descriptor (https://github.com/ClusterLabs/libqb/issues/325)
it shall hand over these descriptors here if/once they are successfully
pre-opened in (presumably) child_liveness(), to avoid any remaining
room for races */
// \return Standard Pacemaker return code
static int
start_child(pcmk_child_t * child)
{
uid_t uid = 0;
gid_t gid = 0;
gboolean use_valgrind = FALSE;
gboolean use_callgrind = FALSE;
const char *env_valgrind = pcmk__env_option(PCMK__ENV_VALGRIND_ENABLED);
const char *env_callgrind = pcmk__env_option(PCMK__ENV_CALLGRIND_ENABLED);
child->flags &= ~child_active_before_startup;
child->check_count = 0;
if (child->command == NULL) {
crm_info("Nothing to do for child \"%s\"", child->name);
return pcmk_rc_ok;
}
if (env_callgrind != NULL && crm_is_true(env_callgrind)) {
use_callgrind = TRUE;
use_valgrind = TRUE;
} else if (env_callgrind != NULL && strstr(env_callgrind, child->name)) {
use_callgrind = TRUE;
use_valgrind = TRUE;
} else if (env_valgrind != NULL && crm_is_true(env_valgrind)) {
use_valgrind = TRUE;
} else if (env_valgrind != NULL && strstr(env_valgrind, child->name)) {
use_valgrind = TRUE;
}
if (use_valgrind && strlen(VALGRIND_BIN) == 0) {
crm_warn("Cannot enable valgrind for %s:"
" The location of the valgrind binary is unknown", child->name);
use_valgrind = FALSE;
}
if (child->uid) {
if (crm_user_lookup(child->uid, &uid, &gid) < 0) {
crm_err("Invalid user (%s) for %s: not found", child->uid, child->name);
return EACCES;
}
crm_info("Using uid=%u and group=%u for process %s", uid, gid, child->name);
}
child->pid = fork();
CRM_ASSERT(child->pid != -1);
if (child->pid > 0) {
/* parent */
mainloop_child_add(child->pid, 0, child->name, child, pcmk_child_exit);
crm_info("Forked child %lld for process %s%s",
(long long) child->pid, child->name,
use_valgrind ? " (valgrind enabled: " VALGRIND_BIN ")" : "");
return pcmk_rc_ok;
} else {
/* Start a new session */
(void)setsid();
/* Setup the two alternate arg arrays */
opts_vgrind[0] = strdup(VALGRIND_BIN);
if (use_callgrind) {
opts_vgrind[1] = strdup("--tool=callgrind");
opts_vgrind[2] = strdup("--callgrind-out-file=" CRM_STATE_DIR "/callgrind.out.%p");
opts_vgrind[3] = strdup(child->command);
opts_vgrind[4] = NULL;
} else {
opts_vgrind[1] = strdup(child->command);
opts_vgrind[2] = NULL;
opts_vgrind[3] = NULL;
opts_vgrind[4] = NULL;
}
opts_default[0] = strdup(child->command);
if(gid) {
// Drop root group access if not needed
if (!need_root_group && (setgid(gid) < 0)) {
crm_warn("Could not set group to %d: %s", gid, strerror(errno));
}
/* Initialize supplementary groups to only those always granted to
* the user, plus haclient (so we can access IPC).
*/
if (initgroups(child->uid, gid) < 0) {
crm_err("Cannot initialize groups for %s: %s (%d)",
child->uid, pcmk_rc_str(errno), errno);
}
}
if (uid && setuid(uid) < 0) {
crm_warn("Could not set user to %s (id %d): %s",
child->uid, uid, strerror(errno));
}
pcmk__close_fds_in_child(true);
pcmk__open_devnull(O_RDONLY); // stdin (fd 0)
pcmk__open_devnull(O_WRONLY); // stdout (fd 1)
pcmk__open_devnull(O_WRONLY); // stderr (fd 2)
if (use_valgrind) {
(void)execvp(VALGRIND_BIN, opts_vgrind);
} else {
(void)execvp(child->command, opts_default);
}
crm_crit("Could not execute %s: %s", child->command, strerror(errno));
crm_exit(CRM_EX_FATAL);
}
return pcmk_rc_ok; /* never reached */
}
/*!
* \internal
* \brief Check the liveness of the child based on IPC name and PID if tracked
*
* \param[in,out] child Child tracked data
*
* \return Standard Pacemaker return code
*
* \note Return codes of particular interest include pcmk_rc_ipc_unresponsive
* indicating that no trace of IPC liveness was detected,
* pcmk_rc_ipc_unauthorized indicating that the IPC endpoint is blocked by
* an unauthorized process, and pcmk_rc_ipc_pid_only indicating that
* the child is up by PID but not IPC end-point (possibly starting).
* \note This function doesn't modify any of \p child members but \c pid,
* and is not actively toying with processes as such but invoking
* \c stop_child in one particular case (there's for some reason
* a different authentic holder of the IPC end-point).
*/
static int
child_liveness(pcmk_child_t *child)
{
uid_t cl_uid = 0;
gid_t cl_gid = 0;
const uid_t root_uid = 0;
const gid_t root_gid = 0;
const uid_t *ref_uid;
const gid_t *ref_gid;
int rc = pcmk_rc_ipc_unresponsive;
pid_t ipc_pid = 0;
if (child->endpoint == NULL
&& (child->pid <= 0 || child->pid == PCMK__SPECIAL_PID)) {
crm_err("Cannot track child %s for missing both API end-point and PID",
child->name);
rc = EINVAL; // Misuse of function when child is not trackable
} else if (child->endpoint != NULL) {
int legacy_rc = pcmk_ok;
if (child->uid == NULL) {
ref_uid = &root_uid;
ref_gid = &root_gid;
} else {
ref_uid = &cl_uid;
ref_gid = &cl_gid;
legacy_rc = pcmk_daemon_user(&cl_uid, &cl_gid);
}
if (legacy_rc < 0) {
rc = pcmk_legacy2rc(legacy_rc);
crm_err("Could not find user and group IDs for user %s: %s "
CRM_XS " rc=%d", CRM_DAEMON_USER, pcmk_rc_str(rc), rc);
} else {
rc = pcmk__ipc_is_authentic_process_active(child->endpoint,
*ref_uid, *ref_gid,
&ipc_pid);
if ((rc == pcmk_rc_ok) || (rc == pcmk_rc_ipc_unresponsive)) {
if (child->pid <= 0) {
/* If rc is pcmk_rc_ok, ipc_pid is nonzero and this
* initializes a new child. If rc is
* pcmk_rc_ipc_unresponsive, ipc_pid is zero, and we will
* investigate further.
*/
child->pid = ipc_pid;
} else if ((ipc_pid != 0) && (child->pid != ipc_pid)) {
/* An unexpected (but authorized) process is responding to
* IPC. Investigate further.
*/
rc = pcmk_rc_ipc_unresponsive;
}
}
}
}
if (rc == pcmk_rc_ipc_unresponsive) {
/* If we get here, a child without IPC is being tracked, no IPC liveness
* has been detected, or IPC liveness has been detected with an
* unexpected (but authorized) process. This is safe on FreeBSD since
* the only change possible from a proper child's PID into "special" PID
* of 1 behind more loosely related process.
*/
int ret = pcmk__pid_active(child->pid, child->name);
if (ipc_pid && ((ret != pcmk_rc_ok)
|| ipc_pid == PCMK__SPECIAL_PID
|| (pcmk__pid_active(ipc_pid,
child->name) == pcmk_rc_ok))) {
/* An unexpected (but authorized) process was detected at the IPC
* endpoint, and either it is active, or the child we're tracking is
* not.
*/
if (ret == pcmk_rc_ok) {
/* The child we're tracking is active. Kill it, and adopt the
* detected process. This assumes that our children don't fork
* (thus getting a different PID owning the IPC), but rather the
* tracking got out of sync because of some means external to
* Pacemaker, and adopting the detected process is better than
* killing it and possibly having to spawn a new child.
*/
/* not possessing IPC, afterall (what about corosync CPG?) */
stop_child(child, SIGKILL);
}
rc = pcmk_rc_ok;
child->pid = ipc_pid;
} else if (ret == pcmk_rc_ok) {
// Our tracked child's PID was found active, but not its IPC
rc = pcmk_rc_ipc_pid_only;
} else if ((child->pid == 0) && (ret == EINVAL)) {
// FreeBSD can return EINVAL
rc = pcmk_rc_ipc_unresponsive;
} else {
switch (ret) {
case EACCES:
rc = pcmk_rc_ipc_unauthorized;
break;
case ESRCH:
rc = pcmk_rc_ipc_unresponsive;
break;
default:
rc = ret;
break;
}
}
}
return rc;
}
/*!
* \internal
* \brief Initial one-off check of the pre-existing "child" processes
*
* With "child" process, we mean the subdaemon that defines an API end-point
* (all of them do as of the comment) -- the possible complement is skipped
* as it is deemed it has no such shared resources to cause conflicts about,
* hence it can presumably be started anew without hesitation.
* If that won't hold true in the future, the concept of a shared resource
* will have to be generalized beyond the API end-point.
*
* For boundary cases that the "child" is still starting (IPC end-point is yet
* to be witnessed), or more rarely (practically FreeBSD only), when there's
* a pre-existing "untrackable" authentic process, we give the situation some
* time to possibly unfold in the right direction, meaning that said socket
* will appear or the unattainable process will disappear per the observable
* IPC, respectively.
*
* \return Standard Pacemaker return code
*
* \note Since this gets run at the very start, \c respawn_count fields
* for particular children get temporarily overloaded with "rounds
* of waiting" tracking, restored once we are about to finish with
* success (i.e. returning value >=0) and will remain unrestored
* otherwise. One way to suppress liveness detection logic for
* particular child is to set the said value to a negative number.
*/
#define WAIT_TRIES 4 /* together with interleaved sleeps, worst case ~ 1s */
int
find_and_track_existing_processes(void)
{
bool wait_in_progress;
int rc;
size_t i, rounds;
for (rounds = 1; rounds <= WAIT_TRIES; rounds++) {
wait_in_progress = false;
for (i = 0; i < PCMK__NELEM(pcmk_children); i++) {
if ((pcmk_children[i].endpoint == NULL)
|| (pcmk_children[i].respawn_count < 0)) {
continue;
}
rc = child_liveness(&pcmk_children[i]);
if (rc == pcmk_rc_ipc_unresponsive) {
/* As a speculation, don't give up if there are more rounds to
* come for other reasons, but don't artificially wait just
* because of this, since we would preferably start ASAP.
*/
continue;
}
// @TODO Functionize more of this to reduce nesting
pcmk_children[i].respawn_count = rounds;
switch (rc) {
case pcmk_rc_ok:
if (pcmk_children[i].pid == PCMK__SPECIAL_PID) {
if (crm_is_true(pcmk__env_option(PCMK__ENV_FAIL_FAST))) {
crm_crit("Cannot reliably track pre-existing"
" authentic process behind %s IPC on this"
" platform and PCMK_" PCMK__ENV_FAIL_FAST
" requested",
pcmk_children[i].endpoint);
return EOPNOTSUPP;
} else if (pcmk_children[i].respawn_count == WAIT_TRIES) {
crm_notice("Assuming pre-existing authentic, though"
" on this platform untrackable, process"
" behind %s IPC is stable (was in %d"
" previous samples) so rather than"
" bailing out (PCMK_" PCMK__ENV_FAIL_FAST
" not requested), we just switch to a"
" less optimal IPC liveness monitoring"
" (not very suitable for heavy load)",
pcmk_children[i].name, WAIT_TRIES - 1);
crm_warn("The process behind %s IPC cannot be"
" terminated, so the overall shutdown"
" will get delayed implicitly (%ld s),"
" which serves as a graceful period for"
" its native termination if it vitally"
" depends on some other daemons going"
" down in a controlled way already",
pcmk_children[i].name,
(long) SHUTDOWN_ESCALATION_PERIOD);
} else {
wait_in_progress = true;
crm_warn("Cannot reliably track pre-existing"
" authentic process behind %s IPC on this"
" platform, can still disappear in %d"
" attempt(s)", pcmk_children[i].endpoint,
WAIT_TRIES - pcmk_children[i].respawn_count);
continue;
}
}
crm_notice("Tracking existing %s process (pid=%lld)",
pcmk_children[i].name,
(long long) PCMK__SPECIAL_PID_AS_0(
pcmk_children[i].pid));
pcmk_children[i].respawn_count = -1; /* 0~keep watching */
pcmk_children[i].flags |= child_active_before_startup;
break;
case pcmk_rc_ipc_pid_only:
if (pcmk_children[i].respawn_count == WAIT_TRIES) {
crm_crit("%s IPC end-point for existing authentic"
" process %lld did not (re)appear",
pcmk_children[i].endpoint,
(long long) PCMK__SPECIAL_PID_AS_0(
pcmk_children[i].pid));
return rc;
}
wait_in_progress = true;
crm_warn("Cannot find %s IPC end-point for existing"
" authentic process %lld, can still (re)appear"
" in %d attempts (?)",
pcmk_children[i].endpoint,
(long long) PCMK__SPECIAL_PID_AS_0(
pcmk_children[i].pid),
WAIT_TRIES - pcmk_children[i].respawn_count);
continue;
default:
crm_crit("Checked liveness of %s: %s " CRM_XS " rc=%d",
pcmk_children[i].name, pcmk_rc_str(rc), rc);
return rc;
}
}
if (!wait_in_progress) {
break;
}
pcmk__sleep_ms(250); // Wait a bit for changes to possibly happen
}
for (i = 0; i < PCMK__NELEM(pcmk_children); i++) {
pcmk_children[i].respawn_count = 0; /* restore pristine state */
}
g_timeout_add_seconds(PCMK_PROCESS_CHECK_INTERVAL, check_next_subdaemon,
NULL);
return pcmk_rc_ok;
}
gboolean
init_children_processes(void *user_data)
{
if (is_corosync_cluster()) {
/* Corosync clusters can drop root group access, because we set
* uidgid.gid.${gid}=1 via CMAP, which allows these processes to connect
* to corosync.
*/
need_root_group = false;
}
/* start any children that have not been detected */
for (int i = 0; i < PCMK__NELEM(pcmk_children); i++) {
if (pcmk_children[i].pid != 0) {
/* we are already tracking it */
continue;
}
start_child(&(pcmk_children[i]));
}
/* From this point on, any daemons being started will be due to
* respawning rather than node start.
*
* This may be useful for the daemons to know
*/
pcmk__set_env_option(PCMK__ENV_RESPAWNED, "true", false);
pacemakerd_state = XML_PING_ATTR_PACEMAKERDSTATE_RUNNING;
return TRUE;
}
void
pcmk_shutdown(int nsig)
{
if (shutdown_trigger == NULL) {
shutdown_trigger = mainloop_add_trigger(G_PRIORITY_HIGH, pcmk_shutdown_worker, NULL);
}
mainloop_set_trigger(shutdown_trigger);
}
void
restart_cluster_subdaemons(void)
{
for (int i = 0; i < PCMK__NELEM(pcmk_children); i++) {
if (!pcmk_is_set(pcmk_children[i].flags, child_needs_retry) || pcmk_children[i].pid != 0) {
continue;
}
crm_notice("Respawning cluster-based subdaemon: %s", pcmk_children[i].name);
if (start_child(&pcmk_children[i])) {
pcmk_children[i].flags &= ~child_needs_retry;
}
}
}
static gboolean
stop_child(pcmk_child_t * child, int signal)
{
if (signal == 0) {
signal = SIGTERM;
}
/* why to skip PID of 1?
- FreeBSD ~ how untrackable process behind IPC is masqueraded as
- elsewhere: how "init" task is designated; in particular, in systemd
arrangement of socket-based activation, this is pretty real */
if (child->command == NULL || child->pid == PCMK__SPECIAL_PID) {
crm_debug("Nothing to do for child \"%s\" (process %lld)",
child->name, (long long) PCMK__SPECIAL_PID_AS_0(child->pid));
return TRUE;
}
if (child->pid <= 0) {
crm_trace("Client %s not running", child->name);
return TRUE;
}
errno = 0;
if (kill(child->pid, signal) == 0) {
crm_notice("Stopping %s "CRM_XS" sent signal %d to process %lld",
child->name, signal, (long long) child->pid);
} else {
crm_err("Could not stop %s (process %lld) with signal %d: %s",
child->name, (long long) child->pid, signal, strerror(errno));
}
return TRUE;
}
diff --git a/doc/sphinx/Makefile.am b/doc/sphinx/Makefile.am
index dc7ded2058..e48e19a780 100644
--- a/doc/sphinx/Makefile.am
+++ b/doc/sphinx/Makefile.am
@@ -1,214 +1,222 @@
#
# Copyright 2003-2023 the Pacemaker project contributors
#
# The version control history for this file may have further details.
#
# This source code is licensed under the GNU General Public License version 2
# or later (GPLv2+) WITHOUT ANY WARRANTY.
#
include $(top_srcdir)/mk/common.mk
# Define release-related variables
include $(top_srcdir)/mk/release.mk
# Things you might want to override on the command line
# Books to generate
BOOKS ?= Clusters_from_Scratch \
Pacemaker_Administration \
Pacemaker_Development \
Pacemaker_Explained \
Pacemaker_Python_API \
Pacemaker_Remote
# Output formats to generate. Possible values:
# html (multiple HTML files)
# dirhtml (HTML files named index.html in multiple directories)
# singlehtml (a single large HTML file)
# text
# pdf
# epub
# latex
# linkcheck (not actually a format; check validity of external links)
#
# The results will end up in <book>/_build/<format>
BOOK_FORMATS ?= singlehtml
# Set to "a4paper" or "letterpaper" if building latex format
PAPER ?= letterpaper
# Additional options for sphinx-build
SPHINXFLAGS ?=
# toplevel rsync destination for www targets (without trailing slash)
RSYNC_DEST ?= root@www.clusterlabs.org:/var/www/html
# End of useful overrides
# Example scheduler transition graphs
# @TODO The original CIB XML for these is long lost. Ideally, we would recreate
# something similar and keep those here instead of the DOTs (or use a couple of
# scheduler regression test inputs instead), then regenerate the SVG
# equivalents using crm_simulate and dot when making a release.
DOTS = $(wildcard shared/images/*.dot)
# Vector sources for generated PNGs (including SVG equivalents of DOTS, created
# manually using dot)
SVGS = $(wildcard shared/images/pcmk-*.svg) \
$(DOTS:%.dot=%.svg)
# PNG images generated from SVGS
#
# These will not be accessible in a VPATH build, which will generate warnings
# when building the documentation, but the make will still succeed. It is
# nontrivial to get them working for VPATH builds and not worth the effort.
PNGS_GENERATED = $(SVGS:%.svg=%.png)
# Original PNG image sources
PNGS_Clusters_from_Scratch = $(wildcard Clusters_from_Scratch/images/*.png)
PNGS_Pacemaker_Explained = $(wildcard Pacemaker_Explained/images/*.png)
PNGS_Pacemaker_Remote = $(wildcard Pacemaker_Remote/images/*.png)
STATIC_FILES = $(wildcard _static/*.css)
EXTRA_DIST = $(wildcard */*.rst) $(DOTS) $(SVGS) \
$(PNGS_Clusters_from_Scratch) \
$(PNGS_Pacemaker_Explained) \
$(PNGS_Pacemaker_Remote) \
$(wildcard Pacemaker_Python_API/_templates/*rst) \
$(STATIC_FILES) \
conf.py.in
# recursive, preserve symlinks/permissions/times, verbose, compress,
# don't cross filesystems, sparse, show progress
RSYNC_OPTS = -rlptvzxS --progress
-PACKAGE_SERIES=$(shell echo "$VERSION" | awk -F. '{ print $1"."$2 }'`)
+PACKAGE_SERIES=$(shell echo "$VERSION" | awk -F. '{ print $1"."$2 }')
BOOK_RSYNC_DEST = $(RSYNC_DEST)/$(PACKAGE)/doc/$(PACKAGE_SERIES)
BOOK = none
DEPS_intro = shared/pacemaker-intro.rst \
$(PNGS_GENERATED)
DEPS_Clusters_from_Scratch = $(DEPS_intro) \
$(PNGS_Clusters_from_Scratch)
DEPS_Pacemaker_Administration = $(DEPS_intro)
DEPS_Pacemaker_Development =
DEPS_Pacemaker_Explained = $(DEPS_intro) \
$(PNGS_Pacemaker_Explained)
DEPS_Pacemaker_Python_API = ../../python
DEPS_Pacemaker_Remote = $(PNGS_Pacemaker_Remote)
if BUILD_SPHINX_DOCS
INKSCAPE_CMD = $(INKSCAPE) --export-dpi=90 -C
# Pattern rule to generate PNGs from SVGs
# (--export-png works with Inkscape <1.0, --export-filename with >=1.0;
# create the destination directory in case this is a VPATH build)
%.png: %.svg
$(AM_V_at)-$(MKDIR_P) "$(shell dirname "$@")"
$(AM_V_GEN) { \
$(INKSCAPE_CMD) --export-png="$@" "$<" 2>/dev/null \
|| $(INKSCAPE_CMD) --export-filename="$@" "$<"; \
} $(PCMK_quiet)
# Create a book's Sphinx configuration.
# Create the book directory in case this is a VPATH build.
$(BOOKS:%=%/conf.py): conf.py.in
$(AM_V_at)-$(MKDIR_P) "$(@:%/conf.py=%)"
$(AM_V_GEN)sed \
-e 's/%VERSION%/$(VERSION)/g' \
-e 's/%BOOK_ID%/$(@:%/conf.py=%)/g' \
-e 's/%BOOK_TITLE%/$(subst _, ,$(@:%/conf.py=%))/g' \
-e 's#%SRC_DIR%#$(abs_srcdir)#g' \
-e 's#%ABS_TOP_SRCDIR%#$(abs_top_srcdir)#g' \
+ -e 's#%CONFIGDIR%#@CONFIGDIR@#g' \
+ -e 's#%CRM_BLACKBOX_DIR%#@CRM_BLACKBOX_DIR@#g' \
+ -e 's#%CRM_DAEMON_GROUP%#@CRM_DAEMON_GROUP@#g' \
+ -e 's#%CRM_DAEMON_USER%#@CRM_DAEMON_USER@#g' \
+ -e 's#%CRM_LOG_DIR%#@CRM_LOG_DIR@#g' \
+ -e 's#%CRM_SCHEMA_DIRECTORY%#@CRM_SCHEMA_DIRECTORY@#g' \
+ -e 's#%PACEMAKER_CONFIG_DIR%#@PACEMAKER_CONFIG_DIR@#g' \
+ -e 's#%PCMK_GNUTLS_PRIORITIES%#@PCMK_GNUTLS_PRIORITIES@#g' \
$(<) > "$@"
$(BOOK)/_build: $(STATIC_FILES) $(BOOK)/conf.py $(DEPS_$(BOOK)) $(wildcard $(srcdir)/$(BOOK)/*.rst)
@echo 'Building "$(subst _, ,$(BOOK))" because of $?' $(PCMK_quiet)
$(AM_V_at)rm -rf "$@"
$(AM_V_BOOK)for format in $(BOOK_FORMATS); do \
echo -e "\n * Building $$format" $(PCMK_quiet); \
doctrees="doctrees"; \
real_format="$$format"; \
case "$$format" in \
pdf) real_format="latex" ;; \
gettext) doctrees="gettext-doctrees" ;; \
esac; \
$(SPHINX) -b "$$real_format" -d "$@/$$doctrees" \
-c "$(builddir)/$(BOOK)" \
-D latex_elements.papersize=$(PAPER) \
$(SPHINXFLAGS) \
"$(srcdir)/$(BOOK)" "$@/$$format" \
$(PCMK_quiet); \
if [ "$$format" = "pdf" ]; then \
$(MAKE) $(AM_MAKEFLAGS) -C "$@/$$format" \
all-pdf; \
fi; \
done
endif
build-$(PACKAGE_SERIES).txt: all
$(AM_V_GEN)echo "Generated on `date --utc` from version $(TAG)" > "$@"
.PHONY: books-upload
books-upload: all build-$(PACKAGE_SERIES).txt
if BUILD_SPHINX_DOCS
@echo "Uploading $(PACKAGE_SERIES) documentation set"
@for book in $(BOOKS); do \
echo " * $$book"; \
rsync $(RSYNC_OPTS) $(BOOK_FORMATS:%=$$book/_build/%) \
"$(BOOK_RSYNC_DEST)/$$book/"; \
done
@rsync $(RSYNC_OPTS) "$(builddir)/build-$(PACKAGE_SERIES).txt" \
"$(RSYNC_DEST)/$(PACKAGE)/doc"
endif
.PHONY: all-local
all-local:
if BUILD_SPHINX_DOCS
@for book in $(BOOKS); do \
$(MAKE) $(AM_MAKEFLAGS) BOOK=$$book \
PAPER="$(PAPER)" SPHINXFLAGS="$(SPHINXFLAGS)" \
BOOK_FORMATS="$(BOOK_FORMATS)" $$book/_build; \
done
endif
.PHONY: install-data-local
install-data-local: all-local
if BUILD_SPHINX_DOCS
$(AM_V_at)for book in $(BOOKS); do \
for format in $(BOOK_FORMATS); do \
formatdir="$$book/_build/$$format"; \
for f in `find "$$formatdir" -print`; do \
dname="`echo $$f | sed s:_build/::`"; \
dloc="$(DESTDIR)/$(docdir)/$$dname"; \
if [ -d "$$f" ]; then \
$(INSTALL) -d -m 755 "$$dloc"; \
else \
$(INSTALL_DATA) "$$f" "$$dloc"; \
fi \
done; \
done; \
done
endif
.PHONY: uninstall-local
uninstall-local:
if BUILD_SPHINX_DOCS
$(AM_V_at)for book in $(BOOKS); do \
rm -rf "$(DESTDIR)/$(docdir)/$$book"; \
done
endif
.PHONY: clean-local
clean-local:
$(AM_V_at)-rm -rf \
$(BOOKS:%="$(builddir)/%/_build") \
$(BOOKS:%="$(builddir)/%/conf.py") \
$(BOOKS:%="$(builddir)/%/generated") \
$(PNGS_GENERATED)
diff --git a/doc/sphinx/Pacemaker_Administration/pcs-crmsh.rst b/doc/sphinx/Pacemaker_Administration/pcs-crmsh.rst
index 61ab4e6b64..3eda60adfa 100644
--- a/doc/sphinx/Pacemaker_Administration/pcs-crmsh.rst
+++ b/doc/sphinx/Pacemaker_Administration/pcs-crmsh.rst
@@ -1,441 +1,443 @@
Quick Comparison of pcs and crm shell
-------------------------------------
``pcs`` and ``crm shell`` are two popular higher-level command-line interfaces
to Pacemaker. Each has its own syntax; this chapter gives a quick comparion of
how to accomplish the same tasks using either one. Some examples also show the
equivalent command using low-level Pacmaker command-line tools.
These examples show the simplest syntax; see the respective man pages for all
possible options.
Show Cluster Configuration and Status
#####################################
.. topic:: Show Configuration (Raw XML)
.. code-block:: none
crmsh # crm configure show xml
pcs # pcs cluster cib
pacemaker # cibadmin -Q
.. topic:: Show Configuration (Human-friendly)
.. code-block:: none
crmsh # crm configure show
pcs # pcs config
.. topic:: Show Cluster Status
.. code-block:: none
crmsh # crm status
pcs # pcs status
pacemaker # crm_mon -1
Manage Nodes
############
.. topic:: Put node "pcmk-1" in standby mode
.. code-block:: none
crmsh # crm node standby pcmk-1
pcs-0.9 # pcs cluster standby pcmk-1
pcs-0.10 # pcs node standby pcmk-1
pacemaker # crm_standby -N pcmk-1 -v on
.. topic:: Remove node "pcmk-1" from standby mode
.. code-block:: none
crmsh # crm node online pcmk-1
pcs-0.9 # pcs cluster unstandby pcmk-1
pcs-0.10 # pcs node unstandby pcmk-1
pacemaker # crm_standby -N pcmk-1 -v off
Manage Cluster Properties
#########################
.. topic:: Set the "stonith-enabled" cluster property to "false"
.. code-block:: none
crmsh # crm configure property stonith-enabled=false
pcs # pcs property set stonith-enabled=false
pacemaker # crm_attribute -n stonith-enabled -v false
Show Resource Agent Information
###############################
.. topic:: List Resource Agent (RA) Classes
.. code-block:: none
crmsh # crm ra classes
pcs # pcs resource standards
pacmaker # crm_resource --list-standards
.. topic:: List Available Resource Agents (RAs) by Standard
.. code-block:: none
crmsh # crm ra list ocf
pcs # pcs resource agents ocf
pacemaker # crm_resource --list-agents ocf
.. topic:: List Available Resource Agents (RAs) by OCF Provider
.. code-block:: none
crmsh # crm ra list ocf pacemaker
pcs # pcs resource agents ocf:pacemaker
pacemaker # crm_resource --list-agents ocf:pacemaker
.. topic:: List Available Resource Agent Parameters
.. code-block:: none
crmsh # crm ra info IPaddr2
pcs # pcs resource describe IPaddr2
pacemaker # crm_resource --show-metadata ocf:heartbeat:IPaddr2
You can also use the full ``class:provider:type`` format with crmsh and pcs if
multiple RAs with the same name are available.
.. topic:: Show Available Fence Agent Parameters
.. code-block:: none
crmsh # crm ra info stonith:fence_ipmilan
pcs # pcs stonith describe fence_ipmilan
Manage Resources
################
.. topic:: Create a Resource
.. code-block:: none
-
- crmsh # crm configure primitive ClusterIP ocf:heartbeat:IPaddr2 \
- params ip=192.168.122.120 cidr_netmask=24 \
- op monitor interval=30s
+ crmsh # crm configure primitive ClusterIP IPaddr2 params ip=192.168.122.120 cidr_netmask=24
pcs # pcs resource create ClusterIP IPaddr2 ip=192.168.122.120 cidr_netmask=24
-pcs determines the standard and provider (``ocf:heartbeat``) automatically
-since ``IPaddr2`` is unique, and automatically creates operations (including
+Both crmsh and pcs determine the standard and provider (``ocf:heartbeat``) automatically
+since ``IPaddr2`` is unique, and automatically create operations (including
monitor) based on the agent's meta-data.
.. topic:: Show Configuration of All Resources
.. code-block:: none
crmsh # crm configure show
pcs-0.9 # pcs resource show --full
pcs-0.10 # pcs resource config
.. topic:: Show Configuration of One Resource
.. code-block:: none
crmsh # crm configure show ClusterIP
pcs-0.9 # pcs resource show ClusterIP
pcs-0.10 # pcs resource config ClusterIP
.. topic:: Show Configuration of Fencing Resources
.. code-block:: none
crmsh # crm resource status
pcs-0.9 # pcs stonith show --full
pcs-0.10 # pcs stonith config
.. topic:: Start a Resource
.. code-block:: none
crmsh # crm resource start ClusterIP
pcs # pcs resource enable ClusterIP
pacemaker # crm_resource -r ClusterIP --set-parameter target-role --meta -v Started
.. topic:: Stop a Resource
.. code-block:: none
crmsh # crm resource stop ClusterIP
pcs # pcs resource disable ClusterIP
pacemaker # crm_resource -r ClusterIP --set-parameter target-role --meta -v Stopped
.. topic:: Remove a Resource
.. code-block:: none
crmsh # crm configure delete ClusterIP
pcs # pcs resource delete ClusterIP
.. topic:: Modify a Resource's Instance Parameters
.. code-block:: none
crmsh # crm resource param ClusterIP set clusterip_hash=sourceip
pcs # pcs resource update ClusterIP clusterip_hash=sourceip
pacemaker # crm_resource -r ClusterIP --set-parameter clusterip_hash -v sourceip
crmsh also has an `edit` command which edits the simplified CIB syntax
(same commands as the command line) via a configurable text editor.
.. topic:: Modify a Resource's Instance Parameters Interactively
.. code-block:: none
crmsh # crm configure edit ClusterIP
Using the interactive shell mode of crmsh, multiple changes can be
edited and verified before committing to the live configuration:
.. topic:: Make Multiple Configuration Changes Interactively
.. code-block:: none
crmsh # crm configure
crmsh # edit
crmsh # verify
crmsh # commit
.. topic:: Delete a Resource's Instance Parameters
.. code-block:: none
crmsh # crm resource param ClusterIP delete nic
pcs # pcs resource update ClusterIP nic=
pacemaker # crm_resource -r ClusterIP --delete-parameter nic
.. topic:: List Current Resource Defaults
.. code-block:: none
crmsh # crm configure show type:rsc_defaults
pcs # pcs resource defaults
pacemaker # cibadmin -Q --scope rsc_defaults
.. topic:: Set Resource Defaults
.. code-block:: none
crmsh # crm configure rsc_defaults resource-stickiness=100
pcs # pcs resource defaults resource-stickiness=100
.. topic:: List Current Operation Defaults
.. code-block:: none
crmsh # crm configure show type:op_defaults
pcs # pcs resource op defaults
pacemaker # cibadmin -Q --scope op_defaults
.. topic:: Set Operation Defaults
.. code-block:: none
crmsh # crm configure op_defaults timeout=240s
pcs # pcs resource op defaults timeout=240s
.. topic:: Enable Resource Agent Tracing for a Resource
.. code-block:: none
crmsh # crm resource trace Website
.. topic:: Clear Fail Counts for a Resource
.. code-block:: none
crmsh # crm resource cleanup Website
pcs # pcs resource cleanup Website
pacemaker # crm_resource --cleanup -r Website
.. topic:: Create a Clone Resource
.. code-block:: none
crmsh # crm configure clone WebIP ClusterIP meta globally-unique=true clone-max=2 clone-node-max=2
pcs # pcs resource clone ClusterIP globally-unique=true clone-max=2 clone-node-max=2
.. topic:: Create a Promotable Clone Resource
.. code-block:: none
crmsh # crm configure ms WebDataClone WebData \
meta master-max=1 master-node-max=1 \
clone-max=2 clone-node-max=1 notify=true
+ crmsh # crm configure clone WebDataClone WebData \
+ meta promotable=true \
+ promoted-max=1 promoted-node-max=1 \
+ clone-max=2 clone-node-max=1 notify=true
pcs-0.9 # pcs resource master WebDataClone WebData \
master-max=1 master-node-max=1 \
clone-max=2 clone-node-max=1 notify=true
pcs-0.10 # pcs resource promotable WebData WebDataClone \
promoted-max=1 promoted-node-max=1 \
clone-max=2 clone-node-max=1 notify=true
+crmsh supports both ways ('configure ms' is deprecated) to configure promotable clone since crmsh 4.4.0.
pcs will generate the clone name automatically if it is omitted from the
command line.
Manage Constraints
##################
.. topic:: Create a Colocation Constraint
.. code-block:: none
crmsh # crm configure colocation website-with-ip INFINITY: WebSite ClusterIP
pcs # pcs constraint colocation add ClusterIP with WebSite INFINITY
.. topic:: Create a Colocation Constraint Based on Role
.. code-block:: none
crmsh # crm configure colocation another-ip-with-website inf: AnotherIP WebSite:Master
pcs # pcs constraint colocation add Started AnotherIP with Promoted WebSite INFINITY
.. topic:: Create an Ordering Constraint
.. code-block:: none
crmsh # crm configure order apache-after-ip mandatory: ClusterIP WebSite
pcs # pcs constraint order ClusterIP then WebSite
.. topic:: Create an Ordering Constraint Based on Role
.. code-block:: none
crmsh # crm configure order ip-after-website Mandatory: WebSite:Master AnotherIP
pcs # pcs constraint order promote WebSite then start AnotherIP
.. topic:: Create a Location Constraint
.. code-block:: none
crmsh # crm configure location prefer-pcmk-1 WebSite 50: pcmk-1
pcs # pcs constraint location WebSite prefers pcmk-1=50
.. topic:: Create a Location Constraint Based on Role
.. code-block:: none
crmsh # crm configure location prefer-pcmk-1 WebSite rule role=Master 50: \#uname eq pcmk-1
pcs # pcs constraint location WebSite rule role=Promoted 50 \#uname eq pcmk-1
.. topic:: Move a Resource to a Specific Node (by Creating a Location Constraint)
.. code-block:: none
crmsh # crm resource move WebSite pcmk-1
pcs # pcs resource move WebSite pcmk-1
pacemaker # crm_resource -r WebSite --move -N pcmk-1
.. topic:: Move a Resource Away from Its Current Node (by Creating a Location Constraint)
.. code-block:: none
crmsh # crm resource ban Website pcmk-2
pcs # pcs resource ban Website pcmk-2
pacemaker # crm_resource -r WebSite --move
.. topic:: Remove any Constraints Created by Moving a Resource
.. code-block:: none
crmsh # crm resource unmove WebSite
pcs # pcs resource clear WebSite
pacemaker # crm_resource -r WebSite --clear
Advanced Configuration
######################
Manipulate Configuration Elements by Type
_________________________________________
.. topic:: List Constraints with IDs
.. code-block:: none
pcs # pcs constraint list --full
.. topic:: Remove Constraint by ID
.. code-block:: none
pcs # pcs constraint remove cli-ban-Website-on-pcmk-1
crmsh # crm configure remove cli-ban-Website-on-pcmk-1
crmsh's `show` and `edit` commands can be used to manage resources and
constraints by type:
.. topic:: Show Configuration Elements
.. code-block:: none
crmsh # crm configure show type:primitive
crmsh # crm configure edit type:colocation
Batch Changes
_____________
.. topic:: Make Multiple Changes and Apply Together
.. code-block:: none
crmsh # crm
crmsh # cib new drbd_cfg
crmsh # configure primitive WebData ocf:linbit:drbd params drbd_resource=wwwdata \
op monitor interval=60s
crmsh # configure ms WebDataClone WebData meta master-max=1 master-node-max=1 \
clone-max=2 clone-node-max=1 notify=true
crmsh # cib commit drbd_cfg
crmsh # quit
pcs # pcs cluster cib drbd_cfg
pcs # pcs -f drbd_cfg resource create WebData ocf:linbit:drbd drbd_resource=wwwdata \
op monitor interval=60s
pcs-0.9 # pcs -f drbd_cfg resource master WebDataClone WebData \
master-max=1 master-node-max=1 clone-max=2 clone-node-max=1 notify=true
pcs-0.10 # pcs -f drbd_cfg resource promotable WebData WebDataClone \
promoted-max=1 promoted-node-max=1 clone-max=2 clone-node-max=1 notify=true
pcs # pcs cluster cib-push drbd_cfg
Template Creation
_________________
.. topic:: Create Resource Template Based on Existing Primitives of Same Type
.. code-block:: none
crmsh # crm configure assist template ClusterIP AdminIP
Log Analysis
____________
.. topic:: Show Information About Recent Cluster Events
.. code-block:: none
crmsh # crm history
crmsh # peinputs
crmsh # transition pe-input-10
crmsh # transition log pe-input-10
Configuration Scripts
_____________________
.. topic:: Script Multiple-step Cluster Configurations
.. code-block:: none
crmsh # crm script show apache
crmsh # crm script run apache \
id=WebSite \
install=true \
virtual-ip:ip=192.168.0.15 \
database:id=WebData \
database:install=true
diff --git a/doc/sphinx/Pacemaker_Explained/options.rst b/doc/sphinx/Pacemaker_Explained/cluster-options.rst
similarity index 99%
rename from doc/sphinx/Pacemaker_Explained/options.rst
rename to doc/sphinx/Pacemaker_Explained/cluster-options.rst
index d38a2ab892..77bd7e65bc 100644
--- a/doc/sphinx/Pacemaker_Explained/options.rst
+++ b/doc/sphinx/Pacemaker_Explained/cluster-options.rst
@@ -1,921 +1,921 @@
Cluster-Wide Configuration
--------------------------
.. index::
pair: XML element; cib
pair: XML element; configuration
Configuration Layout
####################
The cluster is defined by the Cluster Information Base (CIB), which uses XML
notation. The simplest CIB, an empty one, looks like this:
.. topic:: An empty configuration
.. code-block:: xml
<cib crm_feature_set="3.6.0" validate-with="pacemaker-3.5" epoch="1" num_updates="0" admin_epoch="0">
<configuration>
<crm_config/>
<nodes/>
<resources/>
<constraints/>
</configuration>
<status/>
</cib>
The empty configuration above contains the major sections that make up a CIB:
* ``cib``: The entire CIB is enclosed with a ``cib`` element. Certain
fundamental settings are defined as attributes of this element.
* ``configuration``: This section -- the primary focus of this document --
contains traditional configuration information such as what resources the
cluster serves and the relationships among them.
* ``crm_config``: cluster-wide configuration options
* ``nodes``: the machines that host the cluster
* ``resources``: the services run by the cluster
* ``constraints``: indications of how resources should be placed
* ``status``: This section contains the history of each resource on each
node. Based on this data, the cluster can construct the complete current
state of the cluster. The authoritative source for this section is the
local executor (pacemaker-execd process) on each cluster node, and the
cluster will occasionally repopulate the entire section. For this reason,
it is never written to disk, and administrators are advised against
modifying it in any way.
In this document, configuration settings will be described as properties or
options based on how they are defined in the CIB:
* Properties are XML attributes of an XML element.
* Options are name-value pairs expressed as ``nvpair`` child elements of an XML
element.
Normally, you will use command-line tools that abstract the XML, so the
distinction will be unimportant; both properties and options are cluster
settings you can tweak.
Configuration Value Types
#########################
Throughout this document, configuration values will be designated as having one
of the following types:
.. list-table:: **Configuration Value Types**
:class: longtable
:widths: 1 3
:header-rows: 1
* - Type
- Description
* - .. _boolean:
.. index::
pair: type; boolean
boolean
- Case-insensitive text value where ``1``, ``yes``, ``y``, ``on``,
and ``true`` evaluate as true and ``0``, ``no``, ``n``, ``off``,
``false``, and unset evaluate as false
* - .. _date_time:
.. index::
pair: type; date/time
date/time
- Textual timestamp like ``Sat Dec 21 11:47:45 2013``
* - .. _duration:
.. index::
pair: type; duration
duration
- A time duration, specified either like a :ref:`timeout <timeout>` or an
`ISO 8601 duration <https://en.wikipedia.org/wiki/ISO_8601#Durations>`_.
A duration may be up to approximately 49 days but is intended for much
smaller time periods.
* - .. _enumeration:
.. index::
pair: type; enumeration
enumeration
- Text that must be one of a set of defined values (which will be listed
in the description)
* - .. _integer:
.. index::
pair: type; integer
integer
- 32-bit signed integer value (-2,147,483,648 to 2,147,483,647)
* - .. _nonnegative_integer:
.. index::
pair: type; nonnegative integer
nonnegative integer
- 32-bit nonnegative integer value (0 to 2,147,483,647)
* - .. _port:
.. index::
pair: type; port
port
- Integer TCP port number (0 to 65535)
* - .. _score:
.. index::
pair: type; score
score
- A Pacemaker score can be an integer between -1,000,000 and 1,000,000, or
a string alias: ``INFINITY`` or ``+INFINITY`` is equivalent to
1,000,000, ``-INFINITY`` is equivalent to -1,000,000, and ``red``,
``yellow``, and ``green`` are equivalent to integers as described in
:ref:`node-health`.
* - .. _text:
.. index::
pair: type; text
text
- A text string
* - .. _timeout:
.. index::
pair: type; timeout
timeout
- A time duration, specified as a bare number (in which case it is
considered to be in seconds) or a number with a unit (``ms`` or ``msec``
for milliseconds, ``us`` or ``usec`` for microseconds, ``s`` or ``sec``
for seconds, ``m`` or ``min`` for minutes, ``h`` or ``hr`` for hours)
optionally with whitespace before and/or after the number.
* - .. _version:
.. index::
pair: type; version
version
- Version number (any combination of alphanumeric characters, dots, and
dashes, starting with a number).
Scores
______
Scores are integral to how Pacemaker works. Practically everything from moving
a resource to deciding which resource to stop in a degraded cluster is achieved
by manipulating scores in some way.
Scores are calculated per resource and node. Any node with a negative score for
a resource can't run that resource. The cluster places a resource on the node
with the highest score for it.
Score addition and subtraction follow these rules:
* Any value (including ``INFINITY``) - ``INFINITY`` = ``-INFINITY``
* ``INFINITY`` + any value other than ``-INFINITY`` = ``INFINITY``
.. note::
What if you want to use a score higher than 1,000,000? Typically this possibility
arises when someone wants to base the score on some external metric that might
go above 1,000,000.
The short answer is you can't.
The long answer is it is sometimes possible work around this limitation
creatively. You may be able to set the score to some computed value based on
the external metric rather than use the metric directly. For nodes, you can
store the metric as a node attribute, and query the attribute when computing
the score (possibly as part of a custom resource agent).
CIB Properties
##############
Certain settings are defined by CIB properties (that is, attributes of the
``cib`` tag) rather than with the rest of the cluster configuration in the
``configuration`` section.
