diff --git a/ChangeLog b/ChangeLog index c51c439f27..6e1b1033ce 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,2744 +1,2751 @@ +* Mon Feb 25 2019 Ken Gaillot Pacemaker-2.0.1-rc5 +- Changesets: 17 +- Diff: 15 files changed, 1037 insertions(+), 677 deletions(-) + +- Changes since Pacemaker-2.0.1-rc4 + + scheduler: regression test compatibility with glib 2.59.0 + * Tue Jan 29 2019 Ken Gaillot Pacemaker-2.0.1-rc4 - Changesets: 42 15 files changed, 216 insertions(+), 137 deletions(-) - Changes since Pacemaker-2.0.1-rc3 + attrd: clear election dampening when the writer leaves + controller: clear election dampening when DC is lost + scheduler: don't order non-DC shutdowns before DC fencing + libcrmservice: cancel DBus call when cancelling systemd/upstart actions + tools: remove duplicate fence history state in crm_mon XML output + build: offer configure option to disable tests broken with glib 2.59.0 + build: minor logging fixes to allow compatibility with GCC 9 -Werror * Thu Jan 10 2019 Ken Gaillot Pacemaker-2.0.1-rc3 - Changesets: 27 - Diff: 20 files changed, 375 insertions(+), 195 deletions(-) - Changes since Pacemaker-2.0.1-rc2 + attrd: start new election immediately if writer is lost + attrd: detect alert configuration changes when CIB is entirely replaced + controller: avoid transition timeout if resource cleaned while operation is in-flight (regression in 2.0.1-rc1) + libstonithd: restore C++ compatibility (regression in 2.0.1-rc1) + tools: fix crm_resource --clear when lifetime was used with ban/move + tools: fix crm_resource --move when lifetime was used with previous move * Wed Dec 19 2018 Ken Gaillot Pacemaker-2.0.1-rc2 - Changesets: 12 - Diff: 2 files changed, 6 insertions(+), 2 deletions(-) - Changes since Pacemaker-2.0.1-rc1 + libpe_status: avoid double free of stop_needed list (regression in 2.0.1-rc1) + tools: stonith_admin -I doesn't require an agent (regression in 2.0.1-rc1) * Wed Dec 12 2018 Ken Gaillot Pacemaker-2.0.1-rc1 - Changesets: 481 164 files changed, 7717 insertions(+), 4398 deletions(-) - Features added since Pacemaker-2.0.0 + Pacemaker bundles now support podman container management + fencing: SBD may now be used in a cluster that has guest nodes or bundles + fencing: synchronize fencing history among all nodes + fencing: stonith_admin now has option to clear fence history + tools: crm_mon now supports showing fencing action failures and history + tools: crm_resource --clear supports new --expired option + Pacemaker Remote: option to restrict TLS Diffie-Hellman prime length - Changes since Pacemaker-2.0.0 + tools: restore stonith_admin ability to confirm unseen nodes are down (regression since 1.1.12) + Pacemaker Remote: avoid unnecessary downtime when moving resource to Pacemaker Remote node that fails to come up (regression since 1.1.18) + scheduler: clone notifications could be scheduled for a stopped Pacemaker Remote node and block all further cluster actions (regression since 2.0.0) + tools: crm_resource -C could fail to clean up all failures in one run (regression since 2.0.0) + 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 + 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 + executor: cancel recurring monitors if fence device registration is lost + fencing: check for fence device update when resource defaults change + fencing: fix possible pacemaker-fenced crash with stonith_admin misuse + fencing: limit fencing history to 500 entries + fencing: stonith_admin now complains if no action option is specified + pacemakerd: Linux kernel.sysrq is no longer modified + scheduler: avoid unnecessary recovery of cleaned guest nodes and bundles + scheduler: ensure failures that cause fencing are not expired until fencing completes + scheduler: start unique clone instances in numerical order + scheduler: convert unique clones to anonymous clones if not supported by standard + scheduler: associate pending tasks with correct clone instance + scheduler: ensure bundle clone notifications are directed to correct host + scheduler: avoid improper monitor rescheduling or fail count clearing for bundles + scheduler: honor asymmetric orderings even when restarting + ACLs: assume unprivileged ACL user if can't get user info + Pacemaker Remote: get Diffie-Hellman prime bit length from GnuTLS API + libcrmservice: order systemd resources relative to pacemaker_remote + libpe_status: add public API constructor/destructor for pe_working_set_t + 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 now shows if they still have active resources + tools: crm_diff now ignores attribute ordering when comparing in CIB mode + tools: improve crm_report detection of logs, CIB directory, running processes + tools: crm_verify returns reliable exit codes + tools: crm_simulate simulated resource history uses same name as live cluster would * Fri Jul 6 2018 Ken Gaillot Pacemaker-2.0.0-1 - 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 Pacemaker-1.1.18-1 - 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 Pacemaker-1.1.17-1 - 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 Pacemaker-1.1.16-1 - 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 Pacemaker-1.1.15-1 - 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 Pacemaker-1.1.14-1 - 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 Pacemaker-1.1.13-1 - 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 + 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 Pacemaker-1.1.12-1 - 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 '' * Thu Feb 13 2014 David Vossel Pacemaker-1.1.11-1 - 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 Pacemaker-1.1.10-1 - 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 Pacemaker-1.1.9-1 - 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 Pacemaker-1.1.8-1 - 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 Pacemaker-1.1.7-1 - 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 1.1.6-1 - 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 1.1.5-1 - 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 1.1.4-1 - 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 1.1.3-1 - 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 1.1.2-1 - 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 - 1.1.1-1 - 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 - 1.0.7-1 - 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 - 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 - 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 - 1.0.5-2.1 - rebuilt with new openssl * Wed Aug 19 2009 Andrew Beekhof - 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 - 1.0.5-1 - 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 - 1.0.5-0.7.c9120a53a6ae.hg - Use bzipped upstream tarball. * Wed Jul 29 2009 Andrew Beekhof - 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 - 1.0.5-0.5.c9120a53a6ae.hg - Add a leading zero to the revision when alphatag is used * Tue Jul 28 2009 Andrew Beekhof - 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 - 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 - 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 - 1.0.4-1 - 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 - 1.0.3-1 - 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 - 1.0.2-1 - 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 - 1.0.1-1 - 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 - 1.0.0-1 - 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 - 0.7.3-1 - 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 - 0.7.1-1 - 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 - 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 - 0.7.0-1 - 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 ) preference over persistent ones (in ) + 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 - 0.6.5-1 - 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 - 0.6.4-1 - 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 - 0.6.3-1 - 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 - 0.6.2-1 - 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 - 0.6.1-1 - 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 - 0.6.0-1 - 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/daemons/schedulerd/sched_notif.c b/daemons/schedulerd/sched_notif.c index 8ffdb9597b..2f9c2f22fa 100644 --- a/daemons/schedulerd/sched_notif.c +++ b/daemons/schedulerd/sched_notif.c @@ -1,837 +1,837 @@ /* * Copyright 2004-2019 Andrew Beekhof * * This source code is licensed under the GNU General Public License version 2 * or later (GPLv2+) WITHOUT ANY WARRANTY. */ #include #include #include #include #include typedef struct notify_entry_s { resource_t *rsc; node_t *node; } notify_entry_t; static gint sort_notify_entries(gconstpointer a, gconstpointer b) { int tmp; const notify_entry_t *entry_a = a; const notify_entry_t *entry_b = b; if (entry_a == NULL && entry_b == NULL) { return 0; } if (entry_a == NULL) { return 1; } if (entry_b == NULL) { return -1; } if (entry_a->rsc == NULL && entry_b->rsc == NULL) { return 0; } if (entry_a->rsc == NULL) { return 1; } if (entry_b->rsc == NULL) { return -1; } tmp = strcmp(entry_a->rsc->id, entry_b->rsc->id); if (tmp != 0) { return tmp; } if (entry_a->node == NULL && entry_b->node == NULL) { return 0; } if (entry_a->node == NULL) { return 1; } if (entry_b->node == NULL) { return -1; } return strcmp(entry_a->node->details->id, entry_b->node->details->id); } static notify_entry_t *dup_notify_entry(notify_entry_t *entry) { notify_entry_t *dup = malloc(sizeof(notify_entry_t)); CRM_ASSERT(dup != NULL); dup->rsc = entry->rsc; dup->node = entry->node; return dup; } static void expand_node_list(GListPtr list, char **uname, char **metal) { GListPtr gIter = NULL; char *node_list = NULL; char *metal_list = NULL; CRM_ASSERT(uname != NULL); if (list == NULL) { *uname = strdup(" "); if(metal) { *metal = strdup(" "); } return; } for (gIter = list; gIter != NULL; gIter = gIter->next) { int len = 0; int existing_len = 0; node_t *node = (node_t *) gIter->data; if (node->details->uname == NULL) { continue; } len = 2 + strlen(node->details->uname); if(node_list) { existing_len = strlen(node_list); } // crm_trace("Adding %s (%dc) at offset %d", node->details->uname, len - 2, existing_len); node_list = realloc_safe(node_list, len + existing_len); sprintf(node_list + existing_len, "%s%s", existing_len == 0 ? "":" ", node->details->uname); if(metal) { existing_len = 0; if(metal_list) { existing_len = strlen(metal_list); } if(node->details->remote_rsc && node->details->remote_rsc->container && node->details->remote_rsc->container->running_on) { node = pe__current_node(node->details->remote_rsc->container); } if (node->details->uname == NULL) { continue; } len = 2 + strlen(node->details->uname); metal_list = realloc_safe(metal_list, len + existing_len); sprintf(metal_list + existing_len, "%s%s", existing_len == 0 ? "":" ", node->details->uname); } } *uname = node_list; if(metal) { *metal = metal_list; } } static void expand_list(GListPtr list, char **rsc_list, char **node_list) { GListPtr gIter = NULL; const char *uname = NULL; const char *rsc_id = NULL; const char *last_rsc_id = NULL; if (rsc_list) { *rsc_list = NULL; } if (list == NULL) { if (rsc_list) { *rsc_list = strdup(" "); } if (node_list) { *node_list = strdup(" "); } return; } if (node_list) { *node_list = NULL; } for (gIter = list; gIter != NULL; gIter = gIter->next) { notify_entry_t *entry = (notify_entry_t *) gIter->data; CRM_LOG_ASSERT(entry != NULL); CRM_LOG_ASSERT(entry && entry->rsc != NULL); if(entry == NULL || entry->rsc == NULL) { continue; } /* Uh, why? */ CRM_LOG_ASSERT(node_list == NULL || entry->node != NULL); if(node_list != NULL && entry->node == NULL) { continue; } uname = NULL; rsc_id = entry->rsc->id; CRM_ASSERT(rsc_id != NULL); /* filter dups */ if (safe_str_eq(rsc_id, last_rsc_id)) { continue; } last_rsc_id = rsc_id; if (rsc_list != NULL) { int existing_len = 0; int len = 2 + strlen(rsc_id); /* +1 space, +1 EOS */ if (*rsc_list) { existing_len = strlen(*rsc_list); } crm_trace("Adding %s (%dc) at offset %d", rsc_id, len - 2, existing_len); *rsc_list = realloc_safe(*rsc_list, len + existing_len); sprintf(*rsc_list + existing_len, "%s%s", existing_len == 0 ? "":" ", rsc_id); } if (entry->node != NULL) { uname = entry->node->details->uname; } if (node_list != NULL && uname) { int existing_len = 0; int len = 2 + strlen(uname); if (*node_list) { existing_len = strlen(*node_list); } crm_trace("Adding %s (%dc) at offset %d", uname, len - 2, existing_len); *node_list = realloc_safe(*node_list, len + existing_len); sprintf(*node_list + existing_len, "%s%s", existing_len == 0 ? "":" ", uname); } } } static void dup_attr(gpointer key, gpointer value, gpointer user_data) { add_hash_param(user_data, key, value); } static void add_notify_data_to_action_meta(notify_data_t *n_data, pe_action_t *action) { - for (GList *item = n_data->keys; item; item = item->next) { + for (GSList *item = n_data->keys; item; item = item->next) { pcmk_nvpair_t *nvpair = item->data; add_hash_param(action->meta, nvpair->name, nvpair->value); } } static action_t * pe_notify(resource_t * rsc, node_t * node, action_t * op, action_t * confirm, notify_data_t * n_data, pe_working_set_t * data_set) { char *key = NULL; action_t *trigger = NULL; const char *value = NULL; const char *task = NULL; if (op == NULL || confirm == NULL) { pe_rsc_trace(rsc, "Op=%p confirm=%p", op, confirm); return NULL; } CRM_CHECK(rsc != NULL, return NULL); CRM_CHECK(node != NULL, return NULL); if (node->details->online == FALSE) { pe_rsc_trace(rsc, "Skipping notification for %s: node offline", rsc->id); return NULL; } else if (is_set(op->flags, pe_action_runnable) == FALSE) { pe_rsc_trace(rsc, "Skipping notification for %s: not runnable", op->uuid); return NULL; } value = g_hash_table_lookup(op->meta, "notify_type"); task = g_hash_table_lookup(op->meta, "notify_operation"); pe_rsc_trace(rsc, "Creating notify actions for %s: %s (%s-%s)", op->uuid, rsc->id, value, task); key = generate_notify_key(rsc->id, value, task); trigger = custom_action(rsc, key, op->task, node, is_set(op->flags, pe_action_optional), TRUE, data_set); g_hash_table_foreach(op->meta, dup_attr, trigger->meta); add_notify_data_to_action_meta(n_data, trigger); /* pseudo_notify before notify */ pe_rsc_trace(rsc, "Ordering %s before %s (%d->%d)", op->uuid, trigger->uuid, trigger->id, op->id); order_actions(op, trigger, pe_order_optional); order_actions(trigger, confirm, pe_order_optional); return trigger; } static void pe_post_notify(resource_t * rsc, node_t * node, notify_data_t * n_data, pe_working_set_t * data_set) { action_t *notify = NULL; CRM_CHECK(rsc != NULL, return); if (n_data->post == NULL) { return; /* Nothing to do */ } notify = pe_notify(rsc, node, n_data->post, n_data->post_done, n_data, data_set); if (notify != NULL) { notify->priority = INFINITY; } if (n_data->post_done) { GListPtr gIter = rsc->actions; for (; gIter != NULL; gIter = gIter->next) { action_t *mon = (action_t *) gIter->data; const char *interval_ms_s = g_hash_table_lookup(mon->meta, XML_LRM_ATTR_INTERVAL_MS); if ((interval_ms_s == NULL) || safe_str_eq(interval_ms_s, "0")) { pe_rsc_trace(rsc, "Skipping %s: interval", mon->uuid); continue; } else if (safe_str_eq(mon->task, RSC_CANCEL)) { pe_rsc_trace(rsc, "Skipping %s: cancel", mon->uuid); continue; } order_actions(n_data->post_done, mon, pe_order_optional); } } } notify_data_t * create_notification_boundaries(resource_t * rsc, const char *action, action_t * start, action_t * end, pe_working_set_t * data_set) { /* Create the pseudo ops that precede and follow the actual notifications */ /* * Creates two sequences (conditional on start and end being supplied): * pre_notify -> pre_notify_complete -> start, and * end -> post_notify -> post_notify_complete * * 'start' and 'end' may be the same event or ${X} and ${X}ed as per clones */ char *key = NULL; notify_data_t *n_data = NULL; if (is_not_set(rsc->flags, pe_rsc_notify)) { return NULL; } n_data = calloc(1, sizeof(notify_data_t)); n_data->action = action; if (start) { /* create pre-event notification wrappers */ key = generate_notify_key(rsc->id, "pre", start->task); n_data->pre = custom_action(rsc, key, RSC_NOTIFY, NULL, is_set(start->flags, pe_action_optional), TRUE, data_set); update_action_flags(n_data->pre, pe_action_pseudo, __FUNCTION__, __LINE__); update_action_flags(n_data->pre, pe_action_runnable, __FUNCTION__, __LINE__); add_hash_param(n_data->pre->meta, "notify_type", "pre"); add_hash_param(n_data->pre->meta, "notify_operation", n_data->action); add_hash_param(n_data->pre->meta, "notify_key_type", "pre"); add_hash_param(n_data->pre->meta, "notify_key_operation", start->task); /* create pre_notify_complete */ key = generate_notify_key(rsc->id, "confirmed-pre", start->task); n_data->pre_done = custom_action(rsc, key, RSC_NOTIFIED, NULL, is_set(start->flags, pe_action_optional), TRUE, data_set); update_action_flags(n_data->pre_done, pe_action_pseudo, __FUNCTION__, __LINE__); update_action_flags(n_data->pre_done, pe_action_runnable, __FUNCTION__, __LINE__); add_hash_param(n_data->pre_done->meta, "notify_type", "pre"); add_hash_param(n_data->pre_done->meta, "notify_operation", n_data->action); add_hash_param(n_data->pre_done->meta, "notify_key_type", "confirmed-pre"); add_hash_param(n_data->pre_done->meta, "notify_key_operation", start->task); order_actions(n_data->pre_done, start, pe_order_optional); order_actions(n_data->pre, n_data->pre_done, pe_order_optional); } if (end) { /* create post-event notification wrappers */ key = generate_notify_key(rsc->id, "post", end->task); n_data->post = custom_action(rsc, key, RSC_NOTIFY, NULL, is_set(end->flags, pe_action_optional), TRUE, data_set); n_data->post->priority = INFINITY; update_action_flags(n_data->post, pe_action_pseudo, __FUNCTION__, __LINE__); if (is_set(end->flags, pe_action_runnable)) { update_action_flags(n_data->post, pe_action_runnable, __FUNCTION__, __LINE__); } else { update_action_flags(n_data->post, pe_action_runnable | pe_action_clear, __FUNCTION__, __LINE__); } add_hash_param(n_data->post->meta, "notify_type", "post"); add_hash_param(n_data->post->meta, "notify_operation", n_data->action); add_hash_param(n_data->post->meta, "notify_key_type", "post"); add_hash_param(n_data->post->meta, "notify_key_operation", end->task); /* create post_notify_complete */ key = generate_notify_key(rsc->id, "confirmed-post", end->task); n_data->post_done = custom_action(rsc, key, RSC_NOTIFIED, NULL, is_set(end->flags, pe_action_optional), TRUE, data_set); n_data->post_done->priority = INFINITY; update_action_flags(n_data->post_done, pe_action_pseudo, __FUNCTION__, __LINE__); if (is_set(end->flags, pe_action_runnable)) { update_action_flags(n_data->post_done, pe_action_runnable, __FUNCTION__, __LINE__); } else { update_action_flags(n_data->post_done, pe_action_runnable | pe_action_clear, __FUNCTION__, __LINE__); } add_hash_param(n_data->post_done->meta, "notify_type", "post"); add_hash_param(n_data->post_done->meta, "notify_operation", n_data->action); add_hash_param(n_data->post_done->meta, "notify_key_type", "confirmed-post"); add_hash_param(n_data->post_done->meta, "notify_key_operation", end->task); order_actions(end, n_data->post, pe_order_implies_then); order_actions(n_data->post, n_data->post_done, pe_order_implies_then); } if (start && end) { order_actions(n_data->pre_done, n_data->post, pe_order_optional); } return n_data; } void collect_notification_data(resource_t * rsc, gboolean state, gboolean activity, notify_data_t * n_data) { if(n_data->allowed_nodes == NULL) { n_data->allowed_nodes = rsc->allowed_nodes; } if (rsc->children) { GListPtr gIter = rsc->children; for (; gIter != NULL; gIter = gIter->next) { resource_t *child = (resource_t *) gIter->data; collect_notification_data(child, state, activity, n_data); } return; } if (state) { notify_entry_t *entry = NULL; entry = calloc(1, sizeof(notify_entry_t)); entry->rsc = rsc; if (rsc->running_on) { /* we only take the first one */ entry->node = rsc->running_on->data; } pe_rsc_trace(rsc, "%s state: %s", rsc->id, role2text(rsc->role)); switch (rsc->role) { case RSC_ROLE_STOPPED: n_data->inactive = g_list_prepend(n_data->inactive, entry); break; case RSC_ROLE_STARTED: n_data->active = g_list_prepend(n_data->active, entry); break; case RSC_ROLE_SLAVE: n_data->slave = g_list_prepend(n_data->slave, entry); n_data->active = g_list_prepend(n_data->active, dup_notify_entry(entry)); break; case RSC_ROLE_MASTER: n_data->master = g_list_prepend(n_data->master, entry); n_data->active = g_list_prepend(n_data->active, dup_notify_entry(entry)); break; default: crm_err("Unsupported notify role"); free(entry); break; } } if (activity) { notify_entry_t *entry = NULL; enum action_tasks task; GListPtr gIter = rsc->actions; for (; gIter != NULL; gIter = gIter->next) { action_t *op = (action_t *) gIter->data; if (is_set(op->flags, pe_action_optional) == FALSE && op->node != NULL) { task = text2task(op->task); if(task == stop_rsc && op->node->details->unclean) { // Create anyway (additional noise if node can't be fenced) } else if(is_not_set(op->flags, pe_action_runnable)) { continue; } entry = calloc(1, sizeof(notify_entry_t)); entry->node = op->node; entry->rsc = rsc; switch (task) { case start_rsc: n_data->start = g_list_prepend(n_data->start, entry); break; case stop_rsc: n_data->stop = g_list_prepend(n_data->stop, entry); break; case action_promote: n_data->promote = g_list_prepend(n_data->promote, entry); break; case action_demote: n_data->demote = g_list_prepend(n_data->demote, entry); break; default: free(entry); break; } } } } } #define add_notify_env(n_data, key, value) do { \ n_data->keys = pcmk_prepend_nvpair(n_data->keys, key, value); \ } while (0) #define add_notify_env_free(n_data, key, value) do { \ n_data->keys = pcmk_prepend_nvpair(n_data->keys, key, value); \ free(value); value = NULL; \ } while (0) gboolean expand_notification_data(resource_t *rsc, notify_data_t * n_data, pe_working_set_t * data_set) { /* Expand the notification entries into a key=value hashtable * This hashtable is later used in action2xml() */ gboolean required = FALSE; char *rsc_list = NULL; char *node_list = NULL; char *metal_list = NULL; const char *source = NULL; GListPtr nodes = NULL; if (n_data->stop) { n_data->stop = g_list_sort(n_data->stop, sort_notify_entries); } expand_list(n_data->stop, &rsc_list, &node_list); if (rsc_list != NULL && safe_str_neq(" ", rsc_list)) { if (safe_str_eq(n_data->action, RSC_STOP)) { required = TRUE; } } add_notify_env_free(n_data, "notify_stop_resource", rsc_list); add_notify_env_free(n_data, "notify_stop_uname", node_list); if (n_data->start) { n_data->start = g_list_sort(n_data->start, sort_notify_entries); if (rsc_list && safe_str_eq(n_data->action, RSC_START)) { required = TRUE; } } expand_list(n_data->start, &rsc_list, &node_list); add_notify_env_free(n_data, "notify_start_resource", rsc_list); add_notify_env_free(n_data, "notify_start_uname", node_list); if (n_data->demote) { n_data->demote = g_list_sort(n_data->demote, sort_notify_entries); if (safe_str_eq(n_data->action, RSC_DEMOTE)) { required = TRUE; } } expand_list(n_data->demote, &rsc_list, &node_list); add_notify_env_free(n_data, "notify_demote_resource", rsc_list); add_notify_env_free(n_data, "notify_demote_uname", node_list); if (n_data->promote) { n_data->promote = g_list_sort(n_data->promote, sort_notify_entries); if (safe_str_eq(n_data->action, RSC_PROMOTE)) { required = TRUE; } } expand_list(n_data->promote, &rsc_list, &node_list); add_notify_env_free(n_data, "notify_promote_resource", rsc_list); add_notify_env_free(n_data, "notify_promote_uname", node_list); if (n_data->active) { n_data->active = g_list_sort(n_data->active, sort_notify_entries); } expand_list(n_data->active, &rsc_list, &node_list); add_notify_env_free(n_data, "notify_active_resource", rsc_list); add_notify_env_free(n_data, "notify_active_uname", node_list); if (n_data->slave) { n_data->slave = g_list_sort(n_data->slave, sort_notify_entries); } expand_list(n_data->slave, &rsc_list, &node_list); add_notify_env_free(n_data, "notify_slave_resource", rsc_list); add_notify_env_free(n_data, "notify_slave_uname", node_list); if (n_data->master) { n_data->master = g_list_sort(n_data->master, sort_notify_entries); } expand_list(n_data->master, &rsc_list, &node_list); add_notify_env_free(n_data, "notify_master_resource", rsc_list); add_notify_env_free(n_data, "notify_master_uname", node_list); if (n_data->inactive) { n_data->inactive = g_list_sort(n_data->inactive, sort_notify_entries); } expand_list(n_data->inactive, &rsc_list, NULL); add_notify_env_free(n_data, "notify_inactive_resource", rsc_list); nodes = g_hash_table_get_values(n_data->allowed_nodes); if (is_set(data_set->flags, pe_flag_stdout)) { /* If printing to stdout, sort the node list, for consistent * regression test output (while avoiding the performance hit * for the live cluster). */ nodes = g_list_sort(nodes, sort_node_uname); } expand_node_list(nodes, &node_list, NULL); add_notify_env_free(n_data, "notify_available_uname", node_list); g_list_free(nodes); source = g_hash_table_lookup(rsc->meta, XML_RSC_ATTR_TARGET); if (safe_str_eq("host", source)) { expand_node_list(data_set->nodes, &node_list, &metal_list); add_notify_env_free(n_data, "notify_all_hosts", metal_list); } else { expand_node_list(data_set->nodes, &node_list, NULL); } add_notify_env_free(n_data, "notify_all_uname", node_list); if (required && n_data->pre) { update_action_flags(n_data->pre, pe_action_optional | pe_action_clear, __FUNCTION__, __LINE__); update_action_flags(n_data->pre_done, pe_action_optional | pe_action_clear, __FUNCTION__, __LINE__); } if (required && n_data->post) { update_action_flags(n_data->post, pe_action_optional | pe_action_clear, __FUNCTION__, __LINE__); update_action_flags(n_data->post_done, pe_action_optional | pe_action_clear, __FUNCTION__, __LINE__); } return required; } /* * \internal * \brief Find any remote connection start relevant to an action * * \param[in] action Action to chek * * \return If action is behind a remote connection, connection's start */ static pe_action_t * find_remote_start(pe_action_t *action) { if (action && action->node) { pe_resource_t *remote_rsc = action->node->details->remote_rsc; if (remote_rsc) { return find_first_action(remote_rsc->actions, NULL, RSC_START, NULL); } } return NULL; } void create_notifications(resource_t * rsc, notify_data_t * n_data, pe_working_set_t * data_set) { GListPtr gIter = NULL; action_t *stop = NULL; action_t *start = NULL; enum action_tasks task = text2task(n_data->action); if (rsc->children) { gIter = rsc->children; for (; gIter != NULL; gIter = gIter->next) { resource_t *child = (resource_t *) gIter->data; create_notifications(child, n_data, data_set); } return; } /* Copy notification details into standard ops */ for (gIter = rsc->actions; gIter != NULL; gIter = gIter->next) { action_t *op = (action_t *) gIter->data; if (is_set(op->flags, pe_action_optional) == FALSE && op->node != NULL) { enum action_tasks t = text2task(op->task); switch (t) { case start_rsc: case stop_rsc: case action_promote: case action_demote: add_notify_data_to_action_meta(n_data, op); break; default: break; } } } switch (task) { case start_rsc: if(g_list_length(n_data->start) == 0) { pe_rsc_trace(rsc, "Skipping empty notification for: %s.