diff --git a/daemons/controld/controld_control.c b/daemons/controld/controld_control.c index a68c46357e..2807544d17 100644 --- a/daemons/controld/controld_control.c +++ b/daemons/controld/controld_control.c @@ -1,874 +1,871 @@ /* * Copyright 2004-2022 the Pacemaker project contributors * * The version control history for this file may have further details. * * This source code is licensed under the GNU General Public License version 2 * or later (GPLv2+) WITHOUT ANY WARRANTY. */ #include #include #include #include #include #include #include #include #include #include #include static qb_ipcs_service_t *ipcs = NULL; static crm_trigger_t *config_read_trigger = NULL; #if SUPPORT_COROSYNC extern gboolean crm_connect_corosync(crm_cluster_t * cluster); #endif void crm_shutdown(int nsig); static gboolean crm_read_options(gpointer user_data); /* A_HA_CONNECT */ void do_ha_control(long long action, enum crmd_fsa_cause cause, enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data) { gboolean registered = FALSE; static crm_cluster_t *cluster = NULL; if (cluster == NULL) { cluster = calloc(1, sizeof(crm_cluster_t)); } if (action & A_HA_DISCONNECT) { crm_cluster_disconnect(cluster); crm_info("Disconnected from the cluster"); controld_set_fsa_input_flags(R_HA_DISCONNECTED); } if (action & A_HA_CONNECT) { crm_set_status_callback(&peer_update_callback); crm_set_autoreap(FALSE); if (is_corosync_cluster()) { #if SUPPORT_COROSYNC registered = crm_connect_corosync(cluster); #endif } if (registered) { controld_election_init(cluster->uname); controld_globals.our_nodename = cluster->uname; controld_globals.our_uuid = cluster->uuid; if(cluster->uuid == NULL) { crm_err("Could not obtain local uuid"); registered = FALSE; } } if (!registered) { controld_set_fsa_input_flags(R_HA_DISCONNECTED); register_fsa_error(C_FSA_INTERNAL, I_ERROR, NULL); return; } populate_cib_nodes(node_update_none, __func__); controld_clear_fsa_input_flags(R_HA_DISCONNECTED); crm_info("Connected to the cluster"); } if (action & ~(A_HA_CONNECT | A_HA_DISCONNECT)) { crm_err("Unexpected action %s in %s", fsa_action2string(action), __func__); } } /* A_SHUTDOWN */ void do_shutdown(long long action, enum crmd_fsa_cause cause, enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data) { /* just in case */ controld_set_fsa_input_flags(R_SHUTDOWN); controld_disconnect_fencer(FALSE); } /* A_SHUTDOWN_REQ */ void do_shutdown_req(long long action, enum crmd_fsa_cause cause, enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data) { xmlNode *msg = NULL; controld_set_fsa_input_flags(R_SHUTDOWN); //controld_set_fsa_input_flags(R_STAYDOWN); crm_info("Sending shutdown request to all peers (DC is %s)", pcmk__s(controld_globals.dc_name, "not set")); msg = create_request(CRM_OP_SHUTDOWN_REQ, NULL, NULL, CRM_SYSTEM_CRMD, CRM_SYSTEM_CRMD, NULL); if (send_cluster_message(NULL, crm_msg_crmd, msg, TRUE) == FALSE) { register_fsa_error(C_FSA_INTERNAL, I_ERROR, NULL); } free_xml(msg); } void crmd_fast_exit(crm_exit_t exit_code) { if (pcmk_is_set(controld_globals.fsa_input_register, R_STAYDOWN)) { crm_warn("Inhibiting respawn "CRM_XS" remapping exit code %d to %d", exit_code, CRM_EX_FATAL); exit_code = CRM_EX_FATAL; } else if ((exit_code == CRM_EX_OK) && pcmk_is_set(controld_globals.fsa_input_register, R_IN_RECOVERY)) { crm_err("Could not recover from internal error"); exit_code = CRM_EX_ERROR; } if (controld_globals.logger_out != NULL) { controld_globals.logger_out->finish(controld_globals.logger_out, exit_code, true, NULL); pcmk__output_free(controld_globals.logger_out); controld_globals.logger_out = NULL; } crm_exit(exit_code); } crm_exit_t crmd_exit(crm_exit_t exit_code) { GMainLoop *mloop = controld_globals.mainloop; static bool in_progress = FALSE; if (in_progress && (exit_code == CRM_EX_OK)) { crm_debug("Exit is already in progress"); return exit_code; } else if(in_progress) { crm_notice("Error during shutdown process, exiting now with status %d (%s)", exit_code, crm_exit_str(exit_code)); crm_write_blackbox(SIGTRAP, NULL); crmd_fast_exit(exit_code); } in_progress = TRUE; crm_trace("Preparing to exit with status %d (%s)", exit_code, crm_exit_str(exit_code)); /* Suppress secondary errors resulting from us disconnecting everything */ controld_set_fsa_input_flags(R_HA_DISCONNECTED); /* Close all IPC servers and clients to ensure any and all shared memory files are cleaned up */ if(ipcs) { crm_trace("Closing IPC server"); mainloop_del_ipc_server(ipcs); ipcs = NULL; } controld_close_attrd_ipc(); controld_shutdown_schedulerd_ipc(); controld_disconnect_fencer(TRUE); if ((exit_code == CRM_EX_OK) && (controld_globals.mainloop == NULL)) { crm_debug("No mainloop detected"); exit_code = CRM_EX_ERROR; } /* On an error, just get out. * * Otherwise, make the effort to have mainloop exit gracefully so * that it (mostly) cleans up after itself and valgrind has less * to report on - allowing real errors stand out */ if (exit_code != CRM_EX_OK) { crm_notice("Forcing immediate exit with status %d (%s)", exit_code, crm_exit_str(exit_code)); crm_write_blackbox(SIGTRAP, NULL); crmd_fast_exit(exit_code); } /* Clean up as much memory as possible for valgrind */ for (GList *iter = controld_globals.fsa_message_queue; iter != NULL; iter = iter->next) { fsa_data_t *fsa_data = (fsa_data_t *) iter->data; crm_info("Dropping %s: [ state=%s cause=%s origin=%s ]", fsa_input2string(fsa_data->fsa_input), fsa_state2string(controld_globals.fsa_state), fsa_cause2string(fsa_data->fsa_cause), fsa_data->origin); delete_fsa_input(fsa_data); } controld_clear_fsa_input_flags(R_MEMBERSHIP); g_list_free(controld_globals.fsa_message_queue); controld_globals.fsa_message_queue = NULL; controld_election_fini(); /* Tear down the CIB manager connection, but don't free it yet -- it could * be used when we drain the mainloop later. */ controld_disconnect_cib_manager(); verify_stopped(controld_globals.fsa_state, LOG_WARNING); controld_clear_fsa_input_flags(R_LRM_CONNECTED); lrm_state_destroy_all(); mainloop_destroy_trigger(config_read_trigger); config_read_trigger = NULL; controld_destroy_fsa_trigger(); controld_destroy_transition_trigger(); pcmk__client_cleanup(); crm_peer_destroy(); controld_free_fsa_timers(); te_cleanup_stonith_history_sync(NULL, TRUE); controld_free_sched_timer(); free(controld_globals.our_nodename); controld_globals.our_nodename = NULL; free(controld_globals.our_uuid); controld_globals.our_uuid = NULL; free(controld_globals.dc_name); controld_globals.dc_name = NULL; free(controld_globals.dc_version); controld_globals.dc_version = NULL; free(controld_globals.cluster_name); controld_globals.cluster_name = NULL; free(controld_globals.te_uuid); controld_globals.te_uuid = NULL; - free(failed_stop_offset); failed_stop_offset = NULL; - free(failed_start_offset); failed_start_offset = NULL; - free_max_generation(); mainloop_destroy_signal(SIGPIPE); mainloop_destroy_signal(SIGUSR1); mainloop_destroy_signal(SIGTERM); mainloop_destroy_signal(SIGTRAP); /* leave SIGCHLD engaged as we might still want to drain some service-actions */ if (mloop) { GMainContext *ctx = g_main_loop_get_context(controld_globals.mainloop); /* Don't re-enter this block */ controld_globals.mainloop = NULL; /* no signals on final draining anymore */ mainloop_destroy_signal(SIGCHLD); crm_trace("Draining mainloop %d %d", g_main_loop_is_running(mloop), g_main_context_pending(ctx)); { int lpc = 0; while((g_main_context_pending(ctx) && lpc < 10)) { lpc++; crm_trace("Iteration %d", lpc); g_main_context_dispatch(ctx); } } crm_trace("Closing mainloop %d %d", g_main_loop_is_running(mloop), g_main_context_pending(ctx)); g_main_loop_quit(mloop); /* Won't do anything yet, since we're inside it now */ g_main_loop_unref(mloop); } else { mainloop_destroy_signal(SIGCHLD); } cib_delete(controld_globals.cib_conn); controld_globals.cib_conn = NULL; throttle_fini(); /* Graceful */ crm_trace("Done preparing for exit with status %d (%s)", exit_code, crm_exit_str(exit_code)); return exit_code; } /* A_EXIT_0, A_EXIT_1 */ void do_exit(long long action, enum crmd_fsa_cause cause, enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data) { crm_exit_t exit_code = CRM_EX_OK; int log_level = LOG_INFO; const char *exit_type = "gracefully"; if (action & A_EXIT_1) { log_level = LOG_ERR; exit_type = "forcefully"; exit_code = CRM_EX_ERROR; } verify_stopped(cur_state, LOG_ERR); do_crm_log(log_level, "Performing %s - %s exiting the controller", fsa_action2string(action), exit_type); crm_info("[%s] stopped (%d)", crm_system_name, exit_code); crmd_exit(exit_code); } static void sigpipe_ignore(int nsig) { return; } /* A_STARTUP */ void do_startup(long long action, enum crmd_fsa_cause cause, enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data) { crm_debug("Registering Signal Handlers"); mainloop_add_signal(SIGTERM, crm_shutdown); mainloop_add_signal(SIGPIPE, sigpipe_ignore); config_read_trigger = mainloop_add_trigger(G_PRIORITY_HIGH, crm_read_options, NULL); controld_init_fsa_trigger(); controld_init_transition_trigger(); crm_debug("Creating CIB manager and executor objects"); controld_globals.cib_conn = cib_new(); lrm_state_init_local(); if (controld_init_fsa_timers() == FALSE) { register_fsa_error(C_FSA_INTERNAL, I_ERROR, NULL); } } // \return libqb error code (0 on success, -errno on error) static int32_t accept_controller_client(qb_ipcs_connection_t *c, uid_t uid, gid_t gid) { crm_trace("Accepting new IPC client connection"); if (pcmk__new_client(c, uid, gid) == NULL) { return -EIO; } return 0; } // \return libqb error code (0 on success, -errno on error) static int32_t dispatch_controller_ipc(qb_ipcs_connection_t * c, void *data, size_t size) { uint32_t id = 0; uint32_t flags = 0; pcmk__client_t *client = pcmk__find_client(c); xmlNode *msg = pcmk__client_data2xml(client, data, &id, &flags); if (msg == NULL) { pcmk__ipc_send_ack(client, id, flags, "ack", NULL, CRM_EX_PROTOCOL); return 0; } pcmk__ipc_send_ack(client, id, flags, "ack", NULL, CRM_EX_INDETERMINATE); CRM_ASSERT(client->user != NULL); pcmk__update_acl_user(msg, F_CRM_USER, client->user); crm_xml_add(msg, F_CRM_SYS_FROM, client->id); if (controld_authorize_ipc_message(msg, client, NULL)) { crm_trace("Processing IPC message from client %s", pcmk__client_name(client)); route_message(C_IPC_MESSAGE, msg); } controld_trigger_fsa(); free_xml(msg); return 0; } static int32_t ipc_client_disconnected(qb_ipcs_connection_t *c) { pcmk__client_t *client = pcmk__find_client(c); if (client) { crm_trace("Disconnecting %sregistered client %s (%p/%p)", (client->userdata? "" : "un"), pcmk__client_name(client), c, client); free(client->userdata); pcmk__free_client(client); controld_trigger_fsa(); } return 0; } static void ipc_connection_destroyed(qb_ipcs_connection_t *c) { crm_trace("Connection %p", c); ipc_client_disconnected(c); } /* A_STOP */ void do_stop(long long action, enum crmd_fsa_cause cause, enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data) { crm_trace("Closing IPC server"); mainloop_del_ipc_server(ipcs); ipcs = NULL; register_fsa_input(C_FSA_INTERNAL, I_TERMINATE, NULL); } /* A_STARTED */ void do_started(long long action, enum crmd_fsa_cause cause, enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data) { static struct qb_ipcs_service_handlers crmd_callbacks = { .connection_accept = accept_controller_client, .connection_created = NULL, .msg_process = dispatch_controller_ipc, .connection_closed = ipc_client_disconnected, .connection_destroyed = ipc_connection_destroyed }; if (cur_state != S_STARTING) { crm_err("Start cancelled... %s", fsa_state2string(cur_state)); return; } else if (!pcmk_is_set(controld_globals.fsa_input_register, R_MEMBERSHIP)) { crm_info("Delaying start, no membership data (%.16llx)", R_MEMBERSHIP); crmd_fsa_stall(TRUE); return; } else if (!pcmk_is_set(controld_globals.fsa_input_register, R_LRM_CONNECTED)) { crm_info("Delaying start, not connected to executor (%.16llx)", R_LRM_CONNECTED); crmd_fsa_stall(TRUE); return; } else if (!pcmk_is_set(controld_globals.fsa_input_register, R_CIB_CONNECTED)) { crm_info("Delaying start, CIB not connected (%.16llx)", R_CIB_CONNECTED); crmd_fsa_stall(TRUE); return; } else if (!pcmk_is_set(controld_globals.fsa_input_register, R_READ_CONFIG)) { crm_info("Delaying start, Config not read (%.16llx)", R_READ_CONFIG); crmd_fsa_stall(TRUE); return; } else