The reason is simply a matter of parsing. These options are used by the
configuration database which is, by design, mostly ignorant of the content it
holds. So the decision was made to place them in an easy-to-find location.
.. list-table:: **CIB Properties**
:class: longtable
:widths: 2 2 2 5
:header-rows: 1
* - Name
- Type
- Default
- Description
* - .. _admin_epoch:
.. index::
pair: admin_epoch; cib
admin_epoch
- :ref:`nonnegative integer <nonnegative_integer>`
- 0
- When a node joins the cluster, the cluster asks the node with the
highest (``admin_epoch``, ``epoch``, ``num_updates``) tuple to replace
the configuration on all the nodes -- which makes setting them correctly
very important. ``admin_epoch`` is never modified by the cluster; you
can use this to make the configurations on any inactive nodes obsolete.
* - .. _epoch:
.. index::
pair: epoch; cib
epoch
- :ref:`nonnegative integer <nonnegative_integer>`
- 0
- The cluster increments this every time the CIB's configuration section
is updated.
* - .. _num_updates:
.. index::
pair: num_updates; cib
num_updates
- :ref:`nonnegative integer <nonnegative_integer>`
- 0
- The cluster increments this every time the CIB's configuration or status
sections are updated, and resets it to 0 when epoch changes.
* - .. _validate_with:
.. index::
pair: validate-with; cib
validate-with
- :ref:`enumeration <enumeration>`
-
- Determines the type of XML validation that will be done on the
configuration. Allowed values are ``none`` (in which case the cluster
will not require that updates conform to expected syntax) and the base
names of schema files installed on the local machine (for example,
"pacemaker-3.9")
* - .. _remote_tls_port:
.. index::
pair: remote-tls-port; cib
remote-tls-port
- :ref:`port <port>`
-
- If set, the CIB manager will listen for anonymously encrypted remote
connections on this port, to allow CIB administration from hosts not in
the cluster. No key is used, so this should be used only on a protected
network where man-in-the-middle attacks can be avoided.
* - .. _remote_clear_port:
.. index::
pair: remote-clear-port; cib
remote-clear-port
- :ref:`port <port>`
-
- If set to a TCP port number, the CIB manager will listen for remote
connections on this port, to allow for CIB administration from hosts not
in the cluster. No encryption is used, so this should be used only on a
protected network.
* - .. _cib_last_written:
.. index::
pair: cib-last-written; cib
cib-last-written
- :ref:`date/time <date_time>`
-
- Indicates when the configuration was last written to disk. Maintained by
the cluster; for informational purposes only.
* - .. _have_quorum:
.. index::
pair: have-quorum; cib
have-quorum
- :ref:`boolean <boolean>`
-
- Indicates whether the cluster has quorum. If false, the cluster's
response is determined by ``no-quorum-policy`` (see below). Maintained
by the cluster.
* - .. _dc_uuid:
.. index::
pair: dc-uuid; cib
dc-uuid
- :ref:`text <text>`
-
- Node ID of the cluster's current designated controller (DC). Used and
maintained by the cluster.
.. _cluster_options:
Cluster Options
###############
Cluster options, as you might expect, control how the cluster behaves when
confronted with various situations.
They are grouped into sets within the ``crm_config`` section. In advanced
configurations, there may be more than one set. (This will be described later
in the chapter on :ref:`rules` where we will show how to have the cluster use
different sets of options during working hours than during weekends.) For now,
we will describe the simple case where each option is present at most once.
You can obtain an up-to-date list of cluster options, including their default
values, by running the ``man pacemaker-schedulerd`` and
``man pacemaker-controld`` commands.
.. list-table:: **Cluster Options**
:class: longtable
:widths: 2 2 2 5
:header-rows: 1
* - Name
- Type
- Default
- Description
* - .. _cluster_name:
.. index::
pair: cluster option; cluster-name
cluster-name
- :ref:`text <text>`
-
- An (optional) name for the cluster as a whole. This is mostly for users'
convenience for use as desired in administration, but can be used in the
Pacemaker configuration in :ref:`rules` (as the ``#cluster-name``
:ref:`node attribute <node-attribute-expressions-special>`). It may also
be used by higher-level tools when displaying cluster information, and
by certain resource agents (for example, the ``ocf:heartbeat:GFS2``
agent stores the cluster name in filesystem meta-data).
* - .. _dc_version:
.. index::
pair: cluster option; dc-version
dc-version
- :ref:`version <version>`
- *detected*
- Version of Pacemaker on the cluster's designated controller (DC).
Maintained by the cluster, and intended for diagnostic purposes.
* - .. _cluster_infrastructure:
.. index::
pair: cluster option; cluster-infrastructure
cluster-infrastructure
- :ref:`text <text>`
- *detected*
- The messaging layer with which Pacemaker is currently running.
Maintained by the cluster, and intended for informational and diagnostic
purposes.
* - .. _no_quorum_policy:
.. index::
pair: cluster option; no-quorum-policy
no-quorum-policy
- :ref:`enumeration <enumeration>`
- stop
- What to do when the cluster does not have quorum. Allowed values:
* ``ignore:`` continue all resource management
* ``freeze:`` continue resource management, but don't recover resources
from nodes not in the affected partition
* ``stop:`` stop all resources in the affected cluster partition
* ``demote:`` demote promotable resources and stop all other resources
in the affected cluster partition *(since 2.0.5)*
* ``suicide:`` fence all nodes in the affected cluster partition
* - .. _batch_limit:
.. index::
pair: cluster option; batch-limit
batch-limit
- :ref:`integer <integer>`
- 0
- The maximum number of actions that the cluster may execute in parallel
across all nodes. The ideal value will depend on the speed and load
of your network and cluster nodes. If zero, the cluster will impose a
dynamically calculated limit only when any node has high load. If -1,
the cluster will not impose any limit.
* - .. _migration_limit:
.. index::
pair: cluster option; migration-limit
migration-limit
- :ref:`integer <integer>`
- -1
- The number of :ref:`live migration <live-migration>` actions that the
cluster is allowed to execute in parallel on a node. A value of -1 means
unlimited.
* - .. _symmetric_cluster:
.. index::
pair: cluster option; symmetric-cluster
symmetric-cluster
- :ref:`boolean <boolean>`
- true
- If true, resources can run on any node by default. If false, a resource
is allowed to run on a node only if a
:ref:`location constraint <location-constraint>` enables it.
* - .. _stop_all_resources:
.. index::
pair: cluster option; stop-all-resources
stop-all-resources
- :ref:`boolean <boolean>`
- false
- Whether all resources should be disallowed from running (can be useful
during maintenance or troubleshooting)
* - .. _stop_orphan_resources:
.. index::
pair: cluster option; stop-orphan-resources
stop-orphan-resources
- :ref:`boolean <boolean>`
- true
- Whether resources that have been deleted from the configuration should
be stopped. This value takes precedence over
:ref:`is-managed <is_managed>` (that is, even unmanaged resources will
be stopped when orphaned if this value is ``true``).
* - .. _stop_orphan_actions:
.. index::
pair: cluster option; stop-orphan-actions
stop-orphan-actions
- :ref:`boolean <boolean>`
- true
- Whether recurring :ref:`operations <operation>` that have been deleted
from the configuration should be cancelled
* - .. _start_failure_is_fatal:
.. index::
pair: cluster option; start-failure-is-fatal
start-failure-is-fatal
- :ref:`boolean <boolean>`
- true
- Whether a failure to start a resource on a particular node prevents
further start attempts on that node. If ``false``, the cluster will
decide whether the node is still eligible based on the resource's
current failure count and ``migration-threshold``.
* - .. _enable_startup_probes:
.. index::
pair: cluster option; enable-startup-probes
enable-startup-probes
- :ref:`boolean <boolean>`
- true
- Whether the cluster should check the pre-existing state of resources
when the cluster starts
* - .. _maintenance_mode:
.. index::
pair: cluster option; maintenance-mode
maintenance-mode
- :ref:`boolean <boolean>`
- false
- If true, the cluster will not start or stop any resource in the cluster,
and any recurring operations (expect those specifying ``role`` as
``Stopped``) will be paused. If true, this overrides the
:ref:`maintenance <node_maintenance>` node attribute,
:ref:`is-managed <is_managed>` and :ref:`maintenance <rsc_maintenance>`
resource meta-attributes, and :ref:`enabled <op_enabled>` operation
meta-attribute.
* - .. _stonith_enabled:
.. index::
pair: cluster option; stonith-enabled
stonith-enabled
- :ref:`boolean <boolean>`
- true
- Whether the cluster is allowed to fence nodes (for example, failed nodes
and nodes with resources that can't be stopped).
If true, at least one fence device must be configured before resources
are allowed to run.
If false, unresponsive nodes are immediately assumed to be running no
resources, and resource recovery on online nodes starts without any
further protection (which can mean *data loss* if the unresponsive node
still accesses shared storage, for example). See also the
:ref:`requires <requires>` resource meta-attribute.
* - .. _stonith_action:
.. index::
pair: cluster option; stonith-action
stonith-action
- :ref:`enumeration <enumeration>`
- reboot
- Action the cluster should send to the fence agent when a node must be
fenced. Allowed values are ``reboot``, ``off``, and (for legacy agents
only) ``poweroff``.
* - .. _stonith_timeout:
.. index::
pair: cluster option; stonith-timeout
stonith-timeout
- :ref:`duration <duration>`
- 60s
- How long to wait for ``on``, ``off``, and ``reboot`` fence actions to
complete by default.
* - .. _stonith_max_attempts:
.. index::
pair: cluster option; stonith-max-attempts
stonith-max-attempts
- :ref:`score <score>`
- 10
- How many times fencing can fail for a target before the cluster will no
longer immediately re-attempt it. Any value below 1 will be ignored, and
the default will be used instead.
* - .. _stonith_watchdog_timeout:
.. index::
pair: cluster option; stonith-watchdog-timeout
stonith-watchdog-timeout
- :ref:`timeout <timeout>`
- 0
- If nonzero, and the cluster detects ``have-watchdog`` as ``true``, then
watchdog-based self-fencing will be performed via SBD when fencing is
required, without requiring a fencing resource explicitly configured.
If this is set to a positive value, unseen nodes are assumed to
self-fence within this much time.
**Warning:** It must be ensured that this value is larger than the
``SBD_WATCHDOG_TIMEOUT`` environment variable on all nodes. Pacemaker
verifies the settings individually on all nodes and prevents startup or
shuts down if configured wrongly on the fly. It is strongly recommended
that ``SBD_WATCHDOG_TIMEOUT`` be set to the same value on all nodes.
If this is set to a negative value, and ``SBD_WATCHDOG_TIMEOUT`` is set,
twice that value will be used.
**Warning:** In this case, it is essential (and currently not verified
by pacemaker) that ``SBD_WATCHDOG_TIMEOUT`` is set to the same value on
all nodes.
* - .. _concurrent-fencing:
.. index::
pair: cluster option; concurrent-fencing
concurrent-fencing
- :ref:`boolean <boolean>`
- false
- Whether the cluster is allowed to initiate multiple fence actions
concurrently. Fence actions initiated externally, such as via the
``stonith_admin`` tool or an application such as DLM, or by the fencer
itself such as recurring device monitors and ``status`` and ``list``
commands, are not limited by this option.
* - .. _fence_reaction:
.. index::
pair: cluster option; fence-reaction
fence-reaction
- :ref:`enumeration <enumeration>`
- stop
- How should a cluster node react if notified of its own fencing? A
cluster node may receive notification of its own fencing if fencing is
misconfigured, or if fabric fencing is in use that doesn't cut cluster
communication. Allowed values are ``stop`` to attempt to immediately
stop Pacemaker and stay stopped, or ``panic`` to attempt to immediately
reboot the local node, falling back to stop on failure. The default is
likely to be changed to ``panic`` in a future release. *(since 2.0.3)*
* - .. _priority_fencing_delay:
.. index::
pair: cluster option; priority-fencing-delay
priority-fencing-delay
- :ref:`duration <duration>`
- 0
- Apply this delay to any fencing targeting the lost nodes with the
highest total resource priority in case we don't have the majority of
the nodes in our cluster partition, so that the more significant nodes
potentially win any fencing match (especially meaningful in a
split-brain of a 2-node cluster). A promoted resource instance takes the
resource's priority plus 1 if the resource's priority is not 0. Any
static or random delays introduced by ``pcmk_delay_base`` and
``pcmk_delay_max`` configured for the corresponding fencing resources
will be added to this delay. This delay should be significantly greater
than (safely twice) the maximum delay from those parameters. *(since
2.0.4)*
* - .. _node_pending_timeout:
.. index::
pair: cluster option; node-pending-timeout
node-pending-timeout
- :ref:`duration <duration>`
- - 2h
+ - 0
- Fence nodes that do not join the controller process group within this
much time after joining the cluster, to allow the cluster to continue
- managing resources. A value of 0 means never fence pending nodes.
- *(since 2.1.7)*
+ managing resources. A value of 0 means never fence pending nodes. Setting the value to 2h means fence nodes after 2 hours.
+ *(since 2.1.7)*
* - .. _cluster_delay:
.. index::
pair: cluster option; cluster-delay
cluster-delay
- :ref:`duration <duration>`
- 60s
- If the DC requires an action to be executed on another node, it will
consider the action failed if it does not get a response from the other
node within this time (beyond the action's own timeout). The ideal value
will depend on the speed and load of your network and cluster nodes.
* - .. _dc_deadtime:
.. index::
pair: cluster option; dc-deadtime
dc-deadtime
- :ref:`duration <duration>`
- 20s
- How long to wait for a response from other nodes when electing a DC. The
ideal value will depend on the speed and load of your network and
cluster nodes.
* - .. _cluster_ipc_limit:
.. index::
pair: cluster option; cluster-ipc-limit
cluster-ipc-limit
- :ref:`nonnegative integer <nonnegative_integer>`
- 500
- The maximum IPC message backlog before one cluster daemon will
disconnect another. This is of use in large clusters, for which a good
value is the number of resources in the cluster multiplied by the number
of nodes. The default of 500 is also the minimum. Raise this if you see
"Evicting client" log messages for cluster daemon process IDs.
* - .. _pe_error_series_max:
.. index::
pair: cluster option; pe-error-series-max
pe-error-series-max
- :ref:`integer <integer>`
- -1
- The number of scheduler inputs resulting in errors to save. These inputs
can be helpful during troubleshooting and when reporting issues. A
negative value means save all inputs, and 0 means save none.
* - .. _pe_warn_series_max:
.. index::
pair: cluster option; pe-warn-series-max
pe-warn-series-max
- :ref:`integer <integer>`
- 5000
- The number of scheduler inputs resulting in warnings to save. These
inputs can be helpful during troubleshooting and when reporting issues.
A negative value means save all inputs, and 0 means save none.
* - .. _pe_input_series_max:
.. index::
pair: cluster option; pe-input-series-max
pe-input-series-max
- :ref:`integer <integer>`
- 4000
- The number of "normal" scheduler inputs to save. These inputs can be
helpful during troubleshooting and when reporting issues. A negative
value means save all inputs, and 0 means save none.
* - .. _enable_acl:
.. index::
pair: cluster option; enable-acl
enable-acl
- :ref:`boolean <boolean>`
- false
- Whether :ref:`access control lists <acl>` should be used to authorize
CIB modifications
* - .. _placement_strategy:
.. index::
pair: cluster option; placement-strategy
placement-strategy
- :ref:`enumeration <enumeration>`
- default
- How the cluster should assign resources to nodes (see
:ref:`utilization`). Allowed values are ``default``, ``utilization``,
``balanced``, and ``minimal``.
* - .. _node_health_strategy:
.. index::
pair: cluster option; node-health-strategy
node-health-strategy
- :ref:`enumeration <enumeration>`
- none
- How the cluster should react to :ref:`node health <node-health>`
attributes. Allowed values are ``none``, ``migrate-on-red``,
``only-green``, ``progressive``, and ``custom``.
* - .. _node_health_base:
.. index::
pair: cluster option; node-health-base
node-health-base
- :ref:`score <score>`
- 0
- The base health score assigned to a node. Only used when
``node-health-strategy`` is ``progressive``.
* - .. _node_health_green:
.. index::
pair: cluster option; node-health-green
node-health-green
- :ref:`score <score>`
- 0
- The score to use for a node health attribute whose value is ``green``.
Only used when ``node-health-strategy`` is ``progressive`` or
``custom``.
* - .. _node_health_yellow:
.. index::
pair: cluster option; node-health-yellow
node-health-yellow
- :ref:`score <score>`
- 0
- The score to use for a node health attribute whose value is ``yellow``.
Only used when ``node-health-strategy`` is ``progressive`` or
``custom``.
* - .. _node_health_red:
.. index::
pair: cluster option; node-health-red
node-health-red
- :ref:`score <score>`
- 0
- The score to use for a node health attribute whose value is ``red``.
Only used when ``node-health-strategy`` is ``progressive`` or
``custom``.
* - .. _cluster_recheck_interval:
.. index::
pair: cluster option; cluster-recheck-interval
cluster-recheck-interval
- :ref:`duration <duration>`
- 15min
- Pacemaker is primarily event-driven, and looks ahead to know when to
recheck the cluster for failure timeouts and most time-based rules
*(since 2.0.3)*. However, it will also recheck the cluster after this
amount of inactivity. This has two goals: rules with ``date_spec`` are
only guaranteed to be checked this often, and it also serves as a
fail-safe for some kinds of scheduler bugs. A value of 0 disables this
polling.
* - .. _shutdown_lock:
.. index::
pair: cluster option; shutdown-lock
shutdown-lock
- :ref:`boolean <boolean>`
- false
- The default of false allows active resources to be recovered elsewhere
when their node is cleanly shut down, which is what the vast majority of
users will want. However, some users prefer to make resources highly
available only for failures, with no recovery for clean shutdowns. If
this option is true, resources active on a node when it is cleanly shut
down are kept "locked" to that node (not allowed to run elsewhere) until
they start again on that node after it rejoins (or for at most
``shutdown-lock-limit``, if set). Stonith resources and Pacemaker Remote
connections are never locked. Clone and bundle instances and the
promoted role of promotable clones are currently never locked, though
support could be added in a future release. Locks may be manually
cleared using the ``--refresh`` option of ``crm_resource`` (both the
resource and node must be specified; this works with remote nodes if
their connection resource's ``target-role`` is set to ``Stopped``, but
not if Pacemaker Remote is stopped on the remote node without disabling
the connection resource). *(since 2.0.4)*
* - .. _shutdown_lock_limit:
.. index::
pair: cluster option; shutdown-lock-limit
shutdown-lock-limit
- :ref:`duration <duration>`
- 0
- If ``shutdown-lock`` is true, and this is set to a nonzero time
duration, locked resources will be allowed to start after this much time
has passed since the node shutdown was initiated, even if the node has
not rejoined. (This works with remote nodes only if their connection
resource's ``target-role`` is set to ``Stopped``.) *(since 2.0.4)*
* - .. _remove_after_stop:
.. index::
pair: cluster option; remove-after-stop
remove-after-stop
- :ref:`boolean <boolean>`
- false
- *Deprecated* Whether the cluster should remove resources from
Pacemaker's executor after they are stopped. Values other than the
default are, at best, poorly tested and potentially dangerous. This
option is deprecated and will be removed in a future release.
* - .. _startup_fencing:
.. index::
pair: cluster option; startup-fencing
startup-fencing
- :ref:`boolean <boolean>`
- true
- *Advanced Use Only:* Whether the cluster should fence unseen nodes at
start-up. Setting this to false is unsafe, because the unseen nodes
could be active and running resources but unreachable. ``dc-deadtime``
acts as a grace period before this fencing, since a DC must be elected
to schedule fencing.
* - .. _election_timeout:
.. index::
pair: cluster option; election-timeout
election-timeout
- :ref:`duration <duration>`
- 2min
- *Advanced Use Only:* If a winner is not declared within this much time
of starting an election, the node that initiated the election will
declare itself the winner.
* - .. _shutdown_escalation:
.. index::
pair: cluster option; shutdown-escalation
shutdown-escalation
- :ref:`duration <duration>`
- 20min
- *Advanced Use Only:* The controller will exit immediately if a shutdown
does not complete within this much time.
* - .. _join_integration_timeout:
.. index::
pair: cluster option; join-integration-timeout
join-integration-timeout
- :ref:`duration <duration>`
- 3min
- *Advanced Use Only:* If you need to adjust this value, it probably
indicates the presence of a bug.
* - .. _join_finalization_timeout:
.. index::
pair: cluster option; join-finalization-timeout
join-finalization-timeout
- :ref:`duration <duration>`
- 30min
- *Advanced Use Only:* If you need to adjust this value, it probably
indicates the presence of a bug.
* - .. _transition_delay:
.. index::
pair: cluster option; transition-delay
transition-delay
- :ref:`duration <duration>`
- 0s
- *Advanced Use Only:* Delay cluster recovery for the configured interval
to allow for additional or related events to occur. This can be useful
if your configuration is sensitive to the order in which ping updates
arrive. Enabling this option will slow down cluster recovery under all
conditions.
diff --git a/doc/sphinx/Pacemaker_Explained/index.rst b/doc/sphinx/Pacemaker_Explained/index.rst
index e3b7e9e55e..63387f3421 100644
--- a/doc/sphinx/Pacemaker_Explained/index.rst
+++ b/doc/sphinx/Pacemaker_Explained/index.rst
@@ -1,41 +1,42 @@
Pacemaker Explained
===================
*Configuring Pacemaker Clusters*
Abstract
--------
This document definitively explains Pacemaker's features and capabilities,
particularly the XML syntax used in Pacemaker's Cluster Information Base (CIB).
Table of Contents
-----------------
.. toctree::
:maxdepth: 3
:numbered:
intro
- options
+ local-options
+ cluster-options
nodes
resources
operations
constraints
fencing
alerts
rules
collective
reusing-configuration
utilization
acls
status
multi-site-clusters
ap-samples
Index
-----
* :ref:`genindex`
* :ref:`search`
diff --git a/doc/sphinx/Pacemaker_Explained/local-options.rst b/doc/sphinx/Pacemaker_Explained/local-options.rst
new file mode 100644
index 0000000000..91eda6632d
--- /dev/null
+++ b/doc/sphinx/Pacemaker_Explained/local-options.rst
@@ -0,0 +1,515 @@
+Host-Local Configuration
+------------------------
+
+.. index::
+ pair: XML element; configuration
+
+.. note:: Directory and file paths below may differ on your system depending on
+ your Pacemaker build settings. Check your Pacemaker configuration
+ file to find the correct paths.
+
+Pacemaker supports several host-local configuration options. These options can
+be configured on each node in the main Pacemaker configuration file
+(|PCMK_CONFIG_FILE|) in the format ``<NAME>="<VALUE>"``. They work by setting
+environment variables when Pacemaker daemons start up.
+
+.. list-table:: **Local Options**
+ :class: longtable
+ :widths: 2 2 2 5
+ :header-rows: 1
+
+ * - Name
+ - Type
+ - Default
+ - Description
+ * - .. _pcmk_logfacility:
+
+ .. index::
+ pair: node option; PCMK_logfacility
+
+ PCMK_logfacility
+ - :ref:`enumeration <enumeration>`
+ - daemon
+ - Enable logging via the system log or journal, using the specified log
+ facility. Messages sent here are of value to all Pacemaker
+ administrators. This can be disabled using ``none``, but that is not
+ recommended. Allowed values:
+
+ * ``none``
+ * ``daemon``
+ * ``user``
+ * ``local0``
+ * ``local1``
+ * ``local2``
+ * ``local3``
+ * ``local4``
+ * ``local5``
+ * ``local6``
+ * ``local7``
+
+ * - .. _pcmk_logpriority:
+
+ .. index::
+ pair:: node option; PCMK_logpriority
+
+ PCMK_logpriority
+ - :ref:`enumeration <enumeration>`
+ - notice
+ - Unless system logging is disabled using ``PCMK_logfacility=none``,
+ messages of the specified log severity and higher will be sent to the
+ system log. The default is appropriate for most installations. Allowed
+ values:
+
+ * ``emerg``
+ * ``alert``
+ * ``crit``
+ * ``error``
+ * ``warning``
+ * ``notice``
+ * ``info``
+ * ``debug``
+
+ * - .. _pcmk_logfile:
+
+ .. index::
+ pair:: node option; PCMK_logfile
+
+ PCMK_logfile
+ - :ref:`text <text>`
+ - |PCMK_LOG_FILE|
+ - Unless set to ``none``, more detailed log messages will be sent to the
+ specified file (in addition to the system log, if enabled). These
+ messages may have extended information, and will include messages of info
+ severity. This log is of more use to developers and advanced system
+ administrators, and when reporting problems.
+
+ * - .. _pcmk_logfile_mode:
+
+ .. index::
+ pair:: node option; PCMK_logfile_mode
+
+ PCMK_logfile_mode
+ - :ref:`text <text>`
+ - 0660
+ - Pacemaker will set the permissions on the detail log to this value (see
+ ``chmod(1)``).
+
+ * - .. _pcmk_debug:
+
+ .. index::
+ pair:: node option; PCMK_debug
+
+ PCMK_debug
+ - :ref:`enumeration <enumeration>`
+ - no
+ - Whether to send debug severity messages to the detail log. This may be
+ set for all subsystems (``yes`` or ``no``) or for specific (comma-
+ separated) subsystems. Allowed subsystems are:
+
+ * ``pacemakerd``
+ * ``pacemaker-attrd``
+ * ``pacemaker-based``
+ * ``pacemaker-controld``
+ * ``pacemaker-execd``
+ * ``pacemaker-fenced``
+ * ``pacemaker-schedulerd``
+
+ Example: ``PCMK_debug="pacemakerd,pacemaker-execd"``
+
+ * - .. _pcmk_stderr:
+
+ .. index::
+ pair:: node option; PCMK_stderr
+
+ PCMK_stderr
+ - :ref:`boolean <boolean>`
+ - no
+ - *Advanced Use Only:* Whether to send daemon log messages to stderr. This
+ would be useful only during troubleshooting, when starting Pacemaker
+ manually on the command line.
+
+ Setting this option in the configuration file is pointless, since the
+ file is not read when starting Pacemaker manually. However, it can be set
+ directly as an environment variable on the command line.
+
+ * - .. _pcmk_trace_functions:
+
+ .. index::
+ pair:: node option; PCMK_trace_functions
+
+ PCMK_trace_functions
+ - :ref:`text <text>`
+ -
+ - *Advanced Use Only:* Send debug and trace severity messages from these
+ (comma-separated) source code functions to the detail log.
+
+ Example:
+ ``PCMK_trace_functions="func1,func2"``
+
+ * - .. _pcmk_trace_files:
+
+ .. index::
+ pair:: node option; PCMK_trace_files
+
+ PCMK_trace_files
+ - :ref:`text <text>`
+ -
+ - *Advanced Use Only:* Send debug and trace severity messages from all
+ functions in these (comma-separated) source file names to the detail log.
+
+ Example: ``PCMK_trace_files="file1.c,file2.c"``
+
+ * - .. _pcmk_trace_formats:
+
+ .. index::
+ pair:: node option; PCMK_trace_formats
+
+ PCMK_trace_formats
+ - :ref:`text <text>`
+ -
+ - *Advanced Use Only:* Send trace severity messages that are generated by
+ these (comma-separated) format strings in the source code to the detail
+ log.
+
+ Example: ``PCMK_trace_formats="Error: %s (%d)"``
+
+ * - .. _pcmk_trace_tags:
+
+ .. index::
+ pair:: node option; PCMK_trace_tags
+
+ PCMK_trace_tags
+ - :ref:`text <text>`
+ -
+ - *Advanced Use Only:* Send debug and trace severity messages related to
+ these (comma-separated) resource IDs to the detail log.
+
+ Example: ``PCMK_trace_tags="client-ip,dbfs"``
+
+ * - .. _pcmk_blackbox:
+
+ .. index::
+ pair:: node option; PCMK_blackbox
+
+ PCMK_blackbox
+ - :ref:`enumeration <enumeration>`
+ - no
+ - *Advanced Use Only:* Enable blackbox logging globally (``yes`` or ``no``)
+ or by subsystem. A blackbox contains a rolling buffer of all logs (of all
+ severities). Blackboxes are stored under |CRM_BLACKBOX_DIR| by default,
+ by default, and their contents can be viewed using the ``qb-blackbox(8)``
+ command.
+
+ The blackbox recorder can be enabled at start using this variable, or at
+ runtime by sending a Pacemaker subsystem daemon process a ``SIGUSR1`` or
+ ``SIGTRAP`` signal, and disabled by sending ``SIGUSR2`` (see
+ ``kill(1)``). The blackbox will be written after a crash, assertion
+ failure, or ``SIGTRAP`` signal.
+
+ See :ref:`PCMK_debug <pcmk_debug>` for allowed subsystems.
+
+ Example:
+ ``PCMK_blackbox="pacemakerd,pacemaker-execd"``
+
+ * - .. _pcmk_trace_blackbox:
+
+ .. index::
+ pair:: node option; PCMK_trace_blackbox
+
+ PCMK_trace_blackbox
+ - :ref:`enumeration <enumeration>`
+ -
+ - *Advanced Use Only:* Write a blackbox whenever the message at the
+ specified function and line is logged. Multiple entries may be comma-
+ separated.
+
+ Example: ``PCMK_trace_blackbox="remote.c:144,remote.c:149"``
+
+ * - .. _pcmk_node_start_state:
+
+ .. index::
+ pair:: node option; PCMK_node_start_state
+
+ PCMK_node_start_state
+ - :ref:`enumeration <enumeration>`
+ - default
+ - By default, the local host will join the cluster in an online or standby
+ state when Pacemaker first starts depending on whether it was previously
+ put into standby mode. If this variable is set to ``standby`` or
+ ``online``, it will force the local host to join in the specified state.
+
+ * - .. _pcmk_node_action_limit:
+
+ .. index::
+ pair:: node option; PCMK_node_action_limit
+
+ PCMK_node_action_limit
+ - :ref:`nonnegative integer <nonnegative_integer>`
+ -
+ - Specify the maximum number of jobs that can be scheduled on this node. If
+ set, this overrides the ``node-action-limit`` cluster property for this
+ node.
+
+ * - .. _pcmk_shutdown_delay:
+
+ .. index::
+ pair:: node option; PCMK_shutdown_delay
+
+ PCMK_shutdown_delay
+ - :ref:`timeout <timeout>`
+ -
+ - Specify a delay before shutting down ``pacemakerd`` after shutting down
+ all other Pacemaker daemons.
+
+ * - .. _pcmk_fail_fast:
+
+ .. index::
+ pair:: node option; PCMK_fail_fast
+
+ PCMK_fail_fast
+ - :ref:`boolean <boolean>`
+ - no
+ - By default, if a Pacemaker subsystem crashes, the main ``pacemakerd``
+ process will attempt to restart it. If this variable is set to ``yes``,
+ ``pacemakerd`` will panic the local host instead.
+
+ * - .. _pcmk_panic_action:
+
+ .. index::
+ pair:: node option; PCMK_panic_action
+
+ PCMK_panic_action
+ - :ref:`enumeration <enumeration>`
+ - reboot
+ - Pacemaker will panic the local host under certain conditions. By default,
+ this means rebooting the host. This variable can change that behavior: if
+ ``crash``, trigger a kernel crash (useful if you want a kernel dump to
+ investigate); if ``sync-reboot`` or ``sync-crash``, synchronize
+ filesystems before rebooting the host or triggering a kernel crash. The
+ sync values are more likely to preserve log messages, but with the risk
+ that the host may be left active if the synchronization hangs.
+
+ * - .. _pcmk_authkey_location:
+
+ .. index::
+ pair:: node option; PCMK_authkey_location
+
+ PCMK_authkey_location
+ - :ref:`text <text>`
+ - |PCMK_AUTHKEY_FILE|
+ - Use the contents of this file as the authorization key to use with
+ Pacemaker Remote connections. This file must be readable by Pacemaker
+ daemons (that is, it must allow read permissions to either the
+ |CRM_DAEMON_USER| user or the |CRM_DAEMON_GROUP| group), and its contents
+ must be identical on all nodes.
+
+ * - .. _pcmk_remote_address:
+
+ .. index::
+ pair:: node option; PCMK_remote_address
+
+ PCMK_remote_address
+ - :ref:`text <text>`
+ -
+ - By default, if the Pacemaker Remote service is run on the local node, it
+ will listen for connections on all IP addresses. This may be set to one
+ address to listen on instead, as a resolvable hostname or as a numeric
+ IPv4 or IPv6 address. When resolving names or listening on all addresses,
+ IPv6 will be preferred if available. When listening on an IPv6 address,
+ IPv4 clients will be supported via IPv4-mapped IPv6 addresses.
+
+ Example: ``PCMK_remote_address="192.0.2.1"``
+
+ * - .. _pcmk_remote_port:
+
+ .. index::
+ pair:: node option; PCMK_remote_port
+
+ PCMK_remote_port
+ - :ref:`port <port>`
+ - 3121
+ - Use this TCP port number for Pacemaker Remote node connections. This
+ value must be the same on all nodes.
+
+ * - .. _pcmk_remote_pid1:
+
+ .. index::
+ pair:: node option; PCMK_remote_pid1
+
+ PCMK_remote_pid1
+ - :ref:`enumeration <enumeration>`
+ - default
+ - *Advanced Use Only:* When a bundle resource's ``run-command`` option is
+ left to default, Pacemaker Remote runs as PID 1 in the bundle's
+ containers. When it does so, it loads environment variables from the
+ container's |PCMK_INIT_ENV_FILE| and performs the PID 1 responsibility of
+ reaping dead subprocesses.
+
+ This option controls whether those actions are performed when Pacemaker
+ Remote is not running as PID 1. It is intended primarily for developer
+ testing but can be useful when ``run-command`` is set to a separate,
+ custom PID 1 process that launches Pacemaker Remote.
+
+ * ``full``: Pacemaker Remote loads environment variables from
+ |PCMK_INIT_ENV_FILE| and reaps dead subprocesses.
+ * ``vars``: Pacemaker Remote loads environment variables from
+ |PCMK_INIT_ENV_FILE| but does not reap dead subprocesses.
+ * ``default``: Pacemaker Remote performs neither action.
+
+ If Pacemaker Remote is running as PID 1, this option is ignored, and the
+ behavior is the same as for ``full``.
+
+ * - .. _pcmk_tls_priorities:
+
+ .. index::
+ pair:: node option; PCMK_tls_priorities
+
+ PCMK_tls_priorities
+ - :ref:`text <text>`
+ - |PCMK_GNUTLS_PRIORITIES|
+ - *Advanced Use Only:* These GnuTLS cipher priorities will be used for TLS
+ connections (whether for Pacemaker Remote connections or remote CIB
+ access, when enabled). See:
+
+ https://gnutls.org/manual/html_node/Priority-Strings.html
+
+ Pacemaker will append ``":+ANON-DH"`` for remote CIB access and
+ ``":+DHE-PSK:+PSK"`` for Pacemaker Remote connections, as they are
+ required for the respective functionality.
+
+ Example:
+ ``PCMK_tls_priorities="SECURE128:+SECURE192"``
+
+ * - .. _pcmk_dh_min_bits:
+
+ .. index::
+ pair:: node option; PCMK_dh_min_bits
+
+ PCMK_dh_min_bits
+ - :ref:`nonnegative integer <nonnegative_integer>`
+ - 0 (no minimum)
+ - *Advanced Use Only:* Set a lower bound on the bit length of the prime
+ number generated for Diffie-Hellman parameters needed by TLS connections.
+ The default is no minimum.
+
+ The server (Pacemaker Remote daemon, or CIB manager configured to accept
+ remote clients) will use this value to provide a floor for the value
+ recommended by the GnuTLS library. The library will only accept a limited
+ number of specific values, which vary by library version, so setting
+ these is recommended only when required for compatibility with specific
+ client versions.
+
+ Clients (connecting cluster nodes or remote CIB commands) will require
+ that the server use a prime of at least this size. This is recommended
+ only when the value must be lowered in order for the client's GnuTLS
+ library to accept a connection to an older server.
+
+ * - .. _pcmk_dh_max_bits:
+
+ .. index::
+ pair:: node option; PCMK_dh_max_bits
+
+ PCMK_dh_max_bits
+ - :ref:`nonnegative integer <nonnegative_integer>`
+ - 0 (no maximum)
+ - *Advanced Use Only:* Set an upper bound on the bit length of the prime
+ number generated for Diffie-Hellman parameters needed by TLS connections.
+ The default is no maximum.
+
+ The server (Pacemaker Remote daemon, or CIB manager configured to accept
+ remote clients) will use this value to provide a ceiling for the value
+ recommended by the GnuTLS library. The library will only accept a limited
+ number of specific values, which vary by library version, so setting
+ these is recommended only when required for compatibility with specific
+ client versions.
+
+ Clients do not use ``PCMK_dh_max_bits``.
+
+ * - .. _pcmk_ipc_type:
+
+ .. index::
+ pair:: node option; PCMK_ipc_type
+
+ PCMK_ipc_type
+ - :ref:`enumeration <enumeration>`
+ - shared-mem
+ - *Advanced Use Only:* Force use of a particular IPC method. Allowed values:
+
+ * ``shared-mem``
+ * ``socket``
+ * ``posix``
+ * ``sysv``
+
+ * - .. _pcmk_ipc_buffer:
+
+ .. index::
+ pair:: node option; PCMK_ipc_buffer
+
+ PCMK_ipc_buffer
+ - :ref:`nonnegative integer <nonnegative_integer>`
+ - 131072
+ - *Advanced Use Only:* Specify an IPC buffer size in bytes. This can be
+ useful when connecting to large clusters that result in messages
+ exceeding the default size (which will also result in log messages
+ referencing this variable).
+
+ * - .. _pcmk_cluster_type:
+
+ .. index::
+ pair:: node option; PCMK_cluster_type
+
+ PCMK_cluster_type
+ - :ref:`enumeration <enumeration>`
+ - corosync
+ - *Advanced Use Only:* Specify the cluster layer to be used. If unset,
+ Pacemaker will detect and use a supported cluster layer, if available.
+ Currently, ``"corosync"`` is the only supported cluster layer. If
+ multiple layers are supported in the future, this will allow overriding
+ Pacemaker's automatic detection to select a specific one.
+
+ * - .. _pcmk_schema_directory:
+
+ .. index::
+ pair:: node option; PCMK_schema_directory
+
+ PCMK_schema_directory
+ - :ref:`text <text>`
+ - |CRM_SCHEMA_DIRECTORY|
+ - *Advanced Use Only:* Specify an alternate location for RNG schemas and
+ XSL transforms.
+
+ * - .. _pcmk_valgrind_enabled:
+
+ .. index::
+ pair:: node option; PCMK_valgrind_enabled
+
+ PCMK_valgrind_enabled
+ - :ref:`enumeration <enumeration>`
+ - no
+ - *Advanced Use Only:* Whether subsystem daemons should be run under
+ ``valgrind``. Allowed values are the same as for ``PCMK_debug``.
+
+ * - .. _pcmk_callgrind_enabled:
+
+ .. index::
+ pair:: node option; PCMK_callgrind_enabled
+
+ PCMK_callgrind_enabled
+ - :ref:`enumeration <enumeration>`
+ - no
+ - *Advanced Use Only:* Whether subsystem daemons should be run under
+ ``valgrind`` with the ``callgrind`` tool enabled. Allowed values are the
+ same as for ``PCMK_debug``.