%s (%s->%s)", n_data->action, rsc->id, role2text(rsc->role), role2text(rsc->next_role)); return; } break; case action_promote: if(g_list_length(n_data->promote) == 0) { pe_rsc_trace(rsc, "Skipping empty notification for: %s.%s (%s->%s)", n_data->action, rsc->id, role2text(rsc->role), role2text(rsc->next_role)); return; } break; case action_demote: if(g_list_length(n_data->demote) == 0) { pe_rsc_trace(rsc, "Skipping empty notification for: %s.%s (%s->%s)", n_data->action, rsc->id, role2text(rsc->role), role2text(rsc->next_role)); return; } break; default: /* We cannot do the same for stop_rsc/n_data->stop at it * might be implied by fencing */ break; } pe_rsc_trace(rsc, "Creating notifications for: %s.%s (%s->%s)", n_data->action, rsc->id, role2text(rsc->role), role2text(rsc->next_role)); stop = find_first_action(rsc->actions, NULL, RSC_STOP, NULL); start = find_first_action(rsc->actions, NULL, RSC_START, NULL); /* stop / demote */ if (rsc->role != RSC_ROLE_STOPPED) { if (task == stop_rsc || task == action_demote) { gIter = rsc->running_on; for (; gIter != NULL; gIter = gIter->next) { node_t *current_node = (node_t *) gIter->data; /* if this stop action is a pseudo action as a result of the current * node being fenced, this stop action is implied by the fencing * action. There's no reason to send the fenced node a stop notification */ if (stop && is_set(stop->flags, pe_action_pseudo) && (current_node->details->unclean || current_node->details->remote_requires_reset) ) { continue; } pe_notify(rsc, current_node, n_data->pre, n_data->pre_done, n_data, data_set); if (task == action_demote || stop == NULL || is_set(stop->flags, pe_action_optional)) { pe_post_notify(rsc, current_node, n_data, data_set); } } } } /* start / promote */ if (rsc->next_role != RSC_ROLE_STOPPED) { if (rsc->allocated_to == NULL) { pe_proc_err("Next role '%s' but %s is not allocated", role2text(rsc->next_role), rsc->id); } else if (task == start_rsc || task == action_promote) { if (start) { pe_action_t *remote_start = find_remote_start(start); if (remote_start && is_not_set(remote_start->flags, pe_action_runnable)) { /* Start and promote actions for a clone instance behind * a Pacemaker Remote connection happen after the * connection starts. If the connection start is blocked, do * not schedule notifications for these actions. */ return; } } if (task != start_rsc || start == NULL || is_set(start->flags, pe_action_optional)) { pe_notify(rsc, rsc->allocated_to, n_data->pre, n_data->pre_done, n_data, data_set); } pe_post_notify(rsc, rsc->allocated_to, n_data, data_set); } } } void free_notification_data(notify_data_t * n_data) { if (n_data == NULL) { return; } g_list_free_full(n_data->stop, free); g_list_free_full(n_data->start, free); g_list_free_full(n_data->demote, free); g_list_free_full(n_data->promote, free); g_list_free_full(n_data->master, free); g_list_free_full(n_data->slave, free); g_list_free_full(n_data->active, free); g_list_free_full(n_data->inactive, free); pcmk_free_nvpairs(n_data->keys); free(n_data); } void create_secondary_notification(pe_action_t *action, resource_t *rsc, pe_action_t *stonith_op, pe_working_set_t *data_set) { notify_data_t *n_data; crm_info("Creating secondary notification for %s", action->uuid); n_data = create_notification_boundaries(rsc, RSC_STOP, NULL, stonith_op, data_set); collect_notification_data(rsc, TRUE, FALSE, n_data); add_notify_env(n_data, "notify_stop_resource", rsc->id); add_notify_env(n_data, "notify_stop_uname", action->node->details->uname); create_notifications(uber_parent(rsc), n_data, data_set); free_notification_data(n_data); } diff --git a/doc/Pacemaker_Explained/en-US/Ch-Advanced-Resources.txt b/doc/Pacemaker_Explained/en-US/Ch-Advanced-Resources.txt index 339d2b7bd7..b8efd853fd 100644 --- a/doc/Pacemaker_Explained/en-US/Ch-Advanced-Resources.txt +++ b/doc/Pacemaker_Explained/en-US/Ch-Advanced-Resources.txt @@ -1,1468 +1,1471 @@ :compat-mode: legacy = Advanced Resource Types = [[group-resources]] == Groups - A Syntactic Shortcut == indexterm:[Group Resources] indexterm:[Resource,Groups] One of the most common elements of a cluster is a set of resources that need to be located together, start sequentially, and stop in the reverse order. To simplify this configuration, we support the concept of groups. .A group of two primitive resources ====== [source,XML] ------- ------- ====== Although the example above contains only two resources, there is no limit to the number of resources a group can contain. The example is also sufficient to explain the fundamental properties of a group: * Resources are started in the order they appear in (+Public-IP+ first, then +Email+) * Resources are stopped in the reverse order to which they appear in (+Email+ first, then +Public-IP+) If a resource in the group can't run anywhere, then nothing after that is allowed to run, too. * If +Public-IP+ can't run anywhere, neither can +Email+; * but if +Email+ can't run anywhere, this does not affect +Public-IP+ in any way The group above is logically equivalent to writing: .How the cluster sees a group resource ====== [source,XML] ------- ------- ====== Obviously as the group grows bigger, the reduced configuration effort can become significant. Another (typical) example of a group is a DRBD volume, the filesystem mount, an IP address, and an application that uses them. === Group Properties === .Properties of a Group Resource [width="95%",cols="3m,<5",options="header",align="center"] |========================================================= |Field |Description |id |A unique name for the group indexterm:[id,Group Resource Property] indexterm:[Resource,Group Property,id] |========================================================= === Group Options === Groups inherit the +priority+, +target-role+, and +is-managed+ properties from primitive resources. See <> for information about those properties. === Group Instance Attributes === Groups have no instance attributes. However, any that are set for the group object will be inherited by the group's children. === Group Contents === Groups may only contain a collection of cluster resources (see <>). To refer to a child of a group resource, just use the child's +id+ instead of the group's. === Group Constraints === Although it is possible to reference a group's children in constraints, it is usually preferable to reference the group itself. .Some constraints involving groups ====== [source,XML] ------- ------- ====== === Group Stickiness === indexterm:[resource-stickiness,Groups] Stickiness, the measure of how much a resource wants to stay where it is, is additive in groups. Every active resource of the group will contribute its stickiness value to the group's total. So if the default +resource-stickiness+ is 100, and a group has seven members, five of which are active, then the group as a whole will prefer its current location with a score of 500. [[s-resource-clone]] == Clones - Resources That Can Have Multiple Active Instances == indexterm:[Clone Resources] indexterm:[Resource,Clones] 'Clone' resources are resources that can have more than one copy active at the same time. This allows you, for example, to run a copy of a daemon on every node. You can clone any primitive or group resource. footnote:[ Of course, the service must support running multiple instances. ] === Anonymous versus Unique Clones === A clone resource is configured to be either 'anonymous' or 'globally unique'. Anonymous clones are the simplest. These behave completely identically everywhere they are running. Because of this, there can be only one instance of an anonymous clone active per node. The instances of globally unique clones are distinct entities. All instances are launched identically, but one instance of the clone is not identical to any other instance, whether running on the same node or a different node. As an example, a cloned IP address can use special kernel functionality such that each instance handles a subset of requests for the same IP address. [[s-resource-promotable]] === Promotable clones === indexterm:[Promotable Clone Resources] indexterm:[Resource,Promotable] If a clone is 'promotable', its instances can perform a special role that Pacemaker will manage via the +promote+ and +demote+ actions of the resource agent. Services that support such a special role have various terms for the special role and the default role: primary and secondary, master and replica, controller and worker, etc. Pacemaker uses the terms 'master' and 'slave', footnote:[ These are historical terms that will eventually be replaced, but the extensive use of them and the need for backward compatibility makes it a long process. You may see examples using a +master+ tag instead of a +clone+ tag with the +promotable+ meta-attribute set to +true+; the +master+ tag is supported, but deprecated, and will be removed in a future version. You may also see such services referred to as 'multi-state' or 'stateful'; these means the same thing as 'promotable'. ] but is agnostic to what the service calls them or what they do. All that Pacemaker cares about is that an instance comes up in the default role when started, and the resource agent supports the +promote+ and +demote+ actions to manage entering and exiting the special role. === Clone Properties === .Properties of a Clone Resource [width="95%",cols="3m,<5",options="header",align="center"] |========================================================= |Field |Description |id |A unique name for the clone indexterm:[id,Clone Property] indexterm:[Clone,Property,id] |========================================================= === Clone Options === <> inherited from primitive resources: +priority, target-role, is-managed+ .Clone-specific configuration options [width="95%",cols="1m,1,<3",options="header",align="center"] |========================================================= |Field |Default |Description |globally-unique |false |If +true+, each clone instance performs a distinct function indexterm:[globally-unique,Clone Option] indexterm:[Clone,Option,globally-unique] |clone-max |number of nodes in cluster |The maximum number of clone instances that can be started across the entire cluster indexterm:[clone-max,Clone Option] indexterm:[Clone,Option,clone-max] |clone-node-max |1 |If +globally-unique+ is +true+, the maximum number of clone instances that can be started on a single node indexterm:[clone-node-max,Clone Option] indexterm:[Clone,Option,clone-node-max] |clone-min |0 |Require at least this number of clone instances to be runnable before allowing resources depending on the clone to be runnable. A value of 0 means require all clone instances to be runnable. indexterm:[clone-min,Clone Option] indexterm:[Clone,Option,clone-min] |notify |false |Call the resource agent's +notify+ action for all active instances, before and after starting or stopping any clone instance. The resource agent must support this action. Allowed values: +false+, +true+ indexterm:[notify,Clone Option] indexterm:[Clone,Option,notify] |ordered |false |If +true+, clone instances must be started sequentially instead of in parallel Allowed values: +false+, +true+ indexterm:[ordered,Clone Option] indexterm:[Clone,Option,ordered] |interleave |false |When this clone is ordered relative to another clone, if this option is +false+ (the default), the ordering is relative to 'all' instances of the other clone, whereas if this option is +true+, the ordering is relative only to instances on the same node. Allowed values: +false+, +true+ indexterm:[interleave,Clone Option] indexterm:[Clone,Option,interleave] |promotable |false |If +true+, clone instances can perform a special role that Pacemaker will manage via the resource agent's +promote+ and +demote+ actions. The resource agent must support these actions. Allowed values: +false+, +true+ indexterm:[promotable,Clone Option] indexterm:[Clone,Option,promotable] |promoted-max |1 |If +promotable+ is +true+, the number of instances that can be promoted at one time across the entire cluster indexterm:[promoted-max,Clone Option] indexterm:[Clone,Option,promoted-max] |promoted-node-max |1 |If +promotable+ is +true+ and +globally-unique+ is +false+, the number of clone instances can be promoted at one time on a single node indexterm:[promoted-node-max,Clone Option] indexterm:[Clone,Option,promoted-node-max] |========================================================= For backward compatibility, +master-max+ and +master-node-max+ are accepted as aliases for +promoted-max+ and +promoted-node-max+, but are deprecated since 2.0.0, and support for them will be removed in a future version. === Clone Contents === Clones must contain exactly one primitive or group resource. .A clone that runs a web server on all nodes ==== [source,XML] ---- ---- ==== [WARNING] You should never reference the name of a clone's child (the primitive or group resource being cloned). If you think you need to do this, you probably need to re-evaluate your design. === Clone Instance Attributes === Clones have no instance attributes; however, any that are set here will be inherited by the clone's child. === Clone Constraints === In most cases, a clone will have a single instance on each active cluster node. If this is not the case, you can indicate which nodes the cluster should preferentially assign copies to with resource location constraints. These constraints are written no differently from those for primitive resources except that the clone's +id+ is used. .Some constraints involving clones ====== [source,XML] ------- ------- ====== Ordering constraints behave slightly differently for clones. In the example above, +apache-stats+ will wait until all copies of +apache-clone+ that need to be started have done so before being started itself. Only if _no_ copies can be started will +apache-stats+ be prevented from being active. Additionally, the clone will wait for +apache-stats+ to be stopped before stopping itself. Colocation of a primitive or group resource with a clone means that the resource can run on any node with an active instance of the clone. The cluster will choose an instance based on where the clone is running and the resource's own location preferences. Colocation between clones is also possible. If one clone +A+ is colocated with another clone +B+, the set of allowed locations for +A+ is limited to nodes on which +B+ is (or will be) active. Placement is then performed normally. ==== Promotable Clone Constraints ==== For promotable clone resources, the +first-action+ and/or +then-action+ fields for ordering constraints may be set to +promote+ or +demote+ to constrain the master role, and colocation constraints may contain +rsc-role+ and/or +with-rsc-role+ fields. .Additional colocation constraint options for promotable clone resources [width="95%",cols="1m,1,<3",options="header",align="center"] |========================================================= |Field |Default |Description |rsc-role |Started |An additional attribute of colocation constraints that specifies the role that +rsc+ must be in. Allowed values: +Started+, +Master+, +Slave+. indexterm:[rsc-role,Ordering Constraints] indexterm:[Constraints,Ordering,rsc-role] |with-rsc-role |Started |An additional attribute of colocation constraints that specifies the role that +with-rsc+ must be in. Allowed values: +Started+, +Master+, +Slave+. indexterm:[with-rsc-role,Ordering Constraints] indexterm:[Constraints,Ordering,with-rsc-role] |========================================================= .Constraints involving promotable clone resources ====== [source,XML] ------- ------- ====== In the example above, +myApp+ will wait until one of the database copies has been started and promoted to master before being started itself on the same node. Only if no copies can be promoted will +myApp+ be prevented from being active. Additionally, the cluster will wait for +myApp+ to be stopped before demoting the database. Colocation of a primitive or group resource with a promotable clone resource means that it can run on any node with an active instance of the promotable clone resource that has the specified role (+master+ or +slave+). In the example above, the cluster will choose a location based on where database is running as a +master+, and if there are multiple +master+ instances it will also factor in +myApp+'s own location preferences when deciding which location to choose. Colocation with regular clones and other promotable clone resources is also possible. In such cases, the set of allowed locations for the +rsc+ clone is (after role filtering) limited to nodes on which the +with-rsc+ promotable clone resource is (or will be) in the specified role. Placement is then performed as normal. ==== Using Promotable Clone Resources in Colocation Sets ==== .Additional colocation set options relevant to promotable clone resources [width="95%",cols="1m,1,<6",options="header",align="center"] |========================================================= |Field |Default |Description |role |Started |The role that 'all members' of the set must be in. Allowed values: +Started+, +Master+, +Slave+. indexterm:[role,Ordering Constraints] indexterm:[Constraints,Ordering,role] |========================================================= In the following example +B+'s master must be located on the same node as +A+'s master. Additionally resources +C+ and +D+ must be located on the same node as +A+'s and +B+'s masters. .Colocate C and D with A's and B's master instances ====== [source,XML] ------- ------- ====== ==== Using Promotable Clone Resources in Ordered Sets ==== .Additional ordered set options relevant to promotable clone resources [width="95%",cols="1m,1,<3",options="header",align="center"] |========================================================= |Field |Default |Description |action |value of +first-action+ |An additional attribute of ordering constraint sets that specifies the action that applies to 'all members' of the set. Allowed values: +start+, +stop+, +promote+, +demote+. indexterm:[action,Ordering Constraints] indexterm:[Constraints,Ordering,action] |========================================================= .Start C and D after first promoting A and B ====== [source,XML] ------- ------- ====== In the above example, +B+ cannot be promoted to a master role until +A+ has been promoted. Additionally, resources +C+ and +D+ must wait until +A+ and +B+ have been promoted before they can start. [[s-clone-stickiness]] === Clone Stickiness === indexterm:[resource-stickiness,Clones] To achieve a stable allocation pattern, clones are slightly sticky by default. If no value for +resource-stickiness+ is provided, the clone will use a value of 1. Being a small value, it causes minimal disturbance to the score calculations of other resources but is enough to prevent Pacemaker from needlessly moving copies around the cluster. [NOTE] ==== For globally unique clones, this may result in multiple instances of the clone staying on a single node, even after another eligible node becomes active (for example, after being put into standby mode then made active again). If you do not want this behavior, specify a +resource-stickiness+ of 0 for the clone temporarily and let the cluster adjust, then set it back to 1 if you want the default behavior to apply again. ==== [IMPORTANT] ==== If +resource-stickiness+ is set in the +rsc_defaults+ section, it will apply to clone instances as well. This means an explicit +resource-stickiness+ of 0 in +rsc_defaults+ works differently from the implicit default used when +resource-stickiness+ is not specified. ==== === Clone Resource Agent Requirements === Any resource can be used as an anonymous clone, as it requires no additional support from the resource agent. Whether it makes sense to do so depends on your resource and its resource agent. ==== Resource Agent Requirements for Globally Unique Clones ==== Globally unique clones require additional support in the resource agent. In particular, it must only respond with +$\{OCF_SUCCESS}+ if the node has that exact instance active. All other probes for instances of the clone should result in +$\{OCF_NOT_RUNNING}+ (or one of the other OCF error codes if they are failed). Individual instances of a clone are identified by appending a colon and a numerical offset, e.g. +apache:2+. Resource agents can find out how many copies there are by examining the +OCF_RESKEY_CRM_meta_clone_max+ environment variable and which instance it is by examining +OCF_RESKEY_CRM_meta_clone+. The resource agent must not make any assumptions (based on +OCF_RESKEY_CRM_meta_clone+) about which numerical instances are active. In particular, the list of active copies will not always be an unbroken sequence, nor always start at 0. ==== Resource Agent Requirements for Promotable Clones ==== Promotable clone resources require two extra actions, +demote+ and +promote+, which are responsible for changing the state of the resource. Like +start+ and +stop+, they should return +$\{OCF_SUCCESS}+ if they completed successfully or a relevant error code if they did not. The states can mean whatever you wish, but when the resource is started, it must come up in the mode called +slave+. From there the cluster will decide which instances to promote to +master+. In addition to the clone requirements for monitor actions, agents must also _accurately_ report which state they are in. The cluster relies on the agent to report its status (including role) accurately and does not indicate to the agent what role it currently believes it to be in. .Role implications of OCF return codes [width="95%",cols="1,<1",options="header",align="center"] |========================================================= |Monitor Return Code |Description |OCF_NOT_RUNNING |Stopped indexterm:[Return Code,OCF_NOT_RUNNING] |OCF_SUCCESS |Running (Slave) indexterm:[Return Code,OCF_SUCCESS] |OCF_RUNNING_MASTER |Running (Master) indexterm:[Return Code,OCF_RUNNING_MASTER] |OCF_FAILED_MASTER |Failed (Master) indexterm:[Return Code,OCF_FAILED_MASTER] |Other |Failed (Slave) |========================================================= ==== Clone Notifications ==== If the clone has the +notify+ meta-attribute set to +true+, and the resource agent supports the +notify+ action, Pacemaker will call the action when appropriate, passing a number of extra variables which, when combined with additional context, can be used to calculate the current state of the cluster and what is about to happen to it. .Environment variables supplied with Clone notify actions [width="95%",cols="5,<3",options="header",align="center"] |========================================================= |Variable |Description |OCF_RESKEY_CRM_meta_notify_type |Allowed values: +pre+, +post+ indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,type] indexterm:[type,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_operation |Allowed values: +start+, +stop+ indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,operation] indexterm:[operation,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_start_resource |Resources to be started indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,start_resource] indexterm:[start_resource,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_stop_resource |Resources to be stopped indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,stop_resource] indexterm:[stop_resource,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_active_resource |Resources that are running indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,active_resource] indexterm:[active_resource,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_inactive_resource |Resources that are not running indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,inactive_resource] indexterm:[inactive_resource,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_start_uname |Nodes on which resources will be started indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,start_uname] indexterm:[start_uname,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_stop_uname |Nodes on which resources will be stopped indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,stop_uname] indexterm:[stop_uname,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_active_uname |Nodes on which resources are running indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,active_uname] indexterm:[active_uname,Notification Environment Variable] |========================================================= The variables come in pairs, such as +OCF_RESKEY_CRM_meta_notify_start_resource+ and -+OCF_RESKEY_CRM_meta_notify_start_uname+ and should be treated as an ++OCF_RESKEY_CRM_meta_notify_start_uname+, and should be treated as an array of whitespace-separated elements. -+OCF_RESKEY_CRM_meta_notify_inactive_resource+ is an exception as the ++OCF_RESKEY_CRM_meta_notify_inactive_resource+ is an exception, as the matching +uname+ variable does not exist since inactive resources are not running on any node. -Thus in order to indicate that +clone:0+ will be started on +sles-1+, +Thus, in order to indicate that +clone:0+ will be started on +sles-1+, +clone:2+ will be started on +sles-3+, and +clone:3+ will be started -on +sles-2+, the cluster would set +on +sles-2+, the cluster would set: .Notification variables ====== [source,Bash] ------- OCF_RESKEY_CRM_meta_notify_start_resource="clone:0 clone:2 clone:3" OCF_RESKEY_CRM_meta_notify_start_uname="sles-1 sles-3 sles-2" ------- ====== [NOTE] ==== Pacemaker will log but otherwise ignore failures of notify actions. ==== ==== Interpretation of Notification Variables ==== .Pre-notification (stop): * Active resources: +$OCF_RESKEY_CRM_meta_notify_active_resource+ * Inactive resources: +$OCF_RESKEY_CRM_meta_notify_inactive_resource+ * Resources to be started: +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Resources to be stopped: +$OCF_RESKEY_CRM_meta_notify_stop_resource+ .Post-notification (stop) / Pre-notification (start): * Active resources ** +$OCF_RESKEY_CRM_meta_notify_active_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_stop_resource+ * Inactive resources ** +$OCF_RESKEY_CRM_meta_notify_inactive_resource+ ** plus +$OCF_RESKEY_CRM_meta_notify_stop_resource+ * Resources that were started: +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Resources that were stopped: +$OCF_RESKEY_CRM_meta_notify_stop_resource+ .Post-notification (start): * Active resources: ** +$OCF_RESKEY_CRM_meta_notify_active_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_stop_resource+ ** plus +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Inactive resources: ** +$OCF_RESKEY_CRM_meta_notify_inactive_resource+ ** plus +$OCF_RESKEY_CRM_meta_notify_stop_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Resources that were started: +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Resources that were stopped: +$OCF_RESKEY_CRM_meta_notify_stop_resource+ ==== Extra Notifications for Promotable Clones ==== .Extra environment variables supplied for promotable clones [width="95%",cols="5,<3",options="header",align="center"] |========================================================= +|Variable +|Description + |OCF_RESKEY_CRM_meta_notify_master_resource |Resources that are running in +Master+ mode indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,master_resource] indexterm:[master_resource,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_slave_resource |Resources that are running in +Slave+ mode indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,slave_resource] indexterm:[slave_resource,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_promote_resource |Resources to be promoted indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,promote_resource] indexterm:[promote_resource,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_demote_resource |Resources to be demoted indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,demote_resource] indexterm:[demote_resource,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_promote_uname |Nodes on which resources will be promoted indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,promote_uname] indexterm:[promote_uname,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_demote_uname |Nodes on which resources will be demoted indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,demote_uname] indexterm:[demote_uname,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_master_uname |Nodes on which resources are running in +Master+ mode indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,master_uname] indexterm:[master_uname,Notification Environment Variable] |OCF_RESKEY_CRM_meta_notify_slave_uname |Nodes on which resources are running in +Slave+ mode indexterm:[Environment Variable,OCF_RESKEY_CRM_meta_notify_,slave_uname] indexterm:[slave_uname,Notification Environment Variable] |========================================================= ==== Interpretation of Promotable Notification Variables ==== .Pre-notification (demote): * +Active+ resources: +$OCF_RESKEY_CRM_meta_notify_active_resource+ * +Master+ resources: +$OCF_RESKEY_CRM_meta_notify_master_resource+ * +Slave+ resources: +$OCF_RESKEY_CRM_meta_notify_slave_resource+ * Inactive resources: +$OCF_RESKEY_CRM_meta_notify_inactive_resource+ * Resources to be started: +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Resources to be promoted: +$OCF_RESKEY_CRM_meta_notify_promote_resource+ * Resources to be demoted: +$OCF_RESKEY_CRM_meta_notify_demote_resource+ * Resources to be stopped: +$OCF_RESKEY_CRM_meta_notify_stop_resource+ .Post-notification (demote) / Pre-notification (stop): * +Active+ resources: +$OCF_RESKEY_CRM_meta_notify_active_resource+ * +Master+ resources: ** +$OCF_RESKEY_CRM_meta_notify_master_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_demote_resource+ * +Slave+ resources: +$OCF_RESKEY_CRM_meta_notify_slave_resource+ * Inactive resources: +$OCF_RESKEY_CRM_meta_notify_inactive_resource+ * Resources to be started: +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Resources to be promoted: +$OCF_RESKEY_CRM_meta_notify_promote_resource+ * Resources to be demoted: +$OCF_RESKEY_CRM_meta_notify_demote_resource+ * Resources to be stopped: +$OCF_RESKEY_CRM_meta_notify_stop_resource+ * Resources that were demoted: +$OCF_RESKEY_CRM_meta_notify_demote_resource+ .Post-notification (stop) / Pre-notification (start) * +Active+ resources: ** +$OCF_RESKEY_CRM_meta_notify_active_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_stop_resource+ * +Master+ resources: ** +$OCF_RESKEY_CRM_meta_notify_master_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_demote_resource+ * +Slave+ resources: ** +$OCF_RESKEY_CRM_meta_notify_slave_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_stop_resource+ * Inactive resources: ** +$OCF_RESKEY_CRM_meta_notify_inactive_resource+ ** plus +$OCF_RESKEY_CRM_meta_notify_stop_resource+ * Resources to be started: +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Resources to be promoted: +$OCF_RESKEY_CRM_meta_notify_promote_resource+ * Resources to be demoted: +$OCF_RESKEY_CRM_meta_notify_demote_resource+ * Resources to be stopped: +$OCF_RESKEY_CRM_meta_notify_stop_resource+ * Resources that were demoted: +$OCF_RESKEY_CRM_meta_notify_demote_resource+ * Resources that were stopped: +$OCF_RESKEY_CRM_meta_notify_stop_resource+ .Post-notification (start) / Pre-notification (promote) * +Active+ resources: ** +$OCF_RESKEY_CRM_meta_notify_active_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_stop_resource+ ** plus +$OCF_RESKEY_CRM_meta_notify_start_resource+ * +Master+ resources: ** +$OCF_RESKEY_CRM_meta_notify_master_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_demote_resource+ * +Slave+ resources: ** +$OCF_RESKEY_CRM_meta_notify_slave_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_stop_resource+ ** plus +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Inactive resources: ** +$OCF_RESKEY_CRM_meta_notify_inactive_resource+ ** plus +$OCF_RESKEY_CRM_meta_notify_stop_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Resources to be started: +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Resources to be promoted: +$OCF_RESKEY_CRM_meta_notify_promote_resource+ * Resources to be demoted: +$OCF_RESKEY_CRM_meta_notify_demote_resource+ * Resources to be stopped: +$OCF_RESKEY_CRM_meta_notify_stop_resource+ * Resources that were started: +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Resources that were demoted: +$OCF_RESKEY_CRM_meta_notify_demote_resource+ * Resources that were stopped: +$OCF_RESKEY_CRM_meta_notify_stop_resource+ .Post-notification (promote) * +Active+ resources: ** +$OCF_RESKEY_CRM_meta_notify_active_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_stop_resource+ ** plus +$OCF_RESKEY_CRM_meta_notify_start_resource+ * +Master+ resources: ** +$OCF_RESKEY_CRM_meta_notify_master_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_demote_resource+ ** plus +$OCF_RESKEY_CRM_meta_notify_promote_resource+ * +Slave+ resources: ** +$OCF_RESKEY_CRM_meta_notify_slave_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_stop_resource+ ** plus +$OCF_RESKEY_CRM_meta_notify_start_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_promote_resource+ * Inactive resources: ** +$OCF_RESKEY_CRM_meta_notify_inactive_resource+ ** plus +$OCF_RESKEY_CRM_meta_notify_stop_resource+ ** minus +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Resources to be started: +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Resources to be promoted: +$OCF_RESKEY_CRM_meta_notify_promote_resource+ * Resources to be demoted: +$OCF_RESKEY_CRM_meta_notify_demote_resource+ * Resources to be stopped: +$OCF_RESKEY_CRM_meta_notify_stop_resource+ * Resources that were started: +$OCF_RESKEY_CRM_meta_notify_start_resource+ * Resources that were promoted: +$OCF_RESKEY_CRM_meta_notify_promote_resource+ * Resources that were demoted: +$OCF_RESKEY_CRM_meta_notify_demote_resource+ * Resources that were stopped: +$OCF_RESKEY_CRM_meta_notify_stop_resource+ === Monitoring Promotable Clone Resources === The usual monitor actions are insufficient to monitor a promotable clone resource, because Pacemaker needs to verify not only that the resource is active, but also that its actual role matches its intended one. Define two monitoring actions: the usual one will cover the slave role, and an additional one with +role="master"+ will cover the master role. .Monitoring both states of a promotable clone resource ====== [source,XML] ------- ------- ====== [IMPORTANT] =========== It is crucial that _every_ monitor operation has a different interval! Pacemaker currently differentiates between operations only by resource and interval; so if (for example) a promotable clone resource had the same monitor interval for both roles, Pacemaker would ignore the role when checking the status -- which would cause unexpected return codes, and therefore unnecessary complications. =========== [[s-promotion-scores]] === Determining Which Instance is Promoted === Pacemaker can choose a promotable clone instance to be promoted in one of two ways: * Promotion scores: These are node attributes set via the `crm_master` utility, which generally would be called by the resource agent's start action if it supports promotable clones. This tool automatically detects both the resource and host, and should be used to set a preference for being promoted. Based on this, +promoted-max+, and +promoted-node-max+, the instance(s) with the highest preference will be promoted. * Constraints: Location constraints can indicate which nodes are most preferred as masters. .Explicitly preferring node1 to be promoted to master ====== [source,XML] ------- ------- ====== [[s-resource-bundle]] == Bundles - Isolated Environments == indexterm:[bundle] indexterm:[Resource,bundle] indexterm:[Docker,bundle] indexterm:[rkt,bundle] Pacemaker supports a special syntax for launching a https://en.wikipedia.org/wiki/Operating-system-level_virtualization[container] with any infrastructure it requires: the 'bundle'. Pacemaker bundles support https://www.docker.com/[Docker] and https://coreos.com/rkt/[rkt] container technologies. footnote:[Docker is a trademark of Docker, Inc. No endorsement by or association with Docker, Inc. is implied.] .A bundle for a containerized web server ==== [source,XML] ---- ---- ==== === Bundle Properties === .Properties of a Bundle [width="95%",cols="3m,<5",options="header",align="center"] |========================================================= |Field |Description |id |A unique name for the bundle (required) indexterm:[id,bundle] indexterm:[bundle,Property,id] |description |Arbitrary text (not used by Pacemaker) indexterm:[description,bundle] indexterm:[bundle,Property,description] |========================================================= A bundle must contain exactly one ++ or ++ element. === Docker Properties === Before configuring a Docker bundle in Pacemaker, the user must install Docker and supply a fully configured Docker image on every node allowed to run the bundle. Pacemaker will create an implicit +ocf:heartbeat:docker+ resource to manage a bundle's Docker container. The user must ensure that resource agent is installed on every node allowed to run the bundle. .Properties of a Bundle's Docker Element [width="95%",cols="3m,4,<5",options="header",align="center"] |========================================================= |Field |Default |Description |image | |Docker image tag (required) indexterm:[image,Docker] indexterm:[Docker,Property,image] |replicas |Value of +promoted-max+ if that is positive, else 1 |A positive integer specifying the number of container instances to launch indexterm:[replicas,Docker] indexterm:[Docker,Property,replicas] |replicas-per-host |1 |A positive integer specifying the number of container instances allowed to run on a single node indexterm:[replicas-per-host,Docker] indexterm:[Docker,Property,replicas-per-host] |promoted-max |0 |A non-negative integer that, if positive, indicates that the containerized service should be treated as a promotable service, with this many replicas allowed to run the service in the master role indexterm:[promoted-max,Docker] indexterm:[Docker,Property,promoted-max] |network | |If specified, this will be passed to +docker run+ as the https://docs.docker.com/engine/reference/run/#network-settings[network setting] for the Docker container. indexterm:[network,Docker] indexterm:[Docker,Property,network] |run-command |`/usr/sbin/pacemaker-remoted` if bundle contains a +primitive+, otherwise none |This command will be run inside the container when launching it ("PID 1"). If the bundle contains a +primitive+, this command 'must' start pacemaker-remoted (but could, for example, be a script that does other stuff, too). If the container image has a pre-2.0.0 version of Pacemaker, set this to +/usr/sbin/pacemaker_remoted+ (note the underbar instead of dash). indexterm:[run-command,Docker] indexterm:[Docker,Property,run-command] |options | |Extra command-line options to pass to `docker run` indexterm:[options,Docker] indexterm:[Docker,Property,options] |========================================================= For backward compatibility, +masters+ is accepted as an alias for +promoted-max+, but is deprecated since 2.0.0, and support for it will be removed in a future version. === rkt Properties === Before configuring a rkt bundle in Pacemaker, the user must install rkt and supply a fully configured container image on every node allowed to run the bundle. Pacemaker will create an implicit +ocf:heartbeat:rkt+ resource to manage a bundle's rkt container. The user must ensure that resource agent is installed on every node allowed to run the bundle. .Properties of a Bundle's rkt Element [width="95%",cols="3m,4,<5",options="header",align="center"] |========================================================= |Field |Default |Description |image | |Container image tag (required) indexterm:[image,rkt] indexterm:[rkt,Property,image] |replicas |Value of +promoted-max+ if that is positive, else 1 |A positive integer specifying the number of container instances to launch indexterm:[replicas,rkt] indexterm:[rkt,Property,replicas] |replicas-per-host |1 |A positive integer specifying the number of container instances allowed to run on a single node indexterm:[replicas-per-host,rkt] indexterm:[rkt,Property,replicas-per-host] |promoted-max |0 |A non-negative integer that, if positive, indicates that the containerized service should be treated as a promotable service, with this many replicas allowed to run the service in the master role indexterm:[promoted-max,rkt] indexterm:[rkt,Property,promoted-max] |network | |If specified, this will be passed to +rkt run+ as the network setting for the rkt container. indexterm:[network,rkt] indexterm:[rkt,Property,network] |run-command |`/usr/sbin/pacemaker-remoted` if bundle contains a +primitive+, otherwise none |This command will be run inside the container when launching it ("PID 1"). If the bundle contains a +primitive+, this command 'must' start pacemaker-remoted (but could, for example, be a script that does other stuff, too). If the container image has a pre-2.0.0 version of Pacemaker, set this to +/usr/sbin/pacemaker_remoted+ (note the underbar instead of dash). indexterm:[run-command,rkt] indexterm:[rkt,Property,run-command] |options | |Extra command-line options to pass to `rkt run` indexterm:[options,rkt] indexterm:[rkt,Property,options] |========================================================= For backward compatibility, +masters+ is accepted as an alias for +promoted-max+, but is deprecated since 2.0.0, and support for it will be removed in a future version. === Bundle Network Properties === A bundle may optionally contain one ++ element. indexterm:[bundle,network] .Properties of a Bundle's Network Element [width="95%",cols="2m,1,<4",options="header",align="center"] |========================================================= |Field |Default |Description |add-host |TRUE |If TRUE, and +ip-range-start+ is used, Pacemaker will automatically ensure that +/etc/hosts+ inside the containers has entries for each <> and its assigned IP. indexterm:[add-host,network] indexterm:[network,Property,add-host] |ip-range-start | |If specified, Pacemaker will create an implicit +ocf:heartbeat:IPaddr2+ resource for each container instance, starting with this IP address, using up to +replicas+ sequential addresses. These addresses can be used from the host's network to reach the service inside the container, though it is not visible within the container itself. Only IPv4 addresses are currently supported. indexterm:[ip-range-start,network] indexterm:[network,Property,ip-range-start] |host-netmask |32 |If +ip-range-start+ is specified, the IP addresses are created with this CIDR netmask (as a number of bits). indexterm:[host-netmask,network] indexterm:[network,Property,host-netmask] |host-interface | |If +ip-range-start+ is specified, the IP addresses are created on this host interface (by default, it will be determined from the IP address). indexterm:[host-interface,network] indexterm:[network,Property,host-interface] |control-port |3121 |If the bundle contains a +primitive+, the cluster will use this integer TCP port for communication with Pacemaker Remote inside the container. Changing this is useful when the container is unable to listen on the default port, for example, when the container uses the host's network rather than +ip-range-start+ (in which case +replicas-per-host+ must be 1), or when the bundle may run on a Pacemaker Remote node that is already listening on the default port. Any PCMK_remote_port environment variable set on the host or in the container is ignored for bundle connections. indexterm:[control-port,network] indexterm:[network,Property,control-port] |========================================================= [[s-resource-bundle-note-replica-names]] [NOTE] ==== Replicas are named by the bundle id plus a dash and an integer counter starting with zero. For example, if a bundle named +httpd-bundle+ has +replicas=2+, its containers will be named +httpd-bundle-0+ and +httpd-bundle-1+. ==== Additionally, a ++ element may optionally contain one or more ++ elements. indexterm:[bundle,network,port-mapping] .Properties of a Bundle's Port-Mapping Element [width="95%",cols="2m,1,<4",options="header",align="center"] |========================================================= |Field |Default |Description |id | |A unique name for the port mapping (required) indexterm:[id,port-mapping] indexterm:[port-mapping,Property,id] |port | |If this is specified, connections to this TCP port number on the host network (on the container's assigned IP address, if +ip-range-start+ is specified) will be forwarded to the container network. Exactly one of +port+ or +range+ must be specified in a +port-mapping+. indexterm:[port,port-mapping] indexterm:[port-mapping,Property,port] |internal-port |value of +port+ |If +port+ and this are specified, connections to +port+ on the host's network will be forwarded to this port on the container network. indexterm:[internal-port,port-mapping] indexterm:[port-mapping,Property,internal-port] |range | |If this is specified, connections to these TCP port numbers (expressed as 'first_port'-'last_port') on the host network (on the container's assigned IP address, if +ip-range-start+ is specified) will be forwarded to the same ports in the container network. Exactly one of +port+ or +range+ must be specified in a +port-mapping+. indexterm:[range,port-mapping] indexterm:[port-mapping,Property,range] |========================================================= [NOTE] ==== If the bundle contains a +primitive+, Pacemaker will automatically map the +control-port+, so it is not necessary to specify that port in a +port-mapping+. ==== === Bundle Storage Properties === A bundle may optionally contain one ++ element. A ++ element has no properties of its own, but may contain one or more ++ elements. indexterm:[bundle,storage,storage-mapping] .Properties of a Bundle's Storage-Mapping Element [width="95%",cols="2m,1,<4",options="header",align="center"] |========================================================= |Field |Default |Description |id | |A unique name for the storage mapping (required) indexterm:[id,storage-mapping] indexterm:[storage-mapping,Property,id] |source-dir | |The absolute path on the host's filesystem that will be mapped into the container. Exactly one of +source-dir+ and +source-dir-root+ must be specified in a +storage-mapping+. indexterm:[source-dir,storage-mapping] indexterm:[storage-mapping,Property,source-dir] |source-dir-root | |The start of a path on the host's filesystem that will be mapped into the container, using a different subdirectory on the host for each container instance. The subdirectory will be named the same as the <>. Exactly one of +source-dir+ and +source-dir-root+ must be specified in a +storage-mapping+. indexterm:[source-dir-root,storage-mapping] indexterm:[storage-mapping,Property,source-dir-root] |target-dir | |The path name within the container where the host storage will be mapped (required) indexterm:[target-dir,storage-mapping] indexterm:[storage-mapping,Property,target-dir] |options | |File system mount options to use when mapping the storage indexterm:[options,storage-mapping] indexterm:[storage-mapping,Property,options] |========================================================= [NOTE] ==== Pacemaker does not define the behavior if the source directory does not already exist on the host. However, it is expected that the container technology and/or its resource agent will create the source directory in that case. ==== [NOTE] ==== If the bundle contains a +primitive+, Pacemaker will automatically map the equivalent of +source-dir=/etc/pacemaker/authkey target-dir=/etc/pacemaker/authkey+ and +source-dir-root=/var/log/pacemaker/bundles target-dir=/var/log+ into the container, so it is not necessary to specify those paths in a +storage-mapping+. ==== [IMPORTANT] ==== The +PCMK_authkey_location+ environment variable must not be set to anything other than the default of `/etc/pacemaker/authkey` on any node in the cluster. ==== === Bundle Primitive === A bundle may optionally contain one ++ resource (see <>). The primitive may have operations, instance attributes and meta-attributes defined, as usual. If a bundle contains a primitive resource, the container image must include the Pacemaker Remote daemon, and at least one of +ip-range-start+ or +control-port+ must be configured in the bundle. Pacemaker will create an implicit +ocf:pacemaker:remote+ resource for the connection, launch Pacemaker Remote within the container, and monitor and manage the primitive resource via Pacemaker Remote. If the bundle has more than one container instance (replica), the primitive resource will function as an implicit clone (see <>) -- a promotable clone if the bundle has +masters+ greater than zero (see <>). [IMPORTANT] ==== Containers in