if (!pcmk_is_set(controld_globals.fsa_input_register, R_PEER_DATA)) { crm_info("Delaying start, No peer data (%.16llx)", R_PEER_DATA); crmd_fsa_stall(TRUE); return; } crm_debug("Init server comms"); ipcs = pcmk__serve_controld_ipc(&crmd_callbacks); if (ipcs == NULL) { crm_err("Failed to create IPC server: shutting down and inhibiting respawn"); register_fsa_error(C_FSA_INTERNAL, I_ERROR, NULL); } else { crm_notice("Pacemaker controller successfully started and accepting connections"); } controld_trigger_fencer_connect(); controld_clear_fsa_input_flags(R_STARTING); register_fsa_input(msg_data->fsa_cause, I_PENDING, NULL); } /* A_RECOVER */ void do_recover(long long action, enum crmd_fsa_cause cause, enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data) { controld_set_fsa_input_flags(R_IN_RECOVERY); crm_warn("Fast-tracking shutdown in response to errors"); register_fsa_input(C_FSA_INTERNAL, I_TERMINATE, NULL); } static pcmk__cluster_option_t controller_options[] = { /* name, old name, type, allowed values, * default value, validator, * short description, * long description */ { "dc-version", NULL, "string", NULL, PCMK__VALUE_NONE, NULL, N_("Pacemaker version on cluster node elected Designated Controller (DC)"), N_("Includes a hash which identifies the exact changeset the code was " "built from. Used for diagnostic purposes.") }, { "cluster-infrastructure", NULL, "string", NULL, "corosync", NULL, N_("The messaging stack on which Pacemaker is currently running"), N_("Used for informational and diagnostic purposes.") }, { "cluster-name", NULL, "string", NULL, NULL, NULL, N_("An arbitrary name for the cluster"), N_("This optional value is mostly for users' convenience as desired " "in administration, but may also be used in Pacemaker " "configuration rules via the #cluster-name node attribute, and " "by higher-level tools and resource agents.") }, { XML_CONFIG_ATTR_DC_DEADTIME, NULL, "time", NULL, "20s", pcmk__valid_interval_spec, N_("How long to wait for a response from other nodes during start-up"), N_("The optimal value will depend on the speed and load of your network " "and the type of switches used.") }, { XML_CONFIG_ATTR_RECHECK, NULL, "time", N_("Zero disables polling, while positive values are an interval in seconds" "(unless other units are specified, for example \"5min\")"), "15min", pcmk__valid_interval_spec, N_("Polling interval to recheck cluster state and evaluate rules " "with date specifications"), N_("Pacemaker is primarily event-driven, and looks ahead to know when to " "recheck cluster state for failure timeouts and most time-based " "rules. However, it will also recheck the cluster after this " "amount of inactivity, to evaluate rules with date specifications " "and serve as a fail-safe for certain types of scheduler bugs.") }, { "load-threshold", NULL, "percentage", NULL, "80%", pcmk__valid_percentage, N_("Maximum amount of system load that should be used by cluster nodes"), N_("The cluster will slow down its recovery process when the amount of " "system resources used (currently CPU) approaches this limit"), }, { "node-action-limit", NULL, "integer", NULL, "0", pcmk__valid_number, N_("Maximum number of jobs that can be scheduled per node " "(defaults to 2x cores)") }, { XML_CONFIG_ATTR_FENCE_REACTION, NULL, "string", NULL, "stop", NULL, N_("How a cluster node should react if notified of its own fencing"), N_("A cluster node may receive notification of its own fencing if fencing " "is misconfigured, or if fabric fencing is in use that doesn't cut " "cluster communication. Allowed values are \"stop\" to attempt to " "immediately stop Pacemaker and stay stopped, or \"panic\" to attempt " "to immediately reboot the local node, falling back to stop on failure.") }, { XML_CONFIG_ATTR_ELECTION_FAIL, NULL, "time", NULL, "2min", pcmk__valid_interval_spec, "*** Advanced Use Only ***", N_("Declare an election failed if it is not decided within this much " "time. If you need to adjust this value, it probably indicates " "the presence of a bug.") }, { XML_CONFIG_ATTR_FORCE_QUIT, NULL, "time", NULL, "20min", pcmk__valid_interval_spec, "*** Advanced Use Only ***", N_("Exit immediately if shutdown does not complete within this much " "time. If you need to adjust this value, it probably indicates " "the presence of a bug.") }, { "join-integration-timeout", "crmd-integration-timeout", "time", NULL, "3min", pcmk__valid_interval_spec, "*** Advanced Use Only ***", N_("If you need to adjust this value, it probably indicates " "the presence of a bug.") }, { "join-finalization-timeout", "crmd-finalization-timeout", "time", NULL, "30min", pcmk__valid_interval_spec, "*** Advanced Use Only ***", N_("If you need to adjust this value, it probably indicates " "the presence of a bug.") }, { "transition-delay", "crmd-transition-delay", "time", NULL, "0s", pcmk__valid_interval_spec, N_("*** Advanced Use Only *** Enabling this option will slow down " "cluster recovery under all conditions"), N_("Delay cluster recovery for this much time to allow for additional " "events to occur. Useful if your configuration is sensitive to " "the order in which ping updates arrive.") }, { "stonith-watchdog-timeout", NULL, "time", NULL, "0", controld_verify_stonith_watchdog_timeout, N_("How long before nodes can be assumed to be safely down when " "watchdog-based self-fencing via SBD is in use"), N_("If this is set to a positive value, lost nodes are assumed to " "self-fence using watchdog-based SBD within this much time. This " "does not require a fencing resource to be explicitly configured, " "though a fence_watchdog resource can be configured, to limit use " "to specific nodes. If this is set to 0 (the default), the cluster " "will never assume watchdog-based self-fencing. If this is set to a " "negative value, the cluster will use twice the local value of the " "`SBD_WATCHDOG_TIMEOUT` environment variable if that is positive, " "or otherwise treat this as 0. WARNING: When used, this timeout " "must be larger than `SBD_WATCHDOG_TIMEOUT` on all nodes that use " "watchdog-based SBD, and Pacemaker will refuse to start on any of " "those nodes where this is not true