+
+ * - .. _valgrind_opts:
+
+ .. index::
+ pair:: node option; VALGRIND_OPTS
+
+ VALGRIND_OPTS
+ - :ref:`text <text>`
+ -
+ - *Advanced Use Only:* Pass these options to valgrind, when enabled (see
+ ``valgrind(1)``). ``"--vgdb=no"`` should usually be specified because
+ ``pacemaker-execd`` can lower privileges when executing commands, which
+ would otherwise leave a bunch of unremovable files in ``/tmp``.
diff --git a/doc/sphinx/conf.py.in b/doc/sphinx/conf.py.in
index 7d843d82b7..7d74cbf05b 100644
--- a/doc/sphinx/conf.py.in
+++ b/doc/sphinx/conf.py.in
@@ -1,319 +1,328 @@
""" Sphinx configuration for Pacemaker documentation
"""
__copyright__ = "Copyright 2020-2023 the Pacemaker project contributors"
__license__ = "GNU General Public License version 2 or later (GPLv2+) WITHOUT ANY WARRANTY"
# This file is execfile()d with the current directory set to its containing dir.
#
# Note that not all possible configuration values are present in this
# autogenerated file.
#
# All configuration values have a default; values that are commented out
# serve to show the default.
import datetime
import os
import sys
# Variables that can be used later in this file
authors = "the Pacemaker project contributors"
year = datetime.datetime.now().year
doc_license = "Creative Commons Attribution-ShareAlike International Public License"
doc_license += " version 4.0 or later (CC-BY-SA v4.0+)"
# rST markup to insert at beginning of every document; mainly used for
#
# .. |<abbr>| replace:: <Full text>
#
# where occurrences of |<abbr>| in the rST will be substituted with <Full text>
rst_prolog="""
.. |CFS_DISTRO| replace:: AlmaLinux
.. |CFS_DISTRO_VER| replace:: 9
+.. |CRM_BLACKBOX_DIR| replace:: ``%CRM_BLACKBOX_DIR%``
+.. |CRM_DAEMON_GROUP| replace:: ``%CRM_DAEMON_GROUP%``
+.. |CRM_DAEMON_USER| replace:: ``%CRM_DAEMON_USER%``
+.. |CRM_SCHEMA_DIRECTORY| replace:: %CRM_SCHEMA_DIRECTORY%
+.. |PCMK_AUTHKEY_FILE| replace:: %PACEMAKER_CONFIG_DIR%/authkey
+.. |PCMK_CONFIG_FILE| replace:: ``%CONFIGDIR%/pacemaker``
+.. |PCMK_INIT_ENV_FILE| replace:: ``%PACEMAKER_CONFIG_DIR%/pcmk-init.env``
+.. |PCMK_LOG_FILE| replace:: %CRM_LOG_DIR%/pacemaker.log
+.. |PCMK_GNUTLS_PRIORITIES| replace:: %PCMK_GNUTLS_PRIORITIES%
.. |REMOTE_DISTRO| replace:: AlmaLinux
.. |REMOTE_DISTRO_VER| replace:: 9
"""
# If extensions (or modules to document with autodoc) are in another directory,
# add these directories to sys.path here. If the directory is relative to the
# documentation root, use os.path.abspath to make it absolute, like shown here.
sys.path.insert(0, os.path.abspath('%ABS_TOP_SRCDIR%/python'))
# -- General configuration -----------------------------------------------------
# If your documentation needs a minimal Sphinx version, state it here.
needs_sphinx = '1.0'
# Add any Sphinx extension module names here, as strings. They can be extensions
# coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
extensions = ['sphinx.ext.autodoc',
'sphinx.ext.autosummary']
# Add any paths that contain templates here, relative to this directory.
templates_path = ['_templates']
# The suffix of source filenames.
source_suffix = '.rst'
# The encoding of source files.
#source_encoding = 'utf-8-sig'
# The master toctree document.
master_doc = 'index'
# General information about the project.
project = '%BOOK_ID%'
copyright = "2009-%s %s. Released under the terms of the %s" % (year, authors, doc_license)
# The version info for the project you're documenting, acts as replacement for
# |version| and |release|, also used in various other places throughout the
# built documents.
#
# The full version, including alpha/beta/rc tags.
release = '%VERSION%'
# The short X.Y version.
version = release.rsplit('.', 1)[0]
# The language for content autogenerated by Sphinx. Refer to documentation
# for a list of supported languages.
#language = None
# There are two options for replacing |today|: either, you set today to some
# non-false value, then it is used:
#today = ''
# Else, today_fmt is used as the format for a strftime call.
#today_fmt = '%B %d, %Y'
# List of patterns, relative to source directory, that match files and
# directories to ignore when looking for source files.
exclude_patterns = ['_build']
# The reST default role (used for this markup: `text`) to use for all documents.
#default_role = None
# If true, '()' will be appended to :func: etc. cross-reference text.
#add_function_parentheses = True
# If true, the current module name will be prepended to all description
# unit titles (such as .. function::).
#add_module_names = True
# If true, sectionauthor and moduleauthor directives will be shown in the
# output. They are ignored by default.
#show_authors = False
# The name of the Pygments (syntax highlighting) style to use.
pygments_style = 'vs'
# A list of ignored prefixes for module index sorting.
#modindex_common_prefix = []
# -- Options for HTML output ---------------------------------------------------
# The theme to use for HTML and HTML Help pages. See the documentation for
# a list of builtin themes.
html_theme = 'pyramid'
# Theme options are theme-specific and customize the look and feel of a theme
# further. For a list of options available for each theme, see the
# documentation.
#html_theme_options = {}
# Add any paths that contain custom themes here, relative to this directory.
#html_theme_path = []
html_style = 'pacemaker.css'
# The name for this set of Sphinx documents. If None, it defaults to
# "<project> v<release> documentation".
html_title = "%BOOK_TITLE%"
# A shorter title for the navigation bar. Default is the same as html_title.
#html_short_title = None
# The name of an image file (relative to this directory) to place at the top
# of the sidebar.
#html_logo = None
# The name of an image file (within the static path) to use as favicon of the
# docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32
# pixels large.
#html_favicon = None
# Add any paths that contain custom static files (such as style sheets) here,
# relative to this directory. They are copied after the builtin static files,
# so a file named "default.css" will overwrite the builtin "default.css".
html_static_path = [ '%SRC_DIR%/_static' ]
# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
# using the given strftime format.
#html_last_updated_fmt = '%b %d, %Y'
# If true, SmartyPants will be used to convert quotes and dashes to
# typographically correct entities.
#html_use_smartypants = True
# Custom sidebar templates, maps document names to template names.
#html_sidebars = {}
# Additional templates that should be rendered to pages, maps page names to
# template names.
#html_additional_pages = {}
# If false, no module index is generated.
#html_domain_indices = True
# If false, no index is generated.
#html_use_index = True
# If true, the index is split into individual pages for each letter.
#html_split_index = False
# If true, links to the reST sources are added to the pages.
#html_show_sourcelink = True
# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
#html_show_sphinx = True
# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
#html_show_copyright = True
# If true, an OpenSearch description file will be output, and all pages will
# contain a <link> tag referring to it. The value of this option must be the
# base URL from which the finished HTML is served.
#html_use_opensearch = ''
# This is the file name suffix for HTML files (e.g. ".xhtml").
#html_file_suffix = None
# Output file base name for HTML help builder.
htmlhelp_basename = 'Pacemakerdoc'
# -- Options for LaTeX output --------------------------------------------------
latex_engine = "xelatex"
latex_elements = {
# The paper size ('letterpaper' or 'a4paper').
#'papersize': 'letterpaper',
# The font size ('10pt', '11pt' or '12pt').
#'pointsize': '10pt',
# Additional stuff for the LaTeX preamble.
#'preamble': '',
}
# Grouping the document tree into LaTeX files. List of tuples
# (source start file, target name, title, author, documentclass [howto/manual]).
latex_documents = [
('index', '%BOOK_ID%.tex', '%BOOK_TITLE%', authors, 'manual'),
]
# The name of an image file (relative to this directory) to place at the top of
# the title page.
#latex_logo = None
# For "manual" documents, if this is true, then toplevel headings are parts,
# not chapters.
#latex_use_parts = False
# If true, show page references after internal links.
#latex_show_pagerefs = False
# If true, show URL addresses after external links.
#latex_show_urls = False
# Documents to append as an appendix to all manuals.
#latex_appendices = []
# If false, no module index is generated.
#latex_domain_indices = True
# -- Options for manual page output --------------------------------------------
# One entry per manual page. List of tuples
# (source start file, name, description, authors, manual section).
man_pages = [
('index', '%BOOK_ID%', 'Part of the Pacemaker documentation set', [authors], 8)
]
# If true, show URL addresses after external links.
#man_show_urls = False
# -- Options for Texinfo output ------------------------------------------------
# Grouping the document tree into Texinfo files. List of tuples
# (source start file, target name, title, author,
# dir menu entry, description, category)
texinfo_documents = [
('index', '%BOOK_ID%', '%BOOK_TITLE%', authors, '%BOOK_TITLE%',
'Pacemaker is an advanced, scalable high-availability cluster resource manager.',
'Miscellaneous'),
]
# Documents to append as an appendix to all manuals.
#texinfo_appendices = []
# If false, no module index is generated.
#texinfo_domain_indices = True
# How to display URL addresses: 'footnote', 'no', or 'inline'.
#texinfo_show_urls = 'footnote'
# -- Options for Epub output ---------------------------------------------------
# Bibliographic Dublin Core info.
epub_title = '%BOOK_TITLE%'
epub_author = authors
epub_publisher = 'ClusterLabs.org'
epub_copyright = copyright
# The language of the text. It defaults to the language option
# or en if the language is not set.
#epub_language = ''
# The scheme of the identifier. Typical schemes are ISBN or URL.
epub_scheme = 'URL'
# The unique identifier of the text. This can be a ISBN number
# or the project homepage.
epub_identifier = 'https://www.clusterlabs.org/pacemaker/doc/2.1/%BOOK_ID%/epub/%BOOK_ID%.epub'
# A unique identification for the text.
epub_uid = 'ClusterLabs.org-Pacemaker-%BOOK_ID%'
# A tuple containing the cover image and cover page html template filenames.
#epub_cover = ()
# HTML files that should be inserted before the pages created by sphinx.
# The format is a list of tuples containing the path and title.
#epub_pre_files = []
# HTML files that should be inserted after the pages created by sphinx.
# The format is a list of tuples containing the path and title.
#epub_post_files = []
# A list of files that should not be packed into the epub file.
epub_exclude_files = [
'_static/doctools.js',
'_static/jquery.js',
'_static/searchtools.js',
'_static/underscore.js',
'_static/basic.css',
'_static/websupport.js',
'search.html',
]
# The depth of the table of contents in toc.ncx.
#epub_tocdepth = 3
# Allow duplicate toc entries.
#epub_tocdup = True
autosummary_generate = True
diff --git a/etc/sysconfig/pacemaker.in b/etc/sysconfig/pacemaker.in
index 041da7195f..0c3609d8e7 100644
--- a/etc/sysconfig/pacemaker.in
+++ b/etc/sysconfig/pacemaker.in
@@ -1,338 +1,393 @@
#
# Pacemaker start-up configuration
#
# This file contains environment variables that affect Pacemaker behavior.
# They are not options stored in the Cluster Information Base (CIB) because
# they may be needed before the CIB is available.
#
## Logging
# PCMK_logfacility
#
# Enable logging via the system log or journal, using the specified log
# facility. Messages sent here are of value to all Pacemaker administrators.
# This can be disabled using "none", but that is not recommended. Allowed
# values:
#
# none
# daemon
# user
# local0
# local1
# local2
# local3
# local4
# local5
# local6
# local7
#
# Default: PCMK_logfacility="daemon"
# PCMK_logpriority
#
# Unless system logging is disabled using PCMK_logfacility=none, messages of
# the specified log severity and higher will be sent to the system log. The
# default is appropriate for most installations. Allowed values:
#
# emerg
# alert
# crit
# error
# warning
# notice
# info
# debug
#
# Default: PCMK_logpriority="notice"
# PCMK_logfile
#
# Unless set to "none", more detailed log messages will be sent to the
# specified file (in addition to the system log, if enabled). These messages
# may have extended information, and will include messages of info severity.
# This log is of more use to developers and advanced system administrators, and
# when reporting problems.
#
# Default: PCMK_logfile="@CRM_LOG_DIR@/pacemaker.log"
# PCMK_logfile_mode
#
# Pacemaker will set the permissions on the detail log to this value (see
# chmod(1)).
#
# Default: PCMK_logfile_mode="0660"
# PCMK_debug (Advanced Use Only)
#
# Whether to send debug severity messages to the detail log.
# This may be set for all subsystems (yes or no) or for specific
# (comma-separated) subsystems. Allowed subsystems are:
#
# pacemakerd
# pacemaker-attrd
# pacemaker-based
# pacemaker-controld
# pacemaker-execd
# pacemaker-fenced
# pacemaker-schedulerd
#
# Default: PCMK_debug="no"
# Example: PCMK_debug="pacemakerd,pacemaker-execd"
+# PCMK_stderr (Advanced Use Only)
+#
+# Whether to send daemon log messages to stderr. This would be useful only
+# during troubleshooting, when starting Pacemaker manually on the command line.
+#
+# Setting this option in this file is pointless, since this file is not read
+# when starting Pacemaker manually. However, it can be set directly as an
+# environment variable on the command line.
+#
+# Default: PCMK_stderr="no"
+
# PCMK_trace_functions (Advanced Use Only)
#
# Send debug and trace severity messages from these (comma-separated)
# source code functions to the detail log.
#
# Default: PCMK_trace_functions=""
# Example: PCMK_trace_functions="unpack_colocation_set,pcmk__cmp_instance"
# PCMK_trace_files (Advanced Use Only)
#
# Send debug and trace severity messages from all functions in these
# (comma-separated) source file names to the detail log.
#
# Default: PCMK_trace_files=""
# Example: PCMK_trace_files="remote.c,watchdog.c"
# PCMK_trace_formats (Advanced Use Only)
#
# Send trace severity messages that are generated by these (comma-separated)
# format strings in the source code to the detail log.
#
# Default: PCMK_trace_formats=""
# Example: PCMK_trace_formats="TLS handshake failed: %s (%d)"
# PCMK_trace_tags (Advanced Use Only)
#
# Send debug and trace severity messages related to these (comma-separated)
# resource IDs to the detail log.
#
# Default: PCMK_trace_tags=""
# Example: PCMK_trace_tags="client-ip,dbfs"
# PCMK_blackbox (Advanced Use Only)
#
# Enable blackbox logging globally (yes or no) or by subsystem. A blackbox
# contains a rolling buffer of all logs (of all severities). Blackboxes are
# stored under @CRM_BLACKBOX_DIR@ by default, and their contents can
# be viewed using the qb-blackbox(8) command.
#
# The blackbox recorder can be enabled at start using this variable, or at
# runtime by sending a Pacemaker subsystem daemon process a SIGUSR1 or SIGTRAP
# signal, and disabled by sending SIGUSR2 (see kill(1)). The blackbox will be
# written after a crash, assertion failure, or SIGTRAP signal.
#
# Default: PCMK_blackbox="no"
# Example: PCMK_blackbox="pacemaker-controld,pacemaker-fenced"
# PCMK_trace_blackbox (Advanced Use Only)
#
# Write a blackbox whenever the message at the specified function and line is
# logged. Multiple entries may be comma-separated.
#
# Default: PCMK_trace_blackbox=""
# Example: PCMK_trace_blackbox="remote.c:144,remote.c:149"
-## Node start state
+## Option overrides
# PCMK_node_start_state
#
# By default, the local host will join the cluster in an online or standby
# state when Pacemaker first starts depending on whether it was previously put
# into standby mode. If this variable is set to "standby" or "online", it will
# force the local host to join in the specified state.
#
# Default: PCMK_node_start_state="default"
+# PCMK_node_action_limit
+#
+# Specify the maximum number of jobs that can be scheduled on this node. If set,
+# this overrides the node-action-limit cluster property for this node.
+#
+# Default: PCMK_node_action_limit=""
+
## Crash Handling
# PCMK_fail_fast
#
# By default, if a Pacemaker subsystem crashes, the main pacemakerd process
# will attempt to restart it. If this variable is set to "yes", pacemakerd
# will panic the local host instead.
#
# Default: PCMK_fail_fast="no"
# PCMK_panic_action
#
# Pacemaker will panic the local host under certain conditions. By default,
# this means rebooting the host. This variable can change that behavior: if
# "crash", trigger a kernel crash (useful if you want a kernel dump to
# investigate); if "sync-reboot" or "sync-crash", synchronize filesystems
# before rebooting the host or triggering a kernel crash. The sync values are
# more likely to preserve log messages, but with the risk that the host may be
# left active if the synchronization hangs.
#
# Default: PCMK_panic_action="reboot"
## Pacemaker Remote
# PCMK_authkey_location
#
# Use the contents of this file as the authorization key to use with Pacemaker
# Remote connections. This file must be readable by Pacemaker daemons (that is,
-# it must allow read permissions to either the hacluster user or the haclient
-# group), and its contents must be identical on all nodes.
+# it must allow read permissions to either the @CRM_DAEMON_USER@ user or the
+# @CRM_DAEMON_GROUP@ group), and its contents must be identical on all nodes.
#
# Default: PCMK_authkey_location="@PACEMAKER_CONFIG_DIR@/authkey"
# PCMK_remote_address
#
# By default, if the Pacemaker Remote service is run on the local node, it will
# listen for connections on all IP addresses. This may be set to one address to
# listen on instead, as a resolvable hostname or as a numeric IPv4 or IPv6
# address. When resolving names or listening on all addresses, IPv6 will be
# preferred if available. When listening on an IPv6 address, IPv4 clients will
# be supported via IPv4-mapped IPv6 addresses.
#
# Default: PCMK_remote_address=""
# Example: PCMK_remote_address="192.0.2.1"
# PCMK_remote_port
#
# Use this TCP port number for Pacemaker Remote node connections. This value
# must be the same on all nodes.
#
# Default: PCMK_remote_port="3121"
+# PCMK_remote_pid1 (Advanced Use Only)
+#
+# When a bundle resource's "run-command" option is left to default, Pacemaker
+# Remote runs as PID 1 in the bundle's containers. When it does so, it loads
+# environment variables from the container's
+# @PACEMAKER_CONFIG_DIR@/pcmk-init.env and performs the PID 1 responsibility of
+# reaping dead subprocesses.
+#
+# This option controls whether those actions are performed when Pacemaker
+# Remote is not running as PID 1. It is intended primarily for developer testing
+# but can be useful when "run-command" is set to a separate, custom PID 1
+# process that launches Pacemaker Remote.
+#
+# * If set to "full", Pacemaker Remote loads environment variables from
+# @PACEMAKER_CONFIG_DIR@/pcmk-init.env and reaps dead subprocesses.
+# * If set to "vars", Pacemaker Remote loads environment variables from
+# @PACEMAKER_CONFIG_DIR@/pcmk-init.env but does not reap dead subprocesses.
+# * If set to "default", Pacemaker Remote performs neither action.
+#
+# If Pacemaker Remote is running as PID 1, this option is ignored, and the
+# behavior is the same as for "full".
+#
+# Default: PCMK_remote_pid1="default"
+
# PCMK_tls_priorities (Advanced Use Only)
#
# These GnuTLS cipher priorities will be used for TLS connections (whether for
# Pacemaker Remote connections or remote CIB access, when enabled). See:
#
# https://gnutls.org/manual/html_node/Priority-Strings.html
#
# Pacemaker will append ":+ANON-DH" for remote CIB access and ":+DHE-PSK:+PSK"
# for Pacemaker Remote connections, as they are required for the respective
# functionality.
#
# Default: PCMK_tls_priorities="@PCMK_GNUTLS_PRIORITIES@"
# Example: PCMK_tls_priorities="SECURE128:+SECURE192:-VERS-ALL:+VERS-TLS1.2"
# PCMK_dh_min_bits (Advanced Use Only)
#
# Set a lower bound on the bit length of the prime number generated for
# Diffie-Hellman parameters needed by TLS connections. The default is no
# minimum.
#
# The server (Pacemaker Remote daemon, or CIB manager configured to accept
# remote clients) will use this value to provide a floor for the value
# recommended by the GnuTLS library. The library will only accept a limited
# number of specific values, which vary by library version, so setting these is
# recommended only when required for compatibility with specific client
# versions.
#
# Clients (connecting cluster nodes or remote CIB commands) will require that
# the server use a prime of at least this size. This is recommended only when
# the value must be lowered in order for the client's GnuTLS library to accept
# a connection to an older server.
#
-# Default: PCMK_dh_min_bits="1024"
+# Default: PCMK_dh_min_bits="0" (no minimum)
# PCMK_dh_max_bits (Advanced Use Only)
#
# Set an upper bound on the bit length of the prime number generated for
# Diffie-Hellman parameters needed by TLS connections. The default is no
# maximum.
#
# The server (Pacemaker Remote daemon, or CIB manager configured to accept
# remote clients) will use this value to provide a ceiling for the value
# recommended by the GnuTLS library. The library will only accept a limited
# number of specific values, which vary by library version, so setting these is
# recommended only when required for compatibility with specific client
# versions.
#
# Clients do not use PCMK_dh_max_bits.
#
-# Default: PCMK_dh_max_bits="2048"
+# Default: PCMK_dh_max_bits="0" (no maximum)
## Inter-process Communication
# PCMK_ipc_type (Advanced Use Only)
#
# Force use of a particular IPC method. Allowed values:
#
# shared-mem
# socket
# posix
# sysv
#
# Default: PCMK_ipc_type="shared-mem"
# PCMK_ipc_buffer (Advanced Use Only)
#
# Specify an IPC buffer size in bytes. This can be useful when connecting to
# large clusters that result in messages exceeding the default size (which will
# also result in log messages referencing this variable).
#
# Default: PCMK_ipc_buffer="131072"
+## Cluster type
+
+# PCMK_cluster_type (Advanced Use Only)
+#
+# Specify the cluster layer to be used. If unset, Pacemaker will detect and use
+# a supported cluster layer, if available. Currently, "corosync" is the only
+# supported cluster layer. If multiple layers are supported in the future, this
+# will allow overriding Pacemaker's automatic detection to select a specific
+# one.
+#
+# Default: PCMK_cluster_type=""
+
+
## Developer Options
# PCMK_schema_directory (Advanced Use Only)
#
# Specify an alternate location for RNG schemas and XSL transforms.
#
# Default: PCMK_schema_directory="@CRM_SCHEMA_DIRECTORY@"
# G_SLICE (Advanced Use Only)
#
# Affect the behavior of glib's memory allocator. Setting to "always-malloc"
# when running under valgrind will help valgrind track malloc/free better;
# setting to "debug-blocks" when not running under valgrind will perform
# (somewhat expensive) memory checks.
#
# Default: G_SLICE=""
# Example: G_SLICE="always-malloc"
# MALLOC_PERTURB_ (Advanced Use Only)
#
# Setting this to a decimal byte value will make malloc() initialize newly
# allocated memory and free() wipe it, to help catch uninitialized-memory and
# use-after-free bugs.
#
# Default: MALLOC_PERTURB_=""
# Example: MALLOC_PERTURB_="221"
# MALLOC_CHECK_ (Advanced Use Only)
#
# Setting this to 3 will make malloc() and friends print to stderr and abort
# for some (inexpensive) memory checks.
#
# Default: MALLOC_CHECK_=""
# Example: MALLOC_CHECK_="3"
# PCMK_valgrind_enabled (Advanced Use Only)
#
# Whether subsystem daemons should be run under valgrind. Allowed values are
# the same as for PCMK_debug.
#
# Default: PCMK_valgrind_enabled="no"
# PCMK_callgrind_enabled
#
# Whether subsystem daemons should be run under valgrind with the callgrind
# tool enabled. Allowed values are the same as for PCMK_debug.
#
# Default: PCMK_callgrind_enabled="no"
# VALGRIND_OPTS
#
# Pass these options to valgrind, when enabled (see valgrind(1)). "--vgdb=no"
# is specified because pacemaker-execd can lower privileges when executing
# commands, which would otherwise leave a bunch of unremovable files in /tmp.
#
# Default: VALGRIND_OPTS=""
VALGRIND_OPTS="--leak-check=full --trace-children=no --vgdb=no --num-callers=25"
VALGRIND_OPTS="$VALGRIND_OPTS --log-file=@CRM_PACEMAKER_DIR@/valgrind-%p"
VALGRIND_OPTS="$VALGRIND_OPTS --suppressions=@datadir@/pacemaker/tests/valgrind-pcmk.suppressions"
VALGRIND_OPTS="$VALGRIND_OPTS --gen-suppressions=all"
diff --git a/include/crm/common/options_internal.h b/include/crm/common/options_internal.h
index f80f8fcded..5c561fd1f8 100644
--- a/include/crm/common/options_internal.h
+++ b/include/crm/common/options_internal.h
@@ -1,146 +1,152 @@
/*
* Copyright 2006-2023 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU Lesser General Public License
* version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY.
*/
#ifndef PCMK__OPTIONS_INTERNAL__H
# define PCMK__OPTIONS_INTERNAL__H
# ifndef PCMK__CONFIG_H
# define PCMK__CONFIG_H
# include <config.h> // _Noreturn
# endif
# include <glib.h> // GHashTable
# include <stdbool.h> // bool
_Noreturn void pcmk__cli_help(char cmd);
/*
* Environment variable option handling
*/
const char *pcmk__env_option(const char *option);
void pcmk__set_env_option(const char *option, const char *value, bool compat);
bool pcmk__env_option_enabled(const char *daemon, const char *option);
/*
* Cluster option handling
*/
typedef struct pcmk__cluster_option_s {
const char *name;
const char *alt_name;
const char *type;
const char *values;
const char *default_value;
bool (*is_valid)(const char *);
const char *description_short;
const char *description_long;
} pcmk__cluster_option_t;
const char *pcmk__cluster_option(GHashTable *options,
const pcmk__cluster_option_t *option_list,
int len, const char *name);
gchar *pcmk__format_option_metadata(const char *name, const char *desc_short,
const char *desc_long,
pcmk__cluster_option_t *option_list,
int len);
void pcmk__validate_cluster_options(GHashTable *options,
pcmk__cluster_option_t *option_list,
int len);
bool pcmk__valid_interval_spec(const char *value);
bool pcmk__valid_boolean(const char *value);
bool pcmk__valid_number(const char *value);
bool pcmk__valid_positive_number(const char *value);
bool pcmk__valid_quorum(const char *value);
bool pcmk__valid_script(const char *value);
bool pcmk__valid_percentage(const char *value);
// from watchdog.c
long pcmk__get_sbd_timeout(void);
bool pcmk__get_sbd_sync_resource_startup(void);
long pcmk__auto_watchdog_timeout(void);
bool pcmk__valid_sbd_timeout(const char *value);
// Constants for environment variable names
#define PCMK__ENV_AUTHKEY_LOCATION "authkey_location"
#define PCMK__ENV_BLACKBOX "blackbox"
#define PCMK__ENV_CALLGRIND_ENABLED "callgrind_enabled"
-#define PCMK__ENV_CIB_TIMEOUT "cib_timeout"
#define PCMK__ENV_CLUSTER_TYPE "cluster_type"
#define PCMK__ENV_DEBUG "debug"
#define PCMK__ENV_DH_MAX_BITS "dh_max_bits"
#define PCMK__ENV_DH_MIN_BITS "dh_min_bits"
#define PCMK__ENV_FAIL_FAST "fail_fast"
#define PCMK__ENV_IPC_BUFFER "ipc_buffer"
#define PCMK__ENV_IPC_TYPE "ipc_type"
#define PCMK__ENV_LOGFACILITY "logfacility"
#define PCMK__ENV_LOGFILE "logfile"
#define PCMK__ENV_LOGFILE_MODE "logfile_mode"
#define PCMK__ENV_LOGPRIORITY "logpriority"
#define PCMK__ENV_NODE_ACTION_LIMIT "node_action_limit"
#define PCMK__ENV_NODE_START_STATE "node_start_state"
#define PCMK__ENV_PANIC_ACTION "panic_action"
#define PCMK__ENV_PHYSICAL_HOST "physical_host"
#define PCMK__ENV_REMOTE_ADDRESS "remote_address"
#define PCMK__ENV_REMOTE_PID1 "remote_pid1"
#define PCMK__ENV_REMOTE_PORT "remote_port"
#define PCMK__ENV_RESPAWNED "respawned"
#define PCMK__ENV_SCHEMA_DIRECTORY "schema_directory"
#define PCMK__ENV_SERVICE "service"
-#define PCMK__ENV_SHUTDOWN_DELAY "shutdown_delay"
#define PCMK__ENV_STDERR "stderr"
#define PCMK__ENV_TLS_PRIORITIES "tls_priorities"
#define PCMK__ENV_TRACE_BLACKBOX "trace_blackbox"
#define PCMK__ENV_TRACE_FILES "trace_files"
#define PCMK__ENV_TRACE_FORMATS "trace_formats"
#define PCMK__ENV_TRACE_FUNCTIONS "trace_functions"
#define PCMK__ENV_TRACE_TAGS "trace_tags"
#define PCMK__ENV_VALGRIND_ENABLED "valgrind_enabled"
+// @COMPAT Drop at 3.0.0; default is plenty
+#define PCMK__ENV_CIB_TIMEOUT "cib_timeout"
+
// @COMPAT Drop at 3.0.0; likely last used in 1.1.24
#define PCMK__ENV_MCP "mcp"
// @COMPAT Drop at 3.0.0; added unused in 1.1.9
#define PCMK__ENV_QUORUM_TYPE "quorum_type"
+/* @COMPAT Drop at 3.0.0; added to debug shutdown issues when Pacemaker is
+ * managed by systemd, but no longer useful.
+ */
+#define PCMK__ENV_SHUTDOWN_DELAY "shutdown_delay"
+
// Constants for cluster option names
#define PCMK__OPT_NODE_HEALTH_BASE "node-health-base"
#define PCMK__OPT_NODE_HEALTH_GREEN "node-health-green"
#define PCMK__OPT_NODE_HEALTH_RED "node-health-red"
#define PCMK__OPT_NODE_HEALTH_STRATEGY "node-health-strategy"
#define PCMK__OPT_NODE_HEALTH_YELLOW "node-health-yellow"
// Constants for meta-attribute names
#define PCMK__META_ALLOW_UNHEALTHY_NODES "allow-unhealthy-nodes"
// Constants for enumerated values for various options
#define PCMK__VALUE_CLUSTER "cluster"
#define PCMK__VALUE_CUSTOM "custom"
#define PCMK__VALUE_FENCING "fencing"
#define PCMK__VALUE_GREEN "green"
#define PCMK__VALUE_LOCAL "local"
#define PCMK__VALUE_MIGRATE_ON_RED "migrate-on-red"
#define PCMK__VALUE_NONE "none"
#define PCMK__VALUE_NOTHING "nothing"
#define PCMK__VALUE_ONLY_GREEN "only-green"
#define PCMK__VALUE_PROGRESSIVE "progressive"
#define PCMK__VALUE_QUORUM "quorum"
#define PCMK__VALUE_RED "red"
#define PCMK__VALUE_UNFENCING "unfencing"
#define PCMK__VALUE_YELLOW "yellow"
#endif // PCMK__OPTIONS_INTERNAL__H
diff --git a/lib/common/schemas.c b/lib/common/schemas.c
index 14543859ad..372e872231 100644
--- a/lib/common/schemas.c
+++ b/lib/common/schemas.c
@@ -1,1311 +1,1306 @@
/*
* Copyright 2004-2023 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU Lesser General Public License
* version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY.
*/
#include <crm_internal.h>
#include <stdio.h>
#include <string.h>
#include <dirent.h>
#include <errno.h>
#include <sys/stat.h>
#include <stdarg.h>
#include <libxml/relaxng.h>
#include <libxslt/xslt.h>
#include <libxslt/transform.h>
#include <libxslt/security.h>
#include <libxslt/xsltutils.h>
#include <crm/msg_xml.h>
#include <crm/common/xml.h>
#include <crm/common/xml_internal.h> /* PCMK__XML_LOG_BASE */
#include "crmcommon_private.h"
#define SCHEMA_ZERO { .v = { 0, 0 } }
#define schema_strdup_printf(prefix, version, suffix) \
crm_strdup_printf(prefix "%u.%u" suffix, (version).v[0], (version).v[1])
typedef struct {
xmlRelaxNGPtr rng;
xmlRelaxNGValidCtxtPtr valid;
xmlRelaxNGParserCtxtPtr parser;
} relaxng_ctx_cache_t;
static GList *known_schemas = NULL;
static bool silent_logging = FALSE;
static void G_GNUC_PRINTF(2, 3)
xml_log(int priority, const char *fmt, ...)
{
va_list ap;
va_start(ap, fmt);
if (silent_logging == FALSE) {
/* XXX should not this enable dechunking as well? */
PCMK__XML_LOG_BASE(priority, FALSE, 0, NULL, fmt, ap);
}
va_end(ap);
}
static int
xml_latest_schema_index(GList *schemas)
{
// @COMPAT: pacemaker-next is deprecated since 2.1.5
// FIXME: This function assumes at least three schemas have been added
// before it has been called for the first time, which is only the case
// if we are not unit testing.
#if defined(PCMK__UNIT_TESTING)
return g_list_length(schemas) - 1; // index from 0
#else
return g_list_length(schemas) - 3; // index from 0, ignore "pacemaker-next"/"none"
#endif
}
/* Return the index of the most recent X.0 schema. */
int
pcmk__find_x_0_schema_index(GList *schemas)
{
/* We can't just use best to determine whether we've found the index
* or not. What if we have a very long list of schemas all in the
* same major version series? We'd return 0 for that, which means
* we would still run this function every time.
*/
#if defined(PCMK__UNIT_TESTING)
/* If we're unit testing, these can't be static because they'll stick
* around from one test run to the next. They need to be cleared out
* every time.
*/
bool found = false;
int best = 0;
#else
static bool found = false;
static int best = 0;
#endif
int i;
GList *best_node = NULL;
pcmk__schema_t *best_schema = NULL;
if (found) {
return best;
}
CRM_ASSERT(schemas != NULL);
/* Get the most recent schema so we can look at its version number. */
best = xml_latest_schema_index(schemas);
best_node = g_list_nth(schemas, best);
best_schema = best_node->data;
/* If we are unit testing, we don't add the pacemaker-next/none schemas
* to the list because we're not using the standard schema adding
* functions. Thus, a singleton list means we're done.
*
* On the other hand, if we are running as usually, we have those two
* schemas added to the list. A list of length three actually only has
* one useful schema. So we're still done.
*
* @COMPAT Change this when we stop adding those schemas.
*/
#if defined(PCMK__UNIT_TESTING)
if (pcmk__list_of_1(schemas)) {
goto done;
}
#else
if (g_list_length(schemas) == 3) {
goto done;
}
#endif
/* Start comparing the list from the node before the best schema (there's
* no point in comparing something to itself). Then, 'i' is an index
* starting at the best schema and will always point at the node after
* 'iter'. This makes it the value we want to return when we find what
* we're looking for.
*/
i = best;
for (GList *iter = best_node->prev; iter != NULL; iter = iter->prev) {
pcmk__schema_t *schema = iter->data;
/* We've found a schema in an older major version series. Return
* the index of the first one in the same major version series as
* the best schema.
*/
if (schema->version.v[0] < best_schema->version.v[0]) {
best = i;
goto done;
/* We're out of list to examine. This probably means there was only
* one major version series, so return index 0.
*/
} else if (iter->prev == NULL) {
best = 0;
goto done;
}
i--;
}
done:
found = true;
return best;
}
const char *
xml_latest_schema(void)
{
return get_schema_name(xml_latest_schema_index(known_schemas));
}
static inline bool
version_from_filename(const char *filename, pcmk__schema_version_t *version)
{
return sscanf(filename, "pacemaker-%hhu.%hhu.rng", &(version->v[0]), &(version->v[1])) == 2;
}
static int
schema_filter(const struct dirent *a)
{
int rc = 0;
pcmk__schema_version_t version = SCHEMA_ZERO;
if (strstr(a->d_name, "pacemaker-") != a->d_name) {
/* crm_trace("%s - wrong prefix", a->d_name); */
} else if (!pcmk__ends_with_ext(a->d_name, ".rng")) {
/* crm_trace("%s - wrong suffix", a->d_name); */
} else if (!version_from_filename(a->d_name, &version)) {
/* crm_trace("%s - wrong format", a->d_name); */
} else {
/* crm_debug("%s - candidate", a->d_name); */
rc = 1;
}
return rc;
}
static int
schema_sort(const struct dirent **a, const struct dirent **b)
{
pcmk__schema_version_t a_version = SCHEMA_ZERO;
pcmk__schema_version_t b_version = SCHEMA_ZERO;
if (!version_from_filename(a[0]->d_name, &a_version)
|| !version_from_filename(b[0]->d_name, &b_version)) {
// Shouldn't be possible, but makes static analysis happy
return 0;
}
for (int i = 0; i < 2; ++i) {
if (a_version.v[i] < b_version.v[i]) {
return -1;
} else if (a_version.v[i] > b_version.v[i]) {
return 1;
}
}
return 0;
}
/*!
* \internal
* \brief Add given schema + auxiliary data to internal bookkeeping.
*
* \note When providing \p version, should not be called directly but
* through \c add_schema_by_version.
*/
static void
add_schema(enum pcmk__schema_validator validator, const pcmk__schema_version_t *version,
const char *name, const char *transform,
const char *transform_enter, bool transform_onleave)
{
pcmk__schema_t *schema = NULL;
int last = g_list_length(known_schemas);
schema = calloc(1, sizeof(pcmk__schema_t));
CRM_ASSERT(schema != NULL);
schema->validator = validator;
schema->version.v[0] = version->v[0];
schema->version.v[1] = version->v[1];
schema->transform_onleave = transform_onleave;
if (version->v[0] || version->v[1]) {
schema->name = schema_strdup_printf("pacemaker-", *version, "");
} else {
schema->name = strdup(name);
CRM_ASSERT(schema->name != NULL);
}
if (transform) {
schema->transform = strdup(transform);
CRM_ASSERT(schema->transform != NULL);
}
if (transform_enter) {
schema->transform_enter = strdup(transform_enter);
CRM_ASSERT(schema->transform_enter != NULL);
}
known_schemas = g_list_append(known_schemas, schema);
if (schema->transform != NULL) {
crm_debug("Added supported schema %d: %s (upgrades with %s.xsl)",
last, schema->name, schema->transform);
} else {
crm_debug("Added supported schema %d: %s", last, schema->name);
}
}
/*!
* \internal
* \brief Add version-specified schema + auxiliary data to internal bookkeeping.
* \return Standard Pacemaker return value (the only possible values are
* \c ENOENT when no upgrade schema is associated, or \c pcmk_rc_ok otherwise.
*
* \note There's no reliance on the particular order of schemas entering here.
*
* \par A bit of theory
* We track 3 XSLT stylesheets that differ per usage:
* - "upgrade":
* . sparsely spread over the sequence of all available schemas,
* as they are only relevant when major version of the schema
* is getting bumped -- in that case, it MUST be set
* . name convention: upgrade-X.Y.xsl
* - "upgrade-enter":
* . may only accompany "upgrade" occurrence, but doesn't need to
* be present anytime such one is, i.e., it MAY not be set when
* "upgrade" is
* . name convention: upgrade-X.Y-enter.xsl,
* when not present: upgrade-enter.xsl
* - "upgrade-leave":
* . like "upgrade-enter", but SHOULD be present whenever
* "upgrade-enter" is (and vice versa, but that's only
* to prevent confusion based on observing the files,
* it would get ignored regardless)
* . name convention: (see "upgrade-enter")
*/
static int
add_schema_by_version(const pcmk__schema_version_t *version, bool transform_expected)
{
bool transform_onleave = FALSE;
int rc = pcmk_rc_ok;
struct stat s;
char *xslt = NULL,
*transform_upgrade = NULL,
*transform_enter = NULL;
/* prologue for further transform_expected handling */
if (transform_expected) {
/* check if there's suitable "upgrade" stylesheet */
transform_upgrade = schema_strdup_printf("upgrade-", *version, );
xslt = pcmk__xml_artefact_path(pcmk__xml_artefact_ns_legacy_xslt,
transform_upgrade);
}
if (!transform_expected) {
/* jump directly to the end */
} else if (stat(xslt, &s) == 0) {
/* perhaps there's also a targeted "upgrade-enter" stylesheet */
transform_enter = schema_strdup_printf("upgrade-", *version, "-enter");
free(xslt);
xslt = pcmk__xml_artefact_path(pcmk__xml_artefact_ns_legacy_xslt,
transform_enter);
if (stat(xslt, &s) != 0) {
/* or initially, at least a generic one */
crm_debug("Upgrade-enter transform %s.xsl not found", xslt);
free(xslt);
free(transform_enter);
transform_enter = strdup("upgrade-enter");
xslt = pcmk__xml_artefact_path(pcmk__xml_artefact_ns_legacy_xslt,
transform_enter);
if (stat(xslt, &s) != 0) {
crm_debug("Upgrade-enter transform %s.xsl not found, either", xslt);
free(xslt);
xslt = NULL;
}
}
/* xslt contains full path to "upgrade-enter" stylesheet */
if (xslt != NULL) {
/* then there should be "upgrade-leave" counterpart (enter->leave) */
memcpy(strrchr(xslt, '-') + 1, "leave", sizeof("leave") - 1);
transform_onleave = (stat(xslt, &s) == 0);
free(xslt);
} else {
free(transform_enter);
transform_enter = NULL;
}
} else {
crm_err("Upgrade transform %s not found", xslt);
free(xslt);
free(transform_upgrade);
transform_upgrade = NULL;
rc = ENOENT;
}
add_schema(pcmk__schema_validator_rng, version, NULL,
transform_upgrade, transform_enter, transform_onleave);
free(transform_upgrade);
free(transform_enter);
return rc;
}
static void
wrap_libxslt(bool finalize)
{
static xsltSecurityPrefsPtr secprefs;
int ret = 0;
/* security framework preferences */
if (!finalize) {
CRM_ASSERT(secprefs == NULL);
secprefs = xsltNewSecurityPrefs();
ret = xsltSetSecurityPrefs(secprefs, XSLT_SECPREF_WRITE_FILE,
xsltSecurityForbid)
| xsltSetSecurityPrefs(secprefs, XSLT_SECPREF_CREATE_DIRECTORY,
xsltSecurityForbid)
| xsltSetSecurityPrefs(secprefs, XSLT_SECPREF_READ_NETWORK,
xsltSecurityForbid)
| xsltSetSecurityPrefs(secprefs, XSLT_SECPREF_WRITE_NETWORK,
xsltSecurityForbid);
if (ret != 0) {
return;
}
} else {
xsltFreeSecurityPrefs(secprefs);
secprefs = NULL;
}
/* cleanup only */
if (finalize) {
xsltCleanupGlobals();
}
}
/*!
* \internal
* \brief Load pacemaker schemas into cache
*
* \note This currently also serves as an entry point for the
* generic initialization of the libxslt library.
*/
void
crm_schema_init(void)
{
int lpc, max;
char *base = pcmk__xml_artefact_root(pcmk__xml_artefact_ns_legacy_rng);
struct dirent **namelist = NULL;
const pcmk__schema_version_t zero = SCHEMA_ZERO;
wrap_libxslt(false);
max = scandir(base, &namelist, schema_filter, schema_sort);
if (max < 0) {
crm_notice("scandir(%s) failed: %s (%d)", base, strerror(errno), errno);
free(base);
} else {
free(base);
for (lpc = 0; lpc < max; lpc++) {
bool transform_expected = FALSE;
pcmk__schema_version_t version = SCHEMA_ZERO;
if (!version_from_filename(namelist[lpc]->d_name, &version)) {
// Shouldn't be possible, but makes static analysis happy
crm_err("Skipping schema '%s': could not parse version",
namelist[lpc]->d_name);
continue;
}
if ((lpc + 1) < max) {
pcmk__schema_version_t next_version = SCHEMA_ZERO;
if (version_from_filename(namelist[lpc+1]->d_name, &next_version)
&& (version.v[0] < next_version.v[0])) {
transform_expected = TRUE;
}
}
if (add_schema_by_version(&version, transform_expected)
== ENOENT) {
break;
}
}
for (lpc = 0; lpc < max; lpc++) {
free(namelist[lpc]);
}
free(namelist);
}
// @COMPAT: Deprecated since 2.1.5
add_schema(pcmk__schema_validator_rng, &zero, "pacemaker-next",
NULL, NULL, FALSE);
add_schema(pcmk__schema_validator_none, &zero, PCMK__VALUE_NONE,
NULL, NULL, FALSE);
}
static gboolean
validate_with_relaxng(xmlDocPtr doc, xmlRelaxNGValidityErrorFunc error_handler, void *error_handler_context, const char *relaxng_file,
relaxng_ctx_cache_t **cached_ctx)
{
int rc = 0;
gboolean valid = TRUE;
relaxng_ctx_cache_t *ctx = NULL;
CRM_CHECK(doc != NULL, return FALSE);
CRM_CHECK(relaxng_file != NULL, return FALSE);
if (cached_ctx && *cached_ctx) {
ctx = *cached_ctx;
} else {
crm_debug("Creating RNG parser context");
ctx = calloc(1, sizeof(relaxng_ctx_cache_t));
- xmlLoadExtDtdDefaultValue = 1;
ctx->parser = xmlRelaxNGNewParserCtxt(relaxng_file);
CRM_CHECK(ctx->parser != NULL, goto cleanup);
if (error_handler) {
xmlRelaxNGSetParserErrors(ctx->parser,
(xmlRelaxNGValidityErrorFunc) error_handler,
(xmlRelaxNGValidityWarningFunc) error_handler,
error_handler_context);
} else {
xmlRelaxNGSetParserErrors(ctx->parser,
(xmlRelaxNGValidityErrorFunc) fprintf,
(xmlRelaxNGValidityWarningFunc) fprintf,
stderr);
}
ctx->rng = xmlRelaxNGParse(ctx->parser);
CRM_CHECK(ctx->rng != NULL,
crm_err("Could not find/parse %s", relaxng_file);
goto cleanup);
ctx->valid = xmlRelaxNGNewValidCtxt(ctx->rng);
CRM_CHECK(ctx->valid != NULL, goto cleanup);
if (error_handler) {
xmlRelaxNGSetValidErrors(ctx->valid,
(xmlRelaxNGValidityErrorFunc) error_handler,
(xmlRelaxNGValidityWarningFunc) error_handler,
error_handler_context);
} else {
xmlRelaxNGSetValidErrors(ctx->valid,
(xmlRelaxNGValidityErrorFunc) fprintf,
(xmlRelaxNGValidityWarningFunc) fprintf,
stderr);
}
}
- xmlLineNumbersDefault(1);
rc = xmlRelaxNGValidateDoc(ctx->valid, doc);
if (rc > 0) {
valid = FALSE;
} else if (rc < 0) {
crm_err("Internal libxml error during validation");
}
cleanup:
if (cached_ctx) {
*cached_ctx = ctx;
} else {
if (ctx->parser != NULL) {
xmlRelaxNGFreeParserCtxt(ctx->parser);
}
if (ctx->valid != NULL) {
xmlRelaxNGFreeValidCtxt(ctx->valid);
}
if (ctx->rng != NULL) {
xmlRelaxNGFree(ctx->rng);
}
free(ctx);
}
return valid;
}
static void
free_schema(gpointer data)
{
pcmk__schema_t *schema = data;
relaxng_ctx_cache_t *ctx = NULL;
switch (schema->validator) {
case pcmk__schema_validator_none: // not cached
break;
case pcmk__schema_validator_rng: // cached
ctx = (relaxng_ctx_cache_t *) schema->cache;
if (ctx == NULL) {
break;
}
if (ctx->parser != NULL) {
xmlRelaxNGFreeParserCtxt(ctx->parser);
}
if (ctx->valid != NULL) {
xmlRelaxNGFreeValidCtxt(ctx->valid);
}
if (ctx->rng != NULL) {
xmlRelaxNGFree(ctx->rng);
}
free(ctx);
schema->cache = NULL;
break;
}
free(schema->name);
free(schema->transform);
free(schema->transform_enter);
}
/*!