bundles with a +primitive+ must have an accessible networking environment, so that Pacemaker on the cluster nodes can contact Pacemaker Remote inside the container. For example, the Docker option `--net=none` should not be used with a +primitive+. The default (using a distinct network space inside the container) works in combination with +ip-range-start+. If the Docker option `--net=host` is used (making the container share the host's network space), a unique +control-port+ should be specified for each bundle. Any firewall must allow access to the +control-port+. ==== [[s-bundle-attributes]] === Bundle Node Attributes === If the bundle has a +primitive+, the primitive's resource agent may want to set node attributes such as <>. However, with containers, it is not apparent which node should get the attribute. If the container uses shared storage that is the same no matter which node the container is hosted on, then it is appropriate to use the promotion score on the bundle node itself. On the other hand, if the container uses storage exported from the underlying host, then it may be more appropriate to use the promotion score on the underlying host. Since this depends on the particular situation, the +container-attribute-target+ resource meta-attribute allows the user to specify which approach to use. If it is set to +host+, then user-defined node attributes will be checked on the underlying host. If it is anything else, the local node (in this case the bundle node) is used as usual. This only applies to user-defined attributes; the cluster will always check the local node for cluster-defined attributes such as +#uname+. If +container-attribute-target+ is +host+, the cluster will pass additional environment variables to the primitive's resource agent that allow it to set node attributes appropriately: +CRM_meta_container_attribute_target+ (identical to the meta-attribute value) and +CRM_meta_physical_host+ (the name of the underlying host). [NOTE] ==== When called by a resource agent, the attrd_updater and crm_attribute commands will automatically check those environment variables and set attributes appropriately. ==== === Bundle Meta-Attributes === Any meta-attribute set on a bundle will be inherited by the bundle's primitive and any resources implicitly created by Pacemaker for the bundle. This includes options such as +priority+, +target-role+, and +is-managed+. See <> for more information. === Limitations of Bundles === Restarting pacemaker while a bundle is unmanaged or the cluster is in maintenance mode may cause the bundle to fail. Bundles may not be explicitly cloned or included in groups. This includes the bundle's primitive and any resources implicitly created by Pacemaker for the bundle. (If +replicas+ is greater than 1, the bundle will behave like a clone implicitly.) Bundles do not have instance attributes, utilization attributes, or operations, though a bundle's primitive may have them. A bundle with a primitive can run on a Pacemaker Remote node only if the bundle uses a distinct +control-port+. diff --git a/include/crm/common/nvpair.h b/include/crm/common/nvpair.h index 85f18ee70e..20520dd64e 100644 --- a/include/crm/common/nvpair.h +++ b/include/crm/common/nvpair.h @@ -1,97 +1,97 @@ /* * Copyright 2004-2019 Andrew Beekhof * * This source code is licensed under the GNU Lesser General Public License * version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY. */ #ifndef CRM_COMMON_NVPAIR__H # define CRM_COMMON_NVPAIR__H # ifdef __cplusplus extern "C" { # endif /** * \file * \brief Functionality for manipulating name/value pairs * \ingroup core */ # include // struct timeval # include // gpointer, gboolean, guint # include // xmlNode # include typedef struct pcmk_nvpair_s { char *name; char *value; } pcmk_nvpair_t; -GList *pcmk_prepend_nvpair(GList *nvpairs, const char *name, const char *value); -void pcmk_free_nvpairs(GList *nvpairs); -GList *pcmk_sort_nvpairs(GList *list); -GList *pcmk_xml_attrs2nvpairs(xmlNode *xml); -void pcmk_nvpairs2xml_attrs(GList *list, xmlNode *xml); +GSList *pcmk_prepend_nvpair(GSList *nvpairs, const char *name, const char *value); +void pcmk_free_nvpairs(GSList *nvpairs); +GSList *pcmk_sort_nvpairs(GSList *list); +GSList *pcmk_xml_attrs2nvpairs(xmlNode *xml); +void pcmk_nvpairs2xml_attrs(GSList *list, xmlNode *xml); xmlNode *crm_create_nvpair_xml(xmlNode *parent, const char *id, const char *name, const char *value); void hash2nvpair(gpointer key, gpointer value, gpointer user_data); void hash2field(gpointer key, gpointer value, gpointer user_data); void hash2metafield(gpointer key, gpointer value, gpointer user_data); void hash2smartfield(gpointer key, gpointer value, gpointer user_data); GHashTable *xml2list(xmlNode *parent); const char *crm_xml_add(xmlNode *node, const char *name, const char *value); const char *crm_xml_replace(xmlNode *node, const char *name, const char *value); const char *crm_xml_add_int(xmlNode *node, const char *name, int value); const char *crm_xml_add_ms(xmlNode *node, const char *name, guint ms); const char *crm_element_value(const xmlNode *data, const char *name); int crm_element_value_int(const xmlNode *data, const char *name, int *dest); int crm_element_value_ms(const xmlNode *data, const char *name, guint *dest); int crm_element_value_timeval(const xmlNode *data, const char *name_sec, const char *name_usec, struct timeval *dest); char *crm_element_value_copy(const xmlNode *data, const char *name); /*! * \brief Copy an element from one XML object to another * * \param[in] obj1 Source XML * \param[in,out] obj2 Destination XML * \param[in] element Name of element to copy * * \return Pointer to copied value (from source) */ static inline const char * crm_copy_xml_element(xmlNode *obj1, xmlNode *obj2, const char *element) { const char *value = crm_element_value(obj1, element); crm_xml_add(obj2, element, value); return value; } /*! * \brief Add a boolean attribute to an XML object * * Add an attribute with the value \c XML_BOOLEAN_TRUE or \c XML_BOOLEAN_FALSE * as appropriate to an XML object. * * \param[in,out] node XML object to add attribute to * \param[in] name Name of attribute to add * \param[in] value Boolean whose value will be tested * * \return Pointer to newly created XML attribute's content, or \c NULL on error */ static inline const char * crm_xml_add_boolean(xmlNode *node, const char *name, gboolean value) { return crm_xml_add(node, name, (value? "true" : "false")); } # ifdef __cplusplus } # endif #endif // CRM_COMMON_NVPAIR__H diff --git a/include/crm/pengine/internal.h b/include/crm/pengine/internal.h index e9b7c55d91..c9e57641ed 100644 --- a/include/crm/pengine/internal.h +++ b/include/crm/pengine/internal.h @@ -1,353 +1,353 @@ /* * Copyright 2004-2019 Andrew Beekhof * * This source code is licensed under the GNU Lesser General Public License * version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY. */ #ifndef PE_INTERNAL__H # define PE_INTERNAL__H # include # include # include # define pe_rsc_info(rsc, fmt, args...) crm_log_tag(LOG_INFO, rsc ? rsc->id : "", fmt, ##args) # define pe_rsc_debug(rsc, fmt, args...) crm_log_tag(LOG_DEBUG, rsc ? rsc->id : "", fmt, ##args) # define pe_rsc_trace(rsc, fmt, args...) crm_log_tag(LOG_TRACE, rsc ? rsc->id : "", fmt, ##args) # define pe_err(fmt...) { was_processing_error = TRUE; crm_config_error = TRUE; crm_err(fmt); } # define pe_warn(fmt...) { was_processing_warning = TRUE; crm_config_warning = TRUE; crm_warn(fmt); } # define pe_proc_err(fmt...) { was_processing_error = TRUE; crm_err(fmt); } # define pe_proc_warn(fmt...) { was_processing_warning = TRUE; crm_warn(fmt); } # define pe_set_action_bit(action, bit) action->flags = crm_set_bit(__FUNCTION__, __LINE__, action->uuid, action->flags, bit) # define pe_clear_action_bit(action, bit) action->flags = crm_clear_bit(__FUNCTION__, __LINE__, action->uuid, action->flags, bit) typedef struct pe__location_constraint_s { char *id; // Constraint XML ID pe_resource_t *rsc_lh; // Resource being located enum rsc_role_e role_filter; // Role to locate enum pe_discover_e discover_mode; // Resource discovery GListPtr node_list_rh; // List of pe_node_t* } pe__location_t; typedef struct pe__order_constraint_s { int id; enum pe_ordering type; void *lh_opaque; resource_t *lh_rsc; action_t *lh_action; char *lh_action_task; void *rh_opaque; resource_t *rh_rsc; action_t *rh_action; char *rh_action_task; } pe__ordering_t; typedef struct notify_data_s { - GList *keys; // Environment variable name/value pairs + GSList *keys; // Environment variable name/value pairs const char *action; action_t *pre; action_t *post; action_t *pre_done; action_t *post_done; GListPtr active; /* notify_entry_t* */ GListPtr inactive; /* notify_entry_t* */ GListPtr start; /* notify_entry_t* */ GListPtr stop; /* notify_entry_t* */ GListPtr demote; /* notify_entry_t* */ GListPtr promote; /* notify_entry_t* */ GListPtr master; /* notify_entry_t* */ GListPtr slave; /* notify_entry_t* */ GHashTable *allowed_nodes; } notify_data_t; bool pe_can_fence(pe_working_set_t *data_set, node_t *node); int merge_weights(int w1, int w2); void add_hash_param(GHashTable * hash, const char *name, const char *value); char *native_parameter(resource_t * rsc, node_t * node, gboolean create, const char *name, pe_working_set_t * data_set); pe_node_t *native_location(const pe_resource_t *rsc, GList **list, int current); void pe_metadata(void); void verify_pe_options(GHashTable * options); void common_update_score(resource_t * rsc, const char *id, int score); void native_add_running(resource_t * rsc, node_t * node, pe_working_set_t * data_set); gboolean native_unpack(resource_t * rsc, pe_working_set_t * data_set); gboolean group_unpack(resource_t * rsc, pe_working_set_t * data_set); gboolean clone_unpack(resource_t * rsc, pe_working_set_t * data_set); gboolean container_unpack(resource_t * rsc, pe_working_set_t * data_set); resource_t *native_find_rsc(resource_t *rsc, const char *id, const node_t *node, int flags); gboolean native_active(resource_t * rsc, gboolean all); gboolean group_active(resource_t * rsc, gboolean all); gboolean clone_active(resource_t * rsc, gboolean all); gboolean container_active(resource_t * rsc, gboolean all); void native_print(resource_t * rsc, const char *pre_text, long options, void *print_data); void group_print(resource_t * rsc, const char *pre_text, long options, void *print_data); void clone_print(resource_t * rsc, const char *pre_text, long options, void *print_data); void container_print(resource_t * rsc, const char *pre_text, long options, void *print_data); void native_free(resource_t * rsc); void group_free(resource_t * rsc); void clone_free(resource_t * rsc); void container_free(resource_t * rsc); enum rsc_role_e native_resource_state(const resource_t * rsc, gboolean current); enum rsc_role_e group_resource_state(const resource_t * rsc, gboolean current); enum rsc_role_e clone_resource_state(const resource_t * rsc, gboolean current); enum rsc_role_e container_resource_state(const resource_t * rsc, gboolean current); gboolean common_unpack(xmlNode * xml_obj, resource_t ** rsc, resource_t * parent, pe_working_set_t * data_set); void common_free(resource_t * rsc); extern node_t *node_copy(const node_t *this_node); extern time_t get_effective_time(pe_working_set_t * data_set); /* Failure handling utilities (from failcounts.c) */ // bit flags for fail count handling options enum pe_fc_flags_e { pe_fc_default = 0x00, pe_fc_effective = 0x01, // don't count expired failures pe_fc_fillers = 0x02, // if container, include filler failures in count }; int pe_get_failcount(node_t *node, resource_t *rsc, time_t *last_failure, uint32_t flags, xmlNode *xml_op, pe_working_set_t *data_set); pe_action_t *pe__clear_failcount(pe_resource_t *rsc, pe_node_t *node, const char *reason, pe_working_set_t *data_set); /* Functions for finding/counting a resource's active nodes */ pe_node_t *pe__find_active_on(const pe_resource_t *rsc, unsigned int *count_all, unsigned int *count_clean); pe_node_t *pe__find_active_requires(const pe_resource_t *rsc, unsigned int *count); static inline pe_node_t * pe__current_node(const pe_resource_t *rsc) { return pe__find_active_on(rsc, NULL, NULL); } /* Binary like operators for lists of nodes */ extern void node_list_exclude(GHashTable * list, GListPtr list2, gboolean merge_scores); extern GListPtr node_list_dup(GListPtr list, gboolean reset, gboolean filter); extern GHashTable *node_hash_from_list(GListPtr list); static inline gpointer pe_hash_table_lookup(GHashTable * hash, gconstpointer key) { if (hash) { return g_hash_table_lookup(hash, key); } return NULL; } extern action_t *get_pseudo_op(const char *name, pe_working_set_t * data_set); extern gboolean order_actions(action_t * lh_action, action_t * rh_action, enum pe_ordering order); GHashTable *node_hash_dup(GHashTable * hash); /* Printing functions for debug */ extern void print_node(const char *pre_text, node_t * node, gboolean details); extern void print_resource(int log_level, const char *pre_text, resource_t * rsc, gboolean details); extern void dump_node_scores_worker(int level, const char *file, const char *function, int line, resource_t * rsc, const char *comment, GHashTable * nodes); extern void dump_node_capacity(int level, const char *comment, node_t * node); extern void dump_rsc_utilization(int level, const char *comment, resource_t * rsc, node_t * node); # define dump_node_scores(level, rsc, text, nodes) do { \ dump_node_scores_worker(level, __FILE__, __FUNCTION__, __LINE__, rsc, text, nodes); \ } while(0) /* Sorting functions */ extern gint sort_rsc_priority(gconstpointer a, gconstpointer b); extern gint sort_rsc_index(gconstpointer a, gconstpointer b); extern xmlNode *find_rsc_op_entry(resource_t * rsc, const char *key); extern action_t *custom_action(resource_t * rsc, char *key, const char *task, node_t * on_node, gboolean optional, gboolean foo, pe_working_set_t * data_set); # define delete_key(rsc) generate_op_key(rsc->id, CRMD_ACTION_DELETE, 0) # define delete_action(rsc, node, optional) custom_action( \ rsc, delete_key(rsc), CRMD_ACTION_DELETE, node, \ optional, TRUE, data_set); # define stopped_key(rsc) generate_op_key(rsc->id, CRMD_ACTION_STOPPED, 0) # define stopped_action(rsc, node, optional) custom_action( \ rsc, stopped_key(rsc), CRMD_ACTION_STOPPED, node, \ optional, TRUE, data_set); # define stop_key(rsc) generate_op_key(rsc->id, CRMD_ACTION_STOP, 0) # define stop_action(rsc, node, optional) custom_action( \ rsc, stop_key(rsc), CRMD_ACTION_STOP, node, \ optional, TRUE, data_set); # define reload_key(rsc) generate_op_key(rsc->id, CRMD_ACTION_RELOAD, 0) # define start_key(rsc) generate_op_key(rsc->id, CRMD_ACTION_START, 0) # define start_action(rsc, node, optional) custom_action( \ rsc, start_key(rsc), CRMD_ACTION_START, node, \ optional, TRUE, data_set) # define started_key(rsc) generate_op_key(rsc->id, CRMD_ACTION_STARTED, 0) # define started_action(rsc, node, optional) custom_action( \ rsc, started_key(rsc), CRMD_ACTION_STARTED, node, \ optional, TRUE, data_set) # define promote_key(rsc) generate_op_key(rsc->id, CRMD_ACTION_PROMOTE, 0) # define promote_action(rsc, node, optional) custom_action( \ rsc, promote_key(rsc), CRMD_ACTION_PROMOTE, node, \ optional, TRUE, data_set) # define promoted_key(rsc) generate_op_key(rsc->id, CRMD_ACTION_PROMOTED, 0) # define promoted_action(rsc, node, optional) custom_action( \ rsc, promoted_key(rsc), CRMD_ACTION_PROMOTED, node, \ optional, TRUE, data_set) # define demote_key(rsc) generate_op_key(rsc->id, CRMD_ACTION_DEMOTE, 0) # define demote_action(rsc, node, optional) custom_action( \ rsc, demote_key(rsc), CRMD_ACTION_DEMOTE, node, \ optional, TRUE, data_set) # define demoted_key(rsc) generate_op_key(rsc->id, CRMD_ACTION_DEMOTED, 0) # define demoted_action(rsc, node, optional) custom_action( \ rsc, demoted_key(rsc), CRMD_ACTION_DEMOTED, node, \ optional, TRUE, data_set) extern int pe_get_configured_timeout(resource_t *rsc, const char *action, pe_working_set_t *data_set); extern action_t *find_first_action(GListPtr input, const char *uuid, const char *task, node_t * on_node); extern enum action_tasks get_complex_task(resource_t * rsc, const char *name, gboolean allow_non_atomic); extern GListPtr find_actions(GListPtr input, const char *key, const node_t *on_node); extern GListPtr find_actions_exact(GListPtr input, const char *key, node_t * on_node); extern GListPtr find_recurring_actions(GListPtr input, node_t * not_on_node); extern void pe_free_action(action_t * action); extern void resource_location(resource_t * rsc, node_t * node, int score, const char *tag, pe_working_set_t * data_set); extern gint sort_op_by_callid(gconstpointer a, gconstpointer b); extern gboolean get_target_role(resource_t * rsc, enum rsc_role_e *role); extern resource_t *find_clone_instance(resource_t * rsc, const char *sub_id, pe_working_set_t * data_set); extern void destroy_ticket(gpointer data); extern ticket_t *ticket_new(const char *ticket_id, pe_working_set_t * data_set); // Resources for manipulating resource names const char *pe_base_name_end(const char *id); char *clone_strip(const char *last_rsc_id); char *clone_zero(const char *last_rsc_id); static inline bool pe_base_name_eq(resource_t *rsc, const char *id) { if (id && rsc && rsc->id) { // Number of characters in rsc->id before any clone suffix size_t base_len = pe_base_name_end(rsc->id) - rsc->id + 1; return (strlen(id) == base_len) && !strncmp(id, rsc->id, base_len); } return FALSE; } int get_target_rc(xmlNode * xml_op); gint sort_node_uname(gconstpointer a, gconstpointer b); bool is_set_recursive(resource_t * rsc, long long flag, bool any); enum rsc_digest_cmp_val { /*! Digests are the same */ RSC_DIGEST_MATCH = 0, /*! Params that require a restart changed */ RSC_DIGEST_RESTART, /*! Some parameter changed. */ RSC_DIGEST_ALL, /*! rsc op didn't have a digest associated with it, so * it is unknown if parameters changed or not. */ RSC_DIGEST_UNKNOWN, }; typedef struct op_digest_cache_s { enum rsc_digest_cmp_val rc; xmlNode *params_all; xmlNode *params_secure; xmlNode *params_restart; char *digest_all_calc; char *digest_secure_calc; char *digest_restart_calc; } op_digest_cache_t; op_digest_cache_t *rsc_action_digest_cmp(resource_t * rsc, xmlNode * xml_op, node_t * node, pe_working_set_t * data_set); action_t *pe_fence_op(node_t * node, const char *op, bool optional, const char *reason, pe_working_set_t * data_set); void trigger_unfencing( resource_t * rsc, node_t *node, const char *reason, action_t *dependency, pe_working_set_t * data_set); void pe_action_set_reason(pe_action_t *action, const char *reason, bool overwrite); void pe_action_set_flag_reason(const char *function, long line, pe_action_t *action, pe_action_t *reason, const char *text, enum pe_action_flags flags, bool overwrite); #define pe_action_required(action, reason, text) pe_action_set_flag_reason(__FUNCTION__, __LINE__, action, reason, text, pe_action_optional, FALSE) #define pe_action_implies(action, reason, flag) pe_action_set_flag_reason(__FUNCTION__, __LINE__, action, reason, NULL, flag, FALSE) void set_bit_recursive(resource_t * rsc, unsigned long long flag); void clear_bit_recursive(resource_t * rsc, unsigned long long flag); gboolean add_tag_ref(GHashTable * tags, const char * tag_name, const char * obj_ref); void print_rscs_brief(GListPtr rsc_list, const char * pre_text, long options, void * print_data, gboolean print_all); void pe_fence_node(pe_working_set_t * data_set, node_t * node, const char *reason); node_t *pe_create_node(const char *id, const char *uname, const char *type, const char *score, pe_working_set_t * data_set); bool remote_id_conflict(const char *remote_name, pe_working_set_t *data); void common_print(resource_t * rsc, const char *pre_text, const char *name, node_t *node, long options, void *print_data); resource_t *find_container_child(const resource_t *bundle, const node_t *node); bool container_fix_remote_addr(resource_t *rsc); const char *container_fix_remote_addr_in(resource_t *rsc, xmlNode *xml, const char *field); const char *pe_node_attribute_calculated(const pe_node_t *node, const char *name, const resource_t *rsc); const char *pe_node_attribute_raw(pe_node_t *node, const char *name); bool pe__is_universal_clone(pe_resource_t *rsc, pe_working_set_t *data_set); void pe__add_param_check(xmlNode *rsc_op, pe_resource_t *rsc, pe_node_t *node, enum pe_check_parameters, pe_working_set_t *data_set); void pe__foreach_param_check(pe_working_set_t *data_set, void (*cb)(pe_resource_t*, pe_node_t*, xmlNode*, enum pe_check_parameters, pe_working_set_t*)); void pe__free_param_checks(pe_working_set_t *data_set); #endif diff --git a/lib/common/nvpair.c b/lib/common/nvpair.c index 5c1ce804cb..804a99ebee 100644 --- a/lib/common/nvpair.c +++ b/lib/common/nvpair.c @@ -1,720 +1,720 @@ /* * Copyright 2004-2019 Andrew Beekhof * * This source code is licensed under the GNU Lesser General Public License * version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY. */ #include #include #include #include #include #include #include #include #include #include #include "crmcommon_private.h" /* * This file isolates handling of three types of name/value pairs: * * - pcmk_nvpair_t data type * - XML attributes () * - XML nvpair elements () */ // pcmk_nvpair_t handling /*! * \internal * \brief Allocate a new name/value pair * * \param[in] name New name * \param[in] value New value * * \return Newly allocated name/value pair * \note The caller is responsible for freeing the result with * \c pcmk__free_nvpair(). */ static pcmk_nvpair_t * pcmk__new_nvpair(const char *name, const char *value) { pcmk_nvpair_t *nvpair = calloc(1, sizeof(pcmk_nvpair_t)); CRM_ASSERT(nvpair); nvpair->name = strdup(name); nvpair->value = strdup(value); return nvpair; } /*! * \internal * \brief Free a name/value pair * * \param[in] nvpair Name/value pair to free */ static void pcmk__free_nvpair(gpointer data) { if (data) { pcmk_nvpair_t *nvpair = data; free(nvpair->name); free(nvpair->value); free(nvpair); } } /*! * \brief Prepend a name/value pair to a list * * \param[in,out] nvpairs List to modify * \param[in] name New entry's name * \param[in] value New entry's value * * \return New head of list * \note The caller is responsible for freeing the list with * \c pcmk_free_nvpairs(). */ -GList * -pcmk_prepend_nvpair(GList *nvpairs, const char *name, const char *value) +GSList * +pcmk_prepend_nvpair(GSList *nvpairs, const char *name, const char *value) { - return g_list_prepend(nvpairs, pcmk__new_nvpair(name, value)); + return g_slist_prepend(nvpairs, pcmk__new_nvpair(name, value)); } /*! * \brief Free a list of name/value pairs * * \param[in] list List to free */ void -pcmk_free_nvpairs(GList *nvpairs) +pcmk_free_nvpairs(GSList *nvpairs) { - g_list_free_full(nvpairs, pcmk__free_nvpair); + g_slist_free_full(nvpairs, pcmk__free_nvpair); } /*! * \internal * \brief Compare two name/value pairs * * \param[in] a First name/value pair to compare * \param[in] b Second name/value pair to compare * * \return 0 if a == b, 1 if a > b, -1 if a < b */ static gint pcmk__compare_nvpair(gconstpointer a, gconstpointer b) { int rc = 0; const pcmk_nvpair_t *pair_a = a; const pcmk_nvpair_t *pair_b = b; CRM_ASSERT(a != NULL); CRM_ASSERT(pair_a->name != NULL); CRM_ASSERT(b != NULL); CRM_ASSERT(pair_b->name != NULL); rc = strcmp(pair_a->name, pair_b->name); if (rc < 0) { return -1; } else if (rc > 0) { return 1; } return 0; } /*! * \brief Sort a list of name/value pairs * * \param[in,out] list List to sort * * \return New head of list */ -GList * -pcmk_sort_nvpairs(GList *list) +GSList * +pcmk_sort_nvpairs(GSList *list) { - return g_list_sort(list, pcmk__compare_nvpair); + return g_slist_sort(list, pcmk__compare_nvpair); } /*! * \brief Create a list of name/value pairs from an XML node's attributes * * \param[in] XML to parse * * \return New list of name/value pairs * \note It is the caller's responsibility to free the list with * \c pcmk_free_nvpairs(). */ -GList * +GSList * pcmk_xml_attrs2nvpairs(xmlNode *xml) { - GList *result = NULL; + GSList *result = NULL; for (xmlAttrPtr iter = pcmk__first_xml_attr(xml); iter != NULL; iter = iter->next) { result = pcmk_prepend_nvpair(result, (const char *) iter->name, (const char *) pcmk__xml_attr_value(iter)); } return result; } /*! * \internal * \brief Add an XML attribute corresponding to a name/value pair * - * Suitable for \c g_list_foreach(), this function adds a NAME=VALUE + * Suitable for glib list iterators, this function adds a NAME=VALUE * XML attribute based on a given name/value pair. * * \param[in] data Name/value pair * \param[out] user_data XML node to add attributes to */ static void pcmk__nvpair_add_xml_attr(gpointer data, gpointer user_data) { pcmk_nvpair_t *pair = data; xmlNode *parent = user_data; crm_xml_add(parent, pair->name, pair->value); } /*! * \brief Add XML attributes based on a list of name/value pairs * * \param[in] list List of name/value pairs * \param[in,out] xml XML node to add attributes to */ void -pcmk_nvpairs2xml_attrs(GList *list, xmlNode *xml) +pcmk_nvpairs2xml_attrs(GSList *list, xmlNode *xml) { - g_list_foreach(list, pcmk__nvpair_add_xml_attr, xml); + g_slist_foreach(list, pcmk__nvpair_add_xml_attr, xml); } // XML attribute handling /*! * \brief Create an XML attribute with specified name and value * * \param[in,out] node XML node to modify * \param[in] name Attribute name to set * \param[in] value Attribute value to set * * \return