for the local value or SBD is " "not active. When this is set to a negative value, " "`SBD_WATCHDOG_TIMEOUT` must be set to the same value on all nodes " "that use SBD, otherwise data corruption or loss could occur.") }, { "stonith-max-attempts", NULL, "integer", NULL, "10", pcmk__valid_positive_number, N_("How many times fencing can fail before it will no longer be " "immediately re-attempted on a target") }, // Already documented in libpe_status (other values must be kept identical) { "no-quorum-policy", NULL, "select", "stop, freeze, ignore, demote, suicide", "stop", pcmk__valid_quorum, "What to do when the cluster does not have quorum", NULL }, { XML_CONFIG_ATTR_SHUTDOWN_LOCK, NULL, "boolean", NULL, "false", pcmk__valid_boolean, "Whether to lock resources to a cleanly shut down node", "When true, resources active on a node when it is cleanly shut down " "are kept \"locked\" to that node (not allowed to run elsewhere) " "until they start again on that node after it rejoins (or for at " "most shutdown-lock-limit, if set). Stonith resources and " "Pacemaker Remote connections are never locked. Clone and bundle " "instances and the promoted role of promotable clones are currently" " never locked, though support could be added in a future release." }, }; void crmd_metadata(void) { const char *desc_short = "Pacemaker controller options"; const char *desc_long = "Cluster options used by Pacemaker's controller"; gchar *s = pcmk__format_option_metadata("pacemaker-controld", desc_short, desc_long, controller_options, PCMK__NELEM(controller_options)); printf("%s", s); g_free(s); } static const char * controller_option(GHashTable *options, const char *name) { return pcmk__cluster_option(options, controller_options, PCMK__NELEM(controller_options), name); } static void config_query_callback(xmlNode * msg, int call_id, int rc, xmlNode * output, void *user_data) { const char *value = NULL; GHashTable *config_hash = NULL; crm_time_t *now = crm_time_new(NULL); xmlNode *crmconfig = NULL; xmlNode *alerts = NULL; if (rc != pcmk_ok) { fsa_data_t *msg_data = NULL; crm_err("Local CIB query resulted in an error: %s", pcmk_strerror(rc)); register_fsa_error(C_FSA_INTERNAL, I_ERROR, NULL); if (rc == -EACCES || rc == -pcmk_err_schema_validation) { crm_err("The cluster is mis-configured - shutting down and staying down"); controld_set_fsa_input_flags(R_STAYDOWN); } goto bail; } crmconfig = output; if ((crmconfig) && (crm_element_name(crmconfig)) && (strcmp(crm_element_name(crmconfig), XML_CIB_TAG_CRMCONFIG) != 0)) { crmconfig = first_named_child(crmconfig, XML_CIB_TAG_CRMCONFIG); } if (!crmconfig) { fsa_data_t *msg_data = NULL; crm_err("Local CIB query for " XML_CIB_TAG_CRMCONFIG " section failed"); register_fsa_error(C_FSA_INTERNAL, I_ERROR, NULL); goto bail; } crm_debug("Call %d : Parsing CIB options", call_id); config_hash = pcmk__strkey_table(free, free); pe_unpack_nvpairs(crmconfig, crmconfig, XML_CIB_TAG_PROPSET, NULL, config_hash, CIB_OPTIONS_FIRST, FALSE, now, NULL); pcmk__validate_cluster_options(config_hash, controller_options, PCMK__NELEM(controller_options)); value = controller_option(config_hash, XML_CONFIG_ATTR_DC_DEADTIME); election_timer->period_ms = crm_parse_interval_spec(value); value = controller_option(config_hash, "node-action-limit"); throttle_update_job_max(value); value = controller_option(config_hash, "load-threshold"); if(value) { throttle_set_load_target(strtof(value, NULL) / 100.0); } value = controller_option(config_hash, "no-quorum-policy"); if (pcmk__str_eq(value, "suicide", pcmk__str_casei) && pcmk__locate_sbd()) { controld_set_global_flags(controld_no_quorum_suicide); } set_fence_reaction(controller_option(config_hash, XML_CONFIG_ATTR_FENCE_REACTION)); value = controller_option(config_hash, "stonith-max-attempts"); update_stonith_max_attempts(value); value = controller_option(config_hash, XML_CONFIG_ATTR_FORCE_QUIT); shutdown_escalation_timer->period_ms = crm_parse_interval_spec(value); crm_debug("Shutdown escalation occurs if DC has not responded to request in %ums", shutdown_escalation_timer->period_ms); value = controller_option(config_hash, XML_CONFIG_ATTR_ELECTION_FAIL); controld_set_election_period(value); value = controller_option(config_hash, XML_CONFIG_ATTR_RECHECK); recheck_interval_ms = crm_parse_interval_spec(value); crm_debug("Re-run scheduler after %dms of inactivity", recheck_interval_ms); value = controller_option(config_hash, "transition-delay"); transition_timer->period_ms = crm_parse_interval_spec(value); value = controller_option(config_hash, "join-integration-timeout"); integration_timer->period_ms = crm_parse_interval_spec(value); value = controller_option(config_hash, "join-finalization-timeout"); finalization_timer->period_ms = crm_parse_interval_spec(value); value = controller_option(config_hash, XML_CONFIG_ATTR_SHUTDOWN_LOCK); if (crm_is_true(value)) { controld_set_global_flags(controld_shutdown_lock_enabled); } else { controld_clear_global_flags(controld_shutdown_lock_enabled); } value = g_hash_table_lookup(config_hash, "cluster-name"); pcmk__str_update(&(controld_globals.cluster_name), value); alerts = first_named_child(output, XML_CIB_TAG_ALERTS); crmd_unpack_alerts(alerts); controld_set_fsa_input_flags(R_READ_CONFIG); controld_trigger_fsa(); g_hash_table_destroy(config_hash); bail: crm_time_free(now); } /*! * \internal * \brief Trigger read and processing of the configuration * * \param[in] fn Calling function name * \param[in] line Line number where call occurred */ void controld_trigger_config_as(const char *fn, int line) { if (config_read_trigger != NULL) { crm_trace("%s:%d - Triggered config processing", fn, line); mainloop_set_trigger(config_read_trigger); } } gboolean crm_read_options(gpointer user_data) { cib_t *cib_conn = controld_globals.cib_conn; int call_id = cib_conn->cmds->query(cib_conn, "//" XML_CIB_TAG_CRMCONFIG " | //" XML_CIB_TAG_ALERTS, NULL, cib_xpath|cib_scope_local); fsa_register_cib_callback(call_id, FALSE, NULL, config_query_callback); crm_trace("Querying the CIB... call %d", call_id); return TRUE; } /* A_READCONFIG */ void do_read_config(long long action, enum crmd_fsa_cause