* \internal
* \brief Clean up global memory associated with XML schemas
*/
void
crm_schema_cleanup(void)
{
g_list_free_full(known_schemas, free_schema);
known_schemas = NULL;
wrap_libxslt(true);
}
static gboolean
validate_with(xmlNode *xml, pcmk__schema_t *schema, xmlRelaxNGValidityErrorFunc error_handler, void* error_handler_context)
{
gboolean valid = FALSE;
char *file = NULL;
relaxng_ctx_cache_t **cache = NULL;
if (schema == NULL) {
return FALSE;
}
if (schema->validator == pcmk__schema_validator_none) {
return TRUE;
}
if (pcmk__str_eq(schema->name, "pacemaker-next", pcmk__str_none)) {
crm_warn("The pacemaker-next schema is deprecated and will be removed "
"in a future release.");
}
file = pcmk__xml_artefact_path(pcmk__xml_artefact_ns_legacy_rng,
schema->name);
crm_trace("Validating with %s (type=%d)",
pcmk__s(file, "missing schema"), schema->validator);
switch (schema->validator) {
case pcmk__schema_validator_rng:
cache = (relaxng_ctx_cache_t **) &(schema->cache);
valid = validate_with_relaxng(xml->doc, error_handler, error_handler_context, file, cache);
break;
default:
crm_err("Unknown validator type: %d", schema->validator);
break;
}
free(file);
return valid;
}
static bool
validate_with_silent(xmlNode *xml, pcmk__schema_t *schema)
{
bool rc, sl_backup = silent_logging;
silent_logging = TRUE;
rc = validate_with(xml, schema, (xmlRelaxNGValidityErrorFunc) xml_log, GUINT_TO_POINTER(LOG_ERR));
silent_logging = sl_backup;
return rc;
}
static void
dump_file(const char *filename)
{
FILE *fp = NULL;
int ch, line = 0;
CRM_CHECK(filename != NULL, return);
fp = fopen(filename, "r");
if (fp == NULL) {
crm_perror(LOG_ERR, "Could not open %s for reading", filename);
return;
}
fprintf(stderr, "%4d ", ++line);
do {
ch = getc(fp);
if (ch == EOF) {
putc('\n', stderr);
break;
} else if (ch == '\n') {
fprintf(stderr, "\n%4d ", ++line);
} else {
putc(ch, stderr);
}
} while (1);
fclose(fp);
}
gboolean
validate_xml_verbose(const xmlNode *xml_blob)
{
int fd = 0;
xmlDoc *doc = NULL;
xmlNode *xml = NULL;
gboolean rc = FALSE;
char *filename = NULL;
filename = crm_strdup_printf("%s/cib-invalid.XXXXXX", pcmk__get_tmpdir());
umask(S_IWGRP | S_IWOTH | S_IROTH);
fd = mkstemp(filename);
write_xml_fd(xml_blob, filename, fd, FALSE);
dump_file(filename);
- doc = xmlParseFile(filename);
+ doc = xmlReadFile(filename, NULL, 0);
xml = xmlDocGetRootElement(doc);
rc = validate_xml(xml, NULL, FALSE);
free_xml(xml);
unlink(filename);
free(filename);
return rc;
}
gboolean
validate_xml(xmlNode *xml_blob, const char *validation, gboolean to_logs)
{
return pcmk__validate_xml(xml_blob, validation, to_logs ? (xmlRelaxNGValidityErrorFunc) xml_log : NULL, GUINT_TO_POINTER(LOG_ERR));
}
gboolean
pcmk__validate_xml(xmlNode *xml_blob, const char *validation, xmlRelaxNGValidityErrorFunc error_handler, void* error_handler_context)
{
int version = 0;
CRM_CHECK((xml_blob != NULL) && (xml_blob->doc != NULL), return FALSE);
if (validation == NULL) {
validation = crm_element_value(xml_blob, XML_ATTR_VALIDATION);
}
if (validation == NULL) {
bool valid = FALSE;
for (GList *iter = known_schemas; iter != NULL; iter = iter->next) {
pcmk__schema_t *schema = iter->data;
if (validate_with(xml_blob, schema, NULL, NULL)) {
valid = TRUE;
crm_xml_add(xml_blob, XML_ATTR_VALIDATION, schema->name);
crm_info("XML validated against %s", schema->name);
}
}
return valid;
}
version = get_schema_version(validation);
if (strcmp(validation, PCMK__VALUE_NONE) == 0) {
return TRUE;
} else if (version < g_list_length(known_schemas)) {
pcmk__schema_t *schema = g_list_nth_data(known_schemas, version);
return validate_with(xml_blob, schema, error_handler,
error_handler_context);
}
crm_err("Unknown validator: %s", validation);
return FALSE;
}
/* With this arrangement, an attempt to identify the message severity
as explicitly signalled directly from XSLT is performed in rather
a smart way (no reliance on formatting string + arguments being
always specified as ["%s", purposeful_string], as it can also be
["%s: %s", some_prefix, purposeful_string] etc. so every argument
pertaining %s specifier is investigated), and if such a mark found,
the respective level is determined and, when the messages are to go
to the native logs, the mark itself gets dropped
(by the means of string shift).
NOTE: whether the native logging is the right sink is decided per
the ctx parameter -- NULL denotes this case, otherwise it
carries a pointer to the numeric expression of the desired
target logging level (messages with higher level will be
suppressed)
NOTE: on some architectures, this string shift may not have any
effect, but that's an acceptable tradeoff
The logging level for not explicitly designated messages
(suspicious, likely internal errors or some runaways) is
LOG_WARNING.
*/
static void G_GNUC_PRINTF(2, 3)
cib_upgrade_err(void *ctx, const char *fmt, ...)
{
va_list ap, aq;
char *arg_cur;
bool found = FALSE;
const char *fmt_iter = fmt;
uint8_t msg_log_level = LOG_WARNING; /* default for runaway messages */
const unsigned * log_level = (const unsigned *) ctx;
enum {
escan_seennothing,
escan_seenpercent,
} scan_state = escan_seennothing;
va_start(ap, fmt);
va_copy(aq, ap);
while (!found && *fmt_iter != '\0') {
/* while casing schema borrowed from libqb:qb_vsnprintf_serialize */
switch (*fmt_iter++) {
case '%':
if (scan_state == escan_seennothing) {
scan_state = escan_seenpercent;
} else if (scan_state == escan_seenpercent) {
scan_state = escan_seennothing;
}
break;
case 's':
if (scan_state == escan_seenpercent) {
scan_state = escan_seennothing;
arg_cur = va_arg(aq, char *);
if (arg_cur != NULL) {
switch (arg_cur[0]) {
case 'W':
if (!strncmp(arg_cur, "WARNING: ",
sizeof("WARNING: ") - 1)) {
msg_log_level = LOG_WARNING;
}
if (ctx == NULL) {
memmove(arg_cur, arg_cur + sizeof("WARNING: ") - 1,
strlen(arg_cur + sizeof("WARNING: ") - 1) + 1);
}
found = TRUE;
break;
case 'I':
if (!strncmp(arg_cur, "INFO: ",
sizeof("INFO: ") - 1)) {
msg_log_level = LOG_INFO;
}
if (ctx == NULL) {
memmove(arg_cur, arg_cur + sizeof("INFO: ") - 1,
strlen(arg_cur + sizeof("INFO: ") - 1) + 1);
}
found = TRUE;
break;
case 'D':
if (!strncmp(arg_cur, "DEBUG: ",
sizeof("DEBUG: ") - 1)) {
msg_log_level = LOG_DEBUG;
}
if (ctx == NULL) {
memmove(arg_cur, arg_cur + sizeof("DEBUG: ") - 1,
strlen(arg_cur + sizeof("DEBUG: ") - 1) + 1);
}
found = TRUE;
break;
}
}
}
break;
case '#': case '-': case ' ': case '+': case '\'': case 'I': case '.':
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
case '*':
break;
case 'l':
case 'z':
case 't':
case 'j':
case 'd': case 'i':
case 'o':
case 'u':
case 'x': case 'X':
case 'e': case 'E':
case 'f': case 'F':
case 'g': case 'G':
case 'a': case 'A':
case 'c':
case 'p':
if (scan_state == escan_seenpercent) {
(void) va_arg(aq, void *); /* skip forward */
scan_state = escan_seennothing;
}
break;
default:
scan_state = escan_seennothing;
break;
}
}
if (log_level != NULL) {
/* intention of the following offset is:
cibadmin -V -> start showing INFO labelled messages */
if (*log_level + 4 >= msg_log_level) {
vfprintf(stderr, fmt, ap);
}
} else {
PCMK__XML_LOG_BASE(msg_log_level, TRUE, 0, "CIB upgrade: ", fmt, ap);
}
va_end(aq);
va_end(ap);
}
static xmlNode *
apply_transformation(xmlNode *xml, const char *transform, gboolean to_logs)
{
char *xform = NULL;
xmlNode *out = NULL;
xmlDocPtr res = NULL;
xsltStylesheet *xslt = NULL;
xform = pcmk__xml_artefact_path(pcmk__xml_artefact_ns_legacy_xslt,
transform);
- xmlLoadExtDtdDefaultValue = 1;
- xmlSubstituteEntitiesDefault(1);
-
/* for capturing, e.g., what's emitted via <xsl:message> */
if (to_logs) {
xsltSetGenericErrorFunc(NULL, cib_upgrade_err);
} else {
xsltSetGenericErrorFunc(&crm_log_level, cib_upgrade_err);
}
xslt = xsltParseStylesheetFile((pcmkXmlStr) xform);
CRM_CHECK(xslt != NULL, goto cleanup);
res = xsltApplyStylesheet(xslt, xml->doc, NULL);
CRM_CHECK(res != NULL, goto cleanup);
xsltSetGenericErrorFunc(NULL, NULL); /* restore default one */
out = xmlDocGetRootElement(res);
cleanup:
if (xslt) {
xsltFreeStylesheet(xslt);
}
free(xform);
return out;
}
/*!
* \internal
* \brief Possibly full enter->upgrade->leave trip per internal bookkeeping.
*
* \note Only emits warnings about enter/leave phases in case of issues.
*/
static xmlNode *
apply_upgrade(xmlNode *xml, const pcmk__schema_t *schema, gboolean to_logs)
{
bool transform_onleave = schema->transform_onleave;
char *transform_leave;
xmlNode *upgrade = NULL,
*final = NULL;
if (schema->transform_enter) {
crm_debug("Upgrading %s-style configuration, pre-upgrade phase with %s.xsl",
schema->name, schema->transform_enter);
upgrade = apply_transformation(xml, schema->transform_enter, to_logs);
if (upgrade == NULL) {
crm_warn("Upgrade-enter transformation %s.xsl failed",
schema->transform_enter);
transform_onleave = FALSE;
}
}
if (upgrade == NULL) {
upgrade = xml;
}
crm_debug("Upgrading %s-style configuration, main phase with %s.xsl",
schema->name, schema->transform);
final = apply_transformation(upgrade, schema->transform, to_logs);
if (upgrade != xml) {
free_xml(upgrade);
upgrade = NULL;
}
if (final != NULL && transform_onleave) {
upgrade = final;
/* following condition ensured in add_schema_by_version */
CRM_ASSERT(schema->transform_enter != NULL);
transform_leave = strdup(schema->transform_enter);
/* enter -> leave */
memcpy(strrchr(transform_leave, '-') + 1, "leave", sizeof("leave") - 1);
crm_debug("Upgrading %s-style configuration, post-upgrade phase with %s.xsl",
schema->name, transform_leave);
final = apply_transformation(upgrade, transform_leave, to_logs);
if (final == NULL) {
crm_warn("Upgrade-leave transformation %s.xsl failed", transform_leave);
final = upgrade;
} else {
free_xml(upgrade);
}
free(transform_leave);
}
return final;
}
const char *
get_schema_name(int version)
{
pcmk__schema_t *schema = g_list_nth_data(known_schemas, version);
if (schema == NULL) {
return "unknown";
}
return schema->name;
}
int
get_schema_version(const char *name)
{
int lpc = 0;
if (name == NULL) {
name = PCMK__VALUE_NONE;
}
for (GList *iter = known_schemas; iter != NULL; iter = iter->next) {
pcmk__schema_t *schema = iter->data;
if (pcmk__str_eq(name, schema->name, pcmk__str_casei)) {
return lpc;
}
lpc++;
}
return -1;
}
/* set which validation to use */
int
update_validation(xmlNode **xml_blob, int *best, int max, gboolean transform,
gboolean to_logs)
{
xmlNode *xml = NULL;
char *value = NULL;
int max_stable_schemas = xml_latest_schema_index(known_schemas);
int lpc = 0, match = -1, rc = pcmk_ok;
int next = -1; /* -1 denotes "inactive" value */
xmlRelaxNGValidityErrorFunc error_handler =
to_logs ? (xmlRelaxNGValidityErrorFunc) xml_log : NULL;
CRM_CHECK(best != NULL, return -EINVAL);
*best = 0;
CRM_CHECK((xml_blob != NULL) && (*xml_blob != NULL)
&& ((*xml_blob)->doc != NULL),
return -EINVAL);
xml = *xml_blob;
value = crm_element_value_copy(xml, XML_ATTR_VALIDATION);
if (value != NULL) {
match = get_schema_version(value);
lpc = match;
if (lpc >= 0 && transform == FALSE) {
*best = lpc++;
} else if (lpc < 0) {
crm_debug("Unknown validation schema");
lpc = 0;
}
}
if (match >= max_stable_schemas) {
/* nothing to do */
free(value);
*best = match;
return pcmk_ok;
}
while (lpc <= max_stable_schemas) {
/* FIXME: This will cause us to walk the known_schemas list every time
* this loop iterates, which is not ideal. However, for now it's a lot
* easier than trying to get all the loop indices we're using here
* sorted out and working correctly.
*/
pcmk__schema_t *schema = g_list_nth_data(known_schemas, lpc);
crm_debug("Testing '%s' validation (%d of %d)",
pcmk__s(schema->name, "<unset>"), lpc, max_stable_schemas);
if (validate_with(xml, schema, error_handler, GUINT_TO_POINTER(LOG_ERR)) == FALSE) {
if (next != -1) {
crm_info("Configuration not valid for schema: %s",
schema->name);
next = -1;
} else {
crm_trace("%s validation failed", pcmk__s(schema->name, "<unset>"));
}
if (*best) {
/* we've satisfied the validation, no need to check further */
break;
}
rc = -pcmk_err_schema_validation;
} else {
if (next != -1) {
crm_debug("Configuration valid for schema: %s", schema->name);
next = -1;
}
rc = pcmk_ok;
}
if (rc == pcmk_ok) {
*best = lpc;
}
if (rc == pcmk_ok && transform) {
xmlNode *upgrade = NULL;
pcmk__schema_t *next_schema = NULL;
next = lpc+1;
if (next > max_stable_schemas) {
/* There is no next version */
crm_trace("Stopping at %s", schema->name);
break;
}
if (max > 0 && (lpc == max || next > max)) {
crm_trace("Upgrade limit reached at %s (lpc=%d, next=%d, max=%d)",
schema->name, lpc, next, max);
break;
}
next_schema = g_list_nth_data(known_schemas, next);
CRM_ASSERT(next_schema != NULL);
if (schema->transform == NULL
/* possibly avoid transforming when readily valid
(in general more restricted when crossing the major
version boundary, as X.0 "transitional" version is
expected to be more strict than it's successors that
may re-allow constructs from previous major line) */
|| validate_with_silent(xml, next_schema)) {
crm_debug("%s-style configuration is also valid for %s",
schema->name, next_schema->name);
lpc = next;
} else {
crm_debug("Upgrading %s-style configuration to %s with %s.xsl",
schema->name, next_schema->name, schema->transform);
upgrade = apply_upgrade(xml, schema, to_logs);
if (upgrade == NULL) {
crm_err("Transformation %s.xsl failed", schema->transform);
rc = -pcmk_err_transform_failed;
} else if (validate_with(upgrade, next_schema, error_handler,
GUINT_TO_POINTER(LOG_ERR))) {
crm_info("Transformation %s.xsl successful", schema->transform);
lpc = next;
*best = next;
free_xml(xml);
xml = upgrade;
rc = pcmk_ok;
} else {
crm_err("Transformation %s.xsl did not produce a valid configuration",
schema->transform);
crm_log_xml_info(upgrade, "transform:bad");
free_xml(upgrade);
rc = -pcmk_err_schema_validation;
}
next = -1;
}
}
if (transform == FALSE || rc != pcmk_ok) {
/* we need some progress! */
lpc++;
}
}
if (*best > match && *best) {
pcmk__schema_t *best_schema = g_list_nth_data(known_schemas, *best);
crm_info("%s the configuration from %s to %s",
transform?"Transformed":"Upgraded", pcmk__s(value, "<none>"),
best_schema->name);
crm_xml_add(xml, XML_ATTR_VALIDATION, best_schema->name);
}
*xml_blob = xml;
free(value);
return rc;
}
gboolean
cli_config_update(xmlNode **xml, int *best_version, gboolean to_logs)
{
gboolean rc = TRUE;
const char *value = crm_element_value(*xml, XML_ATTR_VALIDATION);
char *const orig_value = strdup(value == NULL ? "(none)" : value);
int version = get_schema_version(value);
int orig_version = version;
int min_version = pcmk__find_x_0_schema_index(known_schemas);
if (version < min_version) {
// Current configuration schema is not acceptable, try to update
xmlNode *converted = NULL;
converted = copy_xml(*xml);
update_validation(&converted, &version, 0, TRUE, to_logs);
value = crm_element_value(converted, XML_ATTR_VALIDATION);
if (version < min_version) {
// Updated configuration schema is still not acceptable
if (version < orig_version || orig_version == -1) {
// We couldn't validate any schema at all
if (to_logs) {
pcmk__config_err("Cannot upgrade configuration (claiming "
"schema %s) to at least %s because it "
"does not validate with any schema from "
"%s to %s",
orig_value,
get_schema_name(min_version),
get_schema_name(orig_version),
xml_latest_schema());
} else {
fprintf(stderr, "Cannot upgrade configuration (claiming "
"schema %s) to at least %s because it "
"does not validate with any schema from "
"%s to %s\n",
orig_value,
get_schema_name(min_version),
get_schema_name(orig_version),
xml_latest_schema());
}
} else {
// We updated configuration successfully, but still too low
if (to_logs) {
pcmk__config_err("Cannot upgrade configuration (claiming "
"schema %s) to at least %s because it "
"would not upgrade past %s",
orig_value,
get_schema_name(min_version),
pcmk__s(value, "unspecified version"));
} else {
fprintf(stderr, "Cannot upgrade configuration (claiming "
"schema %s) to at least %s because it "
"would not upgrade past %s\n",
orig_value,
get_schema_name(min_version),
pcmk__s(value, "unspecified version"));
}
}
free_xml(converted);
converted = NULL;
rc = FALSE;
} else {
// Updated configuration schema is acceptable
free_xml(*xml);
*xml = converted;
if (version < xml_latest_schema_index(known_schemas)) {
if (to_logs) {
pcmk__config_warn("Configuration with schema %s was "
"internally upgraded to acceptable (but "
"not most recent) %s",
orig_value, get_schema_name(version));
}
} else {
if (to_logs) {
crm_info("Configuration with schema %s was internally "
"upgraded to latest version %s",
orig_value, get_schema_name(version));
}
}
}
} else if (version >= get_schema_version(PCMK__VALUE_NONE)) {
// Schema validation is disabled
if (to_logs) {
pcmk__config_warn("Schema validation of configuration is disabled "
"(enabling is encouraged and prevents common "
"misconfigurations)");
} else {
fprintf(stderr, "Schema validation of configuration is disabled "
"(enabling is encouraged and prevents common "
"misconfigurations)\n");
}
}
if (best_version) {
*best_version = version;
}
free(orig_value);
return rc;
}
void
pcmk__log_known_schemas(void)
{
int lpc = 0;
for (GList *iter = known_schemas; iter != NULL; iter = iter->next) {
pcmk__schema_t *schema = iter->data;
if (schema->transform != NULL) {
crm_debug("known_schemas[%d] => %s (upgrades with %s.xsl)",
lpc, schema->name, schema->transform);
} else {
crm_debug("known_schemas[%d] => %s", lpc, schema->name);
}
lpc++;
}
}
diff --git a/lib/common/xml.c b/lib/common/xml.c
index 272d09241d..53ebff770f 100644
--- a/lib/common/xml.c
+++ b/lib/common/xml.c
@@ -1,2736 +1,2736 @@
/*
* Copyright 2004-2023 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU Lesser General Public License
* version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY.
*/
#include <crm_internal.h>
#include <stdio.h>
#include <sys/types.h>
#include <unistd.h>
#include <time.h>
#include <string.h>
#include <stdlib.h>
#include <stdarg.h>
#include <bzlib.h>
#include <libxml/parser.h>
#include <libxml/tree.h>
#include <libxml/xmlIO.h> /* xmlAllocOutputBuffer */
#include <crm/crm.h>
#include <crm/msg_xml.h>
#include <crm/common/xml.h>
#include <crm/common/xml_internal.h> // PCMK__XML_LOG_BASE, etc.
#include "crmcommon_private.h"
// Define this as 1 in development to get insanely verbose trace messages
#ifndef XML_PARSER_DEBUG
#define XML_PARSER_DEBUG 0
#endif
/* @TODO XML_PARSE_RECOVER allows some XML errors to be silently worked around
* by libxml2, which is potentially ambiguous and dangerous. We should drop it
* when we can break backward compatibility with configurations that might be
* relying on it (i.e. pacemaker 3.0.0).
*
* It might be a good idea to have a transitional period where we first try
* parsing without XML_PARSE_RECOVER, and if that fails, try parsing again with
* it, logging a warning if it succeeds.
*/
#define PCMK__XML_PARSE_OPTS_WITHOUT_RECOVER (XML_PARSE_NOBLANKS)
#define PCMK__XML_PARSE_OPTS_WITH_RECOVER (XML_PARSE_NOBLANKS | XML_PARSE_RECOVER)
bool
pcmk__tracking_xml_changes(xmlNode *xml, bool lazy)
{
if(xml == NULL || xml->doc == NULL || xml->doc->_private == NULL) {
return FALSE;
} else if (!pcmk_is_set(((xml_doc_private_t *)xml->doc->_private)->flags,
pcmk__xf_tracking)) {
return FALSE;
} else if (lazy && !pcmk_is_set(((xml_doc_private_t *)xml->doc->_private)->flags,
pcmk__xf_lazy)) {
return FALSE;
}
return TRUE;
}
static inline void
set_parent_flag(xmlNode *xml, long flag)
{
for(; xml; xml = xml->parent) {
xml_node_private_t *nodepriv = xml->_private;
if (nodepriv == NULL) {
/* During calls to xmlDocCopyNode(), _private will be unset for parent nodes */
} else {
pcmk__set_xml_flags(nodepriv, flag);
}
}
}
void
pcmk__set_xml_doc_flag(xmlNode *xml, enum xml_private_flags flag)
{
if(xml && xml->doc && xml->doc->_private){
/* During calls to xmlDocCopyNode(), xml->doc may be unset */
xml_doc_private_t *docpriv = xml->doc->_private;
pcmk__set_xml_flags(docpriv, flag);
}
}
// Mark document, element, and all element's parents as changed
void
pcmk__mark_xml_node_dirty(xmlNode *xml)
{
pcmk__set_xml_doc_flag(xml, pcmk__xf_dirty);
set_parent_flag(xml, pcmk__xf_dirty);
}
// Clear flags on XML node and its children
static void
reset_xml_node_flags(xmlNode *xml)
{
xmlNode *cIter = NULL;
xml_node_private_t *nodepriv = xml->_private;
if (nodepriv) {
nodepriv->flags = 0;
}
for (cIter = pcmk__xml_first_child(xml); cIter != NULL;
cIter = pcmk__xml_next(cIter)) {
reset_xml_node_flags(cIter);
}
}
// Set xpf_created flag on XML node and any children
void
pcmk__mark_xml_created(xmlNode *xml)
{
xmlNode *cIter = NULL;
xml_node_private_t *nodepriv = NULL;
CRM_ASSERT(xml != NULL);
nodepriv = xml->_private;
if (nodepriv && pcmk__tracking_xml_changes(xml, FALSE)) {
if (!pcmk_is_set(nodepriv->flags, pcmk__xf_created)) {
pcmk__set_xml_flags(nodepriv, pcmk__xf_created);
pcmk__mark_xml_node_dirty(xml);
}
for (cIter = pcmk__xml_first_child(xml); cIter != NULL;
cIter = pcmk__xml_next(cIter)) {
pcmk__mark_xml_created(cIter);
}
}
}
#define XML_DOC_PRIVATE_MAGIC 0x81726354UL
#define XML_NODE_PRIVATE_MAGIC 0x54637281UL
// Free an XML object previously marked as deleted
static void
free_deleted_object(void *data)
{
if(data) {
pcmk__deleted_xml_t *deleted_obj = data;
free(deleted_obj->path);
free(deleted_obj);
}
}
// Free and NULL user, ACLs, and deleted objects in an XML node's private data
static void
reset_xml_private_data(xml_doc_private_t *docpriv)
{
if (docpriv != NULL) {
CRM_ASSERT(docpriv->check == XML_DOC_PRIVATE_MAGIC);
free(docpriv->user);
docpriv->user = NULL;
if (docpriv->acls != NULL) {
pcmk__free_acls(docpriv->acls);
docpriv->acls = NULL;
}
if(docpriv->deleted_objs) {
g_list_free_full(docpriv->deleted_objs, free_deleted_object);
docpriv->deleted_objs = NULL;
}
}
}
// Free all private data associated with an XML node
static void
free_private_data(xmlNode *node)
{
/* Note:
This function frees private data assosciated with an XML node,
unless the function is being called as a result of internal
XSLT cleanup.
That could happen through, for example, the following chain of
function calls:
xsltApplyStylesheetInternal
-> xsltFreeTransformContext
-> xsltFreeRVTs
-> xmlFreeDoc
And in that case, the node would fulfill three conditions:
1. It would be a standalone document (i.e. it wouldn't be
part of a document)
2. It would have a space-prefixed name (for reference, please
see xsltInternals.h: XSLT_MARK_RES_TREE_FRAG)
3. It would carry its own payload in the _private field.
We do not free data in this circumstance to avoid a failed
assertion on the XML_*_PRIVATE_MAGIC later.
*/
if (node->name == NULL || node->name[0] != ' ') {
if (node->_private) {
if (node->type == XML_DOCUMENT_NODE) {
reset_xml_private_data(node->_private);
} else {
CRM_ASSERT(((xml_node_private_t *) node->_private)->check
== XML_NODE_PRIVATE_MAGIC);
/* nothing dynamically allocated nested */
}
free(node->_private);
node->_private = NULL;
}
}
}
// Allocate and initialize private data for an XML node
static void
new_private_data(xmlNode *node)
{
switch (node->type) {
case XML_DOCUMENT_NODE: {
xml_doc_private_t *docpriv = NULL;
docpriv = calloc(1, sizeof(xml_doc_private_t));
CRM_ASSERT(docpriv != NULL);
docpriv->check = XML_DOC_PRIVATE_MAGIC;
/* Flags will be reset if necessary when tracking is enabled */
pcmk__set_xml_flags(docpriv, pcmk__xf_dirty|pcmk__xf_created);
node->_private = docpriv;
break;
}
case XML_ELEMENT_NODE:
case XML_ATTRIBUTE_NODE:
case XML_COMMENT_NODE: {
xml_node_private_t *nodepriv = NULL;
nodepriv = calloc(1, sizeof(xml_node_private_t));
CRM_ASSERT(nodepriv != NULL);
nodepriv->check = XML_NODE_PRIVATE_MAGIC;
/* Flags will be reset if necessary when tracking is enabled */
pcmk__set_xml_flags(nodepriv, pcmk__xf_dirty|pcmk__xf_created);
node->_private = nodepriv;
if (pcmk__tracking_xml_changes(node, FALSE)) {
/* XML_ELEMENT_NODE doesn't get picked up here, node->doc is
* not hooked up at the point we are called
*/
pcmk__mark_xml_node_dirty(node);
}
break;
}
case XML_TEXT_NODE:
case XML_DTD_NODE:
case XML_CDATA_SECTION_NODE:
break;
default:
/* Ignore */
crm_trace("Ignoring %p %d", node, node->type);
CRM_LOG_ASSERT(node->type == XML_ELEMENT_NODE);
break;
}
}
void
xml_track_changes(xmlNode * xml, const char *user, xmlNode *acl_source, bool enforce_acls)
{
xml_accept_changes(xml);
crm_trace("Tracking changes%s to %p", enforce_acls?" with ACLs":"", xml);
pcmk__set_xml_doc_flag(xml, pcmk__xf_tracking);
if(enforce_acls) {
if(acl_source == NULL) {
acl_source = xml;
}
pcmk__set_xml_doc_flag(xml, pcmk__xf_acl_enabled);
pcmk__unpack_acl(acl_source, xml, user);
pcmk__apply_acl(xml);
}
}
bool xml_tracking_changes(xmlNode * xml)
{
return (xml != NULL) && (xml->doc != NULL) && (xml->doc->_private != NULL)
&& pcmk_is_set(((xml_doc_private_t *)(xml->doc->_private))->flags,
pcmk__xf_tracking);
}
bool xml_document_dirty(xmlNode *xml)
{
return (xml != NULL) && (xml->doc != NULL) && (xml->doc->_private != NULL)
&& pcmk_is_set(((xml_doc_private_t *)(xml->doc->_private))->flags,
pcmk__xf_dirty);
}
/*!
* \internal
* \brief Return ordinal position of an XML node among its siblings
*
* \param[in] xml XML node to check
* \param[in] ignore_if_set Don't count siblings with this flag set
*
* \return Ordinal position of \p xml (starting with 0)
*/
int
pcmk__xml_position(const xmlNode *xml, enum xml_private_flags ignore_if_set)
{
int position = 0;
for (const xmlNode *cIter = xml; cIter->prev; cIter = cIter->prev) {
xml_node_private_t *nodepriv = ((xmlNode*)cIter->prev)->_private;
if (!pcmk_is_set(nodepriv->flags, ignore_if_set)) {
position++;
}
}
return position;
}
// Remove all attributes marked as deleted from an XML node
static void
accept_attr_deletions(xmlNode *xml)
{
// Clear XML node's flags
((xml_node_private_t *) xml->_private)->flags = pcmk__xf_none;
// Remove this XML node's attributes that were marked as deleted
pcmk__xe_remove_matching_attrs(xml, pcmk__marked_as_deleted, NULL);
// Recursively do the same for this XML node's children
for (xmlNodePtr cIter = pcmk__xml_first_child(xml); cIter != NULL;
cIter = pcmk__xml_next(cIter)) {
accept_attr_deletions(cIter);
}
}
/*!
* \internal
* \brief Find first child XML node matching another given XML node
*
* \param[in] haystack XML whose children should be checked
* \param[in] needle XML to match (comment content or element name and ID)
* \param[in] exact If true and needle is a comment, position must match
*/
xmlNode *
pcmk__xml_match(const xmlNode *haystack, const xmlNode *needle, bool exact)
{
CRM_CHECK(needle != NULL, return NULL);
if (needle->type == XML_COMMENT_NODE) {
return pcmk__xc_match(haystack, needle, exact);
} else {
const char *id = ID(needle);
const char *attr = (id == NULL)? NULL : XML_ATTR_ID;
return pcmk__xe_match(haystack, (const char *) needle->name, attr, id);
}
}
void
xml_accept_changes(xmlNode * xml)
{
xmlNode *top = NULL;
xml_doc_private_t *docpriv = NULL;
if(xml == NULL) {
return;
}
crm_trace("Accepting changes to %p", xml);
docpriv = xml->doc->_private;
top = xmlDocGetRootElement(xml->doc);
reset_xml_private_data(xml->doc->_private);
if (!pcmk_is_set(docpriv->flags, pcmk__xf_dirty)) {
docpriv->flags = pcmk__xf_none;
return;
}
docpriv->flags = pcmk__xf_none;
accept_attr_deletions(top);
}
xmlNode *
find_xml_node(const xmlNode *root, const char *search_path, gboolean must_find)
{
xmlNode *a_child = NULL;
const char *name = (root == NULL)? "<NULL>" : (const char *) root->name;
if (search_path == NULL) {
crm_warn("Will never find <NULL>");
return NULL;
}
for (a_child = pcmk__xml_first_child(root); a_child != NULL;
a_child = pcmk__xml_next(a_child)) {
if (strcmp((const char *)a_child->name, search_path) == 0) {
return a_child;
}
}
if (must_find) {
crm_warn("Could not find %s in %s.", search_path, name);
} else if (root != NULL) {
crm_trace("Could not find %s in %s.", search_path, name);
} else {
crm_trace("Could not find %s in <NULL>.", search_path);
}
return NULL;
}
#define attr_matches(c, n, v) pcmk__str_eq(crm_element_value((c), (n)), \
(v), pcmk__str_none)
/*!
* \internal
* \brief Find first XML child element matching given criteria
*
* \param[in] parent XML element to search
* \param[in] node_name If not NULL, only match children of this type
* \param[in] attr_n If not NULL, only match children with an attribute
* of this name.
* \param[in] attr_v If \p attr_n and this are not NULL, only match children
* with an attribute named \p attr_n and this value
*
* \return Matching XML child element, or NULL if none found
*/
xmlNode *
pcmk__xe_match(const xmlNode *parent, const char *node_name,
const char *attr_n, const char *attr_v)
{
CRM_CHECK(parent != NULL, return NULL);
CRM_CHECK(attr_v == NULL || attr_n != NULL, return NULL);
for (xmlNode *child = pcmk__xml_first_child(parent); child != NULL;
child = pcmk__xml_next(child)) {
if (pcmk__str_eq(node_name, (const char *) (child->name),
pcmk__str_null_matches)
&& ((attr_n == NULL) ||
(attr_v == NULL && xmlHasProp(child, (pcmkXmlStr) attr_n)) ||
(attr_v != NULL && attr_matches(child, attr_n, attr_v)))) {
return child;
}
}
crm_trace("XML child node <%s%s%s%s%s> not found in %s",
(node_name? node_name : "(any)"),
(attr_n? " " : ""),
(attr_n? attr_n : ""),
(attr_n? "=" : ""),
(attr_n? attr_v : ""),
(const char *) parent->name);
return NULL;
}
void
copy_in_properties(xmlNode *target, const xmlNode *src)
{
if (src == NULL) {
crm_warn("No node to copy properties from");
} else if (target == NULL) {
crm_err("No node to copy properties into");
} else {
for (xmlAttrPtr a = pcmk__xe_first_attr(src); a != NULL; a = a->next) {
const char *p_name = (const char *) a->name;
const char *p_value = pcmk__xml_attr_value(a);
expand_plus_plus(target, p_name, p_value);
if (xml_acl_denied(target)) {
crm_trace("Cannot copy %s=%s to %s", p_name, p_value, target->name);
return;
}
}
}
return;
}
/*!
* \brief Parse integer assignment statements on this node and all its child
* nodes
*
* \param[in,out] target Root XML node to be processed
*
* \note This function is recursive
*/
void
fix_plus_plus_recursive(xmlNode *target)
{
/* TODO: Remove recursion and use xpath searches for value++ */
xmlNode *child = NULL;
for (xmlAttrPtr a = pcmk__xe_first_attr(target); a != NULL; a = a->next) {
const char *p_name = (const char *) a->name;
const char *p_value = pcmk__xml_attr_value(a);
expand_plus_plus(target, p_name, p_value);
}
for (child = pcmk__xml_first_child(target); child != NULL;
child = pcmk__xml_next(child)) {
fix_plus_plus_recursive(child);
}
}
/*!
* \brief Update current XML attribute value per parsed integer assignment
statement
*
* \param[in,out] target an XML node, containing a XML attribute that is
* initialized to some numeric value, to be processed
* \param[in] name name of the XML attribute, e.g. X, whose value
* should be updated
* \param[in] value assignment statement, e.g. "X++" or
* "X+=5", to be applied to the initialized value.
*
* \note The original XML attribute value is treated as 0 if non-numeric and
* truncated to be an integer if decimal-point-containing.
* \note The final XML attribute value is truncated to not exceed 1000000.
* \note Undefined behavior if unexpected input.
*/
void
expand_plus_plus(xmlNode * target, const char *name, const char *value)
{
int offset = 1;
int name_len = 0;
int int_value = 0;
int value_len = 0;
const char *old_value = NULL;
if (target == NULL || value == NULL || name == NULL) {
return;
}
old_value = crm_element_value(target, name);
if (old_value == NULL) {
/* if no previous value, set unexpanded */
goto set_unexpanded;
} else if (strstr(value, name) != value) {
goto set_unexpanded;
}
name_len = strlen(name);
value_len = strlen(value);
if (value_len < (name_len + 2)
|| value[name_len] != '+' || (value[name_len + 1] != '+' && value[name_len + 1] != '=')) {
goto set_unexpanded;
}
/* if we are expanding ourselves,
* then no previous value was set and leave int_value as 0
*/
if (old_value != value) {
int_value = char2score(old_value);
}
if (value[name_len + 1] != '+') {
const char *offset_s = value + (name_len + 2);
offset = char2score(offset_s);
}
int_value += offset;
if (int_value > INFINITY) {
int_value = (int)INFINITY;
}
crm_xml_add_int(target, name, int_value);
return;
set_unexpanded:
if (old_value == value) {
/* the old value is already set, nothing to do */
return;
}
crm_xml_add(target, name, value);
return;
}
/*!
* \internal
* \brief Remove an XML element's attributes that match some criteria
*
* \param[in,out] element XML element to modify
* \param[in] match If not NULL, only remove attributes for which
* this function returns true
* \param[in,out] user_data Data to pass to \p match
*/
void
pcmk__xe_remove_matching_attrs(xmlNode *element,
bool (*match)(xmlAttrPtr, void *),
void *user_data)
{
xmlAttrPtr next = NULL;
for (xmlAttrPtr a = pcmk__xe_first_attr(element); a != NULL; a = next) {
next = a->next; // Grab now because attribute might get removed
if ((match == NULL) || match(a, user_data)) {
if (!pcmk__check_acl(element, NULL, pcmk__xf_acl_write)) {
crm_trace("ACLs prevent removal of attributes (%s and "
"possibly others) from %s element",
(const char *) a->name, (const char *) element->name);
return; // ACLs apply to element, not particular attributes
}
if (pcmk__tracking_xml_changes(element, false)) {
// Leave (marked for removal) until after diff is calculated
set_parent_flag(element, pcmk__xf_dirty);
pcmk__set_xml_flags((xml_node_private_t *) a->_private,
pcmk__xf_deleted);
} else {
xmlRemoveProp(a);
}
}
}
}
xmlNode *
add_node_copy(xmlNode * parent, xmlNode * src_node)
{
xmlNode *child = NULL;
CRM_CHECK((parent != NULL) && (src_node != NULL), return NULL);
child = xmlDocCopyNode(src_node, parent->doc, 1);
if (child == NULL) {
return NULL;
}
xmlAddChild(parent, child);
pcmk__mark_xml_created(child);
return child;
}
xmlNode *
create_xml_node(xmlNode * parent, const char *name)
{
xmlDoc *doc = NULL;
xmlNode *node = NULL;
if (pcmk__str_empty(name)) {
CRM_CHECK(name != NULL && name[0] == 0, return NULL);
return NULL;
}
if (parent == NULL) {
doc = xmlNewDoc((pcmkXmlStr) "1.0");
if (doc == NULL) {
return NULL;
}
node = xmlNewDocRawNode(doc, NULL, (pcmkXmlStr) name, NULL);
if (node == NULL) {
xmlFreeDoc(doc);
return NULL;
}
xmlDocSetRootElement(doc, node);
} else {
node = xmlNewChild(parent, NULL, (pcmkXmlStr) name, NULL);
if (node == NULL) {
return NULL;
}
}
pcmk__mark_xml_created(node);
return node;
}
xmlNode *
pcmk_create_xml_text_node(xmlNode * parent, const char *name, const char *content)
{
xmlNode *node = create_xml_node(parent, name);
if (node != NULL) {
xmlNodeSetContent(node, (pcmkXmlStr) content);
}
return node;
}
xmlNode *
pcmk_create_html_node(xmlNode * parent, const char *element_name, const char *id,
const char *class_name, const char *text)
{
xmlNode *node = pcmk_create_xml_text_node(parent, element_name, text);
if (class_name != NULL) {
crm_xml_add(node, "class", class_name);
}
if (id != NULL) {
crm_xml_add(node, "id", id);
}
return node;
}
/*!
* Free an XML element and all of its children, removing it from its parent
*
* \param[in,out] xml XML element to free
*/
void
pcmk_free_xml_subtree(xmlNode *xml)
{
xmlUnlinkNode(xml); // Detaches from parent and siblings
xmlFreeNode(xml); // Frees
}
static void
free_xml_with_position(xmlNode * child, int position)
{
if (child != NULL) {
xmlNode *top = NULL;
xmlDoc *doc = child->doc;
xml_node_private_t *nodepriv = child->_private;
xml_doc_private_t *docpriv = NULL;
if (doc != NULL) {
top = xmlDocGetRootElement(doc);
}
if (doc != NULL && top == child) {
/* Free everything */
xmlFreeDoc(doc);
} else if (pcmk__check_acl(child, NULL, pcmk__xf_acl_write) == FALSE) {
GString *xpath = NULL;
pcmk__if_tracing({}, return);
xpath = pcmk__element_xpath(child);
qb_log_from_external_source(__func__, __FILE__,
"Cannot remove %s %x", LOG_TRACE,
__LINE__, 0, (const char *) xpath->str,
nodepriv->flags);
g_string_free(xpath, TRUE);
return;
} else {
if (doc && pcmk__tracking_xml_changes(child, FALSE)
&& !pcmk_is_set(nodepriv->flags, pcmk__xf_created)) {
GString *xpath = pcmk__element_xpath(child);
if (xpath != NULL) {
pcmk__deleted_xml_t *deleted_obj = NULL;
crm_trace("Deleting %s %p from %p",
(const char *) xpath->str, child, doc);
deleted_obj = calloc(1, sizeof(pcmk__deleted_xml_t));
deleted_obj->path = strdup((const char *) xpath->str);
CRM_ASSERT(deleted_obj->path != NULL);
g_string_free(xpath, TRUE);
deleted_obj->position = -1;
/* Record the "position" only for XML comments for now */
if (child->type == XML_COMMENT_NODE) {
if (position >= 0) {
deleted_obj->position = position;
} else {
deleted_obj->position = pcmk__xml_position(child,
pcmk__xf_skip);
}
}
docpriv = doc->_private;
docpriv->deleted_objs = g_list_append(docpriv->deleted_objs, deleted_obj);
pcmk__set_xml_doc_flag(child, pcmk__xf_dirty);
}
}
pcmk_free_xml_subtree(child);
}
}
}
void
free_xml(xmlNode * child)
{
free_xml_with_position(child, -1);
}
xmlNode *
copy_xml(xmlNode * src)
{
xmlDoc *doc = xmlNewDoc((pcmkXmlStr) "1.0");
xmlNode *copy = xmlDocCopyNode(src, doc, 1);
CRM_ASSERT(copy != NULL);
xmlDocSetRootElement(doc, copy);
return copy;
}
xmlNode *
string2xml(const char *input)
{
xmlNode *xml = NULL;
xmlDocPtr output = NULL;
xmlParserCtxtPtr ctxt = NULL;
- xmlErrorPtr last_error = NULL;
+ const xmlError *last_error = NULL;
if (input == NULL) {
crm_err("Can't parse NULL input");
return NULL;
}
/* create a parser context */
ctxt = xmlNewParserCtxt();
CRM_CHECK(ctxt != NULL, return NULL);
xmlCtxtResetLastError(ctxt);
xmlSetGenericErrorFunc(ctxt, pcmk__log_xmllib_err);
output = xmlCtxtReadDoc(ctxt, (pcmkXmlStr) input, NULL, NULL,
PCMK__XML_PARSE_OPTS_WITHOUT_RECOVER);
if (output == NULL) {
output = xmlCtxtReadDoc(ctxt, (pcmkXmlStr) input, NULL, NULL,
PCMK__XML_PARSE_OPTS_WITH_RECOVER);
if (output) {
crm_warn("Successfully recovered from XML errors "
"(note: a future release will treat this as a fatal failure)");
}
}
if (output) {
xml = xmlDocGetRootElement(output);
}
last_error = xmlCtxtGetLastError(ctxt);
if (last_error && last_error->code != XML_ERR_OK) {
/* crm_abort(__FILE__,__func__,__LINE__, "last_error->code != XML_ERR_OK", TRUE, TRUE); */
/*
* http://xmlsoft.org/html/libxml-xmlerror.html#xmlErrorLevel
* http://xmlsoft.org/html/libxml-xmlerror.html#xmlParserErrors
*/
crm_warn("Parsing failed (domain=%d, level=%d, code=%d): %s",
last_error->domain, last_error->level, last_error->code, last_error->message);
if (last_error->code == XML_ERR_DOCUMENT_EMPTY) {
CRM_LOG_ASSERT("Cannot parse an empty string");
} else if (last_error->code != XML_ERR_DOCUMENT_END) {
crm_err("Couldn't%s parse %d chars: %s", xml ? " fully" : "", (int)strlen(input),
input);
if (xml != NULL) {
crm_log_xml_err(xml, "Partial");
}
} else {
int len = strlen(input);
int lpc = 0;
while(lpc < len) {
crm_warn("Parse error[+%.3d]: %.80s", lpc, input+lpc);
lpc += 80;
}
CRM_LOG_ASSERT("String parsing error");
}
}
xmlFreeParserCtxt(ctxt);
return xml;
}
xmlNode *
stdin2xml(void)
{
size_t data_length = 0;
size_t read_chars = 0;
char *xml_buffer = NULL;
xmlNode *xml_obj = NULL;
do {
xml_buffer = pcmk__realloc(xml_buffer, data_length + PCMK__BUFFER_SIZE);
read_chars = fread(xml_buffer + data_length, 1, PCMK__BUFFER_SIZE,
stdin);
data_length += read_chars;
} while (read_chars == PCMK__BUFFER_SIZE);
if (data_length == 0) {
crm_warn("No XML supplied on stdin");
free(xml_buffer);
return NULL;
}
xml_buffer[data_length] = '\0';
xml_obj = string2xml(xml_buffer);
free(xml_buffer);
crm_log_xml_trace(xml_obj, "Created fragment");
return xml_obj;
}
static char *
decompress_file(const char *filename)
{
char *buffer = NULL;
int rc = 0;
size_t length = 0, read_len = 0;
BZFILE *bz_file = NULL;
FILE *input = fopen(filename, "r");
if (input == NULL) {
crm_perror(LOG_ERR, "Could not open %s for reading", filename);
return NULL;
}
bz_file = BZ2_bzReadOpen(&rc, input, 0, 0, NULL, 0);
rc = pcmk__bzlib2rc(rc);
if (rc != pcmk_rc_ok) {
crm_err("Could not prepare to read compressed %s: %s "
CRM_XS " rc=%d", filename, pcmk_rc_str(rc), rc);
BZ2_bzReadClose(&rc, bz_file);
fclose(input);
return NULL;
}
rc = BZ_OK;
// cppcheck seems not to understand the abort-logic in pcmk__realloc
// cppcheck-suppress memleak
while (rc == BZ_OK) {
buffer = pcmk__realloc(buffer, PCMK__BUFFER_SIZE + length + 1);
read_len = BZ2_bzRead(&rc, bz_file, buffer + length, PCMK__BUFFER_SIZE);
crm_trace("Read %ld bytes from file: %d", (long)read_len, rc);
if (rc == BZ_OK || rc == BZ_STREAM_END) {
length += read_len;
}
}
buffer[length] = '\0';
rc = pcmk__bzlib2rc(rc);
if (rc != pcmk_rc_ok) {
crm_err("Could not read compressed %s: %s " CRM_XS " rc=%d",
filename, pcmk_rc_str(rc), rc);
free(buffer);
buffer = NULL;
}
BZ2_bzReadClose(&rc, bz_file);
fclose(input);
return buffer;
}
/*!