New value on success, \c NULL otherwise * \note This does nothing if node, name, or value are \c NULL or empty. */ const char * crm_xml_add(xmlNode *node, const char *name, const char *value) { bool dirty = FALSE; xmlAttr *attr = NULL; CRM_CHECK(node != NULL, return NULL); CRM_CHECK(name != NULL, return NULL); if (value == NULL) { return NULL; } #if XML_PARANOIA_CHECKS { const char *old_value = NULL; old_value = crm_element_value(node, name); /* Could be re-setting the same value */ CRM_CHECK(old_value != value, crm_err("Cannot reset %s with crm_xml_add(%s)", name, value); return value); } #endif if (pcmk__tracking_xml_changes(node, FALSE)) { const char *old = crm_element_value(node, name); if (old == NULL || value == NULL || strcmp(old, value) != 0) { dirty = TRUE; } } if (dirty && (pcmk__check_acl(node, name, xpf_acl_create) == FALSE)) { crm_trace("Cannot add %s=%s to %s", name, value, node->name); return NULL; } attr = xmlSetProp(node, (const xmlChar *)name, (const xmlChar *)value); if (dirty) { pcmk__mark_xml_attr_dirty(attr); } CRM_CHECK(attr && attr->children && attr->children->content, return NULL); return (char *)attr->children->content; } /*! * \brief Replace an XML attribute with specified name and (possibly NULL) value * * \param[in,out] node XML node to modify * \param[in] name Attribute name to set * \param[in] value Attribute value to set * * \return New value on success, \c NULL otherwise * \note This does nothing if node or name is \c NULL or empty. */ const char * crm_xml_replace(xmlNode *node, const char *name, const char *value) { bool dirty = FALSE; xmlAttr *attr = NULL; const char *old_value = NULL; CRM_CHECK(node != NULL, return NULL); CRM_CHECK(name != NULL && name[0] != 0, return NULL); old_value = crm_element_value(node, name); /* Could be re-setting the same value */ CRM_CHECK(old_value != value, return value); if (pcmk__check_acl(node, name, xpf_acl_write) == FALSE) { /* Create a fake object linked to doc->_private instead? */ crm_trace("Cannot replace %s=%s to %s", name, value, node->name); return NULL; } else if (old_value && !value) { xml_remove_prop(node, name); return NULL; } if (pcmk__tracking_xml_changes(node, FALSE)) { if (!old_value || !value || !strcmp(old_value, value)) { dirty = TRUE; } } attr = xmlSetProp(node, (const xmlChar *)name, (const xmlChar *)value); if (dirty) { pcmk__mark_xml_attr_dirty(attr); } CRM_CHECK(attr && attr->children && attr->children->content, return NULL); return (char *) attr->children->content; } /*! * \brief Create an XML attribute with specified name and integer value * * This is like \c crm_xml_add() but taking an integer value. * * \param[in,out] node XML node to modify * \param[in] name Attribute name to set * \param[in] value Attribute value to set * * \return New value as string on success, \c NULL otherwise * \note This does nothing if node or name are \c NULL or empty. */ const char * crm_xml_add_int(xmlNode *node, const char *name, int value) { char *number = crm_itoa(value); const char *added = crm_xml_add(node, name, number); free(number); return added; } /*! * \brief Create an XML attribute with specified name and unsigned value * * This is like \c crm_xml_add() but taking a guint value. * * \param[in,out] node XML node to modify * \param[in] name Attribute name to set * \param[in] ms Attribute value to set * * \return New value as string on success, \c NULL otherwise * \note This does nothing if node or name are \c NULL or empty. */ const char * crm_xml_add_ms(xmlNode *node, const char *name, guint ms) { char *number = crm_strdup_printf("%u", ms); const char *added = crm_xml_add(node, name, number); free(number); return added; } /*! * \brief Retrieve the value of an XML attribute * * \param[in] data XML node to check * \param[in] name Attribute name to check * * \return Value of specified attribute (may be \c NULL) */ const char * crm_element_value(const xmlNode *data, const char *name) { xmlAttr *attr = NULL; if (data == NULL) { crm_err("Couldn't find %s in NULL", name ? name : ""); CRM_LOG_ASSERT(data != NULL); return NULL; } else if (name == NULL) { crm_err("Couldn't find NULL in %s", crm_element_name(data)); return NULL; } /* The first argument to xmlHasProp() has always been const, * but libxml2 <2.9.2 didn't declare that, so cast it */ attr = xmlHasProp((xmlNode *) data, (const xmlChar *)name); if (!attr || !attr->children) { return NULL; } return (const char *) attr->children->content; } /*! * \brief Retrieve the integer value of an XML attribute * * This is like \c crm_element_value() but returning the value as an integer. * * \param[in] data XML node to check * \param[in] name Attribute name to check * * \return Integer value of specified attribute on success, -1 otherwise */ int crm_element_value_int(const xmlNode *data, const char *name, int *dest) { const char *value = NULL; CRM_CHECK(dest != NULL, return -1); value = crm_element_value(data, name); if (value) { *dest = crm_int_helper(value, NULL); return 0; } return -1; } /*! * \brief Retrieve the millisecond value of an XML attribute * * This is like \c crm_element_value() but returning the value as a guint. * * \param[in] data XML node to check * \param[in] name Attribute name to check * \param[out] dest Where to store attribute value * * \return \c pcmk_ok on success, -1 otherwise */ int crm_element_value_ms(const xmlNode *data, const char *name, guint *dest) { const char *value = NULL; CRM_CHECK(dest != NULL, return -1); value = crm_element_value(data, name); *dest = crm_parse_ms(value); return errno? -1 : 0; } /*! * \brief Retrieve the value of XML second/microsecond attributes as time * * This is like \c crm_element_value() but returning value as a struct timeval. * * \param[in] xml XML to parse * \param[in] name_sec Name of XML attribute for seconds * \param[in] name_usec Name of XML attribute for microseconds * \param[out] dest Where to store result * * \return \c pcmk_ok on success, -errno on error * \note Values default to 0 if XML or XML attribute does not exist */ int crm_element_value_timeval(const xmlNode *xml, const char *name_sec, const char *name_usec, struct timeval *dest) { const char *value_s = NULL; long long value_i = 0; CRM_CHECK(dest != NULL, return -EINVAL); dest->tv_sec = 0; dest->tv_usec = 0; if (xml == NULL) { return 0; } // Parse seconds value_s = crm_element_value(xml, name_sec); if (value_s) { value_i = crm_parse_ll(value_s, NULL); if (errno) { return -errno; } dest->tv_sec = (time_t) value_i; } // Parse microseconds value_s = crm_element_value(xml, name_usec); if (value_s) { value_i = crm_parse_ll(value_s, NULL); if (errno) { return -errno; } dest->tv_usec = (suseconds_t) value_i; } return 0; } /*! * \brief Retrieve a copy of the value of an XML attribute * * This is like \c crm_element_value() but allocating new memory for the result. * * \param[in] data XML node to check * \param[in] name Attribute name to check * * \return Value of specified attribute (may be \c NULL) * \note The caller is responsible for freeing the result. */ char * crm_element_value_copy(const xmlNode *data, const char *name) { char *value_copy = NULL; const char *value = crm_element_value(data, name); if (value != NULL) { value_copy = strdup(value); } return value_copy; } /*! * \brief Add hash table entry to XML as (possibly legacy) name/value * * Suitable for \c g_hash_table_foreach(), this function takes a hash table key * and value, with an XML node passed as user data, and adds an XML attribute * with the specified name and value if it does not already exist. If the key * name starts with a digit, this will instead add a \ child to the XML (for legacy compatibility with heartbeat). * * \param[in] key Key of hash table entry * \param[in] value Value of hash table entry * \param[in] user_data XML node */ void hash2smartfield(gpointer key, gpointer value, gpointer user_data) { const char *name = key; const char *s_value = value; xmlNode *xml_node = user_data; if (isdigit(name[0])) { xmlNode *tmp = create_xml_node(xml_node, XML_TAG_PARAM); crm_xml_add(tmp, XML_NVPAIR_ATTR_NAME, name); crm_xml_add(tmp, XML_NVPAIR_ATTR_VALUE, s_value); } else if (crm_element_value(xml_node, name) == NULL) { crm_xml_add(xml_node, name, s_value); crm_trace("dumped: %s=%s", name, s_value); } else { crm_trace("duplicate: %s=%s", name, s_value); } } /*! * \brief Set XML attribute based on hash table entry * * Suitable for \c g_hash_table_foreach(), this function takes a hash table key * and value, with an XML node passed as user data, and adds an XML attribute * with the specified name and value if it does not already exist. * * \param[in] key Key of hash table entry * \param[in] value Value of hash table entry * \param[in] user_data XML node */ void hash2field(gpointer key, gpointer value, gpointer user_data) { const char *name = key; const char *s_value = value; xmlNode *xml_node = user_data; if (crm_element_value(xml_node, name) == NULL) { crm_xml_add(xml_node, name, s_value); } else { crm_trace("duplicate: %s=%s", name, s_value); } } /*! * \brief Set XML attribute based on hash table entry, as meta-attribute name * * Suitable for \c g_hash_table_foreach(), this function takes a hash table key * and value, with an XML node passed as user data, and adds an XML attribute * with the meta-attribute version of the specified name and value if it does * not already exist and if the name does not appear to be cluster-internal. * * \param[in] key Key of hash table entry * \param[in] value Value of hash table entry * \param[in] user_data XML node */ void hash2metafield(gpointer key, gpointer value, gpointer user_data) { char *crm_name = NULL; if (key == NULL || value == NULL) { return; } /* Filter out cluster-generated attributes that contain a '#' or ':' * (like fail-count and last-failure). */ for (crm_name = key; *crm_name; ++crm_name) { if ((*crm_name == '#') || (*crm_name == ':')) { return; } } crm_name = crm_meta_name(key); hash2field(crm_name, value, user_data); free(crm_name); } // nvpair handling /*! * \brief Create an XML name/value pair * * \param[in] parent If not \c NULL, make new XML node a child of this one * \param[in] id If not \c NULL, use this as ID (otherwise auto-generate) * \param[in] name Name to use * \param[in] value Value to use * * \return New XML object on success, \c NULL otherwise */ xmlNode * crm_create_nvpair_xml(xmlNode *parent, const char *id, const char *name, const char *value) { xmlNode *nvp; /* id can be NULL so we auto-generate one, and name can be NULL if this * will be used to delete a name/value pair by ID, but both can't be NULL */ CRM_CHECK(id || name, return NULL); nvp = create_xml_node(parent, XML_CIB_TAG_NVPAIR); CRM_CHECK(nvp, return NULL); if (id) { crm_xml_add(nvp, XML_ATTR_ID, id); } else { const char *parent_id = ID(parent); crm_xml_set_id(nvp, "%s-%s", (parent_id? parent_id : XML_CIB_TAG_NVPAIR), name); } crm_xml_add(nvp, XML_NVPAIR_ATTR_NAME, name); crm_xml_add(nvp, XML_NVPAIR_ATTR_VALUE, value); return nvp; } /*! * \brief Add XML nvpair element based on hash table entry * * Suitable for \c g_hash_table_foreach(), this function takes a hash table key * and value, with an XML node passed as the user data, and adds an \c nvpair * XML element with the specified name and value. * * \param[in] key Key of hash table entry * \param[in] value Value of hash table entry * \param[in] user_data XML node */ void hash2nvpair(gpointer key, gpointer value, gpointer user_data) { const char *name = key; const char *s_value = value; xmlNode *xml_node = user_data; crm_create_nvpair_xml(xml_node, name, name, s_value); crm_trace("dumped: name=%s value=%s", name, s_value); } /*! * \brief Retrieve XML attributes as a hash table * * Given an XML element, this will look for any \ element child, * creating a hash table of (newly allocated string) name/value pairs taken * first from the attributes element's NAME=VALUE XML attributes, and then * from any \ children of attributes. * * \param[in] XML node to parse * * \return Hash table with name/value pairs * \note It is the caller's responsibility to free the result using * \c g_hash_table_destroy(). */ GHashTable * xml2list(xmlNode *parent) { xmlNode *child = NULL; xmlAttrPtr pIter = NULL; xmlNode *nvpair_list = NULL; GHashTable *nvpair_hash = crm_str_table_new(); CRM_CHECK(parent != NULL, return nvpair_hash); nvpair_list = find_xml_node(parent, XML_TAG_ATTRS, FALSE); if (nvpair_list == NULL) { crm_trace("No attributes in %s", crm_element_name(parent)); crm_log_xml_trace(parent, "No attributes for resource op"); } crm_log_xml_trace(nvpair_list, "Unpacking"); for (pIter = pcmk__first_xml_attr(nvpair_list); pIter != NULL; pIter = pIter->next) { const char *p_name = (const char *)pIter->name; const char *p_value = pcmk__xml_attr_value(pIter); crm_trace("Added %s=%s", p_name, p_value); g_hash_table_insert(nvpair_hash, strdup(p_name), strdup(p_value)); } for (child = __xml_first_child(nvpair_list); child != NULL; child = __xml_next(child)) { if (strcmp((const char *)child->name, XML_TAG_PARAM) == 0) { const char *key = crm_element_value(child, XML_NVPAIR_ATTR_NAME); const char *value = crm_element_value(child, XML_NVPAIR_ATTR_VALUE); crm_trace("Added %s=%s", key, value); if (key != NULL && value != NULL) { g_hash_table_insert(nvpair_hash, strdup(key), strdup(value)); } } } return nvpair_hash; } diff --git a/lib/common/xml.c b/lib/common/xml.c index 657458dca1..8b95ec8e36 100644 --- a/lib/common/xml.c +++ b/lib/common/xml.c @@ -1,4232 +1,4232 @@ /* * Copyright 2004-2019 Andrew Beekhof * * This source code is licensed under the GNU Lesser General Public License * version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY. */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include /* CRM_XML_LOG_BASE */ #include "crmcommon_private.h" #if HAVE_BZLIB_H # include #endif #define XML_BUFFER_SIZE 4096 #define XML_PARSER_DEBUG 0 typedef struct { int found; const char *string; } filter_t; typedef struct xml_deleted_obj_s { char *path; int position; } xml_deleted_obj_t; /* *INDENT-OFF* */ static filter_t filter[] = { { 0, XML_ATTR_ORIGIN }, { 0, XML_CIB_ATTR_WRITTEN }, { 0, XML_ATTR_UPDATE_ORIG }, { 0, XML_ATTR_UPDATE_CLIENT }, { 0, XML_ATTR_UPDATE_USER }, }; /* *INDENT-ON* */ static xmlNode *subtract_xml_comment(xmlNode * parent, xmlNode * left, xmlNode * right, gboolean * changed); static xmlNode *find_xml_comment(xmlNode * root, xmlNode * search_comment, gboolean exact); static int add_xml_comment(xmlNode * parent, xmlNode * target, xmlNode * update); #define CHUNK_SIZE 1024 bool pcmk__tracking_xml_changes(xmlNode *xml, bool lazy) { if(xml == NULL || xml->doc == NULL || xml->doc->_private == NULL) { return FALSE; } else if(is_not_set(((xml_private_t *)xml->doc->_private)->flags, xpf_tracking)) { return FALSE; } else if (lazy && is_not_set(((xml_private_t *)xml->doc->_private)->flags, xpf_lazy)) { return FALSE; } return TRUE; } #define buffer_print(buffer, max, offset, fmt, args...) do { \ int rc = (max); \ if(buffer) { \ rc = snprintf((buffer) + (offset), (max) - (offset), fmt, ##args); \ } \ if(buffer && rc < 0) { \ crm_perror(LOG_ERR, "snprintf failed at offset %d", offset); \ (buffer)[(offset)] = 0; \ break; \ } else if(rc >= ((max) - (offset))) { \ char *tmp = NULL; \ (max) = QB_MAX(CHUNK_SIZE, (max) * 2); \ tmp = realloc_safe((buffer), (max)); \ CRM_ASSERT(tmp); \ (buffer) = tmp; \ } else { \ offset += rc; \ break; \ } \ } while(1); static void insert_prefix(int options, char **buffer, int *offset, int *max, int depth) { if (options & xml_log_option_formatted) { size_t spaces = 2 * depth; if ((*buffer) == NULL || spaces >= ((*max) - (*offset))) { (*max) = QB_MAX(CHUNK_SIZE, (*max) * 2); (*buffer) = realloc_safe((*buffer), (*max)); } memset((*buffer) + (*offset), ' ', spaces); (*offset) += spaces; } } static void set_parent_flag(xmlNode *xml, long flag) { for(; xml; xml = xml->parent) { xml_private_t *p = xml->_private; if(p == NULL) { /* During calls to xmlDocCopyNode(), _private will be unset for parent nodes */ } else { p->flags |= flag; /* crm_trace("Setting flag %x due to %s[@id=%s]", flag, xml->name, ID(xml)); */ } } } void pcmk__set_xml_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_private_t *p = xml->doc->_private; p->flags |= flag; /* crm_trace("Setting flag %x due to %s[@id=%s]", flag, xml->name, ID(xml)); */ } } static void __xml_node_dirty(xmlNode *xml) { pcmk__set_xml_flag(xml, xpf_dirty); set_parent_flag(xml, xpf_dirty); } static void __xml_node_clean(xmlNode *xml) { xmlNode *cIter = NULL; xml_private_t *p = xml->_private; if(p) { p->flags = 0; } for (cIter = __xml_first_child(xml); cIter != NULL; cIter = __xml_next(cIter)) { __xml_node_clean(cIter); } } static void crm_node_created(xmlNode *xml) { xmlNode *cIter = NULL; xml_private_t *p = xml->_private; if(p && pcmk__tracking_xml_changes(xml, FALSE)) { if(is_not_set(p->flags, xpf_created)) { p->flags |= xpf_created; __xml_node_dirty(xml); } for (cIter = __xml_first_child(xml); cIter != NULL; cIter = __xml_next(cIter)) { crm_node_created(cIter); } } } void pcmk__mark_xml_attr_dirty(xmlAttr *a) { xmlNode *parent = a->parent; xml_private_t *p = NULL; p = a->_private; p->flags |= (xpf_dirty|xpf_modified); p->flags = (p->flags & ~xpf_deleted); /* crm_trace("Setting flag %x due to %s[@id=%s, @%s=%s]", */ /* xpf_dirty, parent?parent->name:NULL, ID(parent), a->name, a->children->content); */ __xml_node_dirty(parent); } int get_tag_name(const char *input, size_t offset, size_t max); int get_attr_name(const char *input, size_t offset, size_t max); int get_attr_value(const char *input, size_t offset, size_t max); gboolean can_prune_leaf(xmlNode * xml_node); static int add_xml_object(xmlNode * parent, xmlNode * target, xmlNode * update, gboolean as_diff); #define XML_PRIVATE_MAGIC (long) 0x81726354 static void __xml_deleted_obj_free(void *data) { if(data) { xml_deleted_obj_t *deleted_obj = data; free(deleted_obj->path); free(deleted_obj); } } static void __xml_private_clean(xml_private_t *p) { if(p) { CRM_ASSERT(p->check == XML_PRIVATE_MAGIC); free(p->user); p->user = NULL; if(p->acls) { pcmk__free_acls(p->acls); p->acls = NULL; } if(p->deleted_objs) { g_list_free_full(p->deleted_objs, __xml_deleted_obj_free); p->deleted_objs = NULL; } } } static void __xml_private_free(xml_private_t *p) { __xml_private_clean(p); free(p); } static void pcmkDeregisterNode(xmlNodePtr node) { /* need to explicitly avoid our custom _private field cleanup when called from internal XSLT cleanup (xsltApplyStylesheetInternal -> xsltFreeTransformContext -> xsltFreeRVTs -> xmlFreeDoc) onto result tree fragments, represented as standalone documents with otherwise infeasible space-prefixed name (xsltInternals.h: XSLT_MARK_RES_TREE_FRAG) and carrying it's own load at _private field -- later assert on the XML_PRIVATE_MAGIC would explode */ if (node->type != XML_DOCUMENT_NODE || node->name == NULL || node->name[0] != ' ') { __xml_private_free(node->_private); } } static void pcmkRegisterNode(xmlNodePtr node) { xml_private_t *p = NULL; switch(node->type) { case XML_ELEMENT_NODE: case XML_DOCUMENT_NODE: case XML_ATTRIBUTE_NODE: case XML_COMMENT_NODE: p = calloc(1, sizeof(xml_private_t)); p->check = XML_PRIVATE_MAGIC; /* Flags will be reset if necessary when tracking is enabled */ p->flags |= (xpf_dirty|xpf_created); node->_private = p; 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; } if(p && 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__set_xml_flag(node, xpf_dirty); __xml_node_dirty(node); } } 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_flag(xml, xpf_tracking); if(enforce_acls) { if(acl_source == NULL) { acl_source = xml; } pcmk__set_xml_flag(xml, xpf_acl_enabled); pcmk__unpack_acl(acl_source, xml, user); pcmk__apply_acl(xml); } } bool xml_tracking_changes(xmlNode * xml) { if(xml == NULL) { return FALSE; } else if(is_set(((xml_private_t *)xml->doc->_private)->flags, xpf_tracking)) { return TRUE; } return FALSE; } bool xml_document_dirty(xmlNode *xml) { if(xml != NULL && xml->doc && xml->doc->_private) { xml_private_t *doc = xml->doc->_private; return is_set(doc->flags, xpf_dirty); } return FALSE; } /* */ static int __xml_offset(xmlNode *xml) { int position = 0; xmlNode *cIter = NULL; for(cIter = xml; cIter->prev; cIter = cIter->prev) { xml_private_t *p = ((xmlNode*)cIter->prev)->_private; if(is_not_set(p->flags, xpf_skip)) { position++; } } return position; } static int __xml_offset_no_deletions(xmlNode *xml) { int position = 0; xmlNode *cIter = NULL; for(cIter = xml; cIter->prev; cIter = cIter->prev) { xml_private_t *p = ((xmlNode*)cIter->prev)->_private; if(is_not_set(p->flags, xpf_deleted)) { position++; } } return position; } static void __xml_build_changes(xmlNode * xml, xmlNode *patchset) { xmlNode *cIter = NULL; xmlAttr *pIter = NULL; xmlNode *change = NULL; xml_private_t *p = xml->_private; if(patchset && is_set(p->flags, xpf_created)) { int offset = 0; char buffer[XML_BUFFER_SIZE]; if (pcmk__element_xpath(NULL, xml->parent, buffer, offset, sizeof(buffer)) > 0) { int position = __xml_offset_no_deletions(xml); change = create_xml_node(patchset, XML_DIFF_CHANGE); crm_xml_add(change, XML_DIFF_OP, "create"); crm_xml_add(change, XML_DIFF_PATH, buffer); crm_xml_add_int(change, XML_DIFF_POSITION, position); add_node_copy(change, xml); } return; } for (pIter = pcmk__first_xml_attr(xml); pIter != NULL; pIter = pIter->next) { xmlNode *attr = NULL; p = pIter->_private; if(is_not_set(p->flags, xpf_deleted) && is_not_set(p->flags, xpf_dirty)) { continue; } if(change == NULL) { int offset = 0; char buffer[XML_BUFFER_SIZE]; if (pcmk__element_xpath(NULL, xml, buffer, offset, sizeof(buffer)) > 0) { change = create_xml_node(patchset, XML_DIFF_CHANGE); crm_xml_add(change, XML_DIFF_OP, "modify"); crm_xml_add(change, XML_DIFF_PATH, buffer); change = create_xml_node(change, XML_DIFF_LIST); } } attr = create_xml_node(change, XML_DIFF_ATTR); crm_xml_add(attr, XML_NVPAIR_ATTR_NAME, (const char *)pIter->name); if(p->flags & xpf_deleted) { crm_xml_add(attr, XML_DIFF_OP, "unset"); } else { const char *value = crm_element_value(xml, (const char *)pIter->name); crm_xml_add(attr, XML_DIFF_OP, "set"); crm_xml_add(attr, XML_NVPAIR_ATTR_VALUE, value); } } if(change) { xmlNode *result = NULL; change = create_xml_node(change->parent, XML_DIFF_RESULT); result = create_xml_node(change, (const char *)xml->name); for (pIter = pcmk__first_xml_attr(xml); pIter != NULL; pIter = pIter->next) { const char *value = crm_element_value(xml, (const char *)pIter->name); p = pIter->_private; if (is_not_set(p->flags, xpf_deleted)) { crm_xml_add(result, (const char *)pIter->name, value); } } } for (cIter = __xml_first_child(xml); cIter != NULL; cIter = __xml_next(cIter)) { __xml_build_changes(cIter, patchset); } p = xml->_private; if(patchset && is_set(p->flags, xpf_moved)) { int offset = 0; char buffer[XML_BUFFER_SIZE]; crm_trace("%s.