cause, enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data) { throttle_init(); controld_trigger_config(); } void crm_shutdown(int nsig) { if ((controld_globals.mainloop == NULL) || !g_main_loop_is_running(controld_globals.mainloop)) { crmd_exit(CRM_EX_OK); return; } if (pcmk_is_set(controld_globals.fsa_input_register, R_SHUTDOWN)) { crm_err("Escalating shutdown"); register_fsa_input_before(C_SHUTDOWN, I_ERROR, NULL); return; } controld_set_fsa_input_flags(R_SHUTDOWN); register_fsa_input(C_SHUTDOWN, I_SHUTDOWN, NULL); if (shutdown_escalation_timer->period_ms == 0) { const char *value = controller_option(NULL, XML_CONFIG_ATTR_FORCE_QUIT); shutdown_escalation_timer->period_ms = crm_parse_interval_spec(value); } crm_notice("Initiating controller shutdown sequence " CRM_XS " limit=%ums", shutdown_escalation_timer->period_ms); controld_start_timer(shutdown_escalation_timer); } diff --git a/daemons/controld/controld_te_events.c b/daemons/controld/controld_te_events.c index f798ce2066..443c751a7c 100644 --- a/daemons/controld/controld_te_events.c +++ b/daemons/controld/controld_te_events.c @@ -1,547 +1,541 @@ /* * Copyright 2004-2022 the Pacemaker project contributors * * The version control history for this file may have further details. * * This source code is licensed under the GNU General Public License version 2 * or later (GPLv2+) WITHOUT ANY WARRANTY. */ #include #include #include #include #include #include #include #include #include -char *failed_stop_offset = NULL; -char *failed_start_offset = NULL; - gboolean fail_incompletable_actions(pcmk__graph_t *graph, const char *down_node) { const char *target_uuid = NULL; const char *router = NULL; const char *router_uuid = NULL; xmlNode *last_action = NULL; GList *gIter = NULL; GList *gIter2 = NULL; if (graph == NULL || graph->complete) { return FALSE; } gIter = graph->synapses; for (; gIter != NULL; gIter = gIter->next) { pcmk__graph_synapse_t *synapse = (pcmk__graph_synapse_t *) gIter->data; if (pcmk_any_flags_set(synapse->flags, pcmk__synapse_confirmed|pcmk__synapse_failed)) { /* We've already been here */ continue; } gIter2 = synapse->actions; for (; gIter2 != NULL; gIter2 = gIter2->next) { pcmk__graph_action_t *action = (pcmk__graph_action_t *) gIter2->data; if ((action->type == pcmk__pseudo_graph_action) || pcmk_is_set(action->flags, pcmk__graph_action_confirmed)) { continue; } else if (action->type == pcmk__cluster_graph_action) { const char *task = crm_element_value(action->xml, XML_LRM_ATTR_TASK); if (pcmk__str_eq(task, CRM_OP_FENCE, pcmk__str_casei)) { continue; } } target_uuid = crm_element_value(action->xml, XML_LRM_ATTR_TARGET_UUID); router = crm_element_value(action->xml, XML_LRM_ATTR_ROUTER_NODE); if (router) { crm_node_t *node = crm_get_peer(0, router); if (node) { router_uuid = node->uuid; } } if (pcmk__str_eq(target_uuid, down_node, pcmk__str_casei) || pcmk__str_eq(router_uuid, down_node, pcmk__str_casei)) { pcmk__set_graph_action_flags(action, pcmk__graph_action_failed); pcmk__set_synapse_flags(synapse, pcmk__synapse_failed); last_action = action->xml; stop_te_timer(action); pcmk__update_graph(graph, action); if (pcmk_is_set(synapse->flags, pcmk__synapse_executed)) { crm_notice("Action %d (%s) was pending on %s (offline)", action->id, crm_element_value(action->xml, XML_LRM_ATTR_TASK_KEY), down_node); } else { crm_info("Action %d (%s) is scheduled for %s (offline)", action->id, crm_element_value(action->xml, XML_LRM_ATTR_TASK_KEY), down_node); } } } } if (last_action != NULL) { crm_info("Node %s shutdown resulted in un-runnable actions", down_node); abort_transition(INFINITY, pcmk__graph_restart, "Node failure", last_action); return TRUE; } return FALSE; } /*! * \internal * \brief Update failure-related node attributes if warranted * * \param[in] event XML describing operation that (maybe) failed * \param[in] event_node_uuid Node that event occurred on * \param[in] rc Actual operation return code * \param[in] target_rc Expected operation return code * \param[in] do_update If TRUE, do update regardless of operation type * \param[in] ignore_failures If TRUE, update last failure but not fail count * * \return TRUE if this was not a direct nack, success or lrm status refresh */ static gboolean update_failcount(const xmlNode *event, const char *event_node_uuid, int rc, int target_rc, gboolean do_update, gboolean ignore_failures) { guint interval_ms = 0; char *task = NULL; char *rsc_id = NULL; const char *value = NULL; const char *id = crm_element_value(event, XML_LRM_ATTR_TASK_KEY); const char *on_uname = crm_peer_uname(event_node_uuid); const char *origin = crm_element_value(event, XML_ATTR_ORIGIN); // Nothing needs to be done for success or status refresh if (rc == target_rc) { return FALSE; } else if (pcmk__str_eq(origin, "build_active_RAs", pcmk__str_casei)) { crm_debug("No update for %s (rc=%d) on %s: Old failure from lrm status refresh", id, rc, on_uname); return FALSE; } /* Sanity check */ CRM_CHECK(on_uname != NULL, return TRUE); CRM_CHECK(parse_op_key(id, &rsc_id, &task, &interval_ms), crm_err("Couldn't parse: %s", ID(event)); goto bail); /* Decide whether update is necessary and what value to use */ - if ((interval_ms > 0) || pcmk__str_eq(task, CRMD_ACTION_PROMOTE, pcmk__str_casei) - || pcmk__str_eq(task, CRMD_ACTION_DEMOTE, pcmk__str_casei)) { + if ((interval_ms > 0) + || pcmk__str_eq(task, CRMD_ACTION_PROMOTE, pcmk__str_none) + || pcmk__str_eq(task, CRMD_ACTION_DEMOTE, pcmk__str_none)) { do_update = TRUE; - } else if (pcmk__str_eq(task, CRMD_ACTION_START, pcmk__str_casei)) { + } else if (pcmk__str_eq(task, CRMD_ACTION_START, pcmk__str_none)) { do_update = TRUE; - if (failed_start_offset == NULL) { - failed_start_offset = strdup(CRM_INFINITY_S); - } - value = failed_start_offset; + value = pcmk__s(controld_globals.transition_graph->failed_start_offset, + CRM_INFINITY_S); - } else if (pcmk__str_eq(task, CRMD_ACTION_STOP, pcmk__str_casei)) { + } else if (pcmk__str_eq(task, CRMD_ACTION_STOP, pcmk__str_none)) { do_update = TRUE; - if (failed_stop_offset == NULL) { - failed_stop_offset = strdup(CRM_INFINITY_S); - } - value = failed_stop_offset; + value = pcmk__s(controld_globals.transition_graph->failed_stop_offset, + CRM_INFINITY_S); } /* Fail count will be either incremented or set to infinity */ if (!pcmk_str_is_infinity(value)) { value = XML_NVPAIR_ATTR_VALUE "++"; } if (do_update) { pcmk__attrd_query_pair_t *fail_pair = NULL; pcmk__attrd_query_pair_t *last_pair = NULL; char *fail_name = NULL; char *last_name = NULL; GList *attrs = NULL; uint32_t opts = pcmk__node_attr_none; char *now = pcmk__ttoa(time(NULL)); if (g_hash_table_lookup(crm_remote_peer_cache, event_node_uuid)) { opts |= pcmk__node_attr_remote; } crm_info("Updating %s for %s on %s after failed %s: rc=%d (update=%s, time=%s)", (ignore_failures? "last failure" : "failcount"), rsc_id, on_uname, task, rc, value, now); /* Update the fail count, if we're not ignoring failures */ if (!ignore_failures) { fail_pair = calloc(1, sizeof(pcmk__attrd_query_pair_t)); CRM_ASSERT(fail_pair != NULL); fail_name = pcmk__failcount_name(rsc_id, task, interval_ms); fail_pair->name = fail_name; fail_pair->value = value; fail_pair->node = on_uname; attrs = g_list_prepend(attrs, fail_pair); } /* Update the last failure time (even if we're ignoring failures, * so that failure can still be detected and shown, e.g. by crm_mon) */ last_pair = calloc(1, sizeof(pcmk__attrd_query_pair_t)); CRM_ASSERT(last_pair != NULL); last_name = pcmk__lastfailure_name(rsc_id, task, interval_ms); last_pair->name = last_name; last_pair->value = now; last_pair->node = on_uname; attrs = g_list_prepend(attrs, last_pair); update_attrd_list(attrs, opts); if (!ignore_failures) { free(fail_name); free(fail_pair); } free(last_name); free(last_pair); g_list_free(attrs); free(now); } bail: free(rsc_id); free(task); return TRUE; } pcmk__graph_action_t * controld_get_action(int id) { for (GList *item = controld_globals.transition_graph->synapses; item != NULL; item = item->next) { pcmk__graph_synapse_t *synapse = (pcmk__graph_synapse_t *) item->data; for (GList *item2 = synapse->actions; item2; item2 = item2->next) { pcmk__graph_action_t *action = (pcmk__graph_action_t *) item2->data; if (action->id == id) { return action; } } } return NULL; } pcmk__graph_action_t * get_cancel_action(const char *id, const char *node) { GList *gIter = NULL; GList *gIter2 = NULL; gIter = controld_globals.transition_graph->synapses; for (; gIter != NULL; gIter = gIter->next) { pcmk__graph_synapse_t *synapse = (pcmk__graph_synapse_t *) gIter->data; gIter2 = synapse->actions; for (; gIter2 != NULL; gIter2 = gIter2->next) { const char *task = NULL; const char *target = NULL; pcmk__graph_action_t *action = (pcmk__graph_action_t *) gIter2->data; task = crm_element_value(action->xml, XML_LRM_ATTR_TASK); if (!pcmk__str_eq(CRMD_ACTION_CANCEL, task, pcmk__str_casei)) { continue; } task = crm_element_value(action->xml, XML_LRM_ATTR_TASK_KEY); if (!pcmk__str_eq(task, id, pcmk__str_casei)) { crm_trace("Wrong key %s for %s on %s", task, id, node); continue; } target = crm_element_value(action->xml, XML_LRM_ATTR_TARGET_UUID); if (node && !pcmk__str_eq(target, node, pcmk__str_casei)) { crm_trace("Wrong node %s for %s on %s", target, id, node); continue; } crm_trace("Found %s on %s", id, node); return action; } } return NULL; } bool confirm_cancel_action(const char *id, const char *node_id) { const char *op_key = NULL; const char *node_name = NULL; pcmk__graph_action_t *cancel = get_cancel_action(id, node_id); if (cancel == NULL) { return FALSE; } op_key = crm_element_value(cancel->xml, XML_LRM_ATTR_TASK_KEY); node_name = crm_element_value(cancel->xml, XML_LRM_ATTR_TARGET); stop_te_timer(cancel); te_action_confirmed(cancel, controld_globals.transition_graph); crm_info("Cancellation of %s on %s confirmed (action %d)", op_key, node_name, cancel->id); return TRUE; } /* downed nodes are listed like: ... */ #define XPATH_DOWNED "//" XML_GRAPH_TAG_DOWNED \ "/" XML_CIB_TAG_NODE "[@" XML_ATTR_UUID "='%s']" /*! * \brief Find a transition event that would have made a specified node down * * \param[in] target UUID of node to match * * \return Matching event if found, NULL otherwise */ pcmk__graph_action_t * match_down_event(const char *target) { pcmk__graph_action_t *match = NULL; xmlXPathObjectPtr xpath_ret = NULL; GList *gIter, *gIter2; char *xpath = crm_strdup_printf(XPATH_DOWNED, target); for (gIter = controld_globals.transition_graph->synapses; gIter != NULL && match == NULL; gIter = gIter->next) { for (gIter2 = ((pcmk__graph_synapse_t * ) gIter->data)->actions; gIter2 != NULL && match == NULL; gIter2 = gIter2->next) { match = (pcmk__graph_action_t *) gIter2->data; if (pcmk_is_set(match->flags, pcmk__graph_action_executed)) { xpath_ret = xpath_search(match->xml, xpath); if (numXpathResults(xpath_ret) < 1) { match = NULL; } freeXpathObject(xpath_ret); } else { // Only actions that were actually started can match match = NULL; } } } free(xpath); if (match != NULL) { crm_debug("Shutdown action %d (%s) found for node %s", match->id, crm_element_value(match->xml, XML_LRM_ATTR_TASK_KEY), target); } else { crm_debug("No reason to expect node %s to be down", target); } return match; } void process_graph_event(xmlNode *event, const char *event_node) { int rc = -1; // Actual result int target_rc = -1; // Expected result int status = -1; // Executor status int callid = -1; // Executor call ID int transition_num = -1; // Transition number int action_num = -1; // Action number within transition char *update_te_uuid = NULL; bool ignore_failures = FALSE; const char *id = NULL; const char *desc = NULL; const char *magic = NULL; const char *uname = NULL; CRM_ASSERT(event != NULL); /* */ magic = crm_element_value(event, XML_ATTR_TRANSITION_KEY); if (magic == NULL) { /* non-change */ return; } crm_element_value_int(event, XML_LRM_ATTR_OPSTATUS, &status); if (status == PCMK_EXEC_PENDING) { return; } id = crm_element_value(event, XML_LRM_ATTR_TASK_KEY); crm_element_value_int(event, XML_LRM_ATTR_RC, &rc); crm_element_value_int(event, XML_LRM_ATTR_CALLID, &callid); rc = pcmk__effective_rc(rc); if (decode_transition_key(magic, &update_te_uuid, &transition_num, &action_num, &target_rc) == FALSE) { // decode_transition_key() already logged the bad key crm_err("Can't process action %s result: Incompatible versions? " CRM_XS " call-id=%d", id, callid); abort_transition(INFINITY, pcmk__graph_restart, "Bad event", event); return; } if (transition_num == -1) { // E.g. crm_resource --fail desc = "initiated outside of the cluster"; abort_transition(INFINITY, pcmk__graph_restart, "Unexpected event", event); } else if ((action_num < 0) || !pcmk__str_eq(update_te_uuid, controld_globals.te_uuid, pcmk__str_none)) { desc = "initiated by a different DC"; abort_transition(INFINITY, pcmk__graph_restart, "Foreign event", event); } else if ((controld_globals.transition_graph->id != transition_num) || controld_globals.transition_graph->complete) { // Action is not from currently active transition guint interval_ms = 0; if (parse_op_key(id, NULL, NULL, &interval_ms) && (interval_ms != 0)) { /* Recurring actions have the transition number they were first * scheduled in. */ if (status == PCMK_EXEC_CANCELLED) { confirm_cancel_action(id, get_node_id(event)); goto bail; } desc = "arrived after initial scheduling"; abort_transition(INFINITY, pcmk__graph_restart, "Change in recurring result", event); } else if (controld_globals.transition_graph->id != transition_num) { desc = "arrived really late"; abort_transition(INFINITY, pcmk__graph_restart, "Old event", event); } else { desc = "arrived late"; abort_transition(INFINITY, pcmk__graph_restart, "Inactive graph", event); } } else { // Event is result of an action from currently active transition pcmk__graph_action_t *action = controld_get_action(action_num); if (action == NULL) { // Should never happen desc = "unknown"; abort_transition(INFINITY, pcmk__graph_restart, "Unknown event", event); } else if (pcmk_is_set(action->flags, pcmk__graph_action_confirmed)) { /* Nothing further needs to be done if the action has already been * confirmed. This can happen e.g. when processing both an * "xxx_last_0" or "xxx_last_failure_0" record as well as the main * history record, which would otherwise result in incorrectly * bumping the fail count twice. */ crm_log_xml_debug(event, "Event already confirmed:"); goto bail; } else { /* An action result needs to be confirmed. * (This is the only case where desc == NULL.) */ if (pcmk__str_eq(crm_meta_value(action->params, XML_OP_ATTR_ON_FAIL), "ignore", pcmk__str_casei)) { ignore_failures = TRUE; } else if (rc != target_rc) { pcmk__set_graph_action_flags(action, pcmk__graph_action_failed); } stop_te_timer(action); te_action_confirmed(action, controld_globals.transition_graph); if (pcmk_is_set(action->flags, pcmk__graph_action_failed)) { abort_transition(action->synapse->priority + 1, pcmk__graph_restart, "Event failed", event); } } } if (id == NULL) { id = "unknown action"; } uname = crm_element_value(event, XML_LRM_ATTR_TARGET); if (uname == NULL) { uname = "unknown node"; } if (status == PCMK_EXEC_INVALID) { // We couldn't attempt the action crm_info("Transition %d action %d (%s on %s): %s", transition_num, action_num, id, uname, pcmk_exec_status_str(status)); } else if (desc && update_failcount(event, event_node, rc, target_rc, (transition_num == -1), FALSE)) { crm_notice("Transition %d action %d (%s on %s): expected '%s' but got '%s' " CRM_XS " target-rc=%d rc=%d call-id=%d event='%s'", transition_num, action_num, id, uname, services_ocf_exitcode_str(target_rc), services_ocf_exitcode_str(rc), target_rc, rc, callid, desc); } else if (desc) { crm_info("Transition %d action %d (%s on %s): %s " CRM_XS " rc=%d target-rc=%d call-id=%d", transition_num, action_num, id, uname, desc, rc, target_rc, callid); } else if (rc == target_rc) { crm_info("Transition %d action %d (%s on %s) confirmed: %s " CRM_XS " rc=%d call-id=%d", transition_num, action_num, id, uname, services_ocf_exitcode_str(rc), rc, callid); } else { update_failcount(event, event_node, rc, target_rc, (transition_num == -1), ignore_failures); crm_notice("Transition %d action %d (%s on %s): expected '%s' but got '%s' " CRM_XS " target-rc=%d rc=%d call-id=%d", transition_num, action_num, id, uname, services_ocf_exitcode_str(target_rc), services_ocf_exitcode_str(rc), target_rc, rc, callid); } bail: free(update_te_uuid); } diff --git a/daemons/controld/controld_transition.c b/daemons/controld/controld_transition.c index c93ed85f0d..f2330b28c9 100644 --- a/daemons/controld/controld_transition.c +++ b/daemons/controld/controld_transition.c @@ -1,214 +1,202 @@ /* * Copyright 2004-2022 the Pacemaker project contributors * * The version control history for this file may have further details. * * This source code is licensed under the GNU General Public License version 2 * or later (GPLv2+) WITHOUT ANY WARRANTY. */ #include #include #include #include #include static void global_cib_callback(const xmlNode * msg, int callid, int rc, xmlNode * output) { } static pcmk__graph_t * create_blank_graph(void) { pcmk__graph_t *a_graph = pcmk__unpack_graph(NULL, NULL); a_graph->complete = true; a_graph->abort_reason = "DC Takeover"; a_graph->completion_action = pcmk__graph_restart; return a_graph; } /* A_TE_START, A_TE_STOP, O_TE_RESTART */ void do_te_control(long long action, enum crmd_fsa_cause cause, enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data) { cib_t *cib_conn = controld_globals.cib_conn; gboolean init_ok = TRUE; if (pcmk_is_set(action, A_TE_STOP)) { pcmk__free_graph(controld_globals.transition_graph); controld_globals.transition_graph = NULL; if (cib_conn != NULL) { cib_conn->cmds->del_notify_callback(cib_conn, T_CIB_DIFF_NOTIFY, te_update_diff); } controld_clear_fsa_input_flags(R_TE_CONNECTED); crm_info("Transitioner is now inactive"); } if ((action & A_TE_START) == 0) { return; } else if (pcmk_is_set(controld_globals.fsa_input_register, R_TE_CONNECTED)) { crm_debug("The transitioner is already active"); return; } else if ((action & A_TE_START) && cur_state == S_STOPPING) { crm_info("Ignoring request to start the transitioner while shutting down"); return; } if (controld_globals.te_uuid == NULL) { controld_globals.te_uuid = crm_generate_uuid(); crm_info("Registering TE UUID: %s", controld_globals.te_uuid); } if (cib_conn == NULL) { crm_err("Could not set CIB callbacks"); init_ok = FALSE; } else { if (cib_conn->cmds->add_notify_callback(cib_conn, T_CIB_DIFF_NOTIFY, te_update_diff) != pcmk_ok) { crm_err("Could not set CIB notification callback"); init_ok = FALSE; } if (cib_conn->cmds->set_op_callback(cib_conn, global_cib_callback) != pcmk_ok) { crm_err("Could not set CIB global callback"); init_ok = FALSE; } } if (init_ok) { controld_register_graph_functions(); pcmk__free_graph(controld_globals.transition_graph); /* create a blank one */ crm_debug("Transitioner is now active"); controld_globals.transition_graph = create_blank_graph(); controld_set_fsa_input_flags(R_TE_CONNECTED); } } /* A_TE_INVOKE, A_TE_CANCEL */ void do_te_invoke(long long action, enum crmd_fsa_cause cause, enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data) { if (!AM_I_DC || ((controld_globals.fsa_state != S_TRANSITION_ENGINE) && pcmk_is_set(action, A_TE_INVOKE))) { crm_notice("No need to invoke the TE (%s) in state %s", fsa_action2string(action), fsa_state2string(controld_globals.fsa_state)); return; } if (action & A_TE_CANCEL) { crm_debug("Cancelling the transition: %sactive", controld_globals.transition_graph->complete? "in" : ""); abort_transition(INFINITY, pcmk__graph_restart, "Peer Cancelled", NULL); if (!controld_globals.transition_graph->complete) { crmd_fsa_stall(FALSE); } } else if (action & A_TE_HALT) { abort_transition(INFINITY, pcmk__graph_wait, "Peer Halt", NULL); if (!controld_globals.transition_graph->complete) { crmd_fsa_stall(FALSE); } } else if (action & A_TE_INVOKE) { - const char *value = NULL; - xmlNode *graph_data = NULL; ha_msg_input_t *input = fsa_typed_data(fsa_dt_ha_msg); + xmlNode *graph_data = input->xml; const char *ref = crm_element_value(input->msg, XML_ATTR_REFERENCE); const char *graph_file = crm_element_value(input->msg, F_CRM_TGRAPH); const char *graph_input = crm_element_value(input->msg, F_CRM_TGRAPH_INPUT); - if (graph_file == NULL && input->xml == NULL) { + if (graph_file == NULL && graph_data == NULL) { crm_log_xml_err(input->msg, "Bad command"); register_fsa_error(C_FSA_INTERNAL, I_FAIL, NULL); return; } if (!controld_globals.transition_graph->complete) { crm_info("Another transition is already active"); abort_transition(INFINITY, pcmk__graph_restart, "Transition Active", NULL); return; } if ((controld_globals.fsa_pe_ref == NULL) || !pcmk__str_eq(controld_globals.fsa_pe_ref, ref, pcmk__str_none)) { crm_info("Transition is redundant: %s expected but %s received", pcmk__s(controld_globals.fsa_pe_ref, "no reference"), pcmk__s(ref, "no reference")); abort_transition(INFINITY, pcmk__graph_restart, "Transition Redundant", NULL); } - graph_data = input->xml; - if (graph_data == NULL && graph_file != NULL) { graph_data = filename2xml(graph_file); } if (is_timer_started(transition_timer)) { crm_debug("The transitioner wait for a transition timer"); return; } CRM_CHECK(graph_data != NULL, crm_err("Input raised by %s is invalid", msg_data->origin); crm_log_xml_err(input->msg, "Bad command"); return); pcmk__free_graph(controld_globals.transition_graph); controld_globals.transition_graph = pcmk__unpack_graph(graph_data, graph_input); CRM_CHECK(controld_globals.transition_graph != NULL, controld_globals.transition_graph = create_blank_graph(); return); crm_info("Processing graph %d (ref=%s) derived from %s", controld_globals.transition_graph->id, ref, graph_input); te_reset_job_counts(); - value = crm_element_value(graph_data, "failed-stop-offset"); - if (value != NULL) { - pcmk__str_update(&failed_stop_offset, value); - } - - value = crm_element_value(graph_data, "failed-start-offset"); - if (value != NULL) { - pcmk__str_update(&failed_start_offset, value); - } if ((crm_element_value_epoch(graph_data, "recheck-by", &recheck_by) != pcmk_ok) || (recheck_by < 0)) { recheck_by = 0; } trigger_graph(); pcmk__log_graph(LOG_TRACE, controld_globals.transition_graph); if (graph_data != input->xml) { free_xml(graph_data); } } } diff --git a/daemons/controld/controld_transition.h b/daemons/controld/controld_transition.h index 2991efd67e..04a37d849e 100644 --- a/daemons/controld/controld_transition.h +++ b/daemons/controld/controld_transition.h @@ -1,62 +1,59 @@ /* * Copyright 2004-2022 the Pacemaker project contributors * * This source code is licensed under the GNU Lesser General Public License * version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY. */ #ifndef TENGINE__H # define TENGINE__H # include # include # include # include /* tengine */ pcmk__graph_action_t *match_down_event(const char *target); pcmk__graph_action_t *get_cancel_action(const char *id, const char *node); bool confirm_cancel_action(const char *id, const char *node_id); void controld_record_action_timeout(pcmk__graph_action_t *action); gboolean fail_incompletable_actions(pcmk__graph_t *graph, const char *down_node); void process_graph_event(xmlNode *event, const char *event_node); /* utils */ pcmk__graph_action_t *controld_get_action(int id); gboolean stop_te_timer(pcmk__graph_action_t *action); const char *get_rsc_state(const char *task, enum pcmk_exec_status status); void process_te_message(xmlNode *msg, xmlNode *xml_data); void controld_register_graph_functions(void); void notify_crmd(pcmk__graph_t * graph); void cib_action_updated(xmlNode *msg, int call_id, int rc, xmlNode *output, void *user_data); gboolean action_timer_callback(gpointer data); void te_update_diff(const char *event, xmlNode *msg); void controld_init_transition_trigger(void); void controld_destroy_transition_trigger(void); extern void trigger_graph_processing(const char *fn, int line); void abort_after_delay(int abort_priority, enum pcmk__graph_next abort_action, const char *abort_text, guint delay_ms); void abort_transition_graph(int abort_priority, enum pcmk__graph_next abort_action, const char *abort_text, const xmlNode *reason, const char *fn, int line); # define trigger_graph() trigger_graph_processing(__func__, __LINE__) # define abort_transition(pri, action, text, reason) \ abort_transition_graph(pri, action, text, reason,__func__,__LINE__); -extern char *failed_stop_offset; -extern char *failed_start_offset; - void te_action_confirmed(pcmk__graph_action_t *action, pcmk__graph_t *graph); void te_reset_job_counts(void); #endif