* \internal
* \brief Remove XML text nodes from specified XML and all its children
*
* \param[in,out] xml XML to strip text from
*/
void
pcmk__strip_xml_text(xmlNode *xml)
{
xmlNode *iter = xml->children;
while (iter) {
xmlNode *next = iter->next;
switch (iter->type) {
case XML_TEXT_NODE:
/* Remove it */
pcmk_free_xml_subtree(iter);
break;
case XML_ELEMENT_NODE:
/* Search it */
pcmk__strip_xml_text(iter);
break;
default:
/* Leave it */
break;
}
iter = next;
}
}
xmlNode *
filename2xml(const char *filename)
{
xmlNode *xml = NULL;
xmlDocPtr output = NULL;
bool uncompressed = true;
xmlParserCtxtPtr ctxt = NULL;
- xmlErrorPtr last_error = NULL;
+ const xmlError *last_error = NULL;
/* create a parser context */
ctxt = xmlNewParserCtxt();
CRM_CHECK(ctxt != NULL, return NULL);
xmlCtxtResetLastError(ctxt);
xmlSetGenericErrorFunc(ctxt, pcmk__log_xmllib_err);
if (filename) {
uncompressed = !pcmk__ends_with_ext(filename, ".bz2");
}
if (pcmk__str_eq(filename, "-", pcmk__str_null_matches)) {
/* STDIN_FILENO == fileno(stdin) */
output = xmlCtxtReadFd(ctxt, STDIN_FILENO, "unknown.xml", NULL,
PCMK__XML_PARSE_OPTS_WITHOUT_RECOVER);
if (output == NULL) {
output = xmlCtxtReadFd(ctxt, STDIN_FILENO, "unknown.xml", NULL,
PCMK__XML_PARSE_OPTS_WITH_RECOVER);
if (output) {
crm_warn("Successfully recovered from XML errors "
"(note: a future release will treat this as a fatal failure)");
}
}
} else if (uncompressed) {
output = xmlCtxtReadFile(ctxt, filename, NULL,
PCMK__XML_PARSE_OPTS_WITHOUT_RECOVER);
if (output == NULL) {
output = xmlCtxtReadFile(ctxt, filename, NULL,
PCMK__XML_PARSE_OPTS_WITH_RECOVER);
if (output) {
crm_warn("Successfully recovered from XML errors "
"(note: a future release will treat this as a fatal failure)");
}
}
} else {
char *input = decompress_file(filename);
output = xmlCtxtReadDoc(ctxt, (pcmkXmlStr) input, NULL, NULL,
PCMK__XML_PARSE_OPTS_WITHOUT_RECOVER);
if (output == NULL) {
output = xmlCtxtReadDoc(ctxt, (pcmkXmlStr) input, NULL, NULL,
PCMK__XML_PARSE_OPTS_WITH_RECOVER);
if (output) {
crm_warn("Successfully recovered from XML errors "
"(note: a future release will treat this as a fatal failure)");
}
}
free(input);
}
if (output && (xml = xmlDocGetRootElement(output))) {
pcmk__strip_xml_text(xml);
}
last_error = xmlCtxtGetLastError(ctxt);
if (last_error && last_error->code != XML_ERR_OK) {
/* crm_abort(__FILE__,__func__,__LINE__, "last_error->code != XML_ERR_OK", TRUE, TRUE); */
/*
* http://xmlsoft.org/html/libxml-xmlerror.html#xmlErrorLevel
* http://xmlsoft.org/html/libxml-xmlerror.html#xmlParserErrors
*/
crm_err("Parsing failed (domain=%d, level=%d, code=%d): %s",
last_error->domain, last_error->level, last_error->code, last_error->message);
if (last_error && last_error->code != XML_ERR_OK) {
crm_err("Couldn't%s parse %s", xml ? " fully" : "", filename);
if (xml != NULL) {
crm_log_xml_err(xml, "Partial");
}
}
}
xmlFreeParserCtxt(ctxt);
return xml;
}
/*!
* \internal
* \brief Add a "last written" attribute to an XML element, set to current time
*
* \param[in,out] xe XML element to add attribute to
*
* \return Value that was set, or NULL on error
*/
const char *
pcmk__xe_add_last_written(xmlNode *xe)
{
char *now_s = pcmk__epoch2str(NULL, 0);
const char *result = NULL;
result = crm_xml_add(xe, XML_CIB_ATTR_WRITTEN,
pcmk__s(now_s, "Could not determine current time"));
free(now_s);
return result;
}
/*!
* \brief Sanitize a string so it is usable as an XML ID
*
* \param[in,out] id String to sanitize
*/
void
crm_xml_sanitize_id(char *id)
{
char *c;
for (c = id; *c; ++c) {
/* @TODO Sanitize more comprehensively */
switch (*c) {
case ':':
case '#':
*c = '.';
}
}
}
/*!
* \brief Set the ID of an XML element using a format
*
* \param[in,out] xml XML element
* \param[in] fmt printf-style format
* \param[in] ... any arguments required by format
*/
void
crm_xml_set_id(xmlNode *xml, const char *format, ...)
{
va_list ap;
int len = 0;
char *id = NULL;
/* equivalent to crm_strdup_printf() */
va_start(ap, format);
len = vasprintf(&id, format, ap);
va_end(ap);
CRM_ASSERT(len > 0);
crm_xml_sanitize_id(id);
crm_xml_add(xml, XML_ATTR_ID, id);
free(id);
}
/*!
* \internal
* \brief Write XML to a file stream
*
* \param[in] xml XML to write
* \param[in] filename Name of file being written (for logging only)
* \param[in,out] stream Open file stream corresponding to filename
* \param[in] compress Whether to compress XML before writing
* \param[out] nbytes Number of bytes written
*
* \return Standard Pacemaker return code
*/
static int
write_xml_stream(const xmlNode *xml, const char *filename, FILE *stream,
bool compress, unsigned int *nbytes)
{
int rc = pcmk_rc_ok;
char *buffer = NULL;
*nbytes = 0;
crm_log_xml_trace(xml, "writing");
buffer = dump_xml_formatted(xml);
CRM_CHECK(buffer && strlen(buffer),
crm_log_xml_warn(xml, "formatting failed");
rc = pcmk_rc_error;
goto bail);
if (compress) {
unsigned int in = 0;
BZFILE *bz_file = NULL;
rc = BZ_OK;
bz_file = BZ2_bzWriteOpen(&rc, stream, 5, 0, 30);
rc = pcmk__bzlib2rc(rc);
if (rc != pcmk_rc_ok) {
crm_warn("Not compressing %s: could not prepare file stream: %s "
CRM_XS " rc=%d", filename, pcmk_rc_str(rc), rc);
} else {
BZ2_bzWrite(&rc, bz_file, buffer, strlen(buffer));
rc = pcmk__bzlib2rc(rc);
if (rc != pcmk_rc_ok) {
crm_warn("Not compressing %s: could not compress data: %s "
CRM_XS " rc=%d errno=%d",
filename, pcmk_rc_str(rc), rc, errno);
}
}
if (rc == pcmk_rc_ok) {
BZ2_bzWriteClose(&rc, bz_file, 0, &in, nbytes);
rc = pcmk__bzlib2rc(rc);
if (rc != pcmk_rc_ok) {
crm_warn("Not compressing %s: could not write compressed data: %s "
CRM_XS " rc=%d errno=%d",
filename, pcmk_rc_str(rc), rc, errno);
*nbytes = 0; // retry without compression
} else {
crm_trace("Compressed XML for %s from %u bytes to %u",
filename, in, *nbytes);
}
}
rc = pcmk_rc_ok; // Either true, or we'll retry without compression
}
if (*nbytes == 0) {
rc = fprintf(stream, "%s", buffer);
if (rc < 0) {
rc = errno;
crm_perror(LOG_ERR, "writing %s", filename);
} else {
*nbytes = (unsigned int) rc;
rc = pcmk_rc_ok;
}
}
bail:
if (fflush(stream) != 0) {
rc = errno;
crm_perror(LOG_ERR, "flushing %s", filename);
}
/* Don't report error if the file does not support synchronization */
if (fsync(fileno(stream)) < 0 && errno != EROFS && errno != EINVAL) {
rc = errno;
crm_perror(LOG_ERR, "synchronizing %s", filename);
}
fclose(stream);
crm_trace("Saved %d bytes to %s as XML", *nbytes, filename);
free(buffer);
return rc;
}
/*!
* \brief Write XML to a file descriptor
*
* \param[in] xml XML to write
* \param[in] filename Name of file being written (for logging only)
* \param[in] fd Open file descriptor corresponding to filename
* \param[in] compress Whether to compress XML before writing
*
* \return Number of bytes written on success, -errno otherwise
*/
int
write_xml_fd(const xmlNode *xml, const char *filename, int fd,
gboolean compress)
{
FILE *stream = NULL;
unsigned int nbytes = 0;
int rc = pcmk_rc_ok;
CRM_CHECK((xml != NULL) && (fd > 0), return -EINVAL);
stream = fdopen(fd, "w");
if (stream == NULL) {
return -errno;
}
rc = write_xml_stream(xml, filename, stream, compress, &nbytes);
if (rc != pcmk_rc_ok) {
return pcmk_rc2legacy(rc);
}
return (int) nbytes;
}
/*!
* \brief Write XML to a file
*
* \param[in] xml XML to write
* \param[in] filename Name of file to write
* \param[in] compress Whether to compress XML before writing
*
* \return Number of bytes written on success, -errno otherwise
*/
int
write_xml_file(const xmlNode *xml, const char *filename, gboolean compress)
{
FILE *stream = NULL;
unsigned int nbytes = 0;
int rc = pcmk_rc_ok;
CRM_CHECK((xml != NULL) && (filename != NULL), return -EINVAL);
stream = fopen(filename, "w");
if (stream == NULL) {
return -errno;
}
rc = write_xml_stream(xml, filename, stream, compress, &nbytes);
if (rc != pcmk_rc_ok) {
return pcmk_rc2legacy(rc);
}
return (int) nbytes;
}
// Replace a portion of a dynamically allocated string (reallocating memory)
static char *
replace_text(char *text, int start, size_t *length, const char *replace)
{
size_t offset = strlen(replace) - 1; // We have space for 1 char already
*length += offset;
text = pcmk__realloc(text, *length);
for (size_t lpc = (*length) - 1; lpc > (start + offset); lpc--) {
text[lpc] = text[lpc - offset];
}
memcpy(text + start, replace, offset + 1);
return text;
}
/*!
* \brief Replace special characters with their XML escape sequences
*
* \param[in] text Text to escape
*
* \return Newly allocated string equivalent to \p text but with special
* characters replaced with XML escape sequences (or NULL if \p text
* is NULL)
*/
char *
crm_xml_escape(const char *text)
{
size_t length;
char *copy;
/*
* When xmlCtxtReadDoc() parses &lt; and friends in a
* value, it converts them to their human readable
* form.
*
* If one uses xmlNodeDump() to convert it back to a
* string, all is well, because special characters are
* converted back to their escape sequences.
*
* However xmlNodeDump() is randomly dog slow, even with the same
* input. So we need to replicate the escaping in our custom
* version so that the result can be re-parsed by xmlCtxtReadDoc()
* when necessary.
*/
if (text == NULL) {
return NULL;
}
length = 1 + strlen(text);
copy = strdup(text);
CRM_ASSERT(copy != NULL);
for (size_t index = 0; index < length; index++) {
if(copy[index] & 0x80 && copy[index+1] & 0x80){
index++;
break;
}
switch (copy[index]) {
case 0:
break;
case '<':
copy = replace_text(copy, index, &length, "&lt;");
break;
case '>':
copy = replace_text(copy, index, &length, "&gt;");
break;
case '"':
copy = replace_text(copy, index, &length, "&quot;");
break;
case '\'':
copy = replace_text(copy, index, &length, "&apos;");
break;
case '&':
copy = replace_text(copy, index, &length, "&amp;");
break;
case '\t':
/* Might as well just expand to a few spaces... */
copy = replace_text(copy, index, &length, " ");
break;
case '\n':
copy = replace_text(copy, index, &length, "\\n");
break;
case '\r':
copy = replace_text(copy, index, &length, "\\r");
break;
default:
/* Check for and replace non-printing characters with their octal equivalent */
if(copy[index] < ' ' || copy[index] > '~') {
char *replace = crm_strdup_printf("\\%.3o", copy[index]);
copy = replace_text(copy, index, &length, replace);
free(replace);
}
}
}
return copy;
}
/*!
* \internal
* \brief Append a string representation of an XML element to a buffer
*
* \param[in] data XML whose representation to append
* \param[in] options Group of \p pcmk__xml_fmt_options flags
* \param[in,out] buffer Where to append the content (must not be \p NULL)
* \param[in] depth Current indentation level
*/
static void
dump_xml_element(const xmlNode *data, uint32_t options, GString *buffer,
int depth)
{
bool pretty = pcmk_is_set(options, pcmk__xml_fmt_pretty);
bool filtered = pcmk_is_set(options, pcmk__xml_fmt_filtered);
int spaces = pretty? (2 * depth) : 0;
for (int lpc = 0; lpc < spaces; lpc++) {
g_string_append_c(buffer, ' ');
}
pcmk__g_strcat(buffer, "<", data->name, NULL);
for (const xmlAttr *attr = pcmk__xe_first_attr(data); attr != NULL;
attr = attr->next) {
if (!filtered || !pcmk__xa_filterable((const char *) (attr->name))) {
pcmk__dump_xml_attr(attr, buffer);
}
}
if (data->children == NULL) {
g_string_append(buffer, "/>");
} else {
g_string_append_c(buffer, '>');
}
if (pretty) {
g_string_append_c(buffer, '\n');
}
if (data->children) {
for (const xmlNode *child = data->children; child != NULL;
child = child->next) {
pcmk__xml2text(child, options, buffer, depth + 1);
}
for (int lpc = 0; lpc < spaces; lpc++) {
g_string_append_c(buffer, ' ');
}
pcmk__g_strcat(buffer, "</", data->name, ">", NULL);
if (pretty) {
g_string_append_c(buffer, '\n');
}
}
}
/*!
* \internal
* \brief Append XML text content to a buffer
*
* \param[in] data XML whose content to append
* \param[in] options Group of \p xml_log_options flags
* \param[in,out] buffer Where to append the content (must not be \p NULL)
* \param[in] depth Current indentation level
*/
static void
dump_xml_text(const xmlNode *data, uint32_t options, GString *buffer,
int depth)
{
/* @COMPAT: Remove when log_data_element() is removed. There are no internal
* code paths to this, except through the deprecated log_data_element().
*/
bool pretty = pcmk_is_set(options, pcmk__xml_fmt_pretty);
int spaces = pretty? (2 * depth) : 0;
for (int lpc = 0; lpc < spaces; lpc++) {
g_string_append_c(buffer, ' ');
}
g_string_append(buffer, (const gchar *) data->content);
if (pretty) {
g_string_append_c(buffer, '\n');
}
}
/*!
* \internal
* \brief Append XML CDATA content to a buffer
*
* \param[in] data XML whose content to append
* \param[in] options Group of \p pcmk__xml_fmt_options flags
* \param[in,out] buffer Where to append the content (must not be \p NULL)
* \param[in] depth Current indentation level
*/
static void
dump_xml_cdata(const xmlNode *data, uint32_t options, GString *buffer,
int depth)
{
bool pretty = pcmk_is_set(options, pcmk__xml_fmt_pretty);
int spaces = pretty? (2 * depth) : 0;
for (int lpc = 0; lpc < spaces; lpc++) {
g_string_append_c(buffer, ' ');
}
pcmk__g_strcat(buffer, "<![CDATA[", (const char *) data->content, "]]>",
NULL);
if (pretty) {
g_string_append_c(buffer, '\n');
}
}
/*!
* \internal
* \brief Append an XML comment to a buffer
*
* \param[in] data XML whose content to append
* \param[in] options Group of \p pcmk__xml_fmt_options flags
* \param[in,out] buffer Where to append the content (must not be \p NULL)
* \param[in] depth Current indentation level
*/
static void
dump_xml_comment(const xmlNode *data, uint32_t options, GString *buffer,
int depth)
{
bool pretty = pcmk_is_set(options, pcmk__xml_fmt_pretty);
int spaces = pretty? (2 * depth) : 0;
for (int lpc = 0; lpc < spaces; lpc++) {
g_string_append_c(buffer, ' ');
}
pcmk__g_strcat(buffer, "<!--", (const char *) data->content, "-->", NULL);
if (pretty) {
g_string_append_c(buffer, '\n');
}
}
/*!
* \internal
* \brief Get a string representation of an XML element type
*
* \param[in] type XML element type
*
* \return String representation of \p type
*/
static const char *
xml_element_type2str(xmlElementType type)
{
static const char *const element_type_names[] = {
[XML_ELEMENT_NODE] = "element",
[XML_ATTRIBUTE_NODE] = "attribute",
[XML_TEXT_NODE] = "text",
[XML_CDATA_SECTION_NODE] = "CDATA section",
[XML_ENTITY_REF_NODE] = "entity reference",
[XML_ENTITY_NODE] = "entity",
[XML_PI_NODE] = "PI",
[XML_COMMENT_NODE] = "comment",
[XML_DOCUMENT_NODE] = "document",
[XML_DOCUMENT_TYPE_NODE] = "document type",
[XML_DOCUMENT_FRAG_NODE] = "document fragment",
[XML_NOTATION_NODE] = "notation",
[XML_HTML_DOCUMENT_NODE] = "HTML document",
[XML_DTD_NODE] = "DTD",
[XML_ELEMENT_DECL] = "element declaration",
[XML_ATTRIBUTE_DECL] = "attribute declaration",
[XML_ENTITY_DECL] = "entity declaration",
[XML_NAMESPACE_DECL] = "namespace declaration",
[XML_XINCLUDE_START] = "XInclude start",
[XML_XINCLUDE_END] = "XInclude end",
};
if ((type < 0) || (type >= PCMK__NELEM(element_type_names))) {
return "unrecognized type";
}
return element_type_names[type];
}
/*!
* \internal
* \brief Create a text representation of an XML object
*
* \param[in] data XML to convert
* \param[in] options Group of \p pcmk__xml_fmt_options flags
* \param[in,out] buffer Where to store the text (must not be \p NULL)
* \param[in] depth Current indentation level
*/
void
pcmk__xml2text(const xmlNode *data, uint32_t options, GString *buffer,
int depth)
{
if (data == NULL) {
crm_trace("Nothing to dump");
return;
}
CRM_ASSERT(buffer != NULL);
CRM_CHECK(depth >= 0, depth = 0);
switch(data->type) {
case XML_ELEMENT_NODE:
/* Handle below */
dump_xml_element(data, options, buffer, depth);
break;
case XML_TEXT_NODE:
if (pcmk_is_set(options, pcmk__xml_fmt_text)) {
dump_xml_text(data, options, buffer, depth);
}
break;
case XML_COMMENT_NODE:
dump_xml_comment(data, options, buffer, depth);
break;
case XML_CDATA_SECTION_NODE:
dump_xml_cdata(data, options, buffer, depth);
break;
default:
crm_warn("Cannot convert XML %s node to text " CRM_XS " type=%d",
xml_element_type2str(data->type), data->type);
break;
}
}
char *
dump_xml_formatted_with_text(const xmlNode *xml)
{
/* libxml's xmlNodeDumpOutput() would work here since we're not specifically
* filtering out any nodes. However, use pcmk__xml2text() for consistency,
* to escape attribute values, and to allow a const argument.
*/
char *buffer = NULL;
GString *g_buffer = g_string_sized_new(1024);
pcmk__xml2text(xml, pcmk__xml_fmt_pretty|pcmk__xml_fmt_text, g_buffer, 0);
pcmk__str_update(&buffer, g_buffer->str);
g_string_free(g_buffer, TRUE);
return buffer;
}
char *
dump_xml_formatted(const xmlNode *xml)
{
char *buffer = NULL;
GString *g_buffer = g_string_sized_new(1024);
pcmk__xml2text(xml, pcmk__xml_fmt_pretty, g_buffer, 0);
pcmk__str_update(&buffer, g_buffer->str);
g_string_free(g_buffer, TRUE);
return buffer;
}
char *
dump_xml_unformatted(const xmlNode *xml)
{
char *buffer = NULL;
GString *g_buffer = g_string_sized_new(1024);
pcmk__xml2text(xml, 0, g_buffer, 0);
pcmk__str_update(&buffer, g_buffer->str);
g_string_free(g_buffer, TRUE);
return buffer;
}
int
pcmk__xml2fd(int fd, xmlNode *cur)
{
bool success;
xmlOutputBuffer *fd_out = xmlOutputBufferCreateFd(fd, NULL);
CRM_ASSERT(fd_out != NULL);
xmlNodeDumpOutput(fd_out, cur->doc, cur, 0, pcmk__xml_fmt_pretty, NULL);
success = xmlOutputBufferWrite(fd_out, sizeof("\n") - 1, "\n") != -1;
success = xmlOutputBufferClose(fd_out) != -1 && success;
if (!success) {
return EIO;
}
fsync(fd);
return pcmk_rc_ok;
}
void
xml_remove_prop(xmlNode * obj, const char *name)
{
if (crm_element_value(obj, name) == NULL) {
return;
}
if (pcmk__check_acl(obj, NULL, pcmk__xf_acl_write) == FALSE) {
crm_trace("Cannot remove %s from %s", name, obj->name);
} else if (pcmk__tracking_xml_changes(obj, FALSE)) {
/* Leave in place (marked for removal) until after the diff is calculated */
xmlAttr *attr = xmlHasProp(obj, (pcmkXmlStr) name);
xml_node_private_t *nodepriv = attr->_private;
set_parent_flag(obj, pcmk__xf_dirty);
pcmk__set_xml_flags(nodepriv, pcmk__xf_deleted);
} else {
xmlUnsetProp(obj, (pcmkXmlStr) name);
}
}
void
save_xml_to_file(const xmlNode *xml, const char *desc, const char *filename)
{
char *f = NULL;
if (filename == NULL) {
char *uuid = crm_generate_uuid();
f = crm_strdup_printf("%s/%s", pcmk__get_tmpdir(), uuid);
filename = f;
free(uuid);
}
crm_info("Saving %s to %s", desc, filename);
write_xml_file(xml, filename, FALSE);
free(f);
}
/*!
* \internal
* \brief Set a flag on all attributes of an XML element
*
* \param[in,out] xml XML node to set flags on
* \param[in] flag XML private flag to set
*/
static void
set_attrs_flag(xmlNode *xml, enum xml_private_flags flag)
{
for (xmlAttr *attr = pcmk__xe_first_attr(xml); attr; attr = attr->next) {
pcmk__set_xml_flags((xml_node_private_t *) (attr->_private), flag);
}
}
/*!
* \internal
* \brief Add an XML attribute to a node, marked as deleted
*
* When calculating XML changes, we need to know when an attribute has been
* deleted. Add the attribute back to the new XML, so that we can check the
* removal against ACLs, and mark it as deleted for later removal after
* differences have been calculated.
*
* \param[in,out] new_xml XML to modify
* \param[in] element Name of XML element that changed (for logging)
* \param[in] attr_name Name of attribute that was deleted
* \param[in] old_value Value of attribute that was deleted
*/
static void
mark_attr_deleted(xmlNode *new_xml, const char *element, const char *attr_name,
const char *old_value)
{
xml_doc_private_t *docpriv = new_xml->doc->_private;
xmlAttr *attr = NULL;
xml_node_private_t *nodepriv;
// Prevent the dirty flag being set recursively upwards
pcmk__clear_xml_flags(docpriv, pcmk__xf_tracking);
// Restore the old value (and the tracking flag)
attr = xmlSetProp(new_xml, (pcmkXmlStr) attr_name, (pcmkXmlStr) old_value);
pcmk__set_xml_flags(docpriv, pcmk__xf_tracking);
// Reset flags (so the attribute doesn't appear as newly created)
nodepriv = attr->_private;
nodepriv->flags = 0;
// Check ACLs and mark restored value for later removal
xml_remove_prop(new_xml, attr_name);
crm_trace("XML attribute %s=%s was removed from %s",
attr_name, old_value, element);
}
/*
* \internal
* \brief Check ACLs for a changed XML attribute
*/
static void
mark_attr_changed(xmlNode *new_xml, const char *element, const char *attr_name,
const char *old_value)
{
char *vcopy = crm_element_value_copy(new_xml, attr_name);
crm_trace("XML attribute %s was changed from '%s' to '%s' in %s",
attr_name, old_value, vcopy, element);
// Restore the original value
xmlSetProp(new_xml, (pcmkXmlStr) attr_name, (pcmkXmlStr) old_value);
// Change it back to the new value, to check ACLs
crm_xml_add(new_xml, attr_name, vcopy);
free(vcopy);
}
/*!
* \internal
* \brief Mark an XML attribute as having changed position
*
* \param[in,out] new_xml XML to modify
* \param[in] element Name of XML element that changed (for logging)
* \param[in,out] old_attr Attribute that moved, in original XML
* \param[in,out] new_attr Attribute that moved, in \p new_xml
* \param[in] p_old Ordinal position of \p old_attr in original XML
* \param[in] p_new Ordinal position of \p new_attr in \p new_xml
*/
static void
mark_attr_moved(xmlNode *new_xml, const char *element, xmlAttr *old_attr,
xmlAttr *new_attr, int p_old, int p_new)
{
xml_node_private_t *nodepriv = new_attr->_private;
crm_trace("XML attribute %s moved from position %d to %d in %s",
old_attr->name, p_old, p_new, element);
// Mark document, element, and all element's parents as changed
pcmk__mark_xml_node_dirty(new_xml);
// Mark attribute as changed
pcmk__set_xml_flags(nodepriv, pcmk__xf_dirty|pcmk__xf_moved);
nodepriv = (p_old > p_new)? old_attr->_private : new_attr->_private;
pcmk__set_xml_flags(nodepriv, pcmk__xf_skip);
}
/*!
* \internal
* \brief Calculate differences in all previously existing XML attributes
*
* \param[in,out] old_xml Original XML to compare
* \param[in,out] new_xml New XML to compare
*/
static void
xml_diff_old_attrs(xmlNode *old_xml, xmlNode *new_xml)
{
xmlAttr *attr_iter = pcmk__xe_first_attr(old_xml);
while (attr_iter != NULL) {
const char *name = (const char *) attr_iter->name;
xmlAttr *old_attr = attr_iter;
xmlAttr *new_attr = xmlHasProp(new_xml, attr_iter->name);
const char *old_value = pcmk__xml_attr_value(attr_iter);
attr_iter = attr_iter->next;
if (new_attr == NULL) {
mark_attr_deleted(new_xml, (const char *) old_xml->name, name,
old_value);
} else {
xml_node_private_t *nodepriv = new_attr->_private;
int new_pos = pcmk__xml_position((xmlNode*) new_attr,
pcmk__xf_skip);
int old_pos = pcmk__xml_position((xmlNode*) old_attr,
pcmk__xf_skip);
const char *new_value = crm_element_value(new_xml, name);
// This attribute isn't new
pcmk__clear_xml_flags(nodepriv, pcmk__xf_created);
if (strcmp(new_value, old_value) != 0) {
mark_attr_changed(new_xml, (const char *) old_xml->name, name,
old_value);
} else if ((old_pos != new_pos)
&& !pcmk__tracking_xml_changes(new_xml, TRUE)) {
mark_attr_moved(new_xml, (const char *) old_xml->name,
old_attr, new_attr, old_pos, new_pos);
}
}
}
}
/*!
* \internal
* \brief Check all attributes in new XML for creation
*
* For each of a given XML element's attributes marked as newly created, accept
* (and mark as dirty) or reject the creation according to ACLs.
*
* \param[in,out] new_xml XML to check
*/
static void
mark_created_attrs(xmlNode *new_xml)
{
xmlAttr *attr_iter = pcmk__xe_first_attr(new_xml);
while (attr_iter != NULL) {
xmlAttr *new_attr = attr_iter;
xml_node_private_t *nodepriv = attr_iter->_private;
attr_iter = attr_iter->next;
if (pcmk_is_set(nodepriv->flags, pcmk__xf_created)) {
const char *attr_name = (const char *) new_attr->name;
crm_trace("Created new attribute %s=%s in %s",
attr_name, pcmk__xml_attr_value(new_attr),
new_xml->name);
/* Check ACLs (we can't use the remove-then-create trick because it
* would modify the attribute position).
*/
if (pcmk__check_acl(new_xml, attr_name, pcmk__xf_acl_write)) {
pcmk__mark_xml_attr_dirty(new_attr);
} else {
// Creation was not allowed, so remove the attribute
xmlUnsetProp(new_xml, new_attr->name);
}
}
}
}
/*!
* \internal
* \brief Calculate differences in attributes between two XML nodes
*
* \param[in,out] old_xml Original XML to compare
* \param[in,out] new_xml New XML to compare
*/
static void
xml_diff_attrs(xmlNode *old_xml, xmlNode *new_xml)
{
set_attrs_flag(new_xml, pcmk__xf_created); // cleared later if not really new
xml_diff_old_attrs(old_xml, new_xml);
mark_created_attrs(new_xml);
}
/*!
* \internal
* \brief Add an XML child element to a node, marked as deleted
*
* When calculating XML changes, we need to know when a child element has been
* deleted. Add the child back to the new XML, so that we can check the removal
* against ACLs, and mark it as deleted for later removal after differences have
* been calculated.
*
* \param[in,out] old_child Child element from original XML
* \param[in,out] new_parent New XML to add marked copy to
*/
static void
mark_child_deleted(xmlNode *old_child, xmlNode *new_parent)
{
// Re-create the child element so we can check ACLs
xmlNode *candidate = add_node_copy(new_parent, old_child);
// Clear flags on new child and its children
reset_xml_node_flags(candidate);
// Check whether ACLs allow the deletion
pcmk__apply_acl(xmlDocGetRootElement(candidate->doc));
// Remove the child again (which will track it in document's deleted_objs)
free_xml_with_position(candidate,
pcmk__xml_position(old_child, pcmk__xf_skip));
if (pcmk__xml_match(new_parent, old_child, true) == NULL) {
pcmk__set_xml_flags((xml_node_private_t *) (old_child->_private),
pcmk__xf_skip);
}
}
static void
mark_child_moved(xmlNode *old_child, xmlNode *new_parent, xmlNode *new_child,
int p_old, int p_new)
{
xml_node_private_t *nodepriv = new_child->_private;
crm_trace("Child element %s with id='%s' moved from position %d to %d under %s",
new_child->name, (ID(new_child)? ID(new_child) : "<no id>"),
p_old, p_new, new_parent->name);
pcmk__mark_xml_node_dirty(new_parent);
pcmk__set_xml_flags(nodepriv, pcmk__xf_moved);
if (p_old > p_new) {
nodepriv = old_child->_private;
} else {
nodepriv = new_child->_private;
}
pcmk__set_xml_flags(nodepriv, pcmk__xf_skip);
}
// Given original and new XML, mark new XML portions that have changed
static void
mark_xml_changes(xmlNode *old_xml, xmlNode *new_xml, bool check_top)
{
xmlNode *cIter = NULL;
xml_node_private_t *nodepriv = NULL;
CRM_CHECK(new_xml != NULL, return);
if (old_xml == NULL) {
pcmk__mark_xml_created(new_xml);
pcmk__apply_creation_acl(new_xml, check_top);
return;
}
nodepriv = new_xml->_private;
CRM_CHECK(nodepriv != NULL, return);
if(nodepriv->flags & pcmk__xf_processed) {
/* Avoid re-comparing nodes */
return;
}
pcmk__set_xml_flags(nodepriv, pcmk__xf_processed);
xml_diff_attrs(old_xml, new_xml);
// Check for differences in the original children
for (cIter = pcmk__xml_first_child(old_xml); cIter != NULL; ) {
xmlNode *old_child = cIter;
xmlNode *new_child = pcmk__xml_match(new_xml, cIter, true);
cIter = pcmk__xml_next(cIter);
if(new_child) {
mark_xml_changes(old_child, new_child, TRUE);
} else {
mark_child_deleted(old_child, new_xml);
}
}
// Check for moved or created children
for (cIter = pcmk__xml_first_child(new_xml); cIter != NULL; ) {
xmlNode *new_child = cIter;
xmlNode *old_child = pcmk__xml_match(old_xml, cIter, true);
cIter = pcmk__xml_next(cIter);
if(old_child == NULL) {
// This is a newly created child
nodepriv = new_child->_private;
pcmk__set_xml_flags(nodepriv, pcmk__xf_skip);
mark_xml_changes(old_child, new_child, TRUE);
} else {
/* Check for movement, we already checked for differences */
int p_new = pcmk__xml_position(new_child, pcmk__xf_skip);
int p_old = pcmk__xml_position(old_child, pcmk__xf_skip);
if(p_old != p_new) {
mark_child_moved(old_child, new_xml, new_child, p_old, p_new);
}
}
}
}
void
xml_calculate_significant_changes(xmlNode *old_xml, xmlNode *new_xml)
{
pcmk__set_xml_doc_flag(new_xml, pcmk__xf_lazy);
xml_calculate_changes(old_xml, new_xml);
}
// Called functions may set the \p pcmk__xf_skip flag on parts of \p old_xml
void
xml_calculate_changes(xmlNode *old_xml, xmlNode *new_xml)
{
CRM_CHECK((old_xml != NULL) && (new_xml != NULL)
&& pcmk__xe_is(old_xml, (const char *) new_xml->name)
&& pcmk__str_eq(ID(old_xml), ID(new_xml), pcmk__str_none),
return);
if(xml_tracking_changes(new_xml) == FALSE) {
xml_track_changes(new_xml, NULL, NULL, FALSE);
}
mark_xml_changes(old_xml, new_xml, FALSE);
}
gboolean
can_prune_leaf(xmlNode * xml_node)
{
xmlNode *cIter = NULL;
gboolean can_prune = TRUE;
CRM_CHECK(xml_node != NULL, return FALSE);
if (pcmk__strcase_any_of((const char *) xml_node->name,
XML_TAG_RESOURCE_REF, XML_CIB_TAG_OBJ_REF,
XML_ACL_TAG_ROLE_REF, XML_ACL_TAG_ROLE_REFv1,
NULL)) {
return FALSE;
}
for (xmlAttrPtr a = pcmk__xe_first_attr(xml_node); a != NULL; a = a->next) {
const char *p_name = (const char *) a->name;
if (strcmp(p_name, XML_ATTR_ID) == 0) {
continue;
}
can_prune = FALSE;
}
cIter = pcmk__xml_first_child(xml_node);
while (cIter) {
xmlNode *child = cIter;
cIter = pcmk__xml_next(cIter);
if (can_prune_leaf(child)) {
free_xml(child);
} else {
can_prune = FALSE;
}
}
return can_prune;
}
/*!
* \internal
* \brief Find a comment with matching content in specified XML
*
* \param[in] root XML to search
* \param[in] search_comment Comment whose content should be searched for
* \param[in] exact If true, comment must also be at same position
*/
xmlNode *
pcmk__xc_match(const xmlNode *root, const xmlNode *search_comment, bool exact)
{
xmlNode *a_child = NULL;
int search_offset = pcmk__xml_position(search_comment, pcmk__xf_skip);
CRM_CHECK(search_comment->type == XML_COMMENT_NODE, return NULL);
for (a_child = pcmk__xml_first_child(root); a_child != NULL;
a_child = pcmk__xml_next(a_child)) {
if (exact) {
int offset = pcmk__xml_position(a_child, pcmk__xf_skip);
xml_node_private_t *nodepriv = a_child->_private;
if (offset < search_offset) {
continue;
} else if (offset > search_offset) {
return NULL;
}
if (pcmk_is_set(nodepriv->flags, pcmk__xf_skip)) {
continue;
}
}
if (a_child->type == XML_COMMENT_NODE
&& pcmk__str_eq((const char *)a_child->content, (const char *)search_comment->content, pcmk__str_casei)) {
return a_child;
} else if (exact) {
return NULL;
}
}
return NULL;
}
/*!
* \internal
* \brief Make one XML comment match another (in content)
*
* \param[in,out] parent If \p target is NULL and this is not, add or update
* comment child of this XML node that matches \p update
* \param[in,out] target If not NULL, update this XML comment node
* \param[in] update Make comment content match this (must not be NULL)
*
* \note At least one of \parent and \target must be non-NULL
*/
void
pcmk__xc_update(xmlNode *parent, xmlNode *target, xmlNode *update)
{
CRM_CHECK(update != NULL, return);
CRM_CHECK(update->type == XML_COMMENT_NODE, return);
if (target == NULL) {
target = pcmk__xc_match(parent, update, false);
}
if (target == NULL) {
add_node_copy(parent, update);
} else if (!pcmk__str_eq((const char *)target->content, (const char *)update->content, pcmk__str_casei)) {
xmlFree(target->content);
target->content = xmlStrdup(update->content);
}
}
/*!
* \internal
* \brief Make one XML tree match another (in children and attributes)
*
* \param[in,out] parent If \p target is NULL and this is not, add or update
* child of this XML node that matches \p update
* \param[in,out] target If not NULL, update this XML
* \param[in] update Make the desired XML match this (must not be NULL)
* \param[in] as_diff If false, expand "++" when making attributes match
*
* \note At least one of \p parent and \p target must be non-NULL
*/
void
pcmk__xml_update(xmlNode *parent, xmlNode *target, xmlNode *update,
bool as_diff)
{
xmlNode *a_child = NULL;
const char *object_name = NULL,
*object_href = NULL,
*object_href_val = NULL;
#if XML_PARSER_DEBUG
crm_log_xml_trace(update, "update:");
crm_log_xml_trace(target, "target:");
#endif
CRM_CHECK(update != NULL, return);
if (update->type == XML_COMMENT_NODE) {
pcmk__xc_update(parent, target, update);
return;
}
object_name = (const char *) update->name;
object_href_val = ID(update);
if (object_href_val != NULL) {
object_href = XML_ATTR_ID;
} else {
object_href_val = crm_element_value(update, XML_ATTR_IDREF);
object_href = (object_href_val == NULL) ? NULL : XML_ATTR_IDREF;
}
CRM_CHECK(object_name != NULL, return);
CRM_CHECK(target != NULL || parent != NULL, return);
if (target == NULL) {
target = pcmk__xe_match(parent, object_name,
object_href, object_href_val);
}
if (target == NULL) {
target = create_xml_node(parent, object_name);
CRM_CHECK(target != NULL, return);
#if XML_PARSER_DEBUG
crm_trace("Added <%s%s%s%s%s/>", pcmk__s(object_name, "<null>"),
object_href ? " " : "",
object_href ? object_href : "",
object_href ? "=" : "",
object_href ? object_href_val : "");
} else {
crm_trace("Found node <%s%s%s%s%s/> to update",
pcmk__s(object_name, "<null>"),
object_href ? " " : "",
object_href ? object_href : "",
object_href ? "=" : "",
object_href ? object_href_val : "");
#endif
}
CRM_CHECK(pcmk__xe_is(target, (const char *) update->name), return);
if (as_diff == FALSE) {
/* So that expand_plus_plus() gets called */
copy_in_properties(target, update);
} else {
/* No need for expand_plus_plus(), just raw speed */
for (xmlAttrPtr a = pcmk__xe_first_attr(update); a != NULL;
a = a->next) {
const char *p_value = pcmk__xml_attr_value(a);
/* Remove it first so the ordering of the update is preserved */
xmlUnsetProp(target, a->name);
xmlSetProp(target, a->name, (pcmkXmlStr) p_value);
}
}
for (a_child = pcmk__xml_first_child(update); a_child != NULL;
a_child = pcmk__xml_next(a_child)) {
#if XML_PARSER_DEBUG
crm_trace("Updating child <%s%s%s%s%s/>",
pcmk__s(object_name, "<null>"),
object_href ? " " : "",
object_href ? object_href : "",
object_href ? "=" : "",
object_href ? object_href_val : "");
#endif
pcmk__xml_update(target, NULL, a_child, as_diff);
}
#if XML_PARSER_DEBUG
crm_trace("Finished with <%s%s%s%s%s/>", pcmk__s(object_name, "<null>"),
object_href ? " " : "",
object_href ? object_href : "",
object_href ? "=" : "",
object_href ? object_href_val : "");
#endif
}
gboolean
update_xml_child(xmlNode * child, xmlNode * to_update)
{
gboolean can_update = TRUE;
xmlNode *child_of_child = NULL;
CRM_CHECK(child != NULL, return FALSE);
CRM_CHECK(to_update != NULL, return FALSE);
if (!pcmk__xe_is(to_update, (const char *) child->name)) {
can_update = FALSE;
} else if (!pcmk__str_eq(ID(to_update), ID(child), pcmk__str_none)) {
can_update = FALSE;
} else if (can_update) {
#if XML_PARSER_DEBUG
crm_log_xml_trace(child, "Update match found...");
#endif
pcmk__xml_update(NULL, child, to_update, false);
}
for (child_of_child = pcmk__xml_first_child(child); child_of_child != NULL;
child_of_child = pcmk__xml_next(child_of_child)) {
/* only update the first one */
if (can_update) {
break;
}
can_update = update_xml_child(child_of_child, to_update);
}
return can_update;
}
int
find_xml_children(xmlNode ** children, xmlNode * root,
const char *tag, const char *field, const char *value, gboolean search_matches)
{
int match_found = 0;
CRM_CHECK(root != NULL, return FALSE);
CRM_CHECK(children != NULL, return FALSE);
if ((tag != NULL) && !pcmk__xe_is(root, tag)) {
} else if (value != NULL && !pcmk__str_eq(value, crm_element_value(root, field), pcmk__str_casei)) {
} else {
if (*children == NULL) {
*children = create_xml_node(NULL, __func__);
}
add_node_copy(*children, root);
match_found = 1;
}
if (search_matches || match_found == 0) {
xmlNode *child = NULL;
for (child = pcmk__xml_first_child(root); child != NULL;
child = pcmk__xml_next(child)) {
match_found += find_xml_children(children, child, tag, field, value, search_matches);
}
}
return match_found;
}
gboolean
replace_xml_child(xmlNode * parent, xmlNode * child, xmlNode * update, gboolean delete_only)
{
gboolean can_delete = FALSE;
xmlNode *child_of_child = NULL;
const char *up_id = NULL;
const char *child_id = NULL;
const char *right_val = NULL;
CRM_CHECK(child != NULL, return FALSE);
CRM_CHECK(update != NULL, return FALSE);
up_id = ID(update);
child_id = ID(child);
if (up_id == NULL || (child_id && strcmp(child_id, up_id) == 0)) {
can_delete = TRUE;
}
if (!pcmk__xe_is(update, (const char *) child->name)) {
can_delete = FALSE;
}
if (can_delete && delete_only) {
for (xmlAttrPtr a = pcmk__xe_first_attr(update); a != NULL;
a = a->next) {
const char *p_name = (const char *) a->name;
const char *p_value = pcmk__xml_attr_value(a);
right_val = crm_element_value(child, p_name);
if (!pcmk__str_eq(p_value, right_val, pcmk__str_casei)) {
can_delete = FALSE;
}
}
}
if (can_delete && parent != NULL) {
crm_log_xml_trace(child, "Delete match found...");
if (delete_only || update == NULL) {
free_xml(child);
} else {
xmlNode *old = child;
xmlNode *new = xmlCopyNode(update, 1);
CRM_ASSERT(new != NULL);
// May be unnecessary but avoids slight changes to some test outputs
reset_xml_node_flags(new);
old = xmlReplaceNode(old, new);
if (xml_tracking_changes(new)) {
// Replaced sections may have included relevant ACLs
pcmk__apply_acl(new);
}
xml_calculate_changes(old, new);
xmlFreeNode(old);
}
return TRUE;
} else if (can_delete) {
crm_log_xml_debug(child, "Cannot delete the search root");
can_delete = FALSE;
}
child_of_child = pcmk__xml_first_child(child);
while (child_of_child) {
xmlNode *next = pcmk__xml_next(child_of_child);
can_delete = replace_xml_child(child, child_of_child, update, delete_only);
/* only delete the first one */
if (can_delete) {
child_of_child = NULL;
} else {
child_of_child = next;
}
}
return can_delete;
}
xmlNode *
sorted_xml(xmlNode *input, xmlNode *parent, gboolean recursive)
{
xmlNode *child = NULL;
GSList *nvpairs = NULL;
xmlNode *result = NULL;
CRM_CHECK(input != NULL, return NULL);
result = create_xml_node(parent, (const char *) input->name);
nvpairs = pcmk_xml_attrs2nvpairs(input);
nvpairs = pcmk_sort_nvpairs(nvpairs);
pcmk_nvpairs2xml_attrs(nvpairs, result);
pcmk_free_nvpairs(nvpairs);
for (child = pcmk__xml_first_child(input); child != NULL;
child = pcmk__xml_next(child)) {
if (recursive) {
sorted_xml(child, result, recursive);
} else {
add_node_copy(result, child);
}
}
return result;
}
xmlNode *
first_named_child(const xmlNode *parent, const char *name)
{
xmlNode *match = NULL;
for (match = pcmk__xe_first_child(parent); match != NULL;
match = pcmk__xe_next(match)) {
/*
* name == NULL gives first child regardless of name; this is
* semantically incorrect in this function, but may be necessary
* due to prior use of xml_child_iter_filter
*/
if (pcmk__str_eq(name, (const char *)match->name, pcmk__str_null_matches)) {
return match;
}
}
return NULL;
}
/*!