%s moved to position %d", xml->name, ID(xml), __xml_offset(xml)); if (pcmk__element_xpath(NULL, xml, buffer, offset, sizeof(buffer)) > 0) { change = create_xml_node(patchset, XML_DIFF_CHANGE); crm_xml_add(change, XML_DIFF_OP, "move"); crm_xml_add(change, XML_DIFF_PATH, buffer); crm_xml_add_int(change, XML_DIFF_POSITION, __xml_offset_no_deletions(xml)); } } } static void __xml_accept_changes(xmlNode * xml) { xmlNode *cIter = NULL; xmlAttr *pIter = NULL; xml_private_t *p = xml->_private; p->flags = xpf_none; pIter = pcmk__first_xml_attr(xml); while (pIter != NULL) { const xmlChar *name = pIter->name; p = pIter->_private; pIter = pIter->next; if(p->flags & xpf_deleted) { xml_remove_prop(xml, (const char *)name); } else { p->flags = xpf_none; } } for (cIter = __xml_first_child(xml); cIter != NULL; cIter = __xml_next(cIter)) { __xml_accept_changes(cIter); } } static bool is_config_change(xmlNode *xml) { GListPtr gIter = NULL; xml_private_t *p = NULL; xmlNode *config = first_named_child(xml, XML_CIB_TAG_CONFIGURATION); if(config) { p = config->_private; } if(p && is_set(p->flags, xpf_dirty)) { return TRUE; } if(xml->doc && xml->doc->_private) { p = xml->doc->_private; for(gIter = p->deleted_objs; gIter; gIter = gIter->next) { xml_deleted_obj_t *deleted_obj = gIter->data; if(strstr(deleted_obj->path, "/"XML_TAG_CIB"/"XML_CIB_TAG_CONFIGURATION) != NULL) { return TRUE; } } } return FALSE; } static void xml_repair_v1_diff(xmlNode * last, xmlNode * next, xmlNode * local_diff, gboolean changed) { int lpc = 0; xmlNode *cib = NULL; xmlNode *diff_child = NULL; const char *tag = NULL; const char *vfields[] = { XML_ATTR_GENERATION_ADMIN, XML_ATTR_GENERATION, XML_ATTR_NUMUPDATES, }; if (local_diff == NULL) { crm_trace("Nothing to do"); return; } tag = "diff-removed"; diff_child = find_xml_node(local_diff, tag, FALSE); if (diff_child == NULL) { diff_child = create_xml_node(local_diff, tag); } tag = XML_TAG_CIB; cib = find_xml_node(diff_child, tag, FALSE); if (cib == NULL) { cib = create_xml_node(diff_child, tag); } for(lpc = 0; last && lpc < DIMOF(vfields); lpc++){ const char *value = crm_element_value(last, vfields[lpc]); crm_xml_add(diff_child, vfields[lpc], value); if(changed || lpc == 2) { crm_xml_add(cib, vfields[lpc], value); } } tag = "diff-added"; diff_child = find_xml_node(local_diff, tag, FALSE); if (diff_child == NULL) { diff_child = create_xml_node(local_diff, tag); } tag = XML_TAG_CIB; cib = find_xml_node(diff_child, tag, FALSE); if (cib == NULL) { cib = create_xml_node(diff_child, tag); } for(lpc = 0; next && lpc < DIMOF(vfields); lpc++){ const char *value = crm_element_value(next, vfields[lpc]); crm_xml_add(diff_child, vfields[lpc], value); } if (next) { xmlAttrPtr xIter = NULL; for (xIter = next->properties; xIter; xIter = xIter->next) { const char *p_name = (const char *)xIter->name; const char *p_value = crm_element_value(next, p_name); xmlSetProp(cib, (const xmlChar *)p_name, (const xmlChar *)p_value); } } crm_log_xml_explicit(local_diff, "Repaired-diff"); } static xmlNode * xml_create_patchset_v1(xmlNode *source, xmlNode *target, bool config, bool suppress) { xmlNode *patchset = diff_xml_object(source, target, suppress); if(patchset) { CRM_LOG_ASSERT(xml_document_dirty(target)); xml_repair_v1_diff(source, target, patchset, config); crm_xml_add(patchset, "format", "1"); } return patchset; } static xmlNode * xml_create_patchset_v2(xmlNode *source, xmlNode *target) { int lpc = 0; GListPtr gIter = NULL; xml_private_t *doc = NULL; xmlNode *v = NULL; xmlNode *version = NULL; xmlNode *patchset = NULL; const char *vfields[] = { XML_ATTR_GENERATION_ADMIN, XML_ATTR_GENERATION, XML_ATTR_NUMUPDATES, }; CRM_ASSERT(target); if(xml_document_dirty(target) == FALSE) { return NULL; } CRM_ASSERT(target->doc); doc = target->doc->_private; patchset = create_xml_node(NULL, XML_TAG_DIFF); crm_xml_add_int(patchset, "format", 2); version = create_xml_node(patchset, XML_DIFF_VERSION); v = create_xml_node(version, XML_DIFF_VSOURCE); for(lpc = 0; lpc < DIMOF(vfields); lpc++){ const char *value = crm_element_value(source, vfields[lpc]); if(value == NULL) { value = "1"; } crm_xml_add(v, vfields[lpc], value); } v = create_xml_node(version, XML_DIFF_VTARGET); for(lpc = 0; lpc < DIMOF(vfields); lpc++){ const char *value = crm_element_value(target, vfields[lpc]); if(value == NULL) { value = "1"; } crm_xml_add(v, vfields[lpc], value); } for(gIter = doc->deleted_objs; gIter; gIter = gIter->next) { xml_deleted_obj_t *deleted_obj = gIter->data; xmlNode *change = create_xml_node(patchset, XML_DIFF_CHANGE); crm_xml_add(change, XML_DIFF_OP, "delete"); crm_xml_add(change, XML_DIFF_PATH, deleted_obj->path); if (deleted_obj->position >= 0) { crm_xml_add_int(change, XML_DIFF_POSITION, deleted_obj->position); } } __xml_build_changes(target, patchset); return patchset; } xmlNode * xml_create_patchset(int format, xmlNode *source, xmlNode *target, bool *config_changed, bool manage_version) { int counter = 0; bool config = FALSE; xmlNode *patch = NULL; const char *version = crm_element_value(source, XML_ATTR_CRM_VERSION); xml_acl_disable(target); if(xml_document_dirty(target) == FALSE) { crm_trace("No change %d", format); return NULL; /* No change */ } config = is_config_change(target); if(config_changed) { *config_changed = config; } if(manage_version && config) { crm_trace("Config changed %d", format); crm_xml_add(target, XML_ATTR_NUMUPDATES, "0"); crm_element_value_int(target, XML_ATTR_GENERATION, &counter); crm_xml_add_int(target, XML_ATTR_GENERATION, counter+1); } else if(manage_version) { crm_element_value_int(target, XML_ATTR_NUMUPDATES, &counter); crm_trace("Status changed %d - %d %s", format, counter, crm_element_value(source, XML_ATTR_NUMUPDATES)); crm_xml_add_int(target, XML_ATTR_NUMUPDATES, counter+1); } if(format == 0) { if (compare_version("3.0.8", version) < 0) { format = 2; } else { format = 1; } crm_trace("Using patch format %d for version: %s", format, version); } switch(format) { case 1: patch = xml_create_patchset_v1(source, target, config, FALSE); break; case 2: patch = xml_create_patchset_v2(source, target); break; default: crm_err("Unknown patch format: %d", format); return NULL; } return patch; } void patchset_process_digest(xmlNode *patch, xmlNode *source, xmlNode *target, bool with_digest) { int format = 1; const char *version = NULL; char *digest = NULL; if (patch == NULL || source == NULL || target == NULL) { return; } /* NOTE: We should always call xml_accept_changes() before calculating digest. */ /* Otherwise, with an on-tracking dirty target, we could get a wrong digest. */ CRM_LOG_ASSERT(xml_document_dirty(target) == FALSE); crm_element_value_int(patch, "format", &format); if (format > 1 && with_digest == FALSE) { return; } version = crm_element_value(source, XML_ATTR_CRM_VERSION); digest = calculate_xml_versioned_digest(target, FALSE, TRUE, version); crm_xml_add(patch, XML_ATTR_DIGEST, digest); free(digest); return; } static void __xml_log_element(int log_level, const char *file, const char *function, int line, const char *prefix, xmlNode * data, int depth, int options); void xml_log_patchset(uint8_t log_level, const char *function, xmlNode * patchset) { int format = 1; xmlNode *child = NULL; xmlNode *added = NULL; xmlNode *removed = NULL; gboolean is_first = TRUE; int add[] = { 0, 0, 0 }; int del[] = { 0, 0, 0 }; const char *fmt = NULL; const char *digest = NULL; int options = xml_log_option_formatted; static struct qb_log_callsite *patchset_cs = NULL; if (patchset_cs == NULL) { patchset_cs = qb_log_callsite_get(function, __FILE__, "xml-patchset", log_level, __LINE__, 0); } if (patchset == NULL) { crm_trace("Empty patch"); return; } else if (log_level == 0) { /* Log to stdout */ } else if (crm_is_callsite_active(patchset_cs, log_level, 0) == FALSE) { return; } xml_patch_versions(patchset, add, del); fmt = crm_element_value(patchset, "format"); digest = crm_element_value(patchset, XML_ATTR_DIGEST); if (add[2] != del[2] || add[1] != del[1] || add[0] != del[0]) { do_crm_log_alias(log_level, __FILE__, function, __LINE__, "Diff: --- %d.%d.%d %s", del[0], del[1], del[2], fmt); do_crm_log_alias(log_level, __FILE__, function, __LINE__, "Diff: +++ %d.%d.%d %s", add[0], add[1], add[2], digest); } else if (patchset != NULL && (add[0] || add[1] || add[2])) { do_crm_log_alias(log_level, __FILE__, function, __LINE__, "%s: Local-only Change: %d.%d.%d", function ? function : "", add[0], add[1], add[2]); } crm_element_value_int(patchset, "format", &format); if(format == 2) { xmlNode *change = NULL; for (change = __xml_first_child(patchset); change != NULL; change = __xml_next(change)) { const char *op = crm_element_value(change, XML_DIFF_OP); const char *xpath = crm_element_value(change, XML_DIFF_PATH); if(op == NULL) { } else if(strcmp(op, "create") == 0) { int lpc = 0, max = 0; char *prefix = crm_strdup_printf("++ %s: ", xpath); max = strlen(prefix); __xml_log_element(log_level, __FILE__, function, __LINE__, prefix, change->children, 0, xml_log_option_formatted|xml_log_option_open); for(lpc = 2; lpc < max; lpc++) { prefix[lpc] = ' '; } __xml_log_element(log_level, __FILE__, function, __LINE__, prefix, change->children, 0, xml_log_option_formatted|xml_log_option_close|xml_log_option_children); free(prefix); } else if(strcmp(op, "move") == 0) { do_crm_log_alias(log_level, __FILE__, function, __LINE__, "+~ %s moved to offset %s", xpath, crm_element_value(change, XML_DIFF_POSITION)); } else if(strcmp(op, "modify") == 0) { xmlNode *clist = first_named_child(change, XML_DIFF_LIST); char buffer_set[XML_BUFFER_SIZE]; char buffer_unset[XML_BUFFER_SIZE]; int o_set = 0; int o_unset = 0; buffer_set[0] = 0; buffer_unset[0] = 0; for (child = __xml_first_child(clist); child != NULL; child = __xml_next(child)) { const char *name = crm_element_value(child, "name"); op = crm_element_value(child, XML_DIFF_OP); if(op == NULL) { } else if(strcmp(op, "set") == 0) { const char *value = crm_element_value(child, "value"); if(o_set > 0) { o_set += snprintf(buffer_set + o_set, XML_BUFFER_SIZE - o_set, ", "); } o_set += snprintf(buffer_set + o_set, XML_BUFFER_SIZE - o_set, "@%s=%s", name, value); } else if(strcmp(op, "unset") == 0) { if(o_unset > 0) { o_unset += snprintf(buffer_unset + o_unset, XML_BUFFER_SIZE - o_unset, ", "); } o_unset += snprintf(buffer_unset + o_unset, XML_BUFFER_SIZE - o_unset, "@%s", name); } } if(o_set) { do_crm_log_alias(log_level, __FILE__, function, __LINE__, "+ %s: %s", xpath, buffer_set); } if(o_unset) { do_crm_log_alias(log_level, __FILE__, function, __LINE__, "-- %s: %s", xpath, buffer_unset); } } else if(strcmp(op, "delete") == 0) { int position = -1; crm_element_value_int(change, XML_DIFF_POSITION, &position); if (position >= 0) { do_crm_log_alias(log_level, __FILE__, function, __LINE__, "-- %s (%d)", xpath, position); } else { do_crm_log_alias(log_level, __FILE__, function, __LINE__, "-- %s", xpath); } } } return; } if (log_level < LOG_DEBUG || function == NULL) { options |= xml_log_option_diff_short; } removed = find_xml_node(patchset, "diff-removed", FALSE); for (child = __xml_first_child(removed); child != NULL; child = __xml_next(child)) { log_data_element(log_level, __FILE__, function, __LINE__, "- ", child, 0, options | xml_log_option_diff_minus); if (is_first) { is_first = FALSE; } else { do_crm_log_alias(log_level, __FILE__, function, __LINE__, " --- "); } } is_first = TRUE; added = find_xml_node(patchset, "diff-added", FALSE); for (child = __xml_first_child(added); child != NULL; child = __xml_next(child)) { log_data_element(log_level, __FILE__, function, __LINE__, "+ ", child, 0, options | xml_log_option_diff_plus); if (is_first) { is_first = FALSE; } else { do_crm_log_alias(log_level, __FILE__, function, __LINE__, " +++ "); } } } void xml_log_changes(uint8_t log_level, const char *function, xmlNode * xml) { GListPtr gIter = NULL; xml_private_t *doc = NULL; CRM_ASSERT(xml); CRM_ASSERT(xml->doc); doc = xml->doc->_private; if(is_not_set(doc->flags, xpf_dirty)) { return; } for(gIter = doc->deleted_objs; gIter; gIter = gIter->next) { xml_deleted_obj_t *deleted_obj = gIter->data; if (deleted_obj->position >= 0) { do_crm_log_alias(log_level, __FILE__, function, __LINE__, "-- %s (%d)", deleted_obj->path, deleted_obj->position); } else { do_crm_log_alias(log_level, __FILE__, function, __LINE__, "-- %s", deleted_obj->path); } } log_data_element(log_level, __FILE__, function, __LINE__, "+ ", xml, 0, xml_log_option_formatted|xml_log_option_dirty_add); } void xml_accept_changes(xmlNode * xml) { xmlNode *top = NULL; xml_private_t *doc = NULL; if(xml == NULL) { return; } crm_trace("Accepting changes to %p", xml); doc = xml->doc->_private; top = xmlDocGetRootElement(xml->doc); __xml_private_clean(xml->doc->_private); if(is_not_set(doc->flags, xpf_dirty)) { doc->flags = xpf_none; return; } doc->flags = xpf_none; __xml_accept_changes(top); } static xmlNode * find_element(xmlNode *haystack, xmlNode *needle, gboolean exact) { CRM_CHECK(needle != NULL, return NULL); return (needle->type == XML_COMMENT_NODE)? find_xml_comment(haystack, needle, exact) : find_entity(haystack, crm_element_name(needle), ID(needle)); } /* Simplified version for applying v1-style XML patches */ static void __subtract_xml_object(xmlNode * target, xmlNode * patch) { xmlNode *patch_child = NULL; xmlNode *cIter = NULL; xmlAttrPtr xIter = NULL; char *id = NULL; const char *name = NULL; const char *value = NULL; if (target == NULL || patch == NULL) { return; } if (target->type == XML_COMMENT_NODE) { gboolean dummy; subtract_xml_comment(target->parent, target, patch, &dummy); } name = crm_element_name(target); CRM_CHECK(name != NULL, return); CRM_CHECK(safe_str_eq(crm_element_name(target), crm_element_name(patch)), return); CRM_CHECK(safe_str_eq(ID(target), ID(patch)), return); /* check for XML_DIFF_MARKER in a child */ id = crm_element_value_copy(target, XML_ATTR_ID); value = crm_element_value(patch, XML_DIFF_MARKER); if (value != NULL && strcmp(value, "removed:top") == 0) { crm_trace("We are the root of the deletion: %s.id=%s", name, id); free_xml(target); free(id); return; } for (xIter = pcmk__first_xml_attr(patch); xIter != NULL; xIter = xIter->next) { const char *p_name = (const char *)xIter->name; /* Removing and then restoring the id field would change the ordering of properties */ if (safe_str_neq(p_name, XML_ATTR_ID)) { xml_remove_prop(target, p_name); } } /* changes to child objects */ cIter = __xml_first_child(target); while (cIter) { xmlNode *target_child = cIter; cIter = __xml_next(cIter); patch_child = find_element(patch, target_child, FALSE); __subtract_xml_object(target_child, patch_child); } free(id); } static void __add_xml_object(xmlNode * parent, xmlNode * target, xmlNode * patch) { xmlNode *patch_child = NULL; xmlNode *target_child = NULL; xmlAttrPtr xIter = NULL; const char *id = NULL; const char *name = NULL; const char *value = NULL; if (patch == NULL) { return; } else if (parent == NULL && target == NULL) { return; } /* check for XML_DIFF_MARKER in a child */ value = crm_element_value(patch, XML_DIFF_MARKER); if (target == NULL && value != NULL && strcmp(value, "added:top") == 0) { id = ID(patch); name = crm_element_name(patch); crm_trace("We are the root of the addition: %s.id=%s", name, id); add_node_copy(parent, patch); return; } else if(target == NULL) { id = ID(patch); name = crm_element_name(patch); crm_err("Could not locate: %s.id=%s", name, id); return; } if (target->type == XML_COMMENT_NODE) { add_xml_comment(parent, target, patch); } name = crm_element_name(target); CRM_CHECK(name != NULL, return); CRM_CHECK(safe_str_eq(crm_element_name(target), crm_element_name(patch)), return); CRM_CHECK(safe_str_eq(ID(target), ID(patch)), return); for (xIter = pcmk__first_xml_attr(patch); xIter != NULL; xIter = xIter->next) { const char *p_name = (const char *)xIter->name; const char *p_value = crm_element_value(patch, p_name); xml_remove_prop(target, p_name); /* Preserve the patch order */ crm_xml_add(target, p_name, p_value); } /* changes to child objects */ for (patch_child = __xml_first_child(patch); patch_child != NULL; patch_child = __xml_next(patch_child)) { target_child = find_element(target, patch_child, FALSE); __add_xml_object(target, target_child, patch_child); } } /*! * \internal * \brief Find additions or removals in a patch set * * \param[in] patchset XML of patch * \param[in] format Patch version * \param[in] added TRUE if looking for additions, FALSE if removals * \param[in,out] patch_node Will be set to node if found * * \return TRUE if format is valid, FALSE if invalid */ static bool find_patch_xml_node(xmlNode *patchset, int format, bool added, xmlNode **patch_node) { xmlNode *cib_node; const char *label; switch(format) { case 1: label = added? "diff-added" : "diff-removed"; *patch_node = find_xml_node(patchset, label, FALSE); cib_node = find_xml_node(*patch_node, "cib", FALSE); if (cib_node != NULL) { *patch_node = cib_node; } break; case 2: label = added? "target" : "source"; *patch_node = find_xml_node(patchset, "version", FALSE); *patch_node = find_xml_node(*patch_node, label, FALSE); break; default: crm_warn("Unknown patch format: %d", format); *patch_node = NULL; return FALSE; } return TRUE; } bool xml_patch_versions(xmlNode *patchset, int add[3], int del[3]) { int lpc = 0; int format = 1; xmlNode *tmp = NULL; const char *vfields[] = { XML_ATTR_GENERATION_ADMIN, XML_ATTR_GENERATION, XML_ATTR_NUMUPDATES, }; crm_element_value_int(patchset, "format", &format); /* Process removals */ if (!find_patch_xml_node(patchset, format, FALSE, &tmp)) { return -EINVAL; } if (tmp) { for(lpc = 0; lpc < DIMOF(vfields); lpc++) { crm_element_value_int(tmp, vfields[lpc], &(del[lpc])); crm_trace("Got %d for del[%s]", del[lpc], vfields[lpc]); } } /* Process additions */ if (!find_patch_xml_node(patchset, format, TRUE, &tmp)) { return -EINVAL; } if (tmp) { for(lpc = 0; lpc < DIMOF(vfields); lpc++) { crm_element_value_int(tmp, vfields[lpc], &(add[lpc])); crm_trace("Got %d for add[%s]", add[lpc], vfields[lpc]); } } return pcmk_ok; } static int xml_patch_version_check(xmlNode *xml, xmlNode *patchset, int format) { int lpc = 0; bool changed = FALSE; int this[] = { 0, 0, 0 }; int add[] = { 0, 0, 0 }; int del[] = { 0, 0, 0 }; const char *vfields[] = { XML_ATTR_GENERATION_ADMIN, XML_ATTR_GENERATION, XML_ATTR_NUMUPDATES, }; for(lpc = 0; lpc < DIMOF(vfields); lpc++) { crm_element_value_int(xml, vfields[lpc], &(this[lpc])); crm_trace("Got %d for this[%s]", this[lpc], vfields[lpc]); if (this[lpc] < 0) { this[lpc] = 0; } } /* Set some defaults in case nothing is present */ add[0] = this[0]; add[1] = this[1]; add[2] = this[2] + 1; for(lpc = 0; lpc < DIMOF(vfields); lpc++) { del[lpc] = this[lpc]; } xml_patch_versions(patchset, add, del); for(lpc = 0; lpc < DIMOF(vfields); lpc++) { if(this[lpc] < del[lpc]) { crm_debug("Current %s is too low (%d.%d.%d < %d.%d.%d --> %d.%d.%d)", vfields[lpc], this[0], this[1], this[2], del[0], del[1], del[2], add[0], add[1], add[2]); return -pcmk_err_diff_resync; } else if(this[lpc] > del[lpc]) { crm_info("Current %s is too high (%d.%d.%d > %d.%d.%d --> %d.%d.%d) %p", vfields[lpc], this[0], this[1], this[2], del[0], del[1], del[2], add[0], add[1], add[2], patchset); crm_log_xml_info(patchset, "OldPatch"); return -pcmk_err_old_data; } } for(lpc = 0; lpc < DIMOF(vfields); lpc++) { if(add[lpc] > del[lpc]) { changed = TRUE; } } if(changed == FALSE) { crm_notice("Versions did not change in patch %d.%d.%d", add[0], add[1], add[2]); return -pcmk_err_old_data; } crm_debug("Can apply patch %d.%d.%d to %d.%d.%d", add[0], add[1], add[2], this[0], this[1], this[2]); return pcmk_ok; } static int xml_apply_patchset_v1(xmlNode *xml, xmlNode *patchset) { int rc = pcmk_ok; int root_nodes_seen = 0; xmlNode *child_diff = NULL; xmlNode *added = find_xml_node(patchset, "diff-added", FALSE); xmlNode *removed = find_xml_node(patchset, "diff-removed", FALSE); xmlNode *old = copy_xml(xml); crm_trace("Subtraction Phase"); for (child_diff = __xml_first_child(removed); child_diff != NULL; child_diff = __xml_next(child_diff)) { CRM_CHECK(root_nodes_seen == 0, rc = FALSE); if (root_nodes_seen == 0) { __subtract_xml_object(xml, child_diff); } root_nodes_seen++; } if (root_nodes_seen > 1) { crm_err("(-) Diffs cannot contain more than one change set... saw %d", root_nodes_seen); rc = -ENOTUNIQ; } root_nodes_seen = 0; crm_trace("Addition Phase"); if (rc == pcmk_ok) { xmlNode *child_diff = NULL; for (child_diff = __xml_first_child(added); child_diff != NULL; child_diff = __xml_next(child_diff)) { CRM_CHECK(root_nodes_seen == 0, rc = FALSE); if (root_nodes_seen == 0) { __add_xml_object(NULL, xml, child_diff); } root_nodes_seen++; } } if (root_nodes_seen > 1) { crm_err("(+) Diffs cannot contain more than one change set... saw %d", root_nodes_seen); rc = -ENOTUNIQ; } purge_diff_markers(xml); /* Purge prior to checking the digest */ free_xml(old); return rc; } static xmlNode * __first_xml_child_match(xmlNode *parent, const char *name, const char *id, int position) { xmlNode *cIter = NULL; for (cIter = __xml_first_child(parent); cIter != NULL; cIter = __xml_next(cIter)) { if(strcmp((const char *)cIter->name, name) != 0) { continue; } else if(id) { const char *cid = ID(cIter); if(cid == NULL || strcmp(cid, id) != 0) { continue; } } /* The "position" makes sense only for XML comments for now */ if (cIter->type == XML_COMMENT_NODE && position >= 0 && __xml_offset(cIter) != position) { continue; } return cIter; } return NULL; } /*! * \internal * \brief Simplified, more efficient alternative to get_xpath_object() * * \param[in] top Root of XML to search * \param[in] key Search xpath * \param[in] target_position If deleting, where to delete * * \return XML child matching xpath if found, NULL otherwise * * \note This only works on simplified xpaths found in v2 patchset diffs, * i.e. the only allowed search predicate is [@id='XXX']. */ static xmlNode * __xml_find_path(xmlNode *top, const char *key, int target_position) { xmlNode *target = (xmlNode*) top->doc; const char *current = key; char *section; char *remainder; char *id; char *tag; char *path = NULL; int rc; size_t key_len; CRM_CHECK(key != NULL, return NULL); key_len = strlen(key); /* These are scanned from key after a slash, so they can't be bigger * than key_len - 1 characters plus a null terminator. */ remainder = calloc(key_len, sizeof(char)); CRM_ASSERT(remainder != NULL); section = calloc(key_len, sizeof(char)); CRM_ASSERT(section != NULL); id = calloc(key_len, sizeof(char)); CRM_ASSERT(id != NULL); tag = calloc(key_len, sizeof(char)); CRM_ASSERT(tag != NULL); do { // Look for /NEXT_COMPONENT/REMAINING_COMPONENTS rc = sscanf(current, "/%[^/]%s", section, remainder); if (rc > 0) { // Separate FIRST_COMPONENT into TAG[@id='ID'] int f = sscanf(section, "%[^[][@id='%[^']", tag, id); int current_position = -1; /* The target position is for the final component tag, so only use * it if there is nothing left to search after this component. */ if ((rc == 1) && (target_position >= 0)) { current_position = target_position; } switch (f) { case 1: target = __first_xml_child_match(target, tag, NULL, current_position); break; case 2: target = __first_xml_child_match(target, tag, id, current_position); break; default: // This should not be possible target = NULL; break; } current = remainder; } // Continue if something remains to search, and we've matched so far } while ((rc == 2) && target); if (target) { crm_trace("Found %s for %s", (path = (char *) xmlGetNodePath(target)), key); free(path); } else { crm_debug("No match for %s", key); } free(remainder); free(section); free(tag); free(id); return target; } static int xml_apply_patchset_v2(xmlNode *xml, xmlNode *patchset) { int rc = pcmk_ok; xmlNode *change = NULL; for (change = __xml_first_child(patchset); change != NULL; change = __xml_next(change)) { xmlNode *match = NULL; const char *op = crm_element_value(change, XML_DIFF_OP); const char *xpath = crm_element_value(change, XML_DIFF_PATH); int position = -1; crm_trace("Processing %s %s", change->name, op); if(op == NULL) { continue; } if(strcmp(op, "delete") == 0) { crm_element_value_int(change, XML_DIFF_POSITION, &position); } match = __xml_find_path(xml, xpath, position); crm_trace("Performing %s on %s with %p", op, xpath, match); if(match == NULL && strcmp(op, "delete") == 0) { crm_debug("No %s match for %s in %p", op, xpath, xml->doc); continue; } else if(match == NULL) { crm_err("No %s match for %s in %p", op, xpath, xml->doc); rc = -pcmk_err_diff_failed; continue; } else if(strcmp(op, "create") == 0) { int position = 0; xmlNode *child = NULL; xmlNode *match_child = NULL; match_child = match->children; crm_element_value_int(change, XML_DIFF_POSITION, &position); while(match_child && position != __xml_offset(match_child)) { match_child = match_child->next; } child = xmlDocCopyNode(change->children, match->doc, 1); if(match_child) { crm_trace("Adding %s at position %d", child->name, position); xmlAddPrevSibling(match_child, child); } else if(match->last) { /* Add to the end */ crm_trace("Adding %s at position %d (end)", child->name, position); xmlAddNextSibling(match->last, child); } else { crm_trace("Adding %s at position %d (first)", child->name, position); CRM_LOG_ASSERT(position == 0); xmlAddChild(match, child); } crm_node_created(child); } else if(strcmp(op, "move") == 0) { int position = 0; crm_element_value_int(change, XML_DIFF_POSITION, &position); if(position != __xml_offset(match)) { xmlNode *match_child = NULL; int p = position; if(p > __xml_offset(match)) { p++; /* Skip ourselves */ } CRM_ASSERT(match->parent != NULL); match_child = match->parent->children; while(match_child && p != __xml_offset(match_child)) { match_child = match_child->next; } crm_trace("Moving %s to position %d (was %d, prev %p, %s %p)", match->name, position, __xml_offset(match), match->prev, match_child?"next":"last", match_child?match_child:match->parent->last); if(match_child) { xmlAddPrevSibling(match_child, match); } else { CRM_ASSERT(match->parent->last != NULL); xmlAddNextSibling(match->parent->last, match); } } else { crm_trace("%s is already in position %d", match->name, position); } if(position != __xml_offset(match)) { crm_err("Moved %s.