* \brief Get next instance of same XML tag
*
* \param[in] sibling XML tag to start from
*
* \return Next sibling XML tag with same name
*/
xmlNode *
crm_next_same_xml(const xmlNode *sibling)
{
xmlNode *match = pcmk__xe_next(sibling);
while (match != NULL) {
if (pcmk__xe_is(match, (const char *) sibling->name)) {
return match;
}
match = pcmk__xe_next(match);
}
return NULL;
}
void
crm_xml_init(void)
{
static bool init = true;
if(init) {
init = false;
/* The default allocator XML_BUFFER_ALLOC_EXACT does far too many
* pcmk__realloc()s and it can take upwards of 18 seconds (yes, seconds)
* to dump a 28kb tree which XML_BUFFER_ALLOC_DOUBLEIT can do in
* less than 1 second.
*/
xmlSetBufferAllocationScheme(XML_BUFFER_ALLOC_DOUBLEIT);
/* Populate and free the _private field when nodes are created and destroyed */
xmlDeregisterNodeDefault(free_private_data);
xmlRegisterNodeDefault(new_private_data);
crm_schema_init();
}
}
void
crm_xml_cleanup(void)
{
crm_schema_cleanup();
xmlCleanupParser();
}
#define XPATH_MAX 512
xmlNode *
expand_idref(xmlNode * input, xmlNode * top)
{
const char *ref = NULL;
xmlNode *result = input;
if (result == NULL) {
return NULL;
} else if (top == NULL) {
top = input;
}
ref = crm_element_value(result, XML_ATTR_IDREF);
if (ref != NULL) {
char *xpath_string = crm_strdup_printf("//%s[@" XML_ATTR_ID "='%s']",
result->name, ref);
result = get_xpath_object(xpath_string, top, LOG_ERR);
if (result == NULL) {
char *nodePath = (char *)xmlGetNodePath(top);
crm_err("No match for %s found in %s: Invalid configuration",
xpath_string, pcmk__s(nodePath, "unrecognizable path"));
free(nodePath);
}
free(xpath_string);
}
return result;
}
char *
pcmk__xml_artefact_root(enum pcmk__xml_artefact_ns ns)
{
static const char *base = NULL;
char *ret = NULL;
if (base == NULL) {
base = pcmk__env_option(PCMK__ENV_SCHEMA_DIRECTORY);
}
if (pcmk__str_empty(base)) {
base = CRM_SCHEMA_DIRECTORY;
}
switch (ns) {
case pcmk__xml_artefact_ns_legacy_rng:
case pcmk__xml_artefact_ns_legacy_xslt:
ret = strdup(base);
break;
case pcmk__xml_artefact_ns_base_rng:
case pcmk__xml_artefact_ns_base_xslt:
ret = crm_strdup_printf("%s/base", base);
break;
default:
crm_err("XML artefact family specified as %u not recognized", ns);
}
return ret;
}
char *
pcmk__xml_artefact_path(enum pcmk__xml_artefact_ns ns, const char *filespec)
{
char *base = pcmk__xml_artefact_root(ns), *ret = NULL;
switch (ns) {
case pcmk__xml_artefact_ns_legacy_rng:
case pcmk__xml_artefact_ns_base_rng:
ret = crm_strdup_printf("%s/%s.rng", base, filespec);
break;
case pcmk__xml_artefact_ns_legacy_xslt:
case pcmk__xml_artefact_ns_base_xslt:
ret = crm_strdup_printf("%s/%s.xsl", base, filespec);
break;
default:
crm_err("XML artefact family specified as %u not recognized", ns);
}
free(base);
return ret;
}
void
pcmk__xe_set_propv(xmlNodePtr node, va_list pairs)
{
while (true) {
const char *name, *value;
name = va_arg(pairs, const char *);
if (name == NULL) {
return;
}
value = va_arg(pairs, const char *);
if (value != NULL) {
crm_xml_add(node, name, value);
}
}
}
void
pcmk__xe_set_props(xmlNodePtr node, ...)
{
va_list pairs;
va_start(pairs, node);
pcmk__xe_set_propv(node, pairs);
va_end(pairs);
}
int
pcmk__xe_foreach_child(xmlNode *xml, const char *child_element_name,
int (*handler)(xmlNode *xml, void *userdata),
void *userdata)
{
xmlNode *children = (xml? xml->children : NULL);
CRM_ASSERT(handler != NULL);
for (xmlNode *node = children; node != NULL; node = node->next) {
if (node->type == XML_ELEMENT_NODE &&
pcmk__str_eq(child_element_name, (const char *) node->name, pcmk__str_null_matches)) {
int rc = handler(node, userdata);
if (rc != pcmk_rc_ok) {
return rc;
}
}
}
return pcmk_rc_ok;
}
// Deprecated functions kept only for backward API compatibility
// LCOV_EXCL_START
#include <crm/common/xml_compat.h>
xmlNode *
find_entity(xmlNode *parent, const char *node_name, const char *id)
{
return pcmk__xe_match(parent, node_name,
((id == NULL)? id : XML_ATTR_ID), id);
}
void
crm_destroy_xml(gpointer data)
{
free_xml(data);
}
xmlDoc *
getDocPtr(xmlNode *node)
{
xmlDoc *doc = NULL;
CRM_CHECK(node != NULL, return NULL);
doc = node->doc;
if (doc == NULL) {
doc = xmlNewDoc((pcmkXmlStr) "1.0");
xmlDocSetRootElement(doc, node);
}
return doc;
}
int
add_node_nocopy(xmlNode *parent, const char *name, xmlNode *child)
{
add_node_copy(parent, child);
free_xml(child);
return 1;
}
gboolean
xml_has_children(const xmlNode * xml_root)
{
if (xml_root != NULL && xml_root->children != NULL) {
return TRUE;
}
return FALSE;
}
// LCOV_EXCL_STOP
// End deprecated API
diff --git a/lib/pengine/common.c b/lib/pengine/common.c
index 1a20775c23..0fdd5a120b 100644
--- a/lib/pengine/common.c
+++ b/lib/pengine/common.c
@@ -1,627 +1,627 @@
/*
* Copyright 2004-2023 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU Lesser General Public License
* version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY.
*/
#include <crm_internal.h>
#include <crm/crm.h>
#include <crm/msg_xml.h>
#include <crm/common/xml.h>
#include <crm/common/util.h>
#include <glib.h>
#include <crm/common/scheduler_internal.h>
#include <crm/pengine/internal.h>
gboolean was_processing_error = FALSE;
gboolean was_processing_warning = FALSE;
static bool
check_placement_strategy(const char *value)
{
return pcmk__strcase_any_of(value, "default", "utilization", "minimal",
"balanced", NULL);
}
static pcmk__cluster_option_t pe_opts[] = {
/* name, old name, type, allowed values,
* default value, validator,
* short description,
* long description
*/
{
"no-quorum-policy", NULL, "select", "stop, freeze, ignore, demote, suicide",
"stop", pcmk__valid_quorum,
N_("What to do when the cluster does not have quorum"),
NULL
},
{
"symmetric-cluster", NULL, "boolean", NULL,
"true", pcmk__valid_boolean,
N_("Whether resources can run on any node by default"),
NULL
},
{
"maintenance-mode", NULL, "boolean", NULL,
"false", pcmk__valid_boolean,
N_("Whether the cluster should refrain from monitoring, starting, "
"and stopping resources"),
NULL
},
{
"start-failure-is-fatal", NULL, "boolean", NULL,
"true", pcmk__valid_boolean,
N_("Whether a start failure should prevent a resource from being "
"recovered on the same node"),
N_("When true, the cluster will immediately ban a resource from a node "
"if it fails to start there. When false, the cluster will instead "
"check the resource's fail count against its migration-threshold.")
},
{
"enable-startup-probes", NULL, "boolean", NULL,
"true", pcmk__valid_boolean,
N_("Whether the cluster should check for active resources during start-up"),
NULL
},
{
XML_CONFIG_ATTR_SHUTDOWN_LOCK, NULL, "boolean", NULL,
"false", pcmk__valid_boolean,
N_("Whether to lock resources to a cleanly shut down node"),
N_("When true, resources active on a node when it is cleanly shut down "
"are kept \"locked\" to that node (not allowed to run elsewhere) "
"until they start again on that node after it rejoins (or for at "
"most shutdown-lock-limit, if set). Stonith resources and "
"Pacemaker Remote connections are never locked. Clone and bundle "
"instances and the promoted role of promotable clones are "
"currently never locked, though support could be added in a future "
"release.")
},
{
XML_CONFIG_ATTR_SHUTDOWN_LOCK_LIMIT, NULL, "time", NULL,
"0", pcmk__valid_interval_spec,
N_("Do not lock resources to a cleanly shut down node longer than "
"this"),
N_("If shutdown-lock is true and this is set to a nonzero time "
"duration, shutdown locks will expire after this much time has "
"passed since the shutdown was initiated, even if the node has not "
"rejoined.")
},
// Fencing-related options
{
"stonith-enabled", NULL, "boolean", NULL,
"true", pcmk__valid_boolean,
N_("*** Advanced Use Only *** "
"Whether nodes may be fenced as part of recovery"),
N_("If false, unresponsive nodes are immediately assumed to be harmless, "
"and resources that were active on them may be recovered "
"elsewhere. This can result in a \"split-brain\" situation, "
"potentially leading to data loss and/or service unavailability.")
},
{
"stonith-action", NULL, "select", "reboot, off, poweroff",
PCMK_ACTION_REBOOT, pcmk__is_fencing_action,
N_("Action to send to fence device when a node needs to be fenced "
"(\"poweroff\" is a deprecated alias for \"off\")"),
NULL
},
{
"stonith-timeout", NULL, "time", NULL,
"60s", pcmk__valid_interval_spec,
N_("*** Advanced Use Only *** Unused by Pacemaker"),
N_("This value is not used by Pacemaker, but is kept for backward "
"compatibility, and certain legacy fence agents might use it.")
},
{
XML_ATTR_HAVE_WATCHDOG, NULL, "boolean", NULL,
"false", pcmk__valid_boolean,
N_("Whether watchdog integration is enabled"),
N_("This is set automatically by the cluster according to whether SBD "
"is detected to be in use. User-configured values are ignored. "
"The value `true` is meaningful if diskless SBD is used and "
"`stonith-watchdog-timeout` is nonzero. In that case, if fencing "
"is required, watchdog-based self-fencing will be performed via "
"SBD without requiring a fencing resource explicitly configured.")
},
{
"concurrent-fencing", NULL, "boolean", NULL,
PCMK__CONCURRENT_FENCING_DEFAULT, pcmk__valid_boolean,
N_("Allow performing fencing operations in parallel"),
NULL
},
{
"startup-fencing", NULL, "boolean", NULL,
"true", pcmk__valid_boolean,
N_("*** Advanced Use Only *** Whether to fence unseen nodes at start-up"),
N_("Setting this to false may lead to a \"split-brain\" situation,"
"potentially leading to data loss and/or service unavailability.")
},
{
XML_CONFIG_ATTR_PRIORITY_FENCING_DELAY, NULL, "time", NULL,
"0", pcmk__valid_interval_spec,
N_("Apply fencing delay targeting the lost nodes with the highest total resource priority"),
N_("Apply specified delay for the fencings that are targeting the lost "
"nodes with the highest total resource priority in case we don't "
"have the majority of the nodes in our cluster partition, so that "
"the more significant nodes potentially win any fencing match, "
"which is especially meaningful under split-brain of 2-node "
"cluster. A promoted resource instance takes the base priority + 1 "
"on calculation if the base priority is not 0. Any static/random "
"delays that are introduced by `pcmk_delay_base/max` configured "
"for the corresponding fencing resources will be added to this "
"delay. This delay should be significantly greater than, safely "
"twice, the maximum `pcmk_delay_base/max`. By default, priority "
"fencing delay is disabled.")
},
-
{
XML_CONFIG_ATTR_NODE_PENDING_TIMEOUT, NULL, "time", NULL,
- "2h", pcmk__valid_interval_spec,
+ "0", pcmk__valid_interval_spec,
N_("How long to wait for a node that has joined the cluster to join "
"the controller process group"),
N_("Fence nodes that do not join the controller process group within "
"this much time after joining the cluster, to allow the cluster "
"to continue managing resources. A value of 0 means never fence "
- "pending nodes.")
+ "pending nodes. Setting the value to 2h means fence nodes after "
+ "2 hours.")
},
{
"cluster-delay", NULL, "time", NULL,
"60s", pcmk__valid_interval_spec,
N_("Maximum time for node-to-node communication"),
N_("The node elected Designated Controller (DC) will consider an action "
"failed if it does not get a response from the node executing the "
"action within this time (after considering the action's own "
"timeout). The \"correct\" value will depend on the speed and "
"load of your network and cluster nodes.")
},
{
"batch-limit", NULL, "integer", NULL,
"0", pcmk__valid_number,
N_("Maximum number of jobs that the cluster may execute in parallel "
"across all nodes"),
N_("The \"correct\" value will depend on the speed and load of your "
"network and cluster nodes. If set to 0, the cluster will "
"impose a dynamically calculated limit when any node has a "
"high load.")
},
{
"migration-limit", NULL, "integer", NULL,
"-1", pcmk__valid_number,
N_("The number of live migration actions that the cluster is allowed "
"to execute in parallel on a node (-1 means no limit)")
},
/* Orphans and stopping */
{
"stop-all-resources", NULL, "boolean", NULL,
"false", pcmk__valid_boolean,
N_("Whether the cluster should stop all active resources"),
NULL
},
{
"stop-orphan-resources", NULL, "boolean", NULL,
"true", pcmk__valid_boolean,
N_("Whether to stop resources that were removed from the configuration"),
NULL
},
{
"stop-orphan-actions", NULL, "boolean", NULL,
"true", pcmk__valid_boolean,
N_("Whether to cancel recurring actions removed from the configuration"),
NULL
},
{
"remove-after-stop", NULL, "boolean", NULL,
"false", pcmk__valid_boolean,
N_("*** Deprecated *** Whether to remove stopped resources from "
"the executor"),
N_("Values other than default are poorly tested and potentially dangerous."
" This option will be removed in a future release.")
},
/* Storing inputs */
{
"pe-error-series-max", NULL, "integer", NULL,
"-1", pcmk__valid_number,
N_("The number of scheduler inputs resulting in errors to save"),
N_("Zero to disable, -1 to store unlimited.")
},
{
"pe-warn-series-max", NULL, "integer", NULL,
"5000", pcmk__valid_number,
N_("The number of scheduler inputs resulting in warnings to save"),
N_("Zero to disable, -1 to store unlimited.")
},
{
"pe-input-series-max", NULL, "integer", NULL,
"4000", pcmk__valid_number,
N_("The number of scheduler inputs without errors or warnings to save"),
N_("Zero to disable, -1 to store unlimited.")
},
/* Node health */
{
PCMK__OPT_NODE_HEALTH_STRATEGY, NULL, "select",
PCMK__VALUE_NONE ", " PCMK__VALUE_MIGRATE_ON_RED ", "
PCMK__VALUE_ONLY_GREEN ", " PCMK__VALUE_PROGRESSIVE ", "
PCMK__VALUE_CUSTOM,
PCMK__VALUE_NONE, pcmk__validate_health_strategy,
N_("How cluster should react to node health attributes"),
N_("Requires external entities to create node attributes (named with "
"the prefix \"#health\") with values \"red\", "
"\"yellow\", or \"green\".")
},
{
PCMK__OPT_NODE_HEALTH_BASE, NULL, "integer", NULL,
"0", pcmk__valid_number,
N_("Base health score assigned to a node"),
N_("Only used when \"node-health-strategy\" is set to \"progressive\".")
},
{
PCMK__OPT_NODE_HEALTH_GREEN, NULL, "integer", NULL,
"0", pcmk__valid_number,
N_("The score to use for a node health attribute whose value is \"green\""),
N_("Only used when \"node-health-strategy\" is set to \"custom\" or \"progressive\".")
},
{
PCMK__OPT_NODE_HEALTH_YELLOW, NULL, "integer", NULL,
"0", pcmk__valid_number,
N_("The score to use for a node health attribute whose value is \"yellow\""),
N_("Only used when \"node-health-strategy\" is set to \"custom\" or \"progressive\".")
},
{
PCMK__OPT_NODE_HEALTH_RED, NULL, "integer", NULL,
"-INFINITY", pcmk__valid_number,
N_("The score to use for a node health attribute whose value is \"red\""),
N_("Only used when \"node-health-strategy\" is set to \"custom\" or \"progressive\".")
},
/*Placement Strategy*/
{
"placement-strategy", NULL, "select",
"default, utilization, minimal, balanced",
"default", check_placement_strategy,
N_("How the cluster should allocate resources to nodes"),
NULL
},
};
void
pe_metadata(pcmk__output_t *out)
{
const char *desc_short = "Pacemaker scheduler options";
const char *desc_long = "Cluster options used by Pacemaker's scheduler";
gchar *s = pcmk__format_option_metadata("pacemaker-schedulerd", desc_short,
desc_long, pe_opts,
PCMK__NELEM(pe_opts));
out->output_xml(out, "metadata", s);
g_free(s);
}
void
verify_pe_options(GHashTable * options)
{
pcmk__validate_cluster_options(options, pe_opts, PCMK__NELEM(pe_opts));
}
const char *
pe_pref(GHashTable * options, const char *name)
{
return pcmk__cluster_option(options, pe_opts, PCMK__NELEM(pe_opts), name);
}
const char *
fail2text(enum action_fail_response fail)
{
const char *result = "<unknown>";
switch (fail) {
case pcmk_on_fail_ignore:
result = "ignore";
break;
case pcmk_on_fail_demote:
result = "demote";
break;
case pcmk_on_fail_block:
result = "block";
break;
case pcmk_on_fail_restart:
result = "recover";
break;
case pcmk_on_fail_ban:
result = "migrate";
break;
case pcmk_on_fail_stop:
result = "stop";
break;
case pcmk_on_fail_fence_node:
result = "fence";
break;
case pcmk_on_fail_standby_node:
result = "standby";
break;
case pcmk_on_fail_restart_container:
result = "restart-container";
break;
case pcmk_on_fail_reset_remote:
result = "reset-remote";
break;
}
return result;
}
enum action_tasks
text2task(const char *task)
{
if (pcmk__str_eq(task, PCMK_ACTION_STOP, pcmk__str_casei)) {
return pcmk_action_stop;
} else if (pcmk__str_eq(task, PCMK_ACTION_STOPPED, pcmk__str_casei)) {
return pcmk_action_stopped;
} else if (pcmk__str_eq(task, PCMK_ACTION_START, pcmk__str_casei)) {
return pcmk_action_start;
} else if (pcmk__str_eq(task, PCMK_ACTION_RUNNING, pcmk__str_casei)) {
return pcmk_action_started;
} else if (pcmk__str_eq(task, PCMK_ACTION_DO_SHUTDOWN, pcmk__str_casei)) {
return pcmk_action_shutdown;
} else if (pcmk__str_eq(task, PCMK_ACTION_STONITH, pcmk__str_casei)) {
return pcmk_action_fence;
} else if (pcmk__str_eq(task, PCMK_ACTION_MONITOR, pcmk__str_casei)) {
return pcmk_action_monitor;
} else if (pcmk__str_eq(task, PCMK_ACTION_NOTIFY, pcmk__str_casei)) {
return pcmk_action_notify;
} else if (pcmk__str_eq(task, PCMK_ACTION_NOTIFIED, pcmk__str_casei)) {
return pcmk_action_notified;
} else if (pcmk__str_eq(task, PCMK_ACTION_PROMOTE, pcmk__str_casei)) {
return pcmk_action_promote;
} else if (pcmk__str_eq(task, PCMK_ACTION_DEMOTE, pcmk__str_casei)) {
return pcmk_action_demote;
} else if (pcmk__str_eq(task, PCMK_ACTION_PROMOTED, pcmk__str_casei)) {
return pcmk_action_promoted;
} else if (pcmk__str_eq(task, PCMK_ACTION_DEMOTED, pcmk__str_casei)) {
return pcmk_action_demoted;
}
return pcmk_action_unspecified;
}
const char *
task2text(enum action_tasks task)
{
const char *result = "<unknown>";
switch (task) {
case pcmk_action_unspecified:
result = "no_action";
break;
case pcmk_action_stop:
result = PCMK_ACTION_STOP;
break;
case pcmk_action_stopped:
result = PCMK_ACTION_STOPPED;
break;
case pcmk_action_start:
result = PCMK_ACTION_START;
break;
case pcmk_action_started:
result = PCMK_ACTION_RUNNING;
break;
case pcmk_action_shutdown:
result = PCMK_ACTION_DO_SHUTDOWN;
break;
case pcmk_action_fence:
result = PCMK_ACTION_STONITH;
break;
case pcmk_action_monitor:
result = PCMK_ACTION_MONITOR;
break;
case pcmk_action_notify:
result = PCMK_ACTION_NOTIFY;
break;
case pcmk_action_notified:
result = PCMK_ACTION_NOTIFIED;
break;
case pcmk_action_promote:
result = PCMK_ACTION_PROMOTE;
break;
case pcmk_action_promoted:
result = PCMK_ACTION_PROMOTED;
break;
case pcmk_action_demote:
result = PCMK_ACTION_DEMOTE;
break;
case pcmk_action_demoted:
result = PCMK_ACTION_DEMOTED;
break;
}
return result;
}
const char *
role2text(enum rsc_role_e role)
{
switch (role) {
case pcmk_role_stopped:
return PCMK__ROLE_STOPPED;
case pcmk_role_started:
return PCMK__ROLE_STARTED;
case pcmk_role_unpromoted:
#ifdef PCMK__COMPAT_2_0
return PCMK__ROLE_UNPROMOTED_LEGACY;
#else
return PCMK__ROLE_UNPROMOTED;
#endif
case pcmk_role_promoted:
#ifdef PCMK__COMPAT_2_0
return PCMK__ROLE_PROMOTED_LEGACY;
#else
return PCMK__ROLE_PROMOTED;
#endif
default: // pcmk_role_unknown
return PCMK__ROLE_UNKNOWN;
}
}
enum rsc_role_e
text2role(const char *role)
{
CRM_ASSERT(role != NULL);
if (pcmk__str_eq(role, PCMK__ROLE_STOPPED, pcmk__str_casei)) {
return pcmk_role_stopped;
} else if (pcmk__str_eq(role, PCMK__ROLE_STARTED, pcmk__str_casei)) {
return pcmk_role_started;
} else if (pcmk__strcase_any_of(role, PCMK__ROLE_UNPROMOTED,
PCMK__ROLE_UNPROMOTED_LEGACY, NULL)) {
return pcmk_role_unpromoted;
} else if (pcmk__strcase_any_of(role, PCMK__ROLE_PROMOTED,
PCMK__ROLE_PROMOTED_LEGACY, NULL)) {
return pcmk_role_promoted;
} else if (pcmk__str_eq(role, PCMK__ROLE_UNKNOWN, pcmk__str_casei)) {
return pcmk_role_unknown;
}
crm_err("Unknown role: %s", role);
return pcmk_role_unknown;
}
void
add_hash_param(GHashTable * hash, const char *name, const char *value)
{
CRM_CHECK(hash != NULL, return);
crm_trace("Adding name='%s' value='%s' to hash table",
pcmk__s(name, "<null>"), pcmk__s(value, "<null>"));
if (name == NULL || value == NULL) {
return;
} else if (pcmk__str_eq(value, "#default", pcmk__str_casei)) {
return;
} else if (g_hash_table_lookup(hash, name) == NULL) {
g_hash_table_insert(hash, strdup(name), strdup(value));
}
}
/*!
* \internal
* \brief Look up an attribute value on the appropriate node
*
* If \p node is a guest node and either the \c XML_RSC_ATTR_TARGET meta
* attribute is set to "host" for \p rsc or \p force_host is \c true, query the
* attribute on the node's host. Otherwise, query the attribute on \p node
* itself.
*
* \param[in] node Node to query attribute value on by default
* \param[in] name Name of attribute to query
* \param[in] rsc Resource on whose behalf we're querying
* \param[in] node_type Type of resource location lookup
* \param[in] force_host Force a lookup on the guest node's host, regardless of
* the \c XML_RSC_ATTR_TARGET value
*
* \return Value of the attribute on \p node or on the host of \p node
*
* \note If \p force_host is \c true, \p node \e must be a guest node.
*/
const char *
pe__node_attribute_calculated(const pcmk_node_t *node, const char *name,
const pcmk_resource_t *rsc,
enum pcmk__rsc_node node_type,
bool force_host)
{
// @TODO: Use pe__is_guest_node() after merging libpe_{rules,status}
bool is_guest = (node != NULL)
&& (node->details->type == pcmk_node_variant_remote)
&& (node->details->remote_rsc != NULL)
&& (node->details->remote_rsc->container != NULL);
const char *source = NULL;
const char *node_type_s = NULL;
const char *reason = NULL;
const pcmk_resource_t *container = NULL;
const pcmk_node_t *host = NULL;
CRM_ASSERT((node != NULL) && (name != NULL) && (rsc != NULL)
&& (!force_host || is_guest));
/* Ignore XML_RSC_ATTR_TARGET if node is not a guest node. This represents a
* user configuration error.
*/
source = g_hash_table_lookup(rsc->meta, XML_RSC_ATTR_TARGET);
if (!force_host
&& (!is_guest || !pcmk__str_eq(source, "host", pcmk__str_casei))) {
return g_hash_table_lookup(node->details->attrs, name);
}
container = node->details->remote_rsc->container;
switch (node_type) {
case pcmk__rsc_node_assigned:
node_type_s = "assigned";
host = container->allocated_to;
if (host == NULL) {
reason = "not assigned";
}
break;
case pcmk__rsc_node_current:
node_type_s = "current";
if (container->running_on != NULL) {
host = container->running_on->data;
}
if (host == NULL) {
reason = "inactive";
}
break;
default:
// Add support for other enum pcmk__rsc_node values if needed
CRM_ASSERT(false);
break;
}
if (host != NULL) {
const char *value = g_hash_table_lookup(host->details->attrs, name);
pe_rsc_trace(rsc,
"%s: Value lookup for %s on %s container host %s %s%s",
rsc->id, name, node_type_s, pe__node_name(host),
((value != NULL)? "succeeded: " : "failed"),
pcmk__s(value, ""));
return value;
}
pe_rsc_trace(rsc,
"%s: Not looking for %s on %s container host: %s is %s",
rsc->id, name, node_type_s, container->id, reason);
return NULL;
}
const char *
pe_node_attribute_raw(const pcmk_node_t *node, const char *name)
{
if(node == NULL) {
return NULL;
}
return g_hash_table_lookup(node->details->attrs, name);
}
diff --git a/rpm/pacemaker.spec.in b/rpm/pacemaker.spec.in
index 55356d749f..c279f881e8 100644
--- a/rpm/pacemaker.spec.in
+++ b/rpm/pacemaker.spec.in
@@ -1,966 +1,966 @@
#
# Copyright 2008-2023 the Pacemaker project contributors
#
# The version control history for this file may have further details.
#
# This source code is licensed under the GNU General Public License version 2
# or later (GPLv2+) WITHOUT ANY WARRANTY.
#
# User-configurable globals and defines to control package behavior
# (these should not test {with X} values, which are declared later)
## User and group to use for nonprivileged services
%global uname hacluster
%global gname haclient
## Where to install Pacemaker documentation
%if 0%{?suse_version} > 0
%global pcmk_docdir %{_docdir}/%{name}-%{version}
%else
%if 0%{?rhel} > 7
%global pcmk_docdir %{_docdir}/%{name}-doc
%else
%global pcmk_docdir %{_docdir}/%{name}
%endif
%endif
## GitHub entity that distributes source (for ease of using a fork)
%global github_owner ClusterLabs
## Where bug reports should be submitted
## Leave bug_url undefined to use ClusterLabs default, others define it here
## What to use as the OCF resource agent root directory
%global ocf_root %{_prefix}/lib/ocf
## Upstream pacemaker version, and its package version (specversion
## can be incremented to build packages reliably considered "newer"
## than previously built packages with the same pcmkversion)
%global pcmkversion X.Y.Z
%global specversion 1
## Upstream commit (full commit ID, abbreviated commit ID, or tag) to build
%global commit HEAD
## Since git v2.11, the extent of abbreviation is autoscaled by default
## (used to be constant of 7), so we need to convey it for non-tags, too.
%if (0%{?fedora} >= 26) || (0%{?rhel} >= 9)
%global commit_abbrev 9
%else
%global commit_abbrev 7
%endif
# Define conditionals so that "rpmbuild --with <feature>" and
# "rpmbuild --without <feature>" can enable and disable specific features
## Add option to enable support for stonith/external fencing agents
%if 0%{?suse_version} > 0
%bcond_without stonithd
%else
%bcond_with stonithd
%endif
## Add option for whether to support storing sensitive information outside CIB
%if (0%{?fedora} && 0%{?fedora} <= 33) || (0%{?rhel} && 0%{?rhel} <= 8)
%bcond_with cibsecrets
%else
%bcond_without cibsecrets
%endif
## Add option to enable Native Language Support (experimental)
%bcond_with nls
## Add option to create binaries suitable for use with profiling tools
%bcond_with profiling
## Allow deprecated option to skip (or enable, on RHEL) documentation
%if 0%{?rhel}
%bcond_with doc
%else
%bcond_without doc
%endif
## Add option to default to start-up synchronization with SBD.
##
## If enabled, SBD *MUST* be built to default similarly, otherwise data
## corruption could occur. Building both Pacemaker and SBD to default
## to synchronization improves safety, without requiring higher-level tools
## to be aware of the setting or requiring users to modify configurations
## after upgrading to versions that support synchronization.
%if 0%{?rhel} && 0%{?rhel} > 8
%bcond_without sbd_sync
%else
%bcond_with sbd_sync
%endif
## Add option to prefix package version with "0."
## (so later "official" packages will be considered updates)
%bcond_with pre_release
## Add option to ship Upstart job files
%bcond_with upstart_job
## Add option to turn off hardening of libraries and daemon executables
%bcond_without hardening
## Add option to enable (or disable, on RHEL 8) links for legacy daemon names
%if 0%{?rhel} && 0%{?rhel} <= 8
%bcond_without legacy_links
%else
%bcond_with legacy_links
%endif
# Define globals for convenient use later
## Workaround to use parentheses in other globals
%global lparen (
%global rparen )
## Whether this is a tagged release (final or release candidate)
%define tag_release %(c=%{commit}; case ${c} in Pacemaker-*%{rparen} echo 1 ;;
*%{rparen} echo 0 ;; esac)
## Portion of export/dist tarball name after "pacemaker-", and release version
%if 0%{tag_release}
%define archive_version %(c=%{commit}; echo ${c:10})
%define archive_github_url %{commit}#/%{name}-%{archive_version}.tar.gz
%define pcmk_release %(c=%{commit}; case $c in *-rc[[:digit:]]*%{rparen}
echo 0.%{specversion}.${c: -3} ;;
*%{rparen} echo %{specversion} ;; esac)
%else
%if "%{commit}" == "DIST"
%define archive_version %{pcmkversion}
%define archive_github_url %{archive_version}#/%{name}-%{pcmkversion}.tar.gz
%if %{with pre_release}
%define pcmk_release 0.%{specversion}
%else
%define pcmk_release %{specversion}
%endif
%else
%define archive_version %(c=%{commit}; echo ${c:0:%{commit_abbrev}})
%define archive_github_url %{archive_version}#/%{name}-%{archive_version}.tar.gz
%if %{with pre_release}
%define pcmk_release 0.%{specversion}.%{archive_version}.git
%else
%define pcmk_release %{specversion}.%{archive_version}.git
%endif
%endif
%endif
## Whether this platform defaults to using systemd as an init system
## (needs to be evaluated prior to BuildRequires being enumerated and
## installed as it's intended to conditionally select some of these, and
## for that there are only few indicators with varying reliability:
## - presence of systemd-defined macros (when building in a full-fledged
## environment, which is not the case with ordinary mock-based builds)
## - systemd-aware rpm as manifested with the presence of particular
## macro (rpm itself will trivially always be present when building)
## - existence of /usr/lib/os-release file, which is something heavily
## propagated by systemd project
## - when not good enough, there's always a possibility to check
## particular distro-specific macros (incl. version comparison)
%define systemd_native (%{?_unitdir:1}%{!?_unitdir:0}%{nil \
} || %{?__transaction_systemd_inhibit:1}%{!?__transaction_systemd_inhibit:0}%{nil \
} || %(test -f /usr/lib/os-release; test $? -ne 0; echo $?))
%if 0%{?fedora} > 20 || 0%{?rhel} > 7
## Base GnuTLS cipher priorities (presumably only the initial, required keyword)
## overridable with "rpmbuild --define 'pcmk_gnutls_priorities PRIORITY-SPEC'"
%define gnutls_priorities %{?pcmk_gnutls_priorities}%{!?pcmk_gnutls_priorities:@SYSTEM}
%endif
%if 0%{?fedora} > 22 || 0%{?rhel} > 7
%global supports_recommends 1
%endif
## Different distros name certain packages differently
## (note: corosync libraries also differ, but all provide corosync-devel)
%if 0%{?suse_version} > 0
%global pkgname_bzip2_devel libbz2-devel
%global pkgname_docbook_xsl docbook-xsl-stylesheets
%global pkgname_gettext gettext-tools
%global pkgname_gnutls_devel libgnutls-devel
%global pkgname_shadow_utils shadow
%global pkgname_procps procps
%global pkgname_glue_libs libglue
%global pkgname_pcmk_libs lib%{name}3
%global hacluster_id 90
%else
%global pkgname_libtool_devel libtool-ltdl-devel
%global pkgname_libtool_devel_arch libtool-ltdl-devel%{?_isa}
%global pkgname_bzip2_devel bzip2-devel
%global pkgname_docbook_xsl docbook-style-xsl
%global pkgname_gettext gettext-devel
%global pkgname_gnutls_devel gnutls-devel
%global pkgname_shadow_utils shadow-utils
%global pkgname_procps procps-ng
%global pkgname_glue_libs cluster-glue-libs
%global pkgname_pcmk_libs %{name}-libs
%global hacluster_id 189
%endif
## Distro-specific configuration choices
### Use 2.0-style output when other distro packages don't support current output
%if 0%{?fedora} || ( 0%{?rhel} && 0%{?rhel} <= 8 )
%global compat20 --enable-compat-2.0
%endif
### Default concurrent-fencing to true when distro prefers that
%if 0%{?rhel} >= 7
%global concurrent_fencing --with-concurrent-fencing-default=true
%endif
### Default resource-stickiness to 1 when distro prefers that
%if 0%{?fedora} >= 35 || 0%{?rhel} >= 9
%global resource_stickiness --with-resource-stickiness-default=1
%endif
# Python-related definitions
## Turn off auto-compilation of Python files outside Python specific paths,
## so there's no risk that unexpected "__python" macro gets picked to do the
## RPM-native byte-compiling there (only "{_datadir}/pacemaker/tests" affected)
## -- distro-dependent tricks or automake's fallback to be applied there
%if %{defined _python_bytecompile_extra}
%global _python_bytecompile_extra 0
%else
### the statement effectively means no RPM-native byte-compiling will occur at
### all, so distro-dependent tricks for Python-specific packages to be applied
%global __os_install_post %(echo '%{__os_install_post}' | {
sed -e 's!/usr/lib[^[:space:]]*/brp-python-bytecompile[[:space:]].*$!!g'; })
%endif
## Prefer Python 3 definitions explicitly, in case 2 is also available
%if %{defined __python3}
%global python_name python3
%global python_path %{__python3}
%define python_site %{?python3_sitelib}%{!?python3_sitelib:%(
%{python_path} -c 'from distutils.sysconfig import get_python_lib as gpl; print(gpl(1))' 2>/dev/null)}
%else
%if %{defined python_version}
%global python_name python%(echo %{python_version} | cut -d'.' -f1)
%define python_path %{?__python}%{!?__python:/usr/bin/%{python_name}}
%else
%global python_name python
%global python_path %{?__python}%{!?__python:/usr/bin/python%{?python_pkgversion}}
%endif
%define python_site %{?python_sitelib}%{!?python_sitelib:%(
%{python_name} -c 'from distutils.sysconfig import get_python_lib as gpl; print(gpl(1))' 2>/dev/null)}
%endif
# Keep sane profiling data if requested
%if %{with profiling}
## Disable -debuginfo package and stripping binaries/libraries
%define debug_package %{nil}
%endif
Name: pacemaker
Summary: Scalable High-Availability cluster resource manager
Version: %{pcmkversion}
Release: %{pcmk_release}%{?dist}
%if %{defined _unitdir}
License: GPL-2.0-or-later AND LGPL-2.1-or-later
%else
# initscript is Revised BSD
License: GPL-2.0-or-later AND LGPL-2.1-or-later AND BSD-3-Clause
%endif
Url: https://www.clusterlabs.org/
# Example: https://codeload.github.com/ClusterLabs/pacemaker/tar.gz/e91769e
# will download pacemaker-e91769e.tar.gz
#
# The ending part starting with '#' is ignored by github but necessary for
# rpmbuild to know what the tar archive name is. (The downloaded file will be
# named correctly only for commit IDs, not tagged releases.)
#
# You can use "spectool -s 0 pacemaker.spec" (rpmdevtools) to show final URL.
Source0: https://codeload.github.com/%{github_owner}/%{name}/tar.gz/%{archive_github_url}
Requires: resource-agents
Requires: %{pkgname_pcmk_libs}%{?_isa} = %{version}-%{release}
Requires: %{name}-cluster-libs%{?_isa} = %{version}-%{release}
Requires: %{name}-cli = %{version}-%{release}
%if %{with stonithd}
Requires: %{python_name}-%{name} = %{version}-%{release}
%endif
%if !%{defined _unitdir}
Requires: %{pkgname_procps}
Requires: psmisc
%endif
%{?systemd_requires}
Requires: %{python_path}
BuildRequires: %{python_name}-devel
BuildRequires: %{python_name}-setuptools
# Pacemaker requires a minimum libqb functionality
Requires: libqb >= 0.17.0
BuildRequires: libqb-devel >= 0.17.0
# Required basic build tools
BuildRequires: autoconf
BuildRequires: automake
BuildRequires: coreutils
BuildRequires: findutils
BuildRequires: gcc
BuildRequires: grep
BuildRequires: libtool
%if %{defined pkgname_libtool_devel}
BuildRequires: %{?pkgname_libtool_devel}
%endif
BuildRequires: make
BuildRequires: pkgconfig
BuildRequires: sed
# Required for core functionality
BuildRequires: pkgconfig(glib-2.0) >= 2.42
-BuildRequires: libxml2-devel
+BuildRequires: libxml2-devel >= 2.6.0
BuildRequires: libxslt-devel
BuildRequires: libuuid-devel
BuildRequires: %{pkgname_bzip2_devel}
# Enables optional functionality
BuildRequires: pkgconfig(dbus-1)
BuildRequires: %{pkgname_docbook_xsl}
BuildRequires: %{pkgname_gnutls_devel}
BuildRequires: help2man
BuildRequires: ncurses-devel
BuildRequires: pam-devel
BuildRequires: %{pkgname_gettext} >= 0.18
# Required for "make check"
BuildRequires: libcmocka-devel >= 1.1.0
%if %{systemd_native}
BuildRequires: pkgconfig(systemd)
%endif
Requires: corosync >= 2.0.0
BuildRequires: corosync-devel >= 2.0.0
%if %{with stonithd}
BuildRequires: %{pkgname_glue_libs}-devel
%endif
%if %{with doc}
BuildRequires: asciidoc
BuildRequires: inkscape
BuildRequires: %{python_name}-sphinx
%endif
# Booth requires this
Provides: pacemaker-ticket-support = 2.0
Provides: pcmk-cluster-manager = %{version}-%{release}
Provides: pcmk-cluster-manager%{?_isa} = %{version}-%{release}
# Bundled bits
## Pacemaker uses the crypto/md5-buffer module from gnulib
%if 0%{?fedora} || 0%{?rhel}
Provides: bundled(gnulib) = 20200404
%endif
%description
Pacemaker is an advanced, scalable High-Availability cluster resource
manager.
It supports more than 16 node clusters with significant capabilities
for managing resources and dependencies.
It will run scripts at initialization, when machines go up or down,
when related resources fail and can be configured to periodically check
resource health.
Available rpmbuild rebuild options:
--with(out) : cibsecrets hardening nls pre_release profiling
stonithd upstart_job
%package cli
License: GPL-2.0-or-later AND LGPL-2.1-or-later
Summary: Command line tools for controlling Pacemaker clusters
Requires: %{pkgname_pcmk_libs}%{?_isa} = %{version}-%{release}
%if 0%{?supports_recommends}
Recommends: pcmk-cluster-manager = %{version}-%{release}
# For crm_report
Recommends: tar
Recommends: bzip2
%endif
Requires: perl-TimeDate
Requires: %{pkgname_procps}
Requires: psmisc
Requires(post):coreutils
%description cli
Pacemaker is an advanced, scalable High-Availability cluster resource
manager.
The %{name}-cli package contains command line tools that can be used
to query and control the cluster from machines that may, or may not,
be part of the cluster.
%package -n %{pkgname_pcmk_libs}
License: GPL-2.0-or-later AND LGPL-2.1-or-later
Summary: Core Pacemaker libraries
Requires(pre): %{pkgname_shadow_utils}
Requires: %{name}-schemas = %{version}-%{release}
# sbd 1.4.0+ supports the libpe_status API for pe_working_set_t
Conflicts: sbd < 1.4.0
%description -n %{pkgname_pcmk_libs}
Pacemaker is an advanced, scalable High-Availability cluster resource
manager.
The %{pkgname_pcmk_libs} package contains shared libraries needed for cluster
nodes and those just running the CLI tools.
%package cluster-libs
License: GPL-2.0-or-later AND LGPL-2.1-or-later
Summary: Cluster Libraries used by Pacemaker
Requires: %{pkgname_pcmk_libs}%{?_isa} = %{version}-%{release}
%description cluster-libs
Pacemaker is an advanced, scalable High-Availability cluster resource
manager.
The %{name}-cluster-libs package contains cluster-aware shared
libraries needed for nodes that will form part of the cluster nodes.
%package -n %{python_name}-%{name}
License: LGPL-2.1-or-later
Summary: Python libraries for Pacemaker
Requires: %{python_path}
Requires: %{pkgname_pcmk_libs} = %{version}-%{release}
BuildArch: noarch
%description -n %{python_name}-%{name}
Pacemaker is an advanced, scalable High-Availability cluster resource
manager.
The %{python_name}-%{name} package contains a Python library that can be used
to interface with Pacemaker.
%package remote
%if %{defined _unitdir}
License: GPL-2.0-or-later AND LGPL-2.1-or-later
%else
# initscript is Revised BSD
License: GPL-2.0-or-later AND LGPL-2.1-or-later AND BSD-3-Clause
%endif
Summary: Pacemaker remote executor daemon for non-cluster nodes
Requires: %{pkgname_pcmk_libs}%{?_isa} = %{version}-%{release}
Requires: %{name}-cli = %{version}-%{release}
Requires: resource-agents
%if !%{defined _unitdir}
Requires: %{pkgname_procps}
%endif
# -remote can be fully independent of systemd
%{?systemd_ordering}%{!?systemd_ordering:%{?systemd_requires}}
Provides: pcmk-cluster-manager = %{version}-%{release}
Provides: pcmk-cluster-manager%{?_isa} = %{version}-%{release}
%description remote
Pacemaker is an advanced, scalable High-Availability cluster resource
manager.
The %{name}-remote package contains the Pacemaker Remote daemon
which is capable of extending pacemaker functionality to remote
nodes not running the full corosync/cluster stack.
%package -n %{pkgname_pcmk_libs}-devel
License: GPL-2.0-or-later AND LGPL-2.1-or-later
Summary: Pacemaker development package
Requires: %{pkgname_pcmk_libs}%{?_isa} = %{version}-%{release}
Requires: %{name}-cluster-libs%{?_isa} = %{version}-%{release}
Requires: %{pkgname_bzip2_devel}%{?_isa}
Requires: corosync-devel >= 2.0.0
Requires: glib2-devel%{?_isa}
Requires: libqb-devel%{?_isa}
%if %{defined pkgname_libtool_devel_arch}
Requires: %{?pkgname_libtool_devel_arch}
%endif
Requires: libuuid-devel%{?_isa}
-Requires: libxml2-devel%{?_isa}
+Requires: libxml2-devel%{?_isa} >= 2.6.0
Requires: libxslt-devel%{?_isa}
%description -n %{pkgname_pcmk_libs}-devel
Pacemaker is an advanced, scalable High-Availability cluster resource
manager.
The %{pkgname_pcmk_libs}-devel package contains headers and shared libraries
for developing tools for Pacemaker.
%package cts
License: GPL-2.0-or-later AND LGPL-2.1-or-later
Summary: Test framework for cluster-related technologies like Pacemaker
Requires: %{python_path}
Requires: %{pkgname_pcmk_libs} = %{version}-%{release}
Requires: %{name}-cli = %{version}-%{release}
Requires: %{python_name}-%{name} = %{version}-%{release}
Requires: %{pkgname_procps}
Requires: psmisc
Requires: %{python_name}-psutil
BuildArch: noarch
# systemd Python bindings are a separate package in some distros
%if %{defined systemd_requires}
%if 0%{?fedora} > 22 || 0%{?rhel} > 7
Requires: %{python_name}-systemd
%endif
%endif
%description cts
Test framework for cluster-related technologies like Pacemaker
%package doc
License: CC-BY-SA-4.0
Summary: Documentation for Pacemaker
BuildArch: noarch
%description doc
Documentation for Pacemaker.
Pacemaker is an advanced, scalable High-Availability cluster resource
manager.
%package schemas
License: GPL-2.0-or-later
Summary: Schemas and upgrade stylesheets for Pacemaker
BuildArch: noarch
%description schemas
Schemas and upgrade stylesheets for Pacemaker
Pacemaker is an advanced, scalable High-Availability cluster resource
manager.
%prep
%setup -q -n %{name}-%{archive_version}
%build
export systemdsystemunitdir=%{?_unitdir}%{!?_unitdir:no}
%if %{with hardening}
# prefer distro-provided hardening flags in case they are defined
# through _hardening_{c,ld}flags macros, configure script will
# use its own defaults otherwise; if such hardenings are completely
# undesired, rpmbuild using "--without hardening"
# (or "--define '_without_hardening 1'")
export CFLAGS_HARDENED_EXE="%{?_hardening_cflags}"
export CFLAGS_HARDENED_LIB="%{?_hardening_cflags}"
export LDFLAGS_HARDENED_EXE="%{?_hardening_ldflags}"
export LDFLAGS_HARDENED_LIB="%{?_hardening_ldflags}"
%endif
./autogen.sh
%{configure} \
PYTHON=%{python_path} \
%{!?with_hardening: --disable-hardening} \
%{?with_legacy_links: --enable-legacy-links} \
%{?with_profiling: --with-profiling} \
%{?with_cibsecrets: --with-cibsecrets} \
%{?with_nls: --enable-nls} \
%{?with_sbd_sync: --with-sbd-sync-default="true"} \
%{?gnutls_priorities: --with-gnutls-priorities="%{gnutls_priorities}"} \
%{?bug_url: --with-bug-url=%{bug_url}} \
%{?ocf_root: --with-ocfdir=%{ocf_root}} \
%{?concurrent_fencing} \
%{?resource_stickiness} \
%{?compat20} \
--disable-static \
--with-initdir=%{_initrddir} \
--with-runstatedir=%{_rundir} \
--localstatedir=%{_var} \
--with-version=%{version}-%{release}
%if 0%{?suse_version} >= 1200
# Fedora handles rpath removal automagically
sed -i 's|^hardcode_libdir_flag_spec=.*|hardcode_libdir_flag_spec=""|g' libtool
sed -i 's|^runpath_var=LD_RUN_PATH|runpath_var=DIE_RPATH_DIE|g' libtool
%endif
make %{_smp_mflags} V=1
pushd python
%py3_build
popd
%check
make %{_smp_mflags} check
{ cts/cts-scheduler --run load-stopped-loop \
&& cts/cts-cli \
&& touch .CHECKED
} 2>&1 | sed 's/[fF]ail/faiil/g' # prevent false positives in rpmlint
[ -f .CHECKED ] && rm -f -- .CHECKED
exit $? # TODO remove when rpm<4.14 compatibility irrelevant
%install
# skip automake-native Python byte-compilation, since RPM-native one (possibly
# distro-confined to Python-specific directories, which is currently the only
# relevant place, anyway) assures proper intrinsic alignment with wider system
# (such as with py_byte_compile macro, which is concurrent Fedora/EL specific)
make install \
DESTDIR=%{buildroot} V=1 docdir=%{pcmk_docdir} \
%{?_python_bytecompile_extra:%{?py_byte_compile:am__py_compile=true}}
pushd python
%py3_install
popd
%if %{with upstart_job}
mkdir -p ${RPM_BUILD_ROOT}%{_sysconfdir}/init
install -m 644 pacemakerd/pacemaker.upstart ${RPM_BUILD_ROOT}%{_sysconfdir}/init/pacemaker.conf
install -m 644 pacemakerd/pacemaker.combined.upstart ${RPM_BUILD_ROOT}%{_sysconfdir}/init/pacemaker.combined.conf
install -m 644 tools/crm_mon.upstart ${RPM_BUILD_ROOT}%{_sysconfdir}/init/crm_mon.conf
%endif
%if %{defined _unitdir}
mkdir -p ${RPM_BUILD_ROOT}%{_localstatedir}/lib/rpm-state/%{name}
%endif
%if %{with nls}
%find_lang %{name}
%endif
# Don't package libtool archives
find %{buildroot} -name '*.la' -type f -print0 | xargs -0 rm -f
%post
%if %{defined _unitdir}
%systemd_post pacemaker.service
%else
/sbin/chkconfig --add pacemaker || :
%endif
%preun
%if %{defined _unitdir}
%systemd_preun pacemaker.service
%else
/sbin/service pacemaker stop >/dev/null 2>&1 || :
if [ "$1" -eq 0 ]; then
# Package removal, not upgrade
/sbin/chkconfig --del pacemaker || :
fi
%endif
%postun
%if %{defined _unitdir}
%systemd_postun_with_restart pacemaker.service
%endif
%pre remote
%if %{defined _unitdir}
# Stop the service before anything is touched, and remember to restart
# it as one of the last actions (compared to using systemd_postun_with_restart,
# this avoids suicide when sbd is in use)
systemctl --quiet is-active pacemaker_remote
if [ $? -eq 0 ] ; then
mkdir -p %{_localstatedir}/lib/rpm-state/%{name}
touch %{_localstatedir}/lib/rpm-state/%{name}/restart_pacemaker_remote
systemctl stop pacemaker_remote >/dev/null 2>&1
else
rm -f %{_localstatedir}/lib/rpm-state/%{name}/restart_pacemaker_remote
fi
%endif
%post remote
%if %{defined _unitdir}
%systemd_post pacemaker_remote.service
%else
/sbin/chkconfig --add pacemaker_remote || :
%endif
%preun remote
%if %{defined _unitdir}
%systemd_preun pacemaker_remote.service
%else
/sbin/service pacemaker_remote stop >/dev/null 2>&1 || :
if [ "$1" -eq 0 ]; then
# Package removal, not upgrade
/sbin/chkconfig --del pacemaker_remote || :
fi
%endif
%postun remote
%if %{defined _unitdir}
# This next line is a no-op, because we stopped the service earlier, but
# we leave it here because it allows us to revert to the standard behavior
# in the future if desired
%systemd_postun_with_restart pacemaker_remote.service
# Explicitly take care of removing the flag-file(s) upon final removal
if [ "$1" -eq 0 ] ; then
rm -f %{_localstatedir}/lib/rpm-state/%{name}/restart_pacemaker_remote
fi
%endif
%posttrans remote
%if %{defined _unitdir}
if [ -e %{_localstatedir}/lib/rpm-state/%{name}/restart_pacemaker_remote ] ; then
systemctl start pacemaker_remote >/dev/null 2>&1
rm -f %{_localstatedir}/lib/rpm-state/%{name}/restart_pacemaker_remote
fi
%endif
%post cli
%if %{defined _unitdir}
%systemd_post crm_mon.service
%endif
if [ "$1" -eq 2 ]; then
# Package upgrade, not initial install:
# Move any pre-2.0 logs to new location to ensure they get rotated
{ mv -fbS.rpmsave %{_var}/log/pacemaker.log* %{_var}/log/pacemaker \
|| mv -f %{_var}/log/pacemaker.log* %{_var}/log/pacemaker
} >/dev/null 2>/dev/null || :
fi
%preun cli
%if %{defined _unitdir}
%systemd_preun crm_mon.service
%endif
%postun cli
%if %{defined _unitdir}
%systemd_postun_with_restart crm_mon.service
%endif
%pre -n %{pkgname_pcmk_libs}
getent group %{gname} >/dev/null || groupadd -r %{gname} -g %{hacluster_id}
getent passwd %{uname} >/dev/null || useradd -r -g %{gname} -u %{hacluster_id} -s /sbin/nologin -c "cluster user" %{uname}
exit 0
%if %{defined ldconfig_scriptlets}
%ldconfig_scriptlets -n %{pkgname_pcmk_libs}
%ldconfig_scriptlets cluster-libs
%else
%post -n %{pkgname_pcmk_libs} -p /sbin/ldconfig
%postun -n %{pkgname_pcmk_libs} -p /sbin/ldconfig
%post cluster-libs -p /sbin/ldconfig
%postun cluster-libs -p /sbin/ldconfig
%endif
%files
###########################################################
%config(noreplace) %{_sysconfdir}/sysconfig/pacemaker
%{_sbindir}/pacemakerd
%if %{defined _unitdir}
%{_unitdir}/pacemaker.service
%else
%{_initrddir}/pacemaker
%endif
%exclude %{_libexecdir}/pacemaker/cts-log-watcher
%exclude %{_libexecdir}/pacemaker/cts-support
%exclude %{_sbindir}/pacemaker-remoted
%exclude %{_sbindir}/pacemaker_remoted
%{_libexecdir}/pacemaker/*
%if %{with stonithd}
%{_sbindir}/fence_legacy
%endif
%{_sbindir}/fence_watchdog
%doc %{_mandir}/man7/pacemaker-controld.*
%doc %{_mandir}/man7/pacemaker-schedulerd.*
%doc %{_mandir}/man7/pacemaker-fenced.*
%doc %{_mandir}/man7/ocf_pacemaker_controld.*
%doc %{_mandir}/man7/ocf_pacemaker_o2cb.*
%doc %{_mandir}/man7/ocf_pacemaker_remote.*
%if %{with stonithd}
%doc %{_mandir}/man8/fence_legacy.*
%endif
%doc %{_mandir}/man8/fence_watchdog.*
%doc %{_mandir}/man8/pacemakerd.*
%doc %{_datadir}/pacemaker/alerts
%license licenses/GPLv2
%doc COPYING
%doc ChangeLog
%dir %attr (750, %{uname}, %{gname}) %{_var}/lib/pacemaker/cib
%dir %attr (750, %{uname}, %{gname}) %{_var}/lib/pacemaker/pengine
%{ocf_root}/resource.d/pacemaker/controld
%{ocf_root}/resource.d/pacemaker/o2cb
%{ocf_root}/resource.d/pacemaker/remote
%if %{with upstart_job}
%config(noreplace) %{_sysconfdir}/init/pacemaker.conf
%config(noreplace) %{_sysconfdir}/init/pacemaker.combined.conf
%endif
%files cli
%dir %attr (750, root, %{gname}) %{_sysconfdir}/pacemaker
%config(noreplace) %{_sysconfdir}/logrotate.d/pacemaker
%config(noreplace) %{_sysconfdir}/sysconfig/crm_mon
%if %{defined _unitdir}
%{_unitdir}/crm_mon.service
%endif
%if %{with upstart_job}
%config(noreplace) %{_sysconfdir}/init/crm_mon.conf
%endif
%{_sbindir}/attrd_updater
%{_sbindir}/cibadmin
%if %{with cibsecrets}
%{_sbindir}/cibsecret
%endif
%{_sbindir}/crm_attribute
%{_sbindir}/crm_diff
%{_sbindir}/crm_error
%{_sbindir}/crm_failcount
%{_sbindir}/crm_master
%{_sbindir}/crm_mon
%{_sbindir}/crm_node
%{_sbindir}/crm_resource
%{_sbindir}/crm_rule
%{_sbindir}/crm_standby
%{_sbindir}/crm_verify
%{_sbindir}/crmadmin
%{_sbindir}/iso8601
%{_sbindir}/crm_shadow
%{_sbindir}/crm_simulate
%{_sbindir}/crm_report
%{_sbindir}/crm_ticket
%{_sbindir}/stonith_admin
# "dirname" is owned by -schemas, which is a prerequisite
%{_datadir}/pacemaker/report.collector
%{_datadir}/pacemaker/report.common
# XXX "dirname" is not owned by any prerequisite
%{_datadir}/snmp/mibs/PCMK-MIB.txt
%exclude %{ocf_root}/resource.d/pacemaker/controld
%exclude %{ocf_root}/resource.d/pacemaker/o2cb
%exclude %{ocf_root}/resource.d/pacemaker/remote
%dir %{ocf_root}
%dir %{ocf_root}/resource.d
%{ocf_root}/resource.d/pacemaker
%doc %{_mandir}/man7/*pacemaker*
%exclude %{_mandir}/man7/pacemaker-controld.*
%exclude %{_mandir}/man7/pacemaker-schedulerd.*
%exclude %{_mandir}/man7/pacemaker-fenced.*
%exclude %{_mandir}/man7/ocf_pacemaker_controld.*
%exclude %{_mandir}/man7/ocf_pacemaker_o2cb.*
%exclude %{_mandir}/man7/ocf_pacemaker_remote.*
%doc %{_mandir}/man8/crm*.8.gz
%doc %{_mandir}/man8/attrd_updater.*
%doc %{_mandir}/man8/cibadmin.*
%if %{with cibsecrets}
%doc %{_mandir}/man8/cibsecret.*
%endif
%doc %{_mandir}/man8/iso8601.*
%doc %{_mandir}/man8/stonith_admin.*
%license licenses/GPLv2
%doc COPYING
%doc ChangeLog
%dir %attr (750, %{uname}, %{gname}) %{_var}/lib/pacemaker
%dir %attr (750, %{uname}, %{gname}) %{_var}/lib/pacemaker/blackbox
%dir %attr (750, %{uname}, %{gname}) %{_var}/lib/pacemaker/cores
%dir %attr (770, %{uname}, %{gname}) %{_var}/log/pacemaker
%dir %attr (770, %{uname}, %{gname}) %{_var}/log/pacemaker/bundles
%files -n %{pkgname_pcmk_libs} %{?with_nls:-f %{name}.lang}
%{_libdir}/libcib.so.*
%{_libdir}/liblrmd.so.*
%{_libdir}/libcrmservice.so.*
%{_libdir}/libcrmcommon.so.*
%{_libdir}/libpe_status.so.*
%{_libdir}/libpe_rules.so.*
%{_libdir}/libpacemaker.so.*
%{_libdir}/libstonithd.so.*
%license licenses/LGPLv2.1
%doc COPYING
%doc ChangeLog
%files cluster-libs
%{_libdir}/libcrmcluster.so.*
%license licenses/LGPLv2.1
%doc COPYING
%doc ChangeLog
%files -n %{python_name}-%{name}
%{python3_sitelib}/pacemaker/
%{python3_sitelib}/pacemaker-*.egg-info
%exclude %{python3_sitelib}/pacemaker/_cts/
%license licenses/LGPLv2.1
%doc COPYING
%doc ChangeLog
%files remote
%config(noreplace) %{_sysconfdir}/sysconfig/pacemaker
%if %{defined _unitdir}
# state directory is shared between the subpackets
# let rpm take care of removing it once it isn't
# referenced anymore and empty
%ghost %dir %{_localstatedir}/lib/rpm-state/%{name}
%{_unitdir}/pacemaker_remote.service
%else
%{_initrddir}/pacemaker_remote
%endif
%{_sbindir}/pacemaker-remoted
%{_sbindir}/pacemaker_remoted
%{_mandir}/man8/pacemaker-remoted.*
%license licenses/GPLv2
%doc COPYING
%doc ChangeLog
%files doc
%doc %{pcmk_docdir}
%license licenses/CC-BY-SA-4.0
%files cts
%{python3_sitelib}/pacemaker/_cts/
%{_datadir}/pacemaker/tests
%{_libexecdir}/pacemaker/cts-log-watcher
%{_libexecdir}/pacemaker/cts-support
%license licenses/GPLv2
%doc COPYING
%doc ChangeLog
%files -n %{pkgname_pcmk_libs}-devel
%{_includedir}/pacemaker
%{_libdir}/libcib.so
%{_libdir}/liblrmd.so
%{_libdir}/libcrmservice.so
%{_libdir}/libcrmcommon.so
%{_libdir}/libpe_status.so
%{_libdir}/libpe_rules.so
%{_libdir}/libpacemaker.so
%{_libdir}/libstonithd.so
%{_libdir}/libcrmcluster.so
%{_libdir}/pkgconfig/*pacemaker*.pc
%license licenses/LGPLv2.1
%doc COPYING
%doc ChangeLog
%files schemas
%license licenses/GPLv2
%dir %{_datadir}/pacemaker
%{_datadir}/pacemaker/*.rng
%{_datadir}/pacemaker/*.xsl
%{_datadir}/pacemaker/api
%{_datadir}/pacemaker/base
%{_datadir}/pkgconfig/pacemaker-schemas.pc
%changelog
* PACKAGE_DATE ClusterLabs <admin@clusterlabs.org> PACKAGE_VERSION
- See included ChangeLog file for details
diff --git a/tools/crm_resource_runtime.c b/tools/crm_resource_runtime.c
index 3d5597ec03..da360fd53c 100644
--- a/tools/crm_resource_runtime.c
+++ b/tools/crm_resource_runtime.c
@@ -1,2239 +1,2244 @@
/*
* Copyright 2004-2023 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU General Public License version 2
* or later (GPLv2+) WITHOUT ANY WARRANTY.
*/
#include <crm_internal.h>
#include <crm_resource.h>
#include <crm/common/ipc_attrd_internal.h>
#include <crm/common/ipc_controld.h>
#include <crm/common/lists_internal.h>
#include <crm/services_internal.h>
static GList *
build_node_info_list(const pcmk_resource_t *rsc)
{
GList *retval = NULL;
for (const GList *iter = rsc->children; iter != NULL; iter = iter->next) {
const pcmk_resource_t *child = (const pcmk_resource_t *) iter->data;
for (const GList *iter2 = child->running_on;
iter2 != NULL; iter2 = iter2->next) {
const pcmk_node_t *node = (const pcmk_node_t *) iter2->data;
node_info_t *ni = calloc(1, sizeof(node_info_t));
ni->node_name = node->details->uname;
ni->promoted = pcmk_is_set(rsc->flags, pcmk_rsc_promotable) &&
child->fns->state(child, TRUE) == pcmk_role_promoted;
retval = g_list_prepend(retval, ni);
}
}
return retval;
}
GList *
cli_resource_search(pcmk_resource_t *rsc, const char *requested_name,
pcmk_scheduler_t *scheduler)
{
GList *retval = NULL;
const pcmk_resource_t *parent = pe__const_top_resource(rsc, false);
if (pe_rsc_is_clone(rsc)) {
retval = build_node_info_list(rsc);
/* The anonymous clone children's common ID is supplied */
} else if (pe_rsc_is_clone(parent)
&& !pcmk_is_set(rsc->flags, pcmk_rsc_unique)
&& rsc->clone_name
&& pcmk__str_eq(requested_name, rsc->clone_name, pcmk__str_casei)
&& !pcmk__str_eq(requested_name, rsc->id, pcmk__str_casei)) {
retval = build_node_info_list(parent);
} else if (rsc->running_on != NULL) {
for (GList *iter = rsc->running_on; iter != NULL; iter = iter->next) {
pcmk_node_t *node = (pcmk_node_t *) iter->data;
node_info_t *ni = calloc(1, sizeof(node_info_t));
ni->node_name = node->details->uname;
ni->promoted = (rsc->fns->state(rsc, TRUE) == pcmk_role_promoted);
retval = g_list_prepend(retval, ni);
}
}
return retval;
}
// \return Standard Pacemaker return code
static int
find_resource_attr(pcmk__output_t *out, cib_t * the_cib, const char *attr,
const char *rsc, const char *attr_set_type, const char *set_name,
const char *attr_id, const char *attr_name, char **value)
{
int rc = pcmk_rc_ok;
xmlNode *xml_search = NULL;
GString *xpath = NULL;
const char *xpath_base = NULL;
if(value) {
*value = NULL;
}
if(the_cib == NULL) {
return ENOTCONN;
}
xpath_base = pcmk_cib_xpath_for(XML_CIB_TAG_RESOURCES);
if (xpath_base == NULL) {
crm_err(XML_CIB_TAG_RESOURCES " CIB element not known (bug?)");
return ENOMSG;
}
xpath = g_string_sized_new(1024);
pcmk__g_strcat(xpath,
xpath_base, "//*[@" XML_ATTR_ID "=\"", rsc, "\"]", NULL);
if (attr_set_type != NULL) {
pcmk__g_strcat(xpath, "/", attr_set_type, NULL);
if (set_name != NULL) {
pcmk__g_strcat(xpath, "[@" XML_ATTR_ID "=\"", set_name, "\"]",
NULL);
}
}
g_string_append(xpath, "//" XML_CIB_TAG_NVPAIR "[");
if (attr_id != NULL) {
pcmk__g_strcat(xpath, "@" XML_ATTR_ID "=\"", attr_id, "\"", NULL);
}
if (attr_name != NULL) {
if (attr_id != NULL) {
g_string_append(xpath, " and ");
}
pcmk__g_strcat(xpath, "@" XML_NVPAIR_ATTR_NAME "=\"", attr_name, "\"",
NULL);
}
g_string_append_c(xpath, ']');
rc = the_cib->cmds->query(the_cib, (const char *) xpath->str, &xml_search,
cib_sync_call | cib_scope_local | cib_xpath);
rc = pcmk_legacy2rc(rc);
if (rc != pcmk_rc_ok) {
goto done;
}
crm_log_xml_debug(xml_search, "Match");
if (xml_search->children != NULL) {
xmlNode *child = NULL;
rc = ENOTUNIQ;
out->info(out, "Multiple attributes match name=%s", attr_name);
for (child = pcmk__xml_first_child(xml_search); child != NULL;
child = pcmk__xml_next(child)) {
out->info(out, " Value: %s \t(id=%s)",
crm_element_value(child, XML_NVPAIR_ATTR_VALUE), ID(child));
}
out->spacer(out);
} else if(value) {
pcmk__str_update(value, crm_element_value(xml_search, attr));
}
done:
g_string_free(xpath, TRUE);
free_xml(xml_search);
return rc;
}
/* PRIVATE. Use the find_matching_attr_resources instead. */
static void
find_matching_attr_resources_recursive(pcmk__output_t *out,
GList /* <pcmk_resource_t*> */ **result,
pcmk_resource_t *rsc, const char *rsc_id,
const char * attr_set, const char * attr_set_type,
const char * attr_id, const char * attr_name,
cib_t * cib, const char * cmd, int depth)
{
int rc = pcmk_rc_ok;
char *lookup_id = clone_strip(rsc->id);
char *local_attr_id = NULL;
/* visit the children */
for(GList *gIter = rsc->children; gIter; gIter = gIter->next) {
find_matching_attr_resources_recursive(out, result,
(pcmk_resource_t *) gIter->data,
rsc_id, attr_set, attr_set_type,
attr_id, attr_name, cib, cmd, depth+1);
/* do it only once for clones */
if (rsc->variant == pcmk_rsc_variant_clone) {
break;
}
}
rc = find_resource_attr(out, cib, XML_ATTR_ID, lookup_id, attr_set_type,
attr_set, attr_id, attr_name, &local_attr_id);
/* Post-order traversal.
* The root is always on the list and it is the last item. */
if((0 == depth) || (pcmk_rc_ok == rc)) {
/* push the head */
*result = g_list_append(*result, rsc);
}
free(local_attr_id);
free(lookup_id);
}
/* The result is a linearized pre-ordered tree of resources. */
static GList/*<pcmk_resource_t*>*/ *
find_matching_attr_resources(pcmk__output_t *out, pcmk_resource_t *rsc,
const char * rsc_id, const char * attr_set,
const char * attr_set_type, const char * attr_id,
const char * attr_name, cib_t * cib, const char * cmd,
gboolean force)
{
int rc = pcmk_rc_ok;
char *lookup_id = NULL;
char *local_attr_id = NULL;
GList * result = NULL;
/* If --force is used, update only the requested resource (clone or primitive).
* Otherwise, if the primitive has the attribute, use that.
* Otherwise use the clone. */
if(force == TRUE) {
return g_list_append(result, rsc);
}
if ((rsc->parent != NULL)
&& (rsc->parent->variant == pcmk_rsc_variant_clone)) {
int rc = pcmk_rc_ok;
char *local_attr_id = NULL;
rc = find_resource_attr(out, cib, XML_ATTR_ID, rsc_id, attr_set_type,
attr_set, attr_id, attr_name, &local_attr_id);
free(local_attr_id);
if(rc != pcmk_rc_ok) {
rsc = rsc->parent;
out->info(out, "Performing %s of '%s' on '%s', the parent of '%s'",
cmd, attr_name, rsc->id, rsc_id);
}
return g_list_append(result, rsc);
} else if ((rsc->parent == NULL) && (rsc->children != NULL)
&& (rsc->variant == pcmk_rsc_variant_clone)) {
pcmk_resource_t *child = rsc->children->data;
if (child->variant == pcmk_rsc_variant_primitive) {
lookup_id = clone_strip(child->id); /* Could be a cloned group! */
rc = find_resource_attr(out, cib, XML_ATTR_ID, lookup_id, attr_set_type,
attr_set, attr_id, attr_name, &local_attr_id);
if(rc == pcmk_rc_ok) {
rsc = child;
out->info(out, "A value for '%s' already exists in child '%s', performing %s on that instead of '%s'",
attr_name, lookup_id, cmd, rsc_id);
}
free(local_attr_id);
free(lookup_id);
}
return g_list_append(result, rsc);
}
/* If the resource is a group ==> children inherit the attribute if defined. */
find_matching_attr_resources_recursive(out, &result, rsc, rsc_id, attr_set,
attr_set_type, attr_id, attr_name,
cib, cmd, 0);
return result;
}
// \return Standard Pacemaker return code
int
cli_resource_update_attribute(pcmk_resource_t *rsc, const char *requested_name,
const char *attr_set, const char *attr_set_type,
const char *attr_id, const char *attr_name,
const char *attr_value, gboolean recursive,
cib_t *cib, int cib_options, gboolean force)
{
pcmk__output_t *out = rsc->cluster->priv;
int rc = pcmk_rc_ok;
char *found_attr_id = NULL;
GList/*<pcmk_resource_t*>*/ *resources = NULL;
const char *top_id = pe__const_top_resource(rsc, false)->id;
if ((attr_id == NULL) && !force) {
find_resource_attr(out, cib, XML_ATTR_ID, top_id, NULL, NULL, NULL,
attr_name, NULL);
}
if (pcmk__str_eq(attr_set_type, XML_TAG_ATTR_SETS, pcmk__str_casei)) {
if (!force) {
rc = find_resource_attr(out, cib, XML_ATTR_ID, top_id,
XML_TAG_META_SETS, attr_set, attr_id,
attr_name, &found_attr_id);
if ((rc == pcmk_rc_ok) && !out->is_quiet(out)) {
out->err(out,
"WARNING: There is already a meta attribute "
"for '%s' called '%s' (id=%s)",
top_id, attr_name, found_attr_id);
out->err(out,
" Delete '%s' first or use the force option "
"to override", found_attr_id);
}
free(found_attr_id);
if (rc == pcmk_rc_ok) {
return ENOTUNIQ;
}
}
resources = g_list_append(resources, rsc);
} else if (pcmk__str_eq(attr_set_type, ATTR_SET_ELEMENT, pcmk__str_none)) {
crm_xml_add(rsc->xml, attr_name, attr_value);
CRM_ASSERT(cib != NULL);
rc = cib->cmds->replace(cib, XML_CIB_TAG_RESOURCES, rsc->xml,
cib_options);
rc = pcmk_legacy2rc(rc);
if (rc == pcmk_rc_ok) {
out->info(out, "Set attribute: name=%s value=%s",
attr_name, attr_value);
}
return rc;
} else {
resources = find_matching_attr_resources(out, rsc, requested_name,
attr_set, attr_set_type,
attr_id, attr_name, cib,
"update", force);
}
/* If the user specified attr_set or attr_id, the intent is to modify a
* single resource, which will be the last item in the list.
*/
if ((attr_set != NULL) || (attr_id != NULL)) {
GList *last = g_list_last(resources);
resources = g_list_remove_link(resources, last);
g_list_free(resources);
resources = last;
}
for (GList *iter = resources; iter != NULL; iter = iter->next) {
char *lookup_id = NULL;
char *local_attr_set = NULL;
const char *rsc_attr_id = attr_id;
const char *rsc_attr_set = attr_set;
xmlNode *xml_top = NULL;
xmlNode *xml_obj = NULL;
found_attr_id = NULL;
rsc = (pcmk_resource_t *) iter->data;
lookup_id = clone_strip(rsc->id); /* Could be a cloned group! */
rc = find_resource_attr(out, cib, XML_ATTR_ID, lookup_id, attr_set_type,
attr_set, attr_id, attr_name, &found_attr_id);
switch (rc) {
case pcmk_rc_ok:
crm_debug("Found a match for name=%s: id=%s",
attr_name, found_attr_id);
rsc_attr_id = found_attr_id;
break;
case ENXIO:
if (rsc_attr_set == NULL) {
local_attr_set = crm_strdup_printf("%s-%s", lookup_id,
attr_set_type);
rsc_attr_set = local_attr_set;
}
if (rsc_attr_id == NULL) {
found_attr_id = crm_strdup_printf("%s-%s",
rsc_attr_set, attr_name);
rsc_attr_id = found_attr_id;
}
xml_top = create_xml_node(NULL, (const char *) rsc->xml->name);
crm_xml_add(xml_top, XML_ATTR_ID, lookup_id);
xml_obj = create_xml_node(xml_top, attr_set_type);
crm_xml_add(xml_obj, XML_ATTR_ID, rsc_attr_set);
break;
default:
free(lookup_id);
free(found_attr_id);
g_list_free(resources);
return rc;
}
xml_obj = crm_create_nvpair_xml(xml_obj, rsc_attr_id, attr_name,
attr_value);
if (xml_top == NULL) {
xml_top = xml_obj;
}
crm_log_xml_debug(xml_top, "Update");
rc = cib->cmds->modify(cib, XML_CIB_TAG_RESOURCES, xml_top,
cib_options);
rc = pcmk_legacy2rc(rc);
if (rc == pcmk_rc_ok) {
out->info(out, "Set '%s' option: id=%s%s%s%s%s value=%s",
lookup_id, found_attr_id,
((rsc_attr_set == NULL)? "" : " set="),
pcmk__s(rsc_attr_set, ""),
((attr_name == NULL)? "" : " name="),
pcmk__s(attr_name, ""), attr_value);
}
free_xml(xml_top);
free(lookup_id);
free(found_attr_id);
free(local_attr_set);
if (recursive
&& pcmk__str_eq(attr_set_type, XML_TAG_META_SETS,
pcmk__str_casei)) {
GList *lpc = NULL;
static bool need_init = true;
if (need_init) {
need_init = false;
pcmk__unpack_constraints(rsc->cluster);
pe__clear_resource_flags_on_all(rsc->cluster,
pcmk_rsc_detect_loop);
}
/* We want to set the attribute only on resources explicitly
* colocated with this one, so we use rsc->rsc_cons_lhs directly
* rather than the with_this_colocations() method.
*/
pe__set_resource_flags(rsc, pcmk_rsc_detect_loop);
for (lpc = rsc->rsc_cons_lhs; lpc != NULL; lpc = lpc->next) {
pcmk__colocation_t *cons = (pcmk__colocation_t *) lpc->data;
crm_debug("Checking %s %d", cons->id, cons->score);
if (!pcmk_is_set(cons->dependent->flags, pcmk_rsc_detect_loop)
&& (cons->score > 0)) {
crm_debug("Setting %s=%s for dependent resource %s",
attr_name, attr_value, cons->dependent->id);
cli_resource_update_attribute(cons->dependent,
cons->dependent->id, NULL,
attr_set_type, NULL,
attr_name, attr_value,
recursive, cib, cib_options,
force);
}
}
}
}
g_list_free(resources);
return rc;
}
// \return Standard Pacemaker return code
int
cli_resource_delete_attribute(pcmk_resource_t *rsc, const char *requested_name,
const char *attr_set, const char *attr_set_type,
const char *attr_id, const char *attr_name,
cib_t *cib, int cib_options, gboolean force)
{
pcmk__output_t *out = rsc->cluster->priv;
int rc = pcmk_rc_ok;
GList/*<pcmk_resource_t*>*/ *resources = NULL;
if ((attr_id == NULL) && !force) {
find_resource_attr(out, cib, XML_ATTR_ID,
pe__const_top_resource(rsc, false)->id, NULL,
NULL, NULL, attr_name, NULL);
}
if (pcmk__str_eq(attr_set_type, XML_TAG_META_SETS, pcmk__str_casei)) {
resources = find_matching_attr_resources(out, rsc, requested_name,
attr_set, attr_set_type,
attr_id, attr_name, cib,
"delete", force);
} else if (pcmk__str_eq(attr_set_type, ATTR_SET_ELEMENT, pcmk__str_none)) {
xml_remove_prop(rsc->xml, attr_name);
CRM_ASSERT(cib != NULL);
rc = cib->cmds->replace(cib, XML_CIB_TAG_RESOURCES, rsc->xml,
cib_options);
rc = pcmk_legacy2rc(rc);
if (rc == pcmk_rc_ok) {
out->info(out, "Deleted attribute: %s", attr_name);
}
return rc;
} else {
resources = g_list_append(resources, rsc);
}
for (GList *iter = resources; iter != NULL; iter = iter->next) {
char *lookup_id = NULL;
xmlNode *xml_obj = NULL;
char *found_attr_id = NULL;
const char *rsc_attr_id = attr_id;
rsc = (pcmk_resource_t *) iter->data;
lookup_id = clone_strip(rsc->id);
rc = find_resource_attr(out, cib, XML_ATTR_ID, lookup_id, attr_set_type,
attr_set, attr_id, attr_name, &found_attr_id);
switch (rc) {
case pcmk_rc_ok:
break;
case ENXIO:
free(lookup_id);
rc = pcmk_rc_ok;
continue;
default:
free(lookup_id);
g_list_free(resources);
return rc;
}
if (rsc_attr_id == NULL) {
rsc_attr_id = found_attr_id;
}
xml_obj = crm_create_nvpair_xml(NULL, rsc_attr_id, attr_name, NULL);
crm_log_xml_debug(xml_obj, "Delete");
CRM_ASSERT(cib);
rc = cib->cmds->remove(cib, XML_CIB_TAG_RESOURCES, xml_obj,
cib_options);
rc = pcmk_legacy2rc(rc);
if (rc == pcmk_rc_ok) {
out->info(out, "Deleted '%s' option: id=%s%s%s%s%s",
lookup_id, found_attr_id,
((attr_set == NULL)? "" : " set="),
pcmk__s(attr_set, ""),
((attr_name == NULL)? "" : " name="),
pcmk__s(attr_name, ""));
}
free(lookup_id);
free_xml(xml_obj);
free(found_attr_id);
}
g_list_free(resources);
return rc;
}
// \return Standard Pacemaker return code
static int
send_lrm_rsc_op(pcmk_ipc_api_t *controld_api, bool do_fail_resource,
const char *host_uname, const char *rsc_id,
pcmk_scheduler_t *scheduler)
{
pcmk__output_t *out = scheduler->priv;
const char *router_node = host_uname;
const char *rsc_api_id = NULL;
const char *rsc_long_id = NULL;
const char *rsc_class = NULL;
const char *rsc_provider = NULL;
const char *rsc_type = NULL;
bool cib_only = false;
pcmk_resource_t *rsc = pe_find_resource(scheduler->resources, rsc_id);
if (rsc == NULL) {
out->err(out, "Resource %s not found", rsc_id);
return ENXIO;
} else if (rsc->variant != pcmk_rsc_variant_primitive) {
out->err(out, "We can only process primitive resources, not %s", rsc_id);
return EINVAL;
}
rsc_class = crm_element_value(rsc->xml, XML_AGENT_ATTR_CLASS);
rsc_provider = crm_element_value(rsc->xml, XML_AGENT_ATTR_PROVIDER),
rsc_type = crm_element_value(rsc->xml, XML_ATTR_TYPE);
if ((rsc_class == NULL) || (rsc_type == NULL)) {
out->err(out, "Resource %s does not have a class and type", rsc_id);
return EINVAL;
}
{
pcmk_node_t *node = pe_find_node(scheduler->nodes, host_uname);
if (node == NULL) {
out->err(out, "Node %s not found", host_uname);
return pcmk_rc_node_unknown;
}
if (!(node->details->online)) {
if (do_fail_resource) {
out->err(out, "Node %s is not online", host_uname);
return ENOTCONN;
} else {
cib_only = true;
}
}
if (!cib_only && pe__is_guest_or_remote_node(node)) {
node = pe__current_node(node->details->remote_rsc);
if (node == NULL) {
out->err(out, "No cluster connection to Pacemaker Remote node %s detected",
host_uname);
return ENOTCONN;
}
router_node = node->details->uname;
}
}
if (rsc->clone_name) {
rsc_api_id = rsc->clone_name;
rsc_long_id = rsc->id;
} else {
rsc_api_id = rsc->id;
}
if (do_fail_resource) {
return pcmk_controld_api_fail(controld_api, host_uname, router_node,
rsc_api_id, rsc_long_id,
rsc_class, rsc_provider, rsc_type);
} else {
return pcmk_controld_api_refresh(controld_api, host_uname, router_node,
rsc_api_id, rsc_long_id, rsc_class,
rsc_provider, rsc_type, cib_only);
}
}
/*!
* \internal
* \brief Get resource name as used in failure-related node attributes
*
* \param[in] rsc Resource to check
*
* \return Newly allocated string containing resource's fail name
* \note The caller is responsible for freeing the result.
*/
static inline char *
rsc_fail_name(const pcmk_resource_t *rsc)
{
const char *name = (rsc->clone_name? rsc->clone_name : rsc->id);
if (pcmk_is_set(rsc->flags, pcmk_rsc_unique)) {
return strdup(name);
}
return clone_strip(name);
}
// \return Standard Pacemaker return code
static int
clear_rsc_history(pcmk_ipc_api_t *controld_api, const char *host_uname,
const char *rsc_id, pcmk_scheduler_t *scheduler)
{
int rc = pcmk_rc_ok;
/* Erase the resource's entire LRM history in the CIB, even if we're only
* clearing a single operation's fail count. If we erased only entries for a
* single operation, we might wind up with a wrong idea of the current
* resource state, and we might not re-probe the resource.
*/
rc = send_lrm_rsc_op(controld_api, false, host_uname, rsc_id, scheduler);
if (rc != pcmk_rc_ok) {
return rc;
}
crm_trace("Processing %d mainloop inputs",
pcmk_controld_api_replies_expected(controld_api));
while (g_main_context_iteration(NULL, FALSE)) {
crm_trace("Processed mainloop input, %d still remaining",
pcmk_controld_api_replies_expected(controld_api));
}
return rc;
}
// \return Standard Pacemaker return code
static int
clear_rsc_failures(pcmk__output_t *out, pcmk_ipc_api_t *controld_api,
const char *node_name, const char *rsc_id, const char *operation,
const char *interval_spec, pcmk_scheduler_t *scheduler)
{
int rc = pcmk_rc_ok;
const char *failed_value = NULL;
const char *failed_id = NULL;
const char *interval_ms_s = NULL;
GHashTable *rscs = NULL;
GHashTableIter iter;
/* Create a hash table to use as a set of resources to clean. This lets us
* clean each resource only once (per node) regardless of how many failed
* operations it has.