%s to position %d instead of %d (%p)", match->name, ID(match), __xml_offset(match), position, match->prev); rc = -pcmk_err_diff_failed; } } else if(strcmp(op, "delete") == 0) { free_xml(match); } else if(strcmp(op, "modify") == 0) { xmlAttr *pIter = pcmk__first_xml_attr(match); xmlNode *attrs = __xml_first_child(first_named_child(change, XML_DIFF_RESULT)); if(attrs == NULL) { rc = -ENOMSG; continue; } while(pIter != NULL) { const char *name = (const char *)pIter->name; pIter = pIter->next; xml_remove_prop(match, name); } for (pIter = pcmk__first_xml_attr(attrs); pIter != NULL; pIter = pIter->next) { const char *name = (const char *)pIter->name; const char *value = crm_element_value(attrs, name); crm_xml_add(match, name, value); } } else { crm_err("Unknown operation: %s", op); } } return rc; } int xml_apply_patchset(xmlNode *xml, xmlNode *patchset, bool check_version) { int format = 1; int rc = pcmk_ok; xmlNode *old = NULL; const char *digest = crm_element_value(patchset, XML_ATTR_DIGEST); if(patchset == NULL) { return rc; } xml_log_patchset(LOG_TRACE, __FUNCTION__, patchset); crm_element_value_int(patchset, "format", &format); if(check_version) { rc = xml_patch_version_check(xml, patchset, format); if(rc != pcmk_ok) { return rc; } } if(digest) { /* Make it available for logging if the result doesn't have the expected digest */ old = copy_xml(xml); } if(rc == pcmk_ok) { switch(format) { case 1: rc = xml_apply_patchset_v1(xml, patchset); break; case 2: rc = xml_apply_patchset_v2(xml, patchset); break; default: crm_err("Unknown patch format: %d", format); rc = -EINVAL; } } if(rc == pcmk_ok && digest) { static struct qb_log_callsite *digest_cs = NULL; char *new_digest = NULL; char *version = crm_element_value_copy(xml, XML_ATTR_CRM_VERSION); if (digest_cs == NULL) { digest_cs = qb_log_callsite_get(__func__, __FILE__, "diff-digest", LOG_TRACE, __LINE__, crm_trace_nonlog); } new_digest = calculate_xml_versioned_digest(xml, FALSE, TRUE, version); if (safe_str_neq(new_digest, digest)) { crm_info("v%d digest mis-match: expected %s, calculated %s", format, digest, new_digest); rc = -pcmk_err_diff_failed; if (digest_cs && digest_cs->targets) { save_xml_to_file(old, "PatchDigest:input", NULL); save_xml_to_file(xml, "PatchDigest:result", NULL); save_xml_to_file(patchset,"PatchDigest:diff", NULL); } else { crm_trace("%p %.6x", digest_cs, digest_cs ? digest_cs->targets : 0); } } else { crm_trace("v%d digest matched: expected %s, calculated %s", format, digest, new_digest); } free(new_digest); free(version); } free_xml(old); return rc; } xmlNode * find_xml_node(xmlNode * root, const char *search_path, gboolean must_find) { xmlNode *a_child = NULL; const char *name = "NULL"; if (root != NULL) { name = crm_element_name(root); } if (search_path == NULL) { crm_warn("Will never find "); return NULL; } for (a_child = __xml_first_child(root); a_child != NULL; a_child = __xml_next(a_child)) { if (strcmp((const char *)a_child->name, search_path) == 0) { /* crm_trace("returning node (%s).", crm_element_name(a_child)); */ 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 .", search_path); } return NULL; } /* As the name suggests, the perfect match is required for both node name and fully specified attribute, otherwise, when attribute not specified, the outcome is the first node matching on the name. */ static xmlNode * find_entity_by_attr_or_just_name(xmlNode *parent, const char *node_name, const char *attr_n, const char *attr_v) { xmlNode *child; /* ensure attr_v specified when attr_n is */ CRM_CHECK(attr_n == NULL || attr_v != NULL, return NULL); for (child = __xml_first_child(parent); child != NULL; child = __xml_next(child)) { /* XXX uncertain if the first check is strictly necessary here */ if (node_name == NULL || !strcmp((const char *) child->name, node_name)) { if (attr_n == NULL || crm_str_eq(crm_element_value(child, attr_n), attr_v, TRUE)) { return child; } } } crm_trace("node <%s%s%s%s%s> not found in %s", crm_str(node_name), attr_n ? " " : "", attr_n ? attr_n : "", attr_n ? "=" : "", attr_n ? attr_v : "", crm_element_name(parent)); return NULL; } xmlNode * find_entity(xmlNode *parent, const char *node_name, const char *id) { return find_entity_by_attr_or_just_name(parent, node_name, (id == NULL) ? id : XML_ATTR_ID, id); } void copy_in_properties(xmlNode * target, 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 { xmlAttrPtr pIter = NULL; for (pIter = pcmk__first_xml_attr(src); pIter != NULL; pIter = pIter->next) { const char *p_name = (const char *)pIter->name; const char *p_value = pcmk__xml_attr_value(pIter); expand_plus_plus(target, p_name, p_value); } } return; } void fix_plus_plus_recursive(xmlNode * target) { /* TODO: Remove recursion and use xpath searches for value++ */ xmlNode *child = NULL; xmlAttrPtr pIter = NULL; for (pIter = pcmk__first_xml_attr(target); pIter != NULL; pIter = pIter->next) { const char *p_name = (const char *)pIter->name; const char *p_value = pcmk__xml_attr_value(pIter); expand_plus_plus(target, p_name, p_value); } for (child = __xml_first_child(target); child != NULL; child = __xml_next(child)) { fix_plus_plus_recursive(child); } } 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 (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; } xmlDoc * getDocPtr(xmlNode * node) { xmlDoc *doc = NULL; CRM_CHECK(node != NULL, return NULL); doc = node->doc; if (doc == NULL) { doc = xmlNewDoc((const xmlChar *)"1.0"); xmlDocSetRootElement(doc, node); xmlSetTreeDoc(node, doc); } return doc; } xmlNode * add_node_copy(xmlNode * parent, xmlNode * src_node) { xmlNode *child = NULL; xmlDoc *doc = getDocPtr(parent); CRM_CHECK(src_node != NULL, return NULL); child = xmlDocCopyNode(src_node, doc, 1); xmlAddChild(parent, child); crm_node_created(child); return child; } int add_node_nocopy(xmlNode * parent, const char *name, xmlNode * child) { add_node_copy(parent, child); free_xml(child); return 1; } xmlNode * create_xml_node(xmlNode * parent, const char *name) { xmlDoc *doc = NULL; xmlNode *node = NULL; if (name == NULL || name[0] == 0) { CRM_CHECK(name != NULL && name[0] == 0, return NULL); return NULL; } if (parent == NULL) { doc = xmlNewDoc((const xmlChar *)"1.0"); node = xmlNewDocRawNode(doc, NULL, (const xmlChar *)name, NULL); xmlDocSetRootElement(doc, node); } else { doc = getDocPtr(parent); node = xmlNewDocRawNode(doc, NULL, (const xmlChar *)name, NULL); xmlAddChild(parent, node); } crm_node_created(node); return node; } int pcmk__element_xpath(const char *prefix, xmlNode *xml, char *buffer, int offset, size_t buffer_size) { const char *id = ID(xml); if(offset == 0 && prefix == NULL && xml->parent) { offset = pcmk__element_xpath(NULL, xml->parent, buffer, offset, buffer_size); } if(id) { offset += snprintf(buffer + offset, buffer_size - offset, "/%s[@id='%s']", (const char *) xml->name, id); } else if(xml->name) { offset += snprintf(buffer + offset, buffer_size - offset, "/%s", (const char *) xml->name); } return offset; } char * xml_get_path(xmlNode *xml) { int offset = 0; char buffer[XML_BUFFER_SIZE]; if (pcmk__element_xpath(NULL, xml, buffer, offset, sizeof(buffer)) > 0) { return strdup(buffer); } return NULL; } static void free_xml_with_position(xmlNode * child, int position) { if (child != NULL) { xmlNode *top = NULL; xmlDoc *doc = child->doc; xml_private_t *p = child->_private; if (doc != NULL) { top = xmlDocGetRootElement(doc); } if (doc != NULL && top == child) { /* Free everything */ xmlFreeDoc(doc); } else if (pcmk__check_acl(child, NULL, xpf_acl_write) == FALSE) { int offset = 0; char buffer[XML_BUFFER_SIZE]; pcmk__element_xpath(NULL, child, buffer, offset, sizeof(buffer)); crm_trace("Cannot remove %s %x", buffer, p->flags); return; } else { if (doc && pcmk__tracking_xml_changes(child, FALSE) && is_not_set(p->flags, xpf_created)) { int offset = 0; char buffer[XML_BUFFER_SIZE]; if (pcmk__element_xpath(NULL, child, buffer, offset, sizeof(buffer)) > 0) { xml_deleted_obj_t *deleted_obj = calloc(1, sizeof(xml_deleted_obj_t)); crm_trace("Deleting %s %p from %p", buffer, child, doc); deleted_obj->path = strdup(buffer); 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 = __xml_offset(child); } } p = doc->_private; p->deleted_objs = g_list_append(p->deleted_objs, deleted_obj); pcmk__set_xml_flag(child, xpf_dirty); } } /* Free this particular subtree * Make sure to unlink it from the parent first */ xmlUnlinkNode(child); xmlFreeNode(child); } } } void free_xml(xmlNode * child) { free_xml_with_position(child, -1); } xmlNode * copy_xml(xmlNode * src) { xmlDoc *doc = xmlNewDoc((const xmlChar *)"1.0"); xmlNode *copy = xmlDocCopyNode(src, doc, 1); xmlDocSetRootElement(doc, copy); xmlSetTreeDoc(copy, doc); return copy; } static void crm_xml_err(void *ctx, const char *fmt, ...) G_GNUC_PRINTF(2, 3); static void crm_xml_err(void *ctx, const char *fmt, ...) { va_list ap; static struct qb_log_callsite *xml_error_cs = NULL; if (xml_error_cs == NULL) { xml_error_cs = qb_log_callsite_get( __func__, __FILE__, "xml library error", LOG_TRACE, __LINE__, crm_trace_nonlog); } va_start(ap, fmt); if (xml_error_cs && xml_error_cs->targets) { CRM_XML_LOG_BASE(LOG_ERR, TRUE, crm_abort(__FILE__, __PRETTY_FUNCTION__, __LINE__, "xml library error", TRUE, TRUE), "XML Error: ", fmt, ap); } else { CRM_XML_LOG_BASE(LOG_ERR, TRUE, 0, "XML Error: ", fmt, ap); } va_end(ap); } xmlNode * string2xml(const char *input) { xmlNode *xml = NULL; xmlDocPtr output = NULL; xmlParserCtxtPtr ctxt = NULL; xmlErrorPtr 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); /* xmlCtxtUseOptions(ctxt, XML_PARSE_NOBLANKS|XML_PARSE_RECOVER); */ xmlCtxtResetLastError(ctxt); xmlSetGenericErrorFunc(ctxt, crm_xml_err); /* initGenericErrorDefaultFunc(crm_xml_err); */ output = xmlCtxtReadDoc(ctxt, (const xmlChar *)input, NULL, NULL, XML_PARSE_NOBLANKS | XML_PARSE_RECOVER); if (output) { xml = xmlDocGetRootElement(output); } last_error = xmlCtxtGetLastError(ctxt); if (last_error && last_error->code != XML_ERR_OK) { /* crm_abort(__FILE__,__FUNCTION__,__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 = realloc_safe(xml_buffer, data_length + XML_BUFFER_SIZE); read_chars = fread(xml_buffer + data_length, 1, XML_BUFFER_SIZE, stdin); data_length += read_chars; } while (read_chars == XML_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; #if HAVE_BZLIB_H 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); if (rc != BZ_OK) { crm_err("Could not prepare to read compressed %s: %s " CRM_XS " bzerror=%d", filename, bz2_strerror(rc), rc); BZ2_bzReadClose(&rc, bz_file); return NULL; } rc = BZ_OK; while (rc == BZ_OK) { buffer = realloc_safe(buffer, XML_BUFFER_SIZE + length + 1); read_len = BZ2_bzRead(&rc, bz_file, buffer + length, XML_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'; if (rc != BZ_STREAM_END) { crm_err("Could not read compressed %s: %s " CRM_XS " bzerror=%d", filename, bz2_strerror(rc), rc); free(buffer); buffer = NULL; } BZ2_bzReadClose(&rc, bz_file); fclose(input); #else crm_err("Could not read compressed %s: not built with bzlib support", filename); #endif return buffer; } void strip_text_nodes(xmlNode * xml) { xmlNode *iter = xml->children; while (iter) { xmlNode *next = iter->next; switch (iter->type) { case XML_TEXT_NODE: /* Remove it */ xmlUnlinkNode(iter); xmlFreeNode(iter); break; case XML_ELEMENT_NODE: /* Search it */ strip_text_nodes(iter); break; default: /* Leave it */ break; } iter = next; } } xmlNode * filename2xml(const char *filename) { xmlNode *xml = NULL; xmlDocPtr output = NULL; gboolean uncompressed = TRUE; xmlParserCtxtPtr ctxt = NULL; xmlErrorPtr last_error = NULL; static int xml_options = XML_PARSE_NOBLANKS | XML_PARSE_RECOVER; /* create a parser context */ ctxt = xmlNewParserCtxt(); CRM_CHECK(ctxt != NULL, return NULL); /* xmlCtxtUseOptions(ctxt, XML_PARSE_NOBLANKS|XML_PARSE_RECOVER); */ xmlCtxtResetLastError(ctxt); xmlSetGenericErrorFunc(ctxt, crm_xml_err); /* initGenericErrorDefaultFunc(crm_xml_err); */ if (filename) { uncompressed = !crm_ends_with_ext(filename, ".bz2"); } if (filename == NULL) { /* STDIN_FILENO == fileno(stdin) */ output = xmlCtxtReadFd(ctxt, STDIN_FILENO, "unknown.xml", NULL, xml_options); } else if (uncompressed) { output = xmlCtxtReadFile(ctxt, filename, NULL, xml_options); } else { char *input = decompress_file(filename); output = xmlCtxtReadDoc(ctxt, (const xmlChar *)input, NULL, NULL, xml_options); free(input); } if (output && (xml = xmlDocGetRootElement(output))) { strip_text_nodes(xml); } last_error = xmlCtxtGetLastError(ctxt); if (last_error && last_error->code != XML_ERR_OK) { /* crm_abort(__FILE__,__FUNCTION__,__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 node, set to current time * * \param[in] xml_node XML node to get attribute * * \return Value that was set, or NULL on error */ const char * crm_xml_add_last_written(xmlNode *xml_node) { time_t now = time(NULL); char *now_str = ctime(&now); now_str[24] = EOS; /* replace the newline */ return crm_xml_add(xml_node, XML_CIB_ATTR_WRITTEN, now_str); } /*! * \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_node XML to write * \param[in] filename Name of file being written (for logging only) * \param[in] stream Open file stream corresponding to filename * \param[in] compress Whether to compress XML before writing * * \return Number of bytes written on success, -errno otherwise */ static int write_xml_stream(xmlNode * xml_node, const char *filename, FILE * stream, gboolean compress) { int res = 0; char *buffer = NULL; unsigned int out = 0; crm_log_xml_trace(xml_node, "writing"); buffer = dump_xml_formatted(xml_node); CRM_CHECK(buffer && strlen(buffer), crm_log_xml_warn(xml_node, "formatting failed"); res = -pcmk_err_generic; goto bail); if (compress) { #if HAVE_BZLIB_H int rc = BZ_OK; unsigned int in = 0; BZFILE *bz_file = NULL; bz_file = BZ2_bzWriteOpen(&rc, stream, 5, 0, 30); if (rc != BZ_OK) { crm_warn("Not compressing %s: could not prepare file stream: %s " CRM_XS " bzerror=%d", filename, bz2_strerror(rc), rc); } else { BZ2_bzWrite(&rc, bz_file, buffer, strlen(buffer)); if (rc != BZ_OK) { crm_warn("Not compressing %s: could not compress data: %s " CRM_XS " bzerror=%d errno=%d", filename, bz2_strerror(rc), rc, errno); } } if (rc == BZ_OK) { BZ2_bzWriteClose(&rc, bz_file, 0, &in, &out); if (rc != BZ_OK) { crm_warn("Not compressing %s: could not write compressed data: %s " CRM_XS " bzerror=%d errno=%d", filename, bz2_strerror(rc), rc, errno); out = 0; // retry without compression } else { res = (int) out; crm_trace("Compressed XML for %s from %u bytes to %u", filename, in, out); } } #else crm_warn("Not compressing %s: not built with bzlib support", filename); #endif } if (out == 0) { res = fprintf(stream, "%s", buffer); if (res < 0) { res = -errno; crm_perror(LOG_ERR, "writing %s", filename); goto bail; } } bail: if (fflush(stream) != 0) { res = -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) { res = -errno; crm_perror(LOG_ERR, "synchronizing %s", filename); } fclose(stream); crm_trace("Saved %d bytes%s to %s as XML", res, ((out > 0)? " (compressed)" : ""), filename); free(buffer); return res; } /*! * \brief Write XML to a file descriptor * * \param[in] xml_node 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(xmlNode * xml_node, const char *filename, int fd, gboolean compress) { FILE *stream = NULL; CRM_CHECK(xml_node && (fd > 0), return -EINVAL); stream = fdopen(fd, "w"); if (stream == NULL) { return -errno; } return write_xml_stream(xml_node, filename, stream, compress); } /*! * \brief Write XML to a file * * \param[in] xml_node 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(xmlNode * xml_node, const char *filename, gboolean compress) { FILE *stream = NULL; CRM_CHECK(xml_node && filename, return -EINVAL); stream = fopen(filename, "w"); if (stream == NULL) { return -errno; } return write_xml_stream(xml_node, filename, stream, compress); } xmlNode * get_message_xml(xmlNode * msg, const char *field) { xmlNode *tmp = first_named_child(msg, field); return __xml_first_child(tmp); } gboolean add_message_xml(xmlNode * msg, const char *field, xmlNode * xml) { xmlNode *holder = create_xml_node(msg, field); add_node_copy(holder, xml); return TRUE; } static char * crm_xml_escape_shuffle(char *text, int start, int *length, const char *replace) { int lpc; int offset = strlen(replace) - 1; /* We have space for 1 char already */ *length += offset; text = realloc_safe(text, *length); for (lpc = (*length) - 1; lpc > (start + offset); lpc--) { text[lpc] = text[lpc - offset]; } memcpy(text + start, replace, offset + 1); return text; } char * crm_xml_escape(const char *text) { int index; int changes = 0; int length = 1 + strlen(text); char *copy = strdup(text); /* * When xmlCtxtReadDoc() parses < 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. */ for (index = 0; index < length; index++) { switch (copy[index]) { case 0: break; case '<': copy = crm_xml_escape_shuffle(copy, index, &length, "<"); changes++; break; case '>': copy = crm_xml_escape_shuffle(copy, index, &length, ">"); changes++; break; case '"': copy = crm_xml_escape_shuffle(copy, index, &length, """); changes++; break; case '\'': copy = crm_xml_escape_shuffle(copy, index, &length, "'"); changes++; break; case '&': copy = crm_xml_escape_shuffle(copy, index, &length, "&"); changes++; break; case '\t': /* Might as well just expand to a few spaces... */ copy = crm_xml_escape_shuffle(copy, index, &length, " "); changes++; break; case '\n': /* crm_trace("Convert: \\%.3o", copy[index]); */ copy = crm_xml_escape_shuffle(copy, index, &length, "\\n"); changes++; break; case '\r': copy = crm_xml_escape_shuffle(copy, index, &length, "\\r"); changes++; break; /* For debugging... case '\\': crm_trace("Passthrough: \\%c", copy[index+1]); 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]); /* crm_trace("Convert to octal: \\%.3o", copy[index]); */ copy = crm_xml_escape_shuffle(copy, index, &length, replace); free(replace); changes++; } } } if (changes) { crm_trace("Dumped '%s'", copy); } return copy; } static inline void dump_xml_attr(xmlAttrPtr attr, int options, char **buffer, int *offset, int *max) { char *p_value = NULL; const char *p_name = NULL; xml_private_t *p = NULL; CRM_ASSERT(buffer != NULL); if (attr == NULL || attr->children == NULL) { return; } p = attr->_private; if (p && is_set(p->flags, xpf_deleted)) { return; } p_name = (const char *)attr->name; p_value = crm_xml_escape((const char *)attr->children->content); buffer_print(*buffer, *max, *offset, " %s=\"%s\"", p_name, p_value); free(p_value); } static void __xml_log_element(int log_level, const char *file, const char *function, int line, const char *prefix, xmlNode * data, int depth, int options) { int max = 0; int offset = 0; const char *name = NULL; const char *hidden = NULL; xmlNode *child = NULL; xmlAttrPtr pIter = NULL; if(data == NULL) { return; } name = crm_element_name(data); if(is_set(options, xml_log_option_open)) { char *buffer = NULL; insert_prefix(options, &buffer, &offset, &max, depth); if (data->type == XML_COMMENT_NODE) { buffer_print(buffer, max, offset, "", data->content); } else { buffer_print(buffer, max, offset, "<%s", name); hidden = crm_element_value(data, "hidden"); for (pIter = pcmk__first_xml_attr(data); pIter != NULL; pIter = pIter->next) { xml_private_t *p = pIter->_private; const char *p_name = (const char *)pIter->name; const char *p_value = pcmk__xml_attr_value(pIter); char *p_copy = NULL; if(is_set(p->flags, xpf_deleted)) { continue; } else if ((is_set(options, xml_log_option_diff_plus) || is_set(options, xml_log_option_diff_minus)) && strcmp(XML_DIFF_MARKER, p_name) == 0) { continue; } else if (hidden != NULL && p_name[0] != 0 && strstr(hidden, p_name) != NULL) { p_copy = strdup("*****"); } else { p_copy = crm_xml_escape(p_value); } buffer_print(buffer, max, offset, " %s=\"%s\"", p_name, p_copy); free(p_copy); } if(xml_has_children(data) == FALSE) { buffer_print(buffer, max, offset, "/>"); } else if(is_set(options, xml_log_option_children)) { buffer_print(buffer, max, offset, ">"); } else { buffer_print(buffer, max, offset, "/>"); } } do_crm_log_alias(log_level, file, function, line, "%s %s", prefix, buffer); free(buffer); } if(data->type == XML_COMMENT_NODE) { return; } else if(xml_has_children(data) == FALSE) { return; } else if(is_set(options, xml_log_option_children)) { offset = 0; max = 0; for (child = __xml_first_child(data); child != NULL; child = __xml_next(child)) { __xml_log_element(log_level, file, function, line, prefix, child, depth + 1, options|xml_log_option_open|xml_log_option_close); } } if(is_set(options, xml_log_option_close)) { char *buffer = NULL; insert_prefix(options, &buffer, &offset, &max, depth); buffer_print(buffer, max, offset, "", name); do_crm_log_alias(log_level, file, function, line, "%s %s", prefix, buffer); free(buffer); } } static void __xml_log_change_element(int log_level, const char *file, const char *function, int line, const char *prefix, xmlNode * data, int depth, int options) { xml_private_t *p; char *prefix_m = NULL; xmlNode *child = NULL; xmlAttrPtr pIter = NULL; if(data == NULL) { return; } p = data->_private; prefix_m = strdup(prefix); prefix_m[1] = '+'; if(is_set(p->flags, xpf_dirty) && is_set(p->flags, xpf_created)) { /* Continue and log full subtree */ __xml_log_element(log_level, file, function, line, prefix_m, data, depth, options|xml_log_option_open|xml_log_option_close|xml_log_option_children); } else if(is_set(p->flags, xpf_dirty)) { char *spaces = calloc(80, 1); int s_count = 0, s_max = 80; char *prefix_del = NULL; char *prefix_moved = NULL; const char *flags = prefix; insert_prefix(options, &spaces, &s_count, &s_max, depth); prefix_del = strdup(prefix); prefix_del[0] = '-'; prefix_del[1] = '-'; prefix_moved = strdup(prefix); prefix_moved[1] = '~'; if(is_set(p->flags, xpf_moved)) { flags = prefix_moved; } else { flags = prefix; } __xml_log_element(log_level, file, function, line, flags, data, depth, options|xml_log_option_open); for (pIter = pcmk__first_xml_attr(data); pIter != NULL; pIter = pIter->next) { const char *aname = (const char*)pIter->name; p = pIter->_private; if(is_set(p->flags, xpf_deleted)) { const char *value = crm_element_value(data, aname); flags = prefix_del; do_crm_log_alias(log_level, file, function, line, "%s %s @%s=%s", flags, spaces, aname, value); } else if(is_set(p->flags, xpf_dirty)) { const char *value = crm_element_value(data, aname); if(is_set(p->flags, xpf_created)) { flags = prefix_m; } else if(is_set(p->flags, xpf_modified)) { flags = prefix; } else if(is_set(p->flags, xpf_moved)) { flags = prefix_moved; } else { flags = prefix; } do_crm_log_alias(log_level, file, function, line, "%s %s @%s=%s", flags, spaces, aname, value); } } free(prefix_moved); free(prefix_del); free(spaces); for (child = __xml_first_child(data); child != NULL; child = __xml_next(child)) { __xml_log_change_element(log_level, file, function, line, prefix, child, depth + 1, options); } __xml_log_element(log_level, file, function, line, prefix, data, depth, options|xml_log_option_close); } else { for (child = __xml_first_child(data); child != NULL; child = __xml_next(child)) { __xml_log_change_element(log_level, file, function, line, prefix, child, depth + 1, options); } } free(prefix_m); } void log_data_element(int log_level, const char *file, const char *function, int line, const char *prefix, xmlNode * data, int depth, int options) { xmlNode *a_child = NULL; char *prefix_m = NULL; if (prefix == NULL) { prefix = ""; } /* Since we use the same file and line, to avoid confusing libqb, we need to use the same format strings */ if (data == NULL) { do_crm_log_alias(log_level, file, function, line, "%s: %s", prefix, "No data to dump as XML"); return; } if(is_set(options, xml_log_option_dirty_add) || is_set(options, xml_log_option_dirty_add)) { __xml_log_change_element(log_level, file, function, line, prefix, data, depth, options); return; } if (is_set(options, xml_log_option_formatted)) { if (is_set(options, xml_log_option_diff_plus) && (data->children == NULL || crm_element_value(data, XML_DIFF_MARKER))) { options |= xml_log_option_diff_all; prefix_m = strdup(prefix); prefix_m[1] = '+'; prefix = prefix_m; } else if (is_set(options, xml_log_option_diff_minus) && (data->children == NULL || crm_element_value(data, XML_DIFF_MARKER))) { options |= xml_log_option_diff_all; prefix_m = strdup(prefix); prefix_m[1] = '-'; prefix = prefix_m; } } if (is_set(options, xml_log_option_diff_short) && is_not_set(options, xml_log_option_diff_all)) { /* Still searching for the actual change */ for (a_child = __xml_first_child(data); a_child != NULL; a_child = __xml_next(a_child)) { log_data_element(log_level, file, function, line, prefix, a_child, depth + 1, options); } } else { __xml_log_element(log_level, file, function, line, prefix, data, depth, options|xml_log_option_open|xml_log_option_close|xml_log_option_children); } free(prefix_m); } static void dump_filtered_xml(xmlNode * data, int options, char **buffer, int *offset, int *max) { int lpc; xmlAttrPtr xIter = NULL; static int filter_len = DIMOF(filter); for (lpc = 0; options && lpc < filter_len; lpc++) { filter[lpc].found = FALSE; } for (xIter = pcmk__first_xml_attr(data); xIter != NULL; xIter = xIter->next) { bool skip = FALSE; const char *p_name = (const char *)xIter->name; for (lpc = 0; skip == FALSE && lpc < filter_len; lpc++) { if (filter[lpc].found == FALSE && strcmp(p_name, filter[lpc].string) == 0) { filter[lpc].found = TRUE; skip = TRUE; break; } } if (skip == FALSE) { dump_xml_attr(xIter, options, buffer, offset, max); } } } static void dump_xml_element(xmlNode * data, int options, char **buffer, int *offset, int *max, int depth) { const char *name = NULL; CRM_ASSERT(max != NULL); CRM_ASSERT(offset != NULL); CRM_ASSERT(buffer != NULL); if (data == NULL) { crm_trace("Nothing to dump"); return; } if (*buffer == NULL) { *offset = 0; *max = 0; } name = crm_element_name(data); CRM_ASSERT(name != NULL); insert_prefix(options, buffer, offset, max, depth); buffer_print(*buffer, *max, *offset, "<%s", name); if (options & xml_log_option_filtered) { dump_filtered_xml(data, options, buffer, offset, max); } else { xmlAttrPtr xIter = NULL; for (xIter = pcmk__first_xml_attr(data); xIter != NULL; xIter = xIter->next) { dump_xml_attr(xIter, options, buffer, offset, max); } } if (data->children == NULL) { buffer_print(*buffer, *max, *offset, "/>"); } else { buffer_print(*buffer, *max, *offset, ">"); } if (options & xml_log_option_formatted) { buffer_print(*buffer, *max, *offset, "\n"); } if (data->children) { xmlNode *xChild = NULL; for(xChild = data->children; xChild != NULL; xChild = xChild->next) { crm_xml_dump(xChild, options, buffer, offset, max, depth + 1); } insert_prefix(options, buffer, offset, max, depth); buffer_print(*buffer, *max, *offset, "", name); if (options & xml_log_option_formatted) { buffer_print(*buffer, *max, *offset, "\n"); } } } static void dump_xml_text(xmlNode * data, int options, char **buffer, int *offset, int *max, int depth) { CRM_ASSERT(max != NULL); CRM_ASSERT(offset != NULL); CRM_ASSERT(buffer != NULL); if (data == NULL) { crm_trace("Nothing to dump"); return; } if (*buffer == NULL) { *offset = 0; *max = 0; } insert_prefix(options, buffer, offset, max, depth); buffer_print(*buffer, *max, *offset, "%s", data->content); if (options & xml_log_option_formatted) { buffer_print(*buffer, *max, *offset, "\n"); } } static void dump_xml_comment(xmlNode * data, int options, char **buffer, int *offset, int *max, int depth) { CRM_ASSERT(max != NULL); CRM_ASSERT(offset != NULL); CRM_ASSERT(buffer != NULL); if (data == NULL) { crm_trace("Nothing to dump"); return; } if (*buffer == NULL) { *offset = 0; *max = 0; } insert_prefix(options, buffer, offset, max, depth); buffer_print(*buffer, *max, *offset, ""); if (options & xml_log_option_formatted) { buffer_print(*buffer, *max, *offset, "\n"); } } void crm_xml_dump(xmlNode * data, int options, char **buffer, int *offset, int *max, int depth) { if(data == NULL) { *offset = 0; *max = 0; return; } #if 0 if (is_not_set(options, xml_log_option_filtered)) { /* Turning this code on also changes the scheduler tests for some reason * (not just newlines). Figure out why before considering to * enable this permanently. * * It exists to help debug slowness in xmlNodeDump() and * potentially if we ever want to go back to it. * * In theory it's a good idea (reuse) but our custom version does * better for the filtered case and avoids the final strdup() for * everything */ time_t now, next; xmlDoc *doc = NULL; xmlBuffer *xml_buffer = NULL; *buffer = NULL; doc = getDocPtr(data); /* doc will only be NULL if data is */ CRM_CHECK(doc != NULL, return); now = time(NULL); xml_buffer = xmlBufferCreate(); CRM_ASSERT(xml_buffer != NULL); /* The default allocator XML_BUFFER_ALLOC_EXACT does far too many * 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. * * We could also use xmlBufferCreateSize() to start with a * sane-ish initial size and avoid the first few doubles. */ xmlBufferSetAllocationScheme(xml_buffer, XML_BUFFER_ALLOC_DOUBLEIT); *max = xmlNodeDump(xml_buffer, doc, data, 0, (options & xml_log_option_formatted)); if (*max > 0) { *buffer = strdup((char *)xml_buffer->content); } next = time(NULL); if ((now + 1) < next) { crm_log_xml_trace(data, "Long time"); crm_err("xmlNodeDump() -> %dbytes took %ds", *max, next - now); } xmlBufferFree(xml_buffer); return; } #endif switch(data->type) { case XML_ELEMENT_NODE: /* Handle below */ dump_xml_element(data, options, buffer, offset, max, depth); break; case XML_TEXT_NODE: /* if option xml_log_option_text is enabled, then dump XML_TEXT_NODE */ if (options & xml_log_option_text) { dump_xml_text(data, options, buffer, offset, max, depth); } return; case XML_COMMENT_NODE: dump_xml_comment(data, options, buffer, offset, max, depth); break; default: crm_warn("Unhandled type: %d", data->type); return; /* XML_ATTRIBUTE_NODE = 2 XML_CDATA_SECTION_NODE = 4 XML_ENTITY_REF_NODE = 5 XML_ENTITY_NODE = 6 XML_PI_NODE = 7 XML_DOCUMENT_NODE = 9 XML_DOCUMENT_TYPE_NODE = 10 XML_DOCUMENT_FRAG_NODE = 11 XML_NOTATION_NODE = 12 XML_HTML_DOCUMENT_NODE = 13 XML_DTD_NODE = 14 XML_ELEMENT_DECL = 15 XML_ATTRIBUTE_DECL = 16 XML_ENTITY_DECL = 17 XML_NAMESPACE_DECL = 18 XML_XINCLUDE_START = 19 XML_XINCLUDE_END = 20 XML_DOCB_DOCUMENT_NODE = 21 */ } } void crm_buffer_add_char(char **buffer, int *offset, int *max, char c) { buffer_print(*buffer, *max, *offset, "%c", c); } char * dump_xml_formatted_with_text(xmlNode * an_xml_node) { char *buffer = NULL; int offset = 0, max = 0; crm_xml_dump(an_xml_node, xml_log_option_formatted|xml_log_option_text, &buffer, &offset, &max, 0); return buffer; } char * dump_xml_formatted(xmlNode * an_xml_node) { char *buffer = NULL; int offset = 0, max = 0; crm_xml_dump(an_xml_node, xml_log_option_formatted, &buffer, &offset, &max, 0); return buffer; } char * dump_xml_unformatted(xmlNode * an_xml_node) { char *buffer = NULL; int offset = 0, max = 0; crm_xml_dump(an_xml_node, 0, &buffer, &offset, &max, 0); return buffer; } gboolean xml_has_children(const xmlNode * xml_root) { if (xml_root != NULL && xml_root->children != NULL) { return TRUE; } return FALSE; } void xml_remove_prop(xmlNode * obj, const char *name) { if (pcmk__check_acl(obj, NULL, xpf_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 */ xml_private_t *p = NULL; xmlAttr *attr = xmlHasProp(obj, (const xmlChar *)name); p = attr->_private; set_parent_flag(obj, xpf_dirty); p->flags |= xpf_deleted; /* crm_trace("Setting flag %x due to %s[@id=%s].%s", xpf_dirty, obj->name, ID(obj), name); */ } else { xmlUnsetProp(obj, (const xmlChar *)name); } } void purge_diff_markers(xmlNode * a_node) { xmlNode *child = NULL; CRM_CHECK(a_node != NULL, return); xml_remove_prop(a_node, XML_DIFF_MARKER); for (child = __xml_first_child(a_node); child != NULL; child = __xml_next(child)) { purge_diff_markers(child); } } void save_xml_to_file(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", crm_get_tmpdir(), uuid); filename = f; free(uuid); } crm_info("Saving %s to %s", desc, filename); write_xml_file(xml, filename, FALSE); free(f); } gboolean apply_xml_diff(xmlNode *old_xml, xmlNode * diff, xmlNode **new_xml) { gboolean result = TRUE; int root_nodes_seen = 0; static struct qb_log_callsite *digest_cs = NULL; const char *digest = crm_element_value(diff, XML_ATTR_DIGEST); const char *version = crm_element_value(diff, XML_ATTR_CRM_VERSION); xmlNode *child_diff = NULL; xmlNode *added = find_xml_node(diff, "diff-added", FALSE); xmlNode *removed = find_xml_node(diff, "diff-removed", FALSE); CRM_CHECK(new_xml != NULL, return FALSE); if (digest_cs == NULL) { digest_cs = qb_log_callsite_get(__func__, __FILE__, "diff-digest", LOG_TRACE, __LINE__, crm_trace_nonlog); } crm_trace("Subtraction Phase"); for (child_diff = __xml_first_child(removed); child_diff != NULL; child_diff = __xml_next(child_diff)) { CRM_CHECK(root_nodes_seen == 0, result = FALSE); if (root_nodes_seen == 0) { *new_xml = subtract_xml_object(NULL, old_xml, child_diff, FALSE, NULL, NULL); } root_nodes_seen++; } if (root_nodes_seen == 0) { *new_xml = copy_xml(old_xml); } else if (root_nodes_seen > 1) { crm_err("(-) Diffs cannot contain more than one change set..." " saw %d", root_nodes_seen); result = FALSE; } root_nodes_seen = 0; crm_trace("Addition Phase"); if (result) { xmlNode *child_diff = NULL; for (child_diff = __xml_first_child(added); child_diff != NULL; child_diff = __xml_next(child_diff)) { CRM_CHECK(root_nodes_seen == 0, result = FALSE); if (root_nodes_seen == 0) { add_xml_object(NULL, *new_xml, child_diff, TRUE); } root_nodes_seen++; } } if (root_nodes_seen > 1) { crm_err("(+) Diffs cannot contain more than one change set..." " saw %d", root_nodes_seen); result = FALSE; } else if (result && digest) { char *new_digest = NULL; purge_diff_markers(*new_xml); /* Purge now so the diff is ok */ new_digest = calculate_xml_versioned_digest(*new_xml, FALSE, TRUE, version); if (safe_str_neq(new_digest, digest)) { crm_info("Digest mis-match: expected %s, calculated %s", digest, new_digest); result = FALSE; crm_trace("%p %.6x", digest_cs, digest_cs ? digest_cs->targets : 0); if (digest_cs && digest_cs->targets) { save_xml_to_file(old_xml, "diff:original", NULL); save_xml_to_file(diff, "diff:input", NULL); save_xml_to_file(*new_xml, "diff:new", NULL); } } else { crm_trace("Digest matched: expected %s, calculated %s", digest, new_digest); } free(new_digest); } else if (result) { purge_diff_markers(*new_xml); /* Purge now so the diff is ok */ } return result; } static void __xml_diff_object(xmlNode *old_xml, xmlNode *new_xml) { xmlNode *cIter = NULL; xmlAttr *pIter = NULL; CRM_CHECK(new_xml != NULL, return); if (old_xml == NULL) { crm_node_created(new_xml); pcmk__post_process_acl(new_xml); // Check creation is allowed return; } else { xml_private_t *p = new_xml->_private; if(p->flags & xpf_processed) { /* Avoid re-comparing nodes */ return; } p->flags |= xpf_processed; } for (pIter = pcmk__first_xml_attr(new_xml); pIter != NULL; pIter = pIter->next) { xml_private_t *p = pIter->_private; /* Assume everything was just created and take it from there */ p->flags |= xpf_created; } for (pIter = pcmk__first_xml_attr(old_xml); pIter != NULL; ) { xmlAttr *prop = pIter; xml_private_t *p = NULL; const char *name = (const char *)pIter->name; const char *old_value = crm_element_value(old_xml, name); xmlAttr *exists = xmlHasProp(new_xml, pIter->name); pIter = pIter->next; if(exists == NULL) { p = new_xml->doc->_private; /* Prevent the dirty flag being set recursively upwards */ clear_bit(p->flags, xpf_tracking); exists = xmlSetProp(new_xml, (const xmlChar *) name, (const xmlChar *) old_value); set_bit(p->flags, xpf_tracking); p = exists->_private; p->flags = 0; crm_trace("Lost %s@%s=%s", old_xml->name, name, old_value); xml_remove_prop(new_xml, name); } else { int p_new = __xml_offset((xmlNode*)exists); int p_old = __xml_offset((xmlNode*)prop); const char *value = crm_element_value(new_xml, name); p = exists->_private; p->flags = (p->flags & ~xpf_created); if(strcmp(value, old_value) != 0) { /* Restore the original value, so we can call crm_xml_add(), * which checks ACLs */ char *vcopy = crm_element_value_copy(new_xml, name); crm_trace("Modified %s@%s %s->%s", old_xml->name, name, old_value, vcopy); xmlSetProp(new_xml, prop->name, (const xmlChar *) old_value); crm_xml_add(new_xml, name, vcopy); free(vcopy); } else if ((p_old != p_new) && !pcmk__tracking_xml_changes(new_xml, TRUE)) { crm_info("Moved %s@%s (%d -> %d)", old_xml->name, name, p_old, p_new); __xml_node_dirty(new_xml); p->flags |= xpf_dirty|xpf_moved; if(p_old > p_new) { p = prop->_private; p->flags |= xpf_skip; } else { p = exists->_private; p->flags |= xpf_skip; } } } } for (pIter = pcmk__first_xml_attr(new_xml); pIter != NULL; ) { xmlAttr *prop = pIter; xml_private_t *p = pIter->_private; pIter = pIter->next; if(is_set(p->flags, xpf_created)) { char *name = strdup((const char *)prop->name); char *value = crm_element_value_copy(new_xml, name); crm_trace("Created %s@%s=%s", new_xml->name, name, value); /* Remove plus create won't work as it will modify the relative attribute ordering */ if (pcmk__check_acl(new_xml, name, xpf_acl_write)) { pcmk__mark_xml_attr_dirty(prop); } else { xmlUnsetProp(new_xml, prop->name); /* Remove - change not allowed */ } free(value); free(name); } } for (cIter = __xml_first_child(old_xml); cIter != NULL; ) { xmlNode *old_child = cIter; xmlNode *new_child = find_element(new_xml, cIter, TRUE); cIter = __xml_next(cIter); if(new_child) { __xml_diff_object(old_child, new_child); } else { /* Create then free (which will check the acls if necessary) */ xmlNode *candidate = add_node_copy(new_xml, old_child); xmlNode *top = xmlDocGetRootElement(candidate->doc); __xml_node_clean(candidate); pcmk__apply_acl(top); /* Make sure any ACLs are applied to 'candidate' */ /* Record the old position */ free_xml_with_position(candidate, __xml_offset(old_child)); if (find_element(new_xml, old_child, TRUE) == NULL) { xml_private_t *p = old_child->_private; p->flags |= xpf_skip; } } } for (cIter = __xml_first_child(new_xml); cIter != NULL; ) { xmlNode *new_child = cIter; xmlNode *old_child = find_element(old_xml, cIter, TRUE); cIter = __xml_next(cIter); if(old_child == NULL) { xml_private_t *p = new_child->_private; p->flags |= xpf_skip; __xml_diff_object(old_child, new_child); } else { /* Check for movement, we already checked for differences */ int p_new = __xml_offset(new_child); int p_old = __xml_offset(old_child); if(p_old != p_new) { xml_private_t *p = new_child->_private; crm_info("%s.%s moved from %d to %d", new_child->name, ID(new_child), p_old, p_new); __xml_node_dirty(new_xml); p->flags |= xpf_moved; if(p_old > p_new) { p = old_child->_private; } else { p = new_child->_private; } p->flags |= xpf_skip; } } } } void xml_calculate_significant_changes(xmlNode *old_xml, xmlNode *new_xml) { pcmk__set_xml_flag(new_xml, xpf_lazy); xml_calculate_changes(old_xml, new_xml); } void xml_calculate_changes(xmlNode *old_xml, xmlNode *new_xml) { CRM_CHECK(safe_str_eq(crm_element_name(old_xml), crm_element_name(new_xml)), return); CRM_CHECK(safe_str_eq(ID(old_xml), ID(new_xml)), return); if(xml_tracking_changes(new_xml) == FALSE) { xml_track_changes(new_xml, NULL, NULL, FALSE); } __xml_diff_object(old_xml, new_xml); } xmlNode * diff_xml_object(xmlNode * old, xmlNode * new, gboolean suppress) { xmlNode *tmp1 = NULL; xmlNode *diff = create_xml_node(NULL, "diff"); xmlNode *removed = create_xml_node(diff, "diff-removed"); xmlNode *added = create_xml_node(diff, "diff-added"); crm_xml_add(diff, XML_ATTR_CRM_VERSION, CRM_FEATURE_SET); tmp1 = subtract_xml_object(removed, old, new, FALSE, NULL, "removed:top"); if (suppress && tmp1 != NULL && can_prune_leaf(tmp1)) { free_xml(tmp1); } tmp1 = subtract_xml_object(added, new, old, TRUE, NULL, "added:top"); if (suppress && tmp1 != NULL && can_prune_leaf(tmp1)) { free_xml(tmp1); } if (added->children == NULL && removed->children == NULL) { free_xml(diff); diff = NULL; } return diff; } gboolean can_prune_leaf(xmlNode * xml_node) { xmlNode *cIter = NULL; xmlAttrPtr pIter = NULL; gboolean can_prune = TRUE; const char *name = crm_element_name(xml_node); if (safe_str_eq(name, XML_TAG_RESOURCE_REF) || safe_str_eq(name, XML_CIB_TAG_OBJ_REF) || safe_str_eq(name, XML_ACL_TAG_ROLE_REF) || safe_str_eq(name, XML_ACL_TAG_ROLE_REFv1)) { return FALSE; } for (pIter = pcmk__first_xml_attr(xml_node); pIter != NULL; pIter = pIter->next) { const char *p_name = (const char *)pIter->name; if (strcmp(p_name, XML_ATTR_ID) == 0) { continue; } can_prune = FALSE; } cIter = __xml_first_child(xml_node); while (cIter) { xmlNode *child = cIter; cIter = __xml_next(cIter); if (can_prune_leaf(child)) { free_xml(child); } else { can_prune = FALSE; } } return can_prune; } static xmlNode * find_xml_comment(xmlNode * root, xmlNode * search_comment, gboolean exact) { xmlNode *a_child = NULL; int search_offset = __xml_offset(search_comment); CRM_CHECK(search_comment->type == XML_COMMENT_NODE, return NULL); for (a_child = __xml_first_child(root); a_child != NULL; a_child = __xml_next(a_child)) { if (exact) { int offset = __xml_offset(a_child); xml_private_t *p = a_child->_private; if (offset < search_offset) { continue; } else if (offset > search_offset) { return NULL; } if (is_set(p->flags, xpf_skip)) { continue; } } if (a_child->type == XML_COMMENT_NODE && safe_str_eq((const char *)a_child->content, (const char *)search_comment->content)) { return a_child; } else if (exact) { return NULL; } } return NULL; } static xmlNode * subtract_xml_comment(xmlNode * parent, xmlNode * left, xmlNode * right, gboolean * changed) { CRM_CHECK(left != NULL, return NULL); CRM_CHECK(left->type == XML_COMMENT_NODE, return NULL); if (right == NULL || safe_str_neq((const char *)left->content, (const char *)right->content)) { xmlNode *deleted = NULL; deleted = add_node_copy(parent, left); *changed = TRUE; return deleted; } return NULL; } xmlNode * subtract_xml_object(xmlNode * parent, xmlNode * left, xmlNode * right, gboolean full, gboolean * changed, const char *marker) { gboolean dummy = FALSE; gboolean skip = FALSE; xmlNode *diff = NULL; xmlNode *right_child = NULL; xmlNode *left_child = NULL; xmlAttrPtr xIter = NULL; const char *id = NULL; const char *name = NULL; const char *value = NULL; const char *right_val = NULL; int lpc = 0; static int filter_len = DIMOF(filter); if (changed == NULL) { changed = &dummy; } if (left == NULL) { return NULL; } if (left->type == XML_COMMENT_NODE) { return subtract_xml_comment(parent, left, right, changed); } id = ID(left); if (right == NULL) { xmlNode *deleted = NULL; crm_trace("Processing <%s id=%s> (complete copy)", crm_element_name(left), id); deleted = add_node_copy(parent, left); crm_xml_add(deleted, XML_DIFF_MARKER, marker); *changed = TRUE; return deleted; } name = crm_element_name(left); CRM_CHECK(name != NULL, return NULL); CRM_CHECK(safe_str_eq(crm_element_name(left), crm_element_name(right)), return NULL); /* check for XML_DIFF_MARKER in a child */ value = crm_element_value(right, XML_DIFF_MARKER); if (value != NULL && strcmp(value, "removed:top") == 0) { crm_trace("We are the root of the deletion: %s.id=%s", name, id); *changed = TRUE; return NULL; } /* Avoiding creating the full heirarchy would save even more work here */ diff = create_xml_node(parent, name); /* Reset filter */ for (lpc = 0; lpc < filter_len; lpc++) { filter[lpc].found = FALSE; } /* changes to child objects */ for (left_child = __xml_first_child(left); left_child != NULL; left_child = __xml_next(left_child)) { gboolean child_changed = FALSE; right_child = find_element(right, left_child, FALSE); subtract_xml_object(diff, left_child, right_child, full, &child_changed, marker); if (child_changed) { *changed = TRUE; } } if (*changed == FALSE) { /* Nothing to do */ } else if (full) { xmlAttrPtr pIter = NULL; for (pIter = pcmk__first_xml_attr(left); pIter != NULL; pIter = pIter->next) { const char *p_name = (const char *)pIter->name; const char *p_value = pcmk__xml_attr_value(pIter); xmlSetProp(diff, (const xmlChar *)p_name, (const xmlChar *)p_value); } /* We already have everything we need... */ goto done; } else if (id) { xmlSetProp(diff, (const xmlChar *)XML_ATTR_ID, (const xmlChar *)id); } /* changes to name/value pairs */ for (xIter = pcmk__first_xml_attr(left); xIter != NULL; xIter = xIter->next) { const char *prop_name = (const char *)xIter->name; xmlAttrPtr right_attr = NULL; xml_private_t *p = NULL; if (strcmp(prop_name, XML_ATTR_ID) == 0) { continue; } skip = FALSE; for (lpc = 0; skip == FALSE && lpc < filter_len; lpc++) { if (filter[lpc].found == FALSE && strcmp(prop_name, filter[lpc].string) == 0) { filter[lpc].found = TRUE; skip = TRUE; break; } } if (skip) { continue; } right_attr = xmlHasProp(right, (const xmlChar *)prop_name); if (right_attr) { p = right_attr->_private; } right_val = crm_element_value(right, prop_name); if (right_val == NULL || (p && is_set(p->flags, xpf_deleted))) { /* new */ *changed = TRUE; if (full) { xmlAttrPtr pIter = NULL; for (pIter = pcmk__first_xml_attr(left); pIter != NULL; pIter = pIter->next) { const char *p_name = (const char *)pIter->name; const char *p_value = pcmk__xml_attr_value(pIter); xmlSetProp(diff, (const xmlChar *)p_name, (const xmlChar *)p_value); } break; } else { const char *left_value = crm_element_value(left, prop_name); xmlSetProp(diff, (const xmlChar *)prop_name, (const xmlChar *)value); crm_xml_add(diff, prop_name, left_value); } } else { /* Only now do we need the left value */ const char *left_value = crm_element_value(left, prop_name); if (strcmp(left_value, right_val) == 0) { /* unchanged */ } else { *changed = TRUE; if (full) { xmlAttrPtr pIter = NULL; crm_trace("Changes detected to %s in <%s id=%s>", prop_name, crm_element_name(left), id); for (pIter = pcmk__first_xml_attr(left); pIter != NULL; pIter = pIter->next) { const char *p_name = (const char *)pIter->name; const char *p_value = pcmk__xml_attr_value(pIter); xmlSetProp(diff, (const xmlChar *)p_name, (const xmlChar *)p_value); } break; } else { crm_trace("Changes detected to %s (%s -> %s) in <%s id=%s>", prop_name, left_value, right_val, crm_element_name(left), id); crm_xml_add(diff, prop_name, left_value); } } } } if (*changed == FALSE) { free_xml(diff); return NULL; } else if (full == FALSE && id) { crm_xml_add(diff, XML_ATTR_ID, id); } done: return diff; } static int add_xml_comment(xmlNode * parent, xmlNode * target, xmlNode * update) { CRM_CHECK(update != NULL, return 0); CRM_CHECK(update->type == XML_COMMENT_NODE, return 0); if (target == NULL) { target = find_xml_comment(parent, update, FALSE); } if (target == NULL) { add_node_copy(parent, update); /* We won't reach here currently */ } else if (safe_str_neq((const char *)target->content, (const char *)update->content)) { xmlFree(target->content); target->content = xmlStrdup(update->content); } return 0; } static int add_xml_object(xmlNode * parent, xmlNode * target, xmlNode * update, gboolean as_diff) { xmlNode *a_child = NULL; const char *object_name = NULL, *object_href = NULL, *object_href_val = NULL; #if XML_PARSE_DEBUG crm_log_xml_trace("update:", update); crm_log_xml_trace("target:", target); #endif CRM_CHECK(update != NULL, return 0); if (update->type == XML_COMMENT_NODE) { return add_xml_comment(parent, target, update); } object_name = crm_element_name(update); 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 0); CRM_CHECK(target != NULL || parent != NULL, return 0); if (target == NULL) { target = find_entity_by_attr_or_just_name(parent, object_name, object_href, object_href_val); } if (target == NULL) { target = create_xml_node(parent, object_name); CRM_CHECK(target != NULL, return 0); #if XML_PARSER_DEBUG crm_trace("Added <%s%s%s%s%s/>", crm_str(object_name), 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", crm_str(object_name), object_href ? " " : "", object_href ? object_href : "", object_href ? "=" : "", object_href ? object_href_val : ""); #endif } CRM_CHECK(safe_str_eq(crm_element_name(target), crm_element_name(update)), return 0); 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 */ xmlAttrPtr pIter = NULL; for (pIter = pcmk__first_xml_attr(update); pIter != NULL; pIter = pIter->next) { const char *p_name = (const char *)pIter->name; const char *p_value = pcmk__xml_attr_value(pIter); /* Remove it first so the ordering of the update is preserved */ xmlUnsetProp(target, (const xmlChar *)p_name); xmlSetProp(target, (const xmlChar *)p_name, (const xmlChar *)p_value); } } for (a_child = __xml_first_child(update); a_child != NULL; a_child = __xml_next(a_child)) { #if XML_PARSER_DEBUG crm_trace("Updating child <%s%s%s%s%s/>", crm_str(object_name), object_href ? " " : "", object_href ? object_href : "", object_href ? "=" : "", object_href ? object_href_val : ""); #endif add_xml_object(target, NULL, a_child, as_diff); } #if XML_PARSER_DEBUG crm_trace("Finished with <%s%s%s%s%s/>", crm_str(object_name), object_href ? " " : "", object_href ? object_href : "", object_href ? "=" : "", object_href ? object_href_val : ""); #endif return 0; } 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 (safe_str_neq(crm_element_name(to_update), crm_element_name(child))) { can_update = FALSE; } else if (safe_str_neq(ID(to_update), ID(child))) { can_update = FALSE; } else if (can_update) { #if XML_PARSER_DEBUG crm_log_xml_trace(child, "Update match found..."); #endif add_xml_object(NULL, child, to_update, FALSE); } for (child_of_child = __xml_first_child(child); child_of_child != NULL; child_of_child = __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 && safe_str_neq(tag, crm_element_name(root))) { } else if (value != NULL && safe_str_neq(value, crm_element_value(root, field))) { } else { if (*children == NULL) { *children = create_xml_node(NULL, __FUNCTION__); } add_node_copy(*children, root); match_found = 1; } if (search_matches || match_found == 0) { xmlNode *child = NULL; for (child = __xml_first_child(root); child != NULL; child = __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 (safe_str_neq(crm_element_name(update), crm_element_name(child))) { can_delete = FALSE; } if (can_delete && delete_only) { xmlAttrPtr pIter = NULL; for (pIter = pcmk__first_xml_attr(update); pIter != NULL; pIter = pIter->next) { const char *p_name = (const char *)pIter->name; const char *p_value = pcmk__xml_attr_value(pIter); right_val = crm_element_value(child, p_name); if (safe_str_neq(p_value, right_val)) { 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 *tmp = copy_xml(update); xmlDoc *doc = tmp->doc; xmlNode *old = NULL; xml_accept_changes(tmp); old = xmlReplaceNode(child, tmp); if(xml_tracking_changes(tmp)) { /* Replaced sections may have included relevant ACLs */ pcmk__apply_acl(tmp); } xml_calculate_changes(old, tmp); xmlDocSetRootElement(doc, old); free_xml(old); } child = NULL; return TRUE; } else if (can_delete) { crm_log_xml_debug(child, "Cannot delete the search root"); can_delete = FALSE; } child_of_child = __xml_first_child(child); while (child_of_child) { xmlNode *next = __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; - GList *nvpairs = NULL; + GSList *nvpairs = NULL; xmlNode *result = NULL; const char *name = NULL; CRM_CHECK(input != NULL, return NULL); name = crm_element_name(input); CRM_CHECK(name != NULL, return NULL); result = create_xml_node(parent, name); nvpairs = pcmk_xml_attrs2nvpairs(input); nvpairs = pcmk_sort_nvpairs(nvpairs); pcmk_nvpairs2xml_attrs(nvpairs, result); pcmk_free_nvpairs(nvpairs); for (child = __xml_first_child(input); child != NULL; child = __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 = __xml_first_child(parent); match != NULL; match = __xml_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 (name == NULL || strcmp((const char *)match->name, name) == 0) { 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 = __xml_next(sibling); const char *name = crm_element_name(sibling); while (match != NULL) { if (!strcmp(crm_element_name(match), name)) { return match; } match = __xml_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 * realloc_safe()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(pcmkDeregisterNode); xmlRegisterNodeDefault(pcmkRegisterNode); crm_schema_init(); } } void crm_xml_cleanup(void) { crm_info("Cleaning up memory from libxml2"); crm_schema_cleanup(); xmlCleanupParser(); } #define XPATH_MAX 512 xmlNode * expand_idref(xmlNode * input, xmlNode * top) { const char *tag = NULL; const char *ref = NULL; xmlNode *result = input; if (result == NULL) { return NULL; } else if (top == NULL) { top = input; } tag = crm_element_name(result); ref = crm_element_value(result, XML_ATTR_IDREF); if (ref != NULL) { char *xpath_string = crm_strdup_printf("//%s[@id='%s']", tag, 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, crm_str(nodePath)); free(nodePath); } free(xpath_string); } return result; } void crm_destroy_xml(gpointer data) { free_xml(data); }