*/
rscs = pcmk__strkey_table(NULL, NULL);
// Normalize interval to milliseconds for comparison to history entry
if (operation) {
interval_ms_s = crm_strdup_printf("%u",
crm_parse_interval_spec(interval_spec));
}
for (xmlNode *xml_op = pcmk__xml_first_child(scheduler->failed);
xml_op != NULL;
xml_op = pcmk__xml_next(xml_op)) {
failed_id = crm_element_value(xml_op, XML_LRM_ATTR_RSCID);
if (failed_id == NULL) {
// Malformed history entry, should never happen
continue;
}
// No resource specified means all resources match
if (rsc_id) {
pcmk_resource_t *fail_rsc = NULL;
fail_rsc = pe_find_resource_with_flags(scheduler->resources,
failed_id,
pcmk_rsc_match_history
|pcmk_rsc_match_anon_basename);
if (!fail_rsc || !pcmk__str_eq(rsc_id, fail_rsc->id, pcmk__str_casei)) {
continue;
}
}
// Host name should always have been provided by this point
failed_value = crm_element_value(xml_op, XML_ATTR_UNAME);
if (!pcmk__str_eq(node_name, failed_value, pcmk__str_casei)) {
continue;
}
// No operation specified means all operations match
if (operation) {
failed_value = crm_element_value(xml_op, XML_LRM_ATTR_TASK);
if (!pcmk__str_eq(operation, failed_value, pcmk__str_casei)) {
continue;
}
// Interval (if operation was specified) defaults to 0 (not all)
failed_value = crm_element_value(xml_op, XML_LRM_ATTR_INTERVAL_MS);
if (!pcmk__str_eq(interval_ms_s, failed_value, pcmk__str_casei)) {
continue;
}
}
g_hash_table_add(rscs, (gpointer) failed_id);
}
g_hash_table_iter_init(&iter, rscs);
while (g_hash_table_iter_next(&iter, (gpointer *) &failed_id, NULL)) {
crm_debug("Erasing failures of %s on %s", failed_id, node_name);
rc = clear_rsc_history(controld_api, node_name, failed_id, scheduler);
if (rc != pcmk_rc_ok) {
return rc;
}
}
g_hash_table_destroy(rscs);
return rc;
}
// \return Standard Pacemaker return code
static int
clear_rsc_fail_attrs(const pcmk_resource_t *rsc, const char *operation,
const char *interval_spec, const pcmk_node_t *node)
{
int rc = pcmk_rc_ok;
int attr_options = pcmk__node_attr_none;
char *rsc_name = rsc_fail_name(rsc);
if (pe__is_guest_or_remote_node(node)) {
attr_options |= pcmk__node_attr_remote;
}
rc = pcmk__attrd_api_clear_failures(NULL, node->details->uname, rsc_name,
operation, interval_spec, NULL,
attr_options);
free(rsc_name);
return rc;
}
// \return Standard Pacemaker return code
int
cli_resource_delete(pcmk_ipc_api_t *controld_api, const char *host_uname,
const pcmk_resource_t *rsc, const char *operation,
const char *interval_spec, bool just_failures,
pcmk_scheduler_t *scheduler, gboolean force)
{
pcmk__output_t *out = scheduler->priv;
int rc = pcmk_rc_ok;
pcmk_node_t *node = NULL;
if (rsc == NULL) {
return ENXIO;
} else if (rsc->children) {
for (const GList *lpc = rsc->children; lpc != NULL; lpc = lpc->next) {
const pcmk_resource_t *child = (const pcmk_resource_t *) lpc->data;
rc = cli_resource_delete(controld_api, host_uname, child, operation,
interval_spec, just_failures, scheduler,
force);
if (rc != pcmk_rc_ok) {
return rc;
}
}
return pcmk_rc_ok;
} else if (host_uname == NULL) {
GList *lpc = NULL;
GList *nodes = g_hash_table_get_values(rsc->known_on);
if(nodes == NULL && force) {
nodes = pcmk__copy_node_list(scheduler->nodes, false);
} else if(nodes == NULL && rsc->exclusive_discover) {
GHashTableIter iter;
pcmk_node_t *node = NULL;
g_hash_table_iter_init(&iter, rsc->allowed_nodes);
while (g_hash_table_iter_next(&iter, NULL, (void**)&node)) {
if(node->weight >= 0) {
nodes = g_list_prepend(nodes, node);
}
}
} else if(nodes == NULL) {
nodes = g_hash_table_get_values(rsc->allowed_nodes);
}
for (lpc = nodes; lpc != NULL; lpc = lpc->next) {
node = (pcmk_node_t *) lpc->data;
if (node->details->online) {
rc = cli_resource_delete(controld_api, node->details->uname, rsc,
operation, interval_spec, just_failures,
scheduler, force);
}
if (rc != pcmk_rc_ok) {
g_list_free(nodes);
return rc;
}
}
g_list_free(nodes);
return pcmk_rc_ok;
}
node = pe_find_node(scheduler->nodes, host_uname);
if (node == NULL) {
out->err(out, "Unable to clean up %s because node %s not found",
rsc->id, host_uname);
return ENODEV;
}
if (!node->details->rsc_discovery_enabled) {
out->err(out, "Unable to clean up %s because resource discovery disabled on %s",
rsc->id, host_uname);
return EOPNOTSUPP;
}
if (controld_api == NULL) {
out->err(out, "Dry run: skipping clean-up of %s on %s due to CIB_file",
rsc->id, host_uname);
return pcmk_rc_ok;
}
rc = clear_rsc_fail_attrs(rsc, operation, interval_spec, node);
if (rc != pcmk_rc_ok) {
out->err(out, "Unable to clean up %s failures on %s: %s",
rsc->id, host_uname, pcmk_rc_str(rc));
return rc;
}
if (just_failures) {
rc = clear_rsc_failures(out, controld_api, host_uname, rsc->id, operation,
interval_spec, scheduler);
} else {
rc = clear_rsc_history(controld_api, host_uname, rsc->id, scheduler);
}
if (rc != pcmk_rc_ok) {
out->err(out, "Cleaned %s failures on %s, but unable to clean history: %s",
rsc->id, host_uname, pcmk_rc_str(rc));
} else {
out->info(out, "Cleaned up %s on %s", rsc->id, host_uname);
}
return rc;
}
// \return Standard Pacemaker return code
int
cli_cleanup_all(pcmk_ipc_api_t *controld_api, const char *node_name,
const char *operation, const char *interval_spec,
pcmk_scheduler_t *scheduler)
{
pcmk__output_t *out = scheduler->priv;
int rc = pcmk_rc_ok;
int attr_options = pcmk__node_attr_none;
const char *display_name = node_name? node_name : "all nodes";
if (controld_api == NULL) {
out->info(out, "Dry run: skipping clean-up of %s due to CIB_file",
display_name);
return rc;
}
if (node_name) {
pcmk_node_t *node = pe_find_node(scheduler->nodes, node_name);
if (node == NULL) {
out->err(out, "Unknown node: %s", node_name);
return ENXIO;
}
if (pe__is_guest_or_remote_node(node)) {
attr_options |= pcmk__node_attr_remote;
}
}
rc = pcmk__attrd_api_clear_failures(NULL, node_name, NULL, operation,
interval_spec, NULL, attr_options);
if (rc != pcmk_rc_ok) {
out->err(out, "Unable to clean up all failures on %s: %s",
display_name, pcmk_rc_str(rc));
return rc;
}
if (node_name) {
rc = clear_rsc_failures(out, controld_api, node_name, NULL,
operation, interval_spec, scheduler);
if (rc != pcmk_rc_ok) {
out->err(out, "Cleaned all resource failures on %s, but unable to clean history: %s",
node_name, pcmk_rc_str(rc));
return rc;
}
} else {
for (GList *iter = scheduler->nodes; iter; iter = iter->next) {
pcmk_node_t *node = (pcmk_node_t *) iter->data;
rc = clear_rsc_failures(out, controld_api, node->details->uname, NULL,
operation, interval_spec, scheduler);
if (rc != pcmk_rc_ok) {
out->err(out, "Cleaned all resource failures on all nodes, but unable to clean history: %s",
pcmk_rc_str(rc));
return rc;
}
}
}
out->info(out, "Cleaned up all resources on %s", display_name);
return rc;
}
static void
check_role(resource_checks_t *checks)
{
const char *role_s = g_hash_table_lookup(checks->rsc->meta,
XML_RSC_ATTR_TARGET_ROLE);
if (role_s == NULL) {
return;
}
switch (text2role(role_s)) {
case pcmk_role_stopped:
checks->flags |= rsc_remain_stopped;
break;
case pcmk_role_unpromoted:
if (pcmk_is_set(pe__const_top_resource(checks->rsc, false)->flags,
pcmk_rsc_promotable)) {
checks->flags |= rsc_unpromotable;
}
break;
default:
break;
}
}
static void
check_managed(resource_checks_t *checks)
{
const char *managed_s = g_hash_table_lookup(checks->rsc->meta,
XML_RSC_ATTR_MANAGED);
if ((managed_s != NULL) && !crm_is_true(managed_s)) {
checks->flags |= rsc_unmanaged;
}
}
static void
check_locked(resource_checks_t *checks)
{
if (checks->rsc->lock_node != NULL) {
checks->flags |= rsc_locked;
checks->lock_node = checks->rsc->lock_node->details->uname;
}
}
static bool
node_is_unhealthy(pcmk_node_t *node)
{
switch (pe__health_strategy(node->details->data_set)) {
case pcmk__health_strategy_none:
break;
case pcmk__health_strategy_no_red:
if (pe__node_health(node) < 0) {
return true;
}
break;
case pcmk__health_strategy_only_green:
if (pe__node_health(node) <= 0) {
return true;
}
break;
case pcmk__health_strategy_progressive:
case pcmk__health_strategy_custom:
/* @TODO These are finite scores, possibly with rules, and possibly
* combining with other scores, so attributing these as a cause is
* nontrivial.
*/
break;
}
return false;
}
static void
check_node_health(resource_checks_t *checks, pcmk_node_t *node)
{
if (node == NULL) {
GHashTableIter iter;
bool allowed = false;
bool all_nodes_unhealthy = true;
g_hash_table_iter_init(&iter, checks->rsc->allowed_nodes);
while (g_hash_table_iter_next(&iter, NULL, (void **) &node)) {
allowed = true;
if (!node_is_unhealthy(node)) {
all_nodes_unhealthy = false;
break;
}
}
if (allowed && all_nodes_unhealthy) {
checks->flags |= rsc_node_health;
}
} else if (node_is_unhealthy(node)) {
checks->flags |= rsc_node_health;
}
}
int
cli_resource_check(pcmk__output_t *out, pcmk_resource_t *rsc, pcmk_node_t *node)
{
resource_checks_t checks = { .rsc = rsc };
check_role(&checks);
check_managed(&checks);
check_locked(&checks);
check_node_health(&checks, node);
return out->message(out, "resource-check-list", &checks);
}
// \return Standard Pacemaker return code
int
cli_resource_fail(pcmk_ipc_api_t *controld_api, const char *host_uname,
const char *rsc_id, pcmk_scheduler_t *scheduler)
{
crm_notice("Failing %s on %s", rsc_id, host_uname);
return send_lrm_rsc_op(controld_api, true, host_uname, rsc_id, scheduler);
}
static GHashTable *
generate_resource_params(pcmk_resource_t *rsc, pcmk_node_t *node,
pcmk_scheduler_t *scheduler)
{
GHashTable *params = NULL;
GHashTable *meta = NULL;
GHashTable *combined = NULL;
GHashTableIter iter;
char *key = NULL;
char *value = NULL;
combined = pcmk__strkey_table(free, free);
params = pe_rsc_params(rsc, node, scheduler);
if (params != NULL) {
g_hash_table_iter_init(&iter, params);
while (g_hash_table_iter_next(&iter, (gpointer *) & key, (gpointer *) & value)) {
g_hash_table_insert(combined, strdup(key), strdup(value));
}
}
meta = pcmk__strkey_table(free, free);
get_meta_attributes(meta, rsc, node, scheduler);
if (meta != NULL) {
g_hash_table_iter_init(&iter, meta);
while (g_hash_table_iter_next(&iter, (gpointer *) & key, (gpointer *) & value)) {
char *crm_name = crm_meta_name(key);
g_hash_table_insert(combined, crm_name, strdup(value));
}
g_hash_table_destroy(meta);
}
return combined;
}
bool resource_is_running_on(pcmk_resource_t *rsc, const char *host)
{
bool found = true;
GList *hIter = NULL;
GList *hosts = NULL;
if (rsc == NULL) {
return false;
}
rsc->fns->location(rsc, &hosts, TRUE);
for (hIter = hosts; host != NULL && hIter != NULL; hIter = hIter->next) {
pcmk_node_t *node = (pcmk_node_t *) hIter->data;
if (pcmk__strcase_any_of(host, node->details->uname, node->details->id, NULL)) {
crm_trace("Resource %s is running on %s\n", rsc->id, host);
goto done;
}
}
if (host != NULL) {
crm_trace("Resource %s is not running on: %s\n", rsc->id, host);
found = false;
} else if(host == NULL && hosts == NULL) {
crm_trace("Resource %s is not running\n", rsc->id);
found = false;
}
done:
g_list_free(hosts);
return found;
}
/*!
* \internal
* \brief Create a list of all resources active on host from a given list
*
* \param[in] host Name of host to check whether resources are active
* \param[in] rsc_list List of resources to check
*
* \return New list of resources from list that are active on host
*/
static GList *
get_active_resources(const char *host, GList *rsc_list)
{
GList *rIter = NULL;
GList *active = NULL;
for (rIter = rsc_list; rIter != NULL; rIter = rIter->next) {
pcmk_resource_t *rsc = (pcmk_resource_t *) rIter->data;
/* Expand groups to their members, because if we're restarting a member
* other than the first, we can't otherwise tell which resources are
* stopping and starting.
*/
if (rsc->variant == pcmk_rsc_variant_group) {
active = g_list_concat(active,
get_active_resources(host, rsc->children));
} else if (resource_is_running_on(rsc, host)) {
active = g_list_append(active, strdup(rsc->id));
}
}
return active;
}
static void dump_list(GList *items, const char *tag)
{
int lpc = 0;
GList *item = NULL;
for (item = items; item != NULL; item = item->next) {
crm_trace("%s[%d]: %s", tag, lpc, (char*)item->data);
lpc++;
}
}
static void display_list(pcmk__output_t *out, GList *items, const char *tag)
{
GList *item = NULL;
for (item = items; item != NULL; item = item->next) {
out->info(out, "%s%s", tag, (const char *)item->data);
}
}
/*!
* \internal
* \brief Upgrade XML to latest schema version and use it as scheduler input
*
* This also updates the scheduler timestamp to the current time.
*
* \param[in,out] scheduler Scheduler data to update
* \param[in,out] xml XML to use as input
*
* \return Standard Pacemaker return code
* \note On success, caller is responsible for freeing memory allocated for
* scheduler->now.
* \todo This follows the example of other callers of cli_config_update()
* and returns ENOKEY ("Required key not available") if that fails,
* but perhaps pcmk_rc_schema_validation would be better in that case.
*/
int
update_scheduler_input(pcmk_scheduler_t *scheduler, xmlNode **xml)
{
if (cli_config_update(xml, NULL, FALSE) == FALSE) {
return ENOKEY;
}
scheduler->input = *xml;
scheduler->now = crm_time_new(NULL);
return pcmk_rc_ok;
}
/*!
* \internal
* \brief Update scheduler XML input based on a CIB query
*
* \param[in] scheduler Scheduler data to initialize
* \param[in] cib Connection to the CIB manager
*
* \return Standard Pacemaker return code
* \note On success, caller is responsible for freeing memory allocated for
* scheduler->input and scheduler->now.
*/
static int
update_scheduler_input_to_cib(pcmk__output_t *out, pcmk_scheduler_t *scheduler,
cib_t *cib)
{
xmlNode *cib_xml_copy = NULL;
int rc = pcmk_rc_ok;
rc = cib->cmds->query(cib, NULL, &cib_xml_copy, cib_scope_local | cib_sync_call);
rc = pcmk_legacy2rc(rc);
if (rc != pcmk_rc_ok) {
out->err(out, "Could not obtain the current CIB: %s (%d)", pcmk_rc_str(rc), rc);
return rc;
}
rc = update_scheduler_input(scheduler, &cib_xml_copy);
if (rc != pcmk_rc_ok) {
out->err(out, "Could not upgrade the current CIB XML");
free_xml(cib_xml_copy);
return rc;
}
return rc;
}
// \return Standard Pacemaker return code
static int
update_dataset(cib_t *cib, pcmk_scheduler_t *scheduler, bool simulate)
{
char *pid = NULL;
char *shadow_file = NULL;
cib_t *shadow_cib = NULL;
int rc = pcmk_rc_ok;
pcmk__output_t *out = scheduler->priv;
pe_reset_working_set(scheduler);
pe__set_working_set_flags(scheduler,
pcmk_sched_no_counts|pcmk_sched_no_compat);
rc = update_scheduler_input_to_cib(out, scheduler, cib);
if (rc != pcmk_rc_ok) {
return rc;
}
if(simulate) {
bool prev_quiet = false;
pid = pcmk__getpid_s();
shadow_cib = cib_shadow_new(pid);
shadow_file = get_shadow_file(pid);
if (shadow_cib == NULL) {
out->err(out, "Could not create shadow cib: '%s'", pid);
rc = ENXIO;
goto done;
}
rc = write_xml_file(scheduler->input, shadow_file, FALSE);
if (rc < 0) {
out->err(out, "Could not populate shadow cib: %s (%d)", pcmk_strerror(rc), rc);
goto done;
}
rc = shadow_cib->cmds->signon(shadow_cib, crm_system_name, cib_command);
rc = pcmk_legacy2rc(rc);
if (rc != pcmk_rc_ok) {
out->err(out, "Could not connect to shadow cib: %s (%d)", pcmk_rc_str(rc), rc);
goto done;
}
pcmk__schedule_actions(scheduler->input,
pcmk_sched_no_counts|pcmk_sched_no_compat,
scheduler);
prev_quiet = out->is_quiet(out);
out->quiet = true;
pcmk__simulate_transition(scheduler, shadow_cib, NULL);
out->quiet = prev_quiet;
rc = update_dataset(shadow_cib, scheduler, false);
} else {
cluster_status(scheduler);
}
done:
// Do not free scheduler->input here, we need rsc->xml to be valid later on
cib_delete(shadow_cib);
free(pid);
if(shadow_file) {
unlink(shadow_file);
free(shadow_file);
}
return rc;
}
/*!
* \internal
* \brief Find the maximum stop timeout of a resource and its children (if any)
*
* \param[in,out] rsc Resource to get timeout for
*
* \return Maximum stop timeout for \p rsc (in milliseconds)
*/
static int
max_rsc_stop_timeout(pcmk_resource_t *rsc)
{
long long result_ll;
int max_delay = 0;
xmlNode *config = NULL;
GHashTable *meta = NULL;
if (rsc == NULL) {
return 0;
}
// If resource is collective, use maximum of its children's stop timeouts
if (rsc->children != NULL) {
for (GList *iter = rsc->children; iter; iter = iter->next) {
pcmk_resource_t *child = iter->data;
int delay = max_rsc_stop_timeout(child);
if (delay > max_delay) {
pe_rsc_trace(rsc,
"Maximum stop timeout for %s is now %s due to %s",
rsc->id, pcmk__readable_interval(delay), child->id);
max_delay = delay;
}
}
return max_delay;
}
// Get resource's stop action configuration from CIB
config = pcmk__find_action_config(rsc, PCMK_ACTION_STOP, 0, true);
/* Get configured timeout for stop action (fully evaluated for rules,
* defaults, etc.).
*
* @TODO This currently ignores node (which might matter for rules)
*/
meta = pcmk__unpack_action_meta(rsc, NULL, PCMK_ACTION_STOP, 0, config);
if ((pcmk__scan_ll(g_hash_table_lookup(meta, XML_ATTR_TIMEOUT),
&result_ll, -1LL) == pcmk_rc_ok)
&& (result_ll >= 0) && (result_ll <= INT_MAX)) {
max_delay = (int) result_ll;
}
g_hash_table_destroy(meta);
return max_delay;
}
/*!
* \internal
* \brief Find a reasonable waiting time for stopping any one resource in a list
*
* \param[in,out] scheduler Scheduler data
* \param[in] resources List of names of resources that will be stopped
*
* \return Rough estimate of a reasonable time to wait (in seconds) to stop any
* one resource in \p resources
* \note This estimate is very rough, simply the maximum stop timeout of all
* given resources and their children, plus a small fudge factor. It does
* not account for children that must be stopped in sequence, action
* throttling, or any demotions needed. It checks the stop timeout, even
* if the resources in question are actually being started.
*/
static int
wait_time_estimate(pcmk_scheduler_t *scheduler, const GList *resources)
{
int max_delay = 0;
// Find maximum stop timeout in milliseconds
for (const GList *item = resources; item != NULL; item = item->next) {
pcmk_resource_t *rsc = pe_find_resource(scheduler->resources,
(const char *) item->data);
int delay = max_rsc_stop_timeout(rsc);
if (delay > max_delay) {
pe_rsc_trace(rsc,
"Wait time is now %s due to %s",
pcmk__readable_interval(delay), rsc->id);
max_delay = delay;
}
}
return (max_delay / 1000) + 5;
}
#define waiting_for_starts(d, r, h) ((d != NULL) || \
(!resource_is_running_on((r), (h))))
/*!
* \internal
* \brief Restart a resource (on a particular host if requested).
*
* \param[in,out] out Output object
* \param[in,out] rsc The resource to restart
* \param[in] node Node to restart resource on (NULL for all)
* \param[in] move_lifetime If not NULL, how long constraint should
* remain in effect (as ISO 8601 string)
* \param[in] timeout_ms Consider failed if actions do not complete
* in this time (specified in milliseconds,
* but a two-second granularity is actually
* used; if 0, it will be calculated based on
* the resource timeout)
* \param[in,out] cib Connection to the CIB manager
* \param[in] cib_options Group of enum cib_call_options flags to
* use with CIB calls
* \param[in] promoted_role_only If true, limit to promoted instances
* \param[in] force If true, apply only to requested instance
* if part of a collective resource
*
* \return Standard Pacemaker return code (exits on certain failures)
*/
int
cli_resource_restart(pcmk__output_t *out, pcmk_resource_t *rsc,
const pcmk_node_t *node, const char *move_lifetime,
int timeout_ms, cib_t *cib, int cib_options,
gboolean promoted_role_only, gboolean force)
{
int rc = pcmk_rc_ok;
int lpc = 0;
int before = 0;
int step_timeout_s = 0;
int sleep_interval = 2;
int timeout = timeout_ms / 1000;
bool stop_via_ban = false;
char *rsc_id = NULL;
char *lookup_id = NULL;
char *orig_target_role = NULL;
GList *list_delta = NULL;
GList *target_active = NULL;
GList *current_active = NULL;
GList *restart_target_active = NULL;
pcmk_scheduler_t *scheduler = NULL;
pcmk_resource_t *parent = uber_parent(rsc);
bool running = false;
const char *id = rsc->clone_name ? rsc->clone_name : rsc->id;
const char *host = node ? node->details->uname : NULL;
/* If the implicit resource or primitive resource of a bundle is given, operate on the
* bundle itself instead.
*/
if (pe_rsc_is_bundled(rsc)) {
rsc = parent->parent;
}
running = resource_is_running_on(rsc, host);
if (pe_rsc_is_clone(parent) && !running) {
if (pe_rsc_is_unique_clone(parent)) {
lookup_id = strdup(rsc->id);
} else {
lookup_id = clone_strip(rsc->id);
}
rsc = parent->fns->find_rsc(parent, lookup_id, node,
pcmk_rsc_match_basename
|pcmk_rsc_match_current_node);
free(lookup_id);
running = resource_is_running_on(rsc, host);
}
if (!running) {
if (host) {
out->err(out, "%s is not running on %s and so cannot be restarted", id, host);
} else {
out->err(out, "%s is not running anywhere and so cannot be restarted", id);
}
return ENXIO;
}
if (!pcmk_is_set(rsc->flags, pcmk_rsc_managed)) {
out->err(out, "Unmanaged resources cannot be restarted.");
return EAGAIN;
}
rsc_id = strdup(rsc->id);
if (pe_rsc_is_unique_clone(parent)) {
lookup_id = strdup(rsc->id);
} else {
lookup_id = clone_strip(rsc->id);
}
if (host) {
if (pe_rsc_is_clone(rsc) || pe_bundle_replicas(rsc)) {
stop_via_ban = true;
} else if (pe_rsc_is_clone(parent)) {
stop_via_ban = true;
free(lookup_id);
lookup_id = strdup(parent->id);
}
}
/*
grab full cib
determine originally active resources
disable or ban
poll cib and watch for affected resources to get stopped
without --timeout, calculate the stop timeout for each step and wait for that
if we hit --timeout or the service timeout, re-enable or un-ban, report failure and indicate which resources we couldn't take down
if everything stopped, re-enable or un-ban
poll cib and watch for affected resources to get started
without --timeout, calculate the start timeout for each step and wait for that
if we hit --timeout or the service timeout, report (different) failure and indicate which resources we couldn't bring back up
report success
Optimizations:
- use constraints to determine ordered list of affected resources
- Allow a --no-deps option (aka. --force-restart)
*/
scheduler = pe_new_working_set();
if (scheduler == NULL) {
rc = errno;
out->err(out, "Could not allocate scheduler data: %s", pcmk_rc_str(rc));
goto done;
}
scheduler->priv = out;
rc = update_dataset(cib, scheduler, false);
if(rc != pcmk_rc_ok) {
out->err(out, "Could not get new resource list: %s (%d)", pcmk_rc_str(rc), rc);
goto done;
}
restart_target_active = get_active_resources(host, scheduler->resources);
current_active = get_active_resources(host, scheduler->resources);
dump_list(current_active, "Origin");
if (stop_via_ban) {
/* Stop the clone or bundle instance by banning it from the host */
out->quiet = true;
rc = cli_resource_ban(out, lookup_id, host, move_lifetime, cib,
cib_options, promoted_role_only,
PCMK__ROLE_PROMOTED);
} else {
/* Stop the resource by setting target-role to Stopped.
* Remember any existing target-role so we can restore it later
* (though it only makes any difference if it's Unpromoted).
*/
find_resource_attr(out, cib, XML_NVPAIR_ATTR_VALUE, lookup_id, NULL, NULL,
NULL, XML_RSC_ATTR_TARGET_ROLE, &orig_target_role);
rc = cli_resource_update_attribute(rsc, rsc_id, NULL, XML_TAG_META_SETS,
NULL, XML_RSC_ATTR_TARGET_ROLE,
PCMK_ACTION_STOPPED, FALSE, cib,
cib_options, force);
}
if(rc != pcmk_rc_ok) {
out->err(out, "Could not set target-role for %s: %s (%d)", rsc_id, pcmk_rc_str(rc), rc);
if (current_active != NULL) {
g_list_free_full(current_active, free);
current_active = NULL;
}
if (restart_target_active != NULL) {
g_list_free_full(restart_target_active, free);
restart_target_active = NULL;
}
goto done;
}
rc = update_dataset(cib, scheduler, true);
if(rc != pcmk_rc_ok) {
out->err(out, "Could not determine which resources would be stopped");
goto failure;
}
target_active = get_active_resources(host, scheduler->resources);
dump_list(target_active, "Target");
list_delta = pcmk__subtract_lists(current_active, target_active, (GCompareFunc) strcmp);
out->info(out, "Waiting for %d resources to stop:", g_list_length(list_delta));
display_list(out, list_delta, " * ");
step_timeout_s = timeout / sleep_interval;
while (list_delta != NULL) {
before = g_list_length(list_delta);
if(timeout_ms == 0) {
step_timeout_s = wait_time_estimate(scheduler, list_delta)
/ sleep_interval;
}
/* We probably don't need the entire step timeout */
for(lpc = 0; (lpc < step_timeout_s) && (list_delta != NULL); lpc++) {
sleep(sleep_interval);
if(timeout) {
timeout -= sleep_interval;
crm_trace("%ds remaining", timeout);
}
rc = update_dataset(cib, scheduler, FALSE);
if(rc != pcmk_rc_ok) {
out->err(out, "Could not determine which resources were stopped");
goto failure;
}
if (current_active != NULL) {
g_list_free_full(current_active, free);
}
current_active = get_active_resources(host, scheduler->resources);
g_list_free(list_delta);
list_delta = pcmk__subtract_lists(current_active, target_active, (GCompareFunc) strcmp);
dump_list(current_active, "Current");
dump_list(list_delta, "Delta");
}
crm_trace("%d (was %d) resources remaining", g_list_length(list_delta), before);
if(before == g_list_length(list_delta)) {
/* aborted during stop phase, print the contents of list_delta */
out->err(out, "Could not complete shutdown of %s, %d resources remaining", rsc_id, g_list_length(list_delta));
display_list(out, list_delta, " * ");
rc = ETIME;
goto failure;
}
}
if (stop_via_ban) {
rc = cli_resource_clear(lookup_id, host, NULL, cib, cib_options, true, force);
} else if (orig_target_role) {
rc = cli_resource_update_attribute(rsc, rsc_id, NULL, XML_TAG_META_SETS,
NULL, XML_RSC_ATTR_TARGET_ROLE,
orig_target_role, FALSE, cib,
cib_options, force);
free(orig_target_role);
orig_target_role = NULL;
} else {
rc = cli_resource_delete_attribute(rsc, rsc_id, NULL, XML_TAG_META_SETS,
NULL, XML_RSC_ATTR_TARGET_ROLE, cib,
cib_options, force);
}
if(rc != pcmk_rc_ok) {
out->err(out, "Could not unset target-role for %s: %s (%d)", rsc_id, pcmk_rc_str(rc), rc);
goto done;
}
if (target_active != NULL) {
g_list_free_full(target_active, free);
}
target_active = restart_target_active;
list_delta = pcmk__subtract_lists(target_active, current_active, (GCompareFunc) strcmp);
out->info(out, "Waiting for %d resources to start again:", g_list_length(list_delta));
display_list(out, list_delta, " * ");
step_timeout_s = timeout / sleep_interval;
while (waiting_for_starts(list_delta, rsc, host)) {
before = g_list_length(list_delta);
if(timeout_ms == 0) {
step_timeout_s = wait_time_estimate(scheduler, list_delta)
/ sleep_interval;
}
/* We probably don't need the entire step timeout */
for (lpc = 0; (lpc < step_timeout_s) && waiting_for_starts(list_delta, rsc, host); lpc++) {
sleep(sleep_interval);
if(timeout) {
timeout -= sleep_interval;
crm_trace("%ds remaining", timeout);
}
rc = update_dataset(cib, scheduler, false);
if(rc != pcmk_rc_ok) {
out->err(out, "Could not determine which resources were started");
goto failure;
}
/* It's OK if dependent resources moved to a different node,
* so we check active resources on all nodes.
*/
if (current_active != NULL) {
g_list_free_full(current_active, free);
}
current_active = get_active_resources(NULL, scheduler->resources);
g_list_free(list_delta);
list_delta = pcmk__subtract_lists(target_active, current_active, (GCompareFunc) strcmp);
dump_list(current_active, "Current");
dump_list(list_delta, "Delta");
}
if(before == g_list_length(list_delta)) {
/* aborted during start phase, print the contents of list_delta */
out->err(out, "Could not complete restart of %s, %d resources remaining", rsc_id, g_list_length(list_delta));
display_list(out, list_delta, " * ");
rc = ETIME;
goto failure;
}
}
rc = pcmk_rc_ok;
goto done;
failure:
if (stop_via_ban) {
cli_resource_clear(lookup_id, host, NULL, cib, cib_options, true, force);
} else if (orig_target_role) {
cli_resource_update_attribute(rsc, rsc_id, NULL, XML_TAG_META_SETS, NULL,
XML_RSC_ATTR_TARGET_ROLE, orig_target_role,
FALSE, cib, cib_options, force);
free(orig_target_role);
} else {
cli_resource_delete_attribute(rsc, rsc_id, NULL, XML_TAG_META_SETS,
NULL, XML_RSC_ATTR_TARGET_ROLE, cib,
cib_options, force);
}
done:
if (list_delta != NULL) {
g_list_free(list_delta);
}
if (current_active != NULL) {
g_list_free_full(current_active, free);
}
if (target_active != NULL && (target_active != restart_target_active)) {
g_list_free_full(target_active, free);
}
if (restart_target_active != NULL) {
g_list_free_full(restart_target_active, free);
}
free(rsc_id);
free(lookup_id);
pe_free_working_set(scheduler);
return rc;
}
static inline bool
action_is_pending(const pcmk_action_t *action)
{
if (pcmk_any_flags_set(action->flags,
pcmk_action_optional|pcmk_action_pseudo)
|| !pcmk_is_set(action->flags, pcmk_action_runnable)
|| pcmk__str_eq(PCMK_ACTION_NOTIFY, action->task, pcmk__str_casei)) {
return false;
}
return true;
}
/*!
* \internal
* \brief Check whether any actions in a list are pending
*
* \param[in] actions List of actions to check
*
* \return true if any actions in the list are pending, otherwise false
*/
static bool
actions_are_pending(const GList *actions)
{
for (const GList *action = actions; action != NULL; action = action->next) {
const pcmk_action_t *a = (const pcmk_action_t *) action->data;
if (action_is_pending(a)) {
crm_notice("Waiting for %s (flags=%#.8x)", a->uuid, a->flags);
return true;
}
}
return false;
}
static void
print_pending_actions(pcmk__output_t *out, GList *actions)
{
GList *action;
out->info(out, "Pending actions:");
for (action = actions; action != NULL; action = action->next) {
pcmk_action_t *a = (pcmk_action_t *) action->data;
if (!action_is_pending(a)) {
continue;
}
if (a->node) {
out->info(out, "\tAction %d: %s\ton %s",
a->id, a->uuid, pe__node_name(a->node));
} else {
out->info(out, "\tAction %d: %s", a->id, a->uuid);
}
}
}
/* For --wait, timeout (in seconds) to use if caller doesn't specify one */
#define WAIT_DEFAULT_TIMEOUT_S (60 * 60)
/* For --wait, how long to sleep between cluster state checks */
#define WAIT_SLEEP_S (2)
/*!
* \internal
* \brief Wait until all pending cluster actions are complete
*
* This waits until either the CIB's transition graph is idle or a timeout is
* reached.
*
* \param[in,out] out Output object
* \param[in] timeout_ms Consider failed if actions do not complete in
* this time (specified in milliseconds, but
* one-second granularity is actually used; if 0, a
* default will be used)
* \param[in,out] cib Connection to the CIB manager
*
* \return Standard Pacemaker return code
*/
int
wait_till_stable(pcmk__output_t *out, int timeout_ms, cib_t * cib)
{
pcmk_scheduler_t *scheduler = NULL;
+ xmlXPathObjectPtr search;
int rc = pcmk_rc_ok;
+ bool pending_unknown_state_resources;
int timeout_s = timeout_ms? ((timeout_ms + 999) / 1000) : WAIT_DEFAULT_TIMEOUT_S;
time_t expire_time = time(NULL) + timeout_s;
time_t time_diff;
bool printed_version_warning = out->is_quiet(out); // i.e. don't print if quiet
scheduler = pe_new_working_set();
if (scheduler == NULL) {
return ENOMEM;
}
do {
-
/* Abort if timeout is reached */
time_diff = expire_time - time(NULL);
if (time_diff > 0) {
crm_info("Waiting up to %lld seconds for cluster actions to complete", (long long) time_diff);
} else {
print_pending_actions(out, scheduler->actions);
pe_free_working_set(scheduler);
return ETIME;
}
if (rc == pcmk_rc_ok) { /* this avoids sleep on first loop iteration */
sleep(WAIT_SLEEP_S);
}
/* Get latest transition graph */
pe_reset_working_set(scheduler);
rc = update_scheduler_input_to_cib(out, scheduler, cib);
if (rc != pcmk_rc_ok) {
pe_free_working_set(scheduler);
return rc;
}
pcmk__schedule_actions(scheduler->input,
pcmk_sched_no_counts|pcmk_sched_no_compat,
scheduler);
if (!printed_version_warning) {
/* If the DC has a different version than the local node, the two
* could come to different conclusions about what actions need to be
* done. Warn the user in this case.
*
* @TODO A possible long-term solution would be to reimplement the
* wait as a new controller operation that would be forwarded to the
* DC. However, that would have potential problems of its own.
*/
const char *dc_version = g_hash_table_lookup(scheduler->config_hash,
"dc-version");
if (!pcmk__str_eq(dc_version, PACEMAKER_VERSION "-" BUILD_VERSION, pcmk__str_casei)) {
out->info(out, "warning: wait option may not work properly in "
"mixed-version cluster");
printed_version_warning = true;
}
}
- } while (actions_are_pending(scheduler->actions));
+ search = xpath_search(scheduler->input, "/cib/status/node_state/lrm/lrm_resources/lrm_resource/"
+ XML_LRM_TAG_RSC_OP "[@" XML_LRM_ATTR_RC "='193']");
+ pending_unknown_state_resources = (numXpathResults(search) > 0);
+ freeXpathObject(search);
+ } while (actions_are_pending(scheduler->actions) || pending_unknown_state_resources);
pe_free_working_set(scheduler);
return rc;
}
static const char *
get_action(const char *rsc_action) {
const char *action = NULL;
if (pcmk__str_eq(rsc_action, "validate", pcmk__str_casei)) {
action = PCMK_ACTION_VALIDATE_ALL;
} else if (pcmk__str_eq(rsc_action, "force-check", pcmk__str_casei)) {
action = PCMK_ACTION_MONITOR;
} else if (pcmk__strcase_any_of(rsc_action, "force-start", "force-stop",
"force-demote", "force-promote", NULL)) {
action = rsc_action+6;
} else {
action = rsc_action;
}
return action;
}
/*!
* \brief Set up environment variables as expected by resource agents
*
* When the cluster executes resource agents, it adds certain environment
* variables (directly or via resource meta-attributes) expected by some
* resource agents. Add the essential ones that many resource agents expect, so
* the behavior is the same for command-line execution.
*
* \param[in,out] params Resource parameters that will be passed to agent
* \param[in] timeout_ms Action timeout (in milliseconds)
* \param[in] check_level OCF check level
* \param[in] verbosity Verbosity level
*/
static void
set_agent_environment(GHashTable *params, int timeout_ms, int check_level,
int verbosity)
{
g_hash_table_insert(params, strdup("CRM_meta_timeout"),
crm_strdup_printf("%d", timeout_ms));
g_hash_table_insert(params, strdup(XML_ATTR_CRM_VERSION),
strdup(CRM_FEATURE_SET));
if (check_level >= 0) {
char *level = crm_strdup_printf("%d", check_level);
setenv("OCF_CHECK_LEVEL", level, 1);
free(level);
}
pcmk__set_env_option(PCMK__ENV_DEBUG, ((verbosity > 0)? "1" : "0"), true);
if (verbosity > 1) {
setenv("OCF_TRACE_RA", "1", 1);
}
/* A resource agent using the standard ocf-shellfuncs library will not print
* messages to stderr if it doesn't have a controlling terminal (e.g. if
* crm_resource is called via script or ssh). This forces it to do so.
*/
setenv("OCF_TRACE_FILE", "/dev/stderr", 0);
}
/*!
* \internal
* \brief Apply command-line overrides to resource parameters
*
* \param[in,out] params Parameters to be passed to agent
* \param[in] overrides Parameters to override (or NULL if none)
*/
static void
apply_overrides(GHashTable *params, GHashTable *overrides)
{
if (overrides != NULL) {
GHashTableIter iter;
char *name = NULL;
char *value = NULL;
g_hash_table_iter_init(&iter, overrides);
while (g_hash_table_iter_next(&iter, (gpointer *) &name,
(gpointer *) &value)) {
g_hash_table_replace(params, strdup(name), strdup(value));
}
}
}
crm_exit_t
cli_resource_execute_from_params(pcmk__output_t *out, const char *rsc_name,
const char *rsc_class, const char *rsc_prov,
const char *rsc_type, const char *rsc_action,
GHashTable *params, GHashTable *override_hash,
int timeout_ms, int resource_verbose, gboolean force,
int check_level)
{
const char *class = rsc_class;
const char *action = get_action(rsc_action);
crm_exit_t exit_code = CRM_EX_OK;
svc_action_t *op = NULL;
// If no timeout was provided, use the same default as the cluster
if (timeout_ms == 0) {
timeout_ms = PCMK_DEFAULT_ACTION_TIMEOUT_MS;
}
set_agent_environment(params, timeout_ms, check_level, resource_verbose);
apply_overrides(params, override_hash);
op = services__create_resource_action(rsc_name? rsc_name : "test",
rsc_class, rsc_prov, rsc_type, action,
0, timeout_ms, params, 0);
if (op == NULL) {
out->err(out, "Could not execute %s using %s%s%s:%s: %s",
action, rsc_class, (rsc_prov? ":" : ""),
(rsc_prov? rsc_prov : ""), rsc_type, strerror(ENOMEM));
g_hash_table_destroy(params);
return CRM_EX_OSERR;
}
if (pcmk__str_eq(rsc_class, PCMK_RESOURCE_CLASS_SERVICE, pcmk__str_casei)) {
class = resources_find_service_class(rsc_type);
}
if (!pcmk__strcase_any_of(class, PCMK_RESOURCE_CLASS_OCF,
PCMK_RESOURCE_CLASS_LSB, NULL)) {
services__format_result(op, CRM_EX_UNIMPLEMENT_FEATURE, PCMK_EXEC_ERROR,
"Manual execution of the %s standard is "
"unsupported", pcmk__s(class, "unspecified"));
}
if (op->rc != PCMK_OCF_UNKNOWN) {
exit_code = op->rc;
goto done;
}
services_action_sync(op);
// Map results to OCF codes for consistent reporting to user
{
enum ocf_exitcode ocf_code = services_result2ocf(class, action, op->rc);
// Cast variable instead of function return to keep compilers happy
exit_code = (crm_exit_t) ocf_code;
}
done:
out->message(out, "resource-agent-action", resource_verbose, rsc_class,
rsc_prov, rsc_type, rsc_name, rsc_action, override_hash,
exit_code, op->status, services__exit_reason(op),
op->stdout_data, op->stderr_data);
services_action_free(op);
return exit_code;
}
crm_exit_t
cli_resource_execute(pcmk_resource_t *rsc, const char *requested_name,
const char *rsc_action, GHashTable *override_hash,
int timeout_ms, cib_t *cib, pcmk_scheduler_t *scheduler,
int resource_verbose, gboolean force, int check_level)
{
pcmk__output_t *out = scheduler->priv;
crm_exit_t exit_code = CRM_EX_OK;
const char *rid = NULL;
const char *rtype = NULL;
const char *rprov = NULL;
const char *rclass = NULL;
GHashTable *params = NULL;
if (pcmk__strcase_any_of(rsc_action, "force-start", "force-demote",
"force-promote", NULL)) {
if(pe_rsc_is_clone(rsc)) {
GList *nodes = cli_resource_search(rsc, requested_name, scheduler);
if(nodes != NULL && force == FALSE) {
out->err(out, "It is not safe to %s %s here: the cluster claims it is already active",
rsc_action, rsc->id);
out->err(out, "Try setting target-role=Stopped first or specifying "
"the force option");
return CRM_EX_UNSAFE;
}
g_list_free_full(nodes, free);
}
}
if(pe_rsc_is_clone(rsc)) {
/* Grab the first child resource in the hope it's not a group */
rsc = rsc->children->data;
}
if (rsc->variant == pcmk_rsc_variant_group) {
out->err(out, "Sorry, the %s option doesn't support group resources", rsc_action);
return CRM_EX_UNIMPLEMENT_FEATURE;
} else if (pe_rsc_is_bundled(rsc)) {
out->err(out, "Sorry, the %s option doesn't support bundled resources", rsc_action);
return CRM_EX_UNIMPLEMENT_FEATURE;
}
rclass = crm_element_value(rsc->xml, XML_AGENT_ATTR_CLASS);
rprov = crm_element_value(rsc->xml, XML_AGENT_ATTR_PROVIDER);
rtype = crm_element_value(rsc->xml, XML_ATTR_TYPE);
params = generate_resource_params(rsc, NULL /* @TODO use local node */,
scheduler);
if (timeout_ms == 0) {
timeout_ms = pe_get_configured_timeout(rsc, get_action(rsc_action),
scheduler);
}
rid = pe_rsc_is_anon_clone(rsc->parent)? requested_name : rsc->id;
exit_code = cli_resource_execute_from_params(out, rid, rclass, rprov, rtype, rsc_action,
params, override_hash, timeout_ms,
resource_verbose, force, check_level);
return exit_code;
}
// \return Standard Pacemaker return code
int
cli_resource_move(const pcmk_resource_t *rsc, const char *rsc_id,
const char *host_name, const char *move_lifetime, cib_t *cib,
int cib_options, pcmk_scheduler_t *scheduler,
gboolean promoted_role_only, gboolean force)
{
pcmk__output_t *out = scheduler->priv;
int rc = pcmk_rc_ok;
unsigned int count = 0;
pcmk_node_t *current = NULL;
pcmk_node_t *dest = pe_find_node(scheduler->nodes, host_name);
bool cur_is_dest = false;
if (dest == NULL) {
return pcmk_rc_node_unknown;
}
if (promoted_role_only
&& !pcmk_is_set(rsc->flags, pcmk_rsc_promotable)) {
const pcmk_resource_t *p = pe__const_top_resource(rsc, false);
if (pcmk_is_set(p->flags, pcmk_rsc_promotable)) {
out->info(out, "Using parent '%s' for move instead of '%s'.", rsc->id, rsc_id);
rsc_id = p->id;
rsc = p;
} else {
out->info(out, "Ignoring --promoted option: %s is not promotable",
rsc_id);
promoted_role_only = FALSE;
}
}
current = pe__find_active_requires(rsc, &count);
if (pcmk_is_set(rsc->flags, pcmk_rsc_promotable)) {
unsigned int promoted_count = 0;
pcmk_node_t *promoted_node = NULL;
for (const GList *iter = rsc->children; iter; iter = iter->next) {
const pcmk_resource_t *child = (const pcmk_resource_t *) iter->data;
enum rsc_role_e child_role = child->fns->state(child, TRUE);
if (child_role == pcmk_role_promoted) {
rsc = child;
promoted_node = pe__current_node(child);
promoted_count++;
}
}
if (promoted_role_only || (promoted_count != 0)) {
count = promoted_count;
current = promoted_node;
}
}
if (count > 1) {
if (pe_rsc_is_clone(rsc)) {
current = NULL;
} else {
return pcmk_rc_multiple;
}
}
if (current && (current->details == dest->details)) {
cur_is_dest = true;
if (force) {
crm_info("%s is already %s on %s, reinforcing placement with location constraint.",
rsc_id, promoted_role_only?"promoted":"active",
pe__node_name(dest));
} else {
return pcmk_rc_already;
}
}
/* Clear any previous prefer constraints across all nodes. */
cli_resource_clear(rsc_id, NULL, scheduler->nodes, cib, cib_options, false,
force);
/* Clear any previous ban constraints on 'dest'. */
cli_resource_clear(rsc_id, dest->details->uname, scheduler->nodes, cib,
cib_options, TRUE, force);
/* Record an explicit preference for 'dest' */
rc = cli_resource_prefer(out, rsc_id, dest->details->uname, move_lifetime,
cib, cib_options, promoted_role_only,
PCMK__ROLE_PROMOTED);
crm_trace("%s%s now prefers %s%s",
rsc->id, (promoted_role_only? " (promoted)" : ""),
pe__node_name(dest), force?"(forced)":"");
/* only ban the previous location if current location != destination location.
* it is possible to use -M to enforce a location without regard of where the
* resource is currently located */
if (force && !cur_is_dest) {
/* Ban the original location if possible */
if(current) {
(void)cli_resource_ban(out, rsc_id, current->details->uname, move_lifetime,
cib, cib_options, promoted_role_only,
PCMK__ROLE_PROMOTED);
} else if(count > 1) {
out->info(out, "Resource '%s' is currently %s in %d locations. "
"One may now move to %s",
rsc_id, (promoted_role_only? "promoted" : "active"),
count, pe__node_name(dest));
out->info(out, "To prevent '%s' from being %s at a specific location, "
"specify a node.",
rsc_id, (promoted_role_only? "promoted" : "active"));
} else {
crm_trace("Not banning %s from its current location: not active", rsc_id);
}
}
return rc;
}

File Metadata

Mime Type
text/x-diff
Expires
Sat, Nov 23, 2:42 PM (20 h, 10 m)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
1018801
Default Alt Text
(895 KB)

Event Timeline