diff --git a/daemons/fenced/fenced_remote.c b/daemons/fenced/fenced_remote.c index f09a2de781..480a2a8917 100644 --- a/daemons/fenced/fenced_remote.c +++ b/daemons/fenced/fenced_remote.c @@ -1,2532 +1,2532 @@ /* * Copyright 2009-2024 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 #include #include #include #include #include #include #include #include #include #include #include #include #define TIMEOUT_MULTIPLY_FACTOR 1.2 /* When one fencer queries its peers for devices able to handle a fencing * request, each peer will reply with a list of such devices available to it. * Each reply will be parsed into a peer_device_info_t, with each device's * information kept in a device_properties_t. */ typedef struct device_properties_s { /* Whether access to this device has been verified */ gboolean verified; /* The remaining members are indexed by the operation's "phase" */ /* Whether this device has been executed in each phase */ gboolean executed[st_phase_max]; /* Whether this device is disallowed from executing in each phase */ gboolean disallowed[st_phase_max]; /* Action-specific timeout for each phase */ int custom_action_timeout[st_phase_max]; /* Action-specific maximum random delay for each phase */ int delay_max[st_phase_max]; /* Action-specific base delay for each phase */ int delay_base[st_phase_max]; /* Group of enum st_device_flags */ uint32_t device_support_flags; } device_properties_t; typedef struct { /* Name of peer that sent this result */ char *host; /* Only try peers for non-topology based operations once */ gboolean tried; /* Number of entries in the devices table */ int ndevices; /* Devices available to this host that are capable of fencing the target */ GHashTable *devices; } peer_device_info_t; GHashTable *stonith_remote_op_list = NULL; extern xmlNode *stonith_create_op(int call_id, const char *token, const char *op, xmlNode * data, int call_options); static void request_peer_fencing(remote_fencing_op_t *op, peer_device_info_t *peer); static void finalize_op(remote_fencing_op_t *op, xmlNode *data, bool dup); static void report_timeout_period(remote_fencing_op_t * op, int op_timeout); static int get_op_total_timeout(const remote_fencing_op_t *op, const peer_device_info_t *chosen_peer); static gint sort_strings(gconstpointer a, gconstpointer b) { return strcmp(a, b); } static void free_remote_query(gpointer data) { if (data != NULL) { peer_device_info_t *peer = data; g_hash_table_destroy(peer->devices); free(peer->host); free(peer); } } void free_stonith_remote_op_list(void) { if (stonith_remote_op_list != NULL) { g_hash_table_destroy(stonith_remote_op_list); stonith_remote_op_list = NULL; } } struct peer_count_data { const remote_fencing_op_t *op; gboolean verified_only; uint32_t support_action_only; int count; }; /*! * \internal * \brief Increment a counter if a device has not been executed yet * * \param[in] key Device ID (ignored) * \param[in] value Device properties * \param[in,out] user_data Peer count data */ static void count_peer_device(gpointer key, gpointer value, gpointer user_data) { device_properties_t *props = (device_properties_t*)value; struct peer_count_data *data = user_data; if (!props->executed[data->op->phase] && (!data->verified_only || props->verified) && ((data->support_action_only == st_device_supports_none) || pcmk_is_set(props->device_support_flags, data->support_action_only))) { ++(data->count); } } /*! * \internal * \brief Check the number of available devices in a peer's query results * * \param[in] op Operation that results are for * \param[in] peer Peer to count * \param[in] verified_only Whether to count only verified devices * \param[in] support_action_only Whether to count only devices that support action * * \return Number of devices available to peer that were not already executed */ static int count_peer_devices(const remote_fencing_op_t *op, const peer_device_info_t *peer, gboolean verified_only, uint32_t support_on_action_only) { struct peer_count_data data; data.op = op; data.verified_only = verified_only; data.support_action_only = support_on_action_only; data.count = 0; if (peer) { g_hash_table_foreach(peer->devices, count_peer_device, &data); } return data.count; } /*! * \internal * \brief Search for a device in a query result * * \param[in] op Operation that result is for * \param[in] peer Query result for a peer * \param[in] device Device ID to search for * * \return Device properties if found, NULL otherwise */ static device_properties_t * find_peer_device(const remote_fencing_op_t *op, const peer_device_info_t *peer, const char *device, uint32_t support_action_only) { device_properties_t *props = g_hash_table_lookup(peer->devices, device); if (props && support_action_only != st_device_supports_none && !pcmk_is_set(props->device_support_flags, support_action_only)) { return NULL; } return (props && !props->executed[op->phase] && !props->disallowed[op->phase])? props : NULL; } /*! * \internal * \brief Find a device in a peer's device list and mark it as executed * * \param[in] op Operation that peer result is for * \param[in,out] peer Peer with results to search * \param[in] device ID of device to mark as done * \param[in] verified_devices_only Only consider verified devices * * \return TRUE if device was found and marked, FALSE otherwise */ static gboolean grab_peer_device(const remote_fencing_op_t *op, peer_device_info_t *peer, const char *device, gboolean verified_devices_only) { device_properties_t *props = find_peer_device(op, peer, device, fenced_support_flag(op->action)); if ((props == NULL) || (verified_devices_only && !props->verified)) { return FALSE; } crm_trace("Removing %s from %s (%d remaining)", device, peer->host, count_peer_devices(op, peer, FALSE, st_device_supports_none)); props->executed[op->phase] = TRUE; return TRUE; } static void clear_remote_op_timers(remote_fencing_op_t * op) { if (op->query_timer) { g_source_remove(op->query_timer); op->query_timer = 0; } if (op->op_timer_total) { g_source_remove(op->op_timer_total); op->op_timer_total = 0; } if (op->op_timer_one) { g_source_remove(op->op_timer_one); op->op_timer_one = 0; } } static void free_remote_op(gpointer data) { remote_fencing_op_t *op = data; crm_log_xml_debug(op->request, "Destroying"); clear_remote_op_timers(op); free(op->id); free(op->action); free(op->delegate); free(op->target); free(op->client_id); free(op->client_name); free(op->originator); if (op->query_results) { g_list_free_full(op->query_results, free_remote_query); } if (op->request) { free_xml(op->request); op->request = NULL; } if (op->devices_list) { g_list_free_full(op->devices_list, free); op->devices_list = NULL; } g_list_free_full(op->automatic_list, free); g_list_free(op->duplicates); pcmk__reset_result(&op->result); free(op); } void init_stonith_remote_op_hash_table(GHashTable **table) { if (*table == NULL) { *table = pcmk__strkey_table(NULL, free_remote_op); } } /*! * \internal * \brief Return an operation's originally requested action (before any remap) * * \param[in] op Operation to check * * \return Operation's original action */ static const char * op_requested_action(const remote_fencing_op_t *op) { return ((op->phase > st_phase_requested)? PCMK_ACTION_REBOOT : op->action); } /*! * \internal * \brief Remap a "reboot" operation to the "off" phase * * \param[in,out] op Operation to remap */ static void op_phase_off(remote_fencing_op_t *op) { crm_info("Remapping multiple-device reboot targeting %s to 'off' " CRM_XS " id=%.8s", op->target, op->id); op->phase = st_phase_off; /* Happily, "off" and "on" are shorter than "reboot", so we can reuse the * memory allocation at each phase. */ strcpy(op->action, PCMK_ACTION_OFF); } /*! * \internal * \brief Advance a remapped reboot operation to the "on" phase * * \param[in,out] op Operation to remap */ static void op_phase_on(remote_fencing_op_t *op) { GList *iter = NULL; crm_info("Remapped 'off' targeting %s complete, " "remapping to 'on' for %s " CRM_XS " id=%.8s", op->target, op->client_name, op->id); op->phase = st_phase_on; strcpy(op->action, PCMK_ACTION_ON); /* Skip devices with automatic unfencing, because the cluster will handle it * when the node rejoins. */ for (iter = op->automatic_list; iter != NULL; iter = iter->next) { GList *match = g_list_find_custom(op->devices_list, iter->data, sort_strings); if (match) { op->devices_list = g_list_remove(op->devices_list, match->data); } } g_list_free_full(op->automatic_list, free); op->automatic_list = NULL; /* Rewind device list pointer */ op->devices = op->devices_list; } /*! * \internal * \brief Reset a remapped reboot operation * * \param[in,out] op Operation to reset */ static void undo_op_remap(remote_fencing_op_t *op) { if (op->phase > 0) { crm_info("Undoing remap of reboot targeting %s for %s " CRM_XS " id=%.8s", op->target, op->client_name, op->id); op->phase = st_phase_requested; strcpy(op->action, PCMK_ACTION_REBOOT); } } /*! * \internal * \brief Create notification data XML for a fencing operation result * * \param[in] op Fencer operation that completed * * \return Newly created XML to add as notification data * \note The caller is responsible for freeing the result. */ static xmlNode * fencing_result2xml(const remote_fencing_op_t *op) { xmlNode *notify_data = create_xml_node(NULL, T_STONITH_NOTIFY_FENCE); crm_xml_add_int(notify_data, PCMK_XA_STATE, op->state); crm_xml_add(notify_data, PCMK__XA_ST_TARGET, op->target); crm_xml_add(notify_data, F_STONITH_ACTION, op->action); crm_xml_add(notify_data, F_STONITH_DELEGATE, op->delegate); crm_xml_add(notify_data, PCMK__XA_ST_REMOTE_OP, op->id); crm_xml_add(notify_data, F_STONITH_ORIGIN, op->originator); crm_xml_add(notify_data, PCMK__XA_ST_CLIENTID, op->client_id); crm_xml_add(notify_data, PCMK__XA_ST_CLIENTNAME, op->client_name); return notify_data; } /*! * \internal * \brief Broadcast a fence result notification to all CPG peers * * \param[in] op Fencer operation that completed * \param[in] op_merged Whether this operation is a duplicate of another */ void fenced_broadcast_op_result(const remote_fencing_op_t *op, bool op_merged) { static int count = 0; xmlNode *bcast = create_xml_node(NULL, T_STONITH_REPLY); xmlNode *notify_data = fencing_result2xml(op); count++; crm_trace("Broadcasting result to peers"); crm_xml_add(bcast, PCMK__XA_T, T_STONITH_NOTIFY); crm_xml_add(bcast, PCMK__XA_SUBT, "broadcast"); crm_xml_add(bcast, PCMK__XA_ST_OP, T_STONITH_NOTIFY); crm_xml_add_int(bcast, PCMK_XA_COUNT, count); if (op_merged) { pcmk__xe_set_bool_attr(bcast, F_STONITH_MERGED, true); } stonith__xe_set_result(notify_data, &op->result); add_message_xml(bcast, PCMK__XA_ST_CALLDATA, notify_data); send_cluster_message(NULL, crm_msg_stonith_ng, bcast, FALSE); free_xml(notify_data); free_xml(bcast); return; } /*! * \internal * \brief Reply to a local request originator and notify all subscribed clients * * \param[in,out] op Fencer operation that completed * \param[in,out] data Top-level XML to add notification to */ static void handle_local_reply_and_notify(remote_fencing_op_t *op, xmlNode *data) { xmlNode *notify_data = NULL; xmlNode *reply = NULL; pcmk__client_t *client = NULL; if (op->notify_sent == TRUE) { /* nothing to do */ return; } /* Do notification with a clean data object */ crm_xml_add_int(data, PCMK_XA_STATE, op->state); crm_xml_add(data, PCMK__XA_ST_TARGET, op->target); crm_xml_add(data, PCMK__XA_ST_OP, op->action); reply = fenced_construct_reply(op->request, data, &op->result); crm_xml_add(reply, F_STONITH_DELEGATE, op->delegate); /* Send fencing OP reply to local client that initiated fencing */ client = pcmk__find_client_by_id(op->client_id); if (client == NULL) { crm_trace("Skipping reply to %s: no longer a client", op->client_id); } else { do_local_reply(reply, client, op->call_options); } /* bcast to all local clients that the fencing operation happend */ notify_data = fencing_result2xml(op); fenced_send_notification(T_STONITH_NOTIFY_FENCE, &op->result, notify_data); free_xml(notify_data); fenced_send_notification(T_STONITH_NOTIFY_HISTORY, NULL, NULL); /* mark this op as having notify's already sent */ op->notify_sent = TRUE; free_xml(reply); } /*! * \internal * \brief Finalize all duplicates of a given fencer operation * * \param[in,out] op Fencer operation that completed * \param[in,out] data Top-level XML to add notification to */ static void finalize_op_duplicates(remote_fencing_op_t *op, xmlNode *data) { for (GList *iter = op->duplicates; iter != NULL; iter = iter->next) { remote_fencing_op_t *other = iter->data; if (other->state == st_duplicate) { other->state = op->state; crm_debug("Performing duplicate notification for %s@%s: %s " CRM_XS " id=%.8s", other->client_name, other->originator, pcmk_exec_status_str(op->result.execution_status), other->id); pcmk__copy_result(&op->result, &other->result); finalize_op(other, data, true); } else { // Possible if (for example) it timed out already crm_err("Skipping duplicate notification for %s@%s " CRM_XS " state=%s id=%.8s", other->client_name, other->originator, stonith_op_state_str(other->state), other->id); } } } static char * delegate_from_xml(xmlNode *xml) { xmlNode *match = get_xpath_object("//@" F_STONITH_DELEGATE, xml, LOG_NEVER); if (match == NULL) { return crm_element_value_copy(xml, PCMK__XA_SRC); } else { return crm_element_value_copy(match, F_STONITH_DELEGATE); } } /*! * \internal * \brief Finalize a peer fencing operation * * Clean up after a fencing operation completes. This function has two code * paths: the executioner uses it to broadcast the result to CPG peers, and then * each peer (including the executioner) uses it to process that broadcast and * notify its IPC clients of the result. * * \param[in,out] op Fencer operation that completed * \param[in,out] data If not NULL, XML reply of last delegated operation * \param[in] dup Whether this operation is a duplicate of another * (in which case, do not broadcast the result) * * \note The operation result should be set before calling this function. */ static void finalize_op(remote_fencing_op_t *op, xmlNode *data, bool dup) { int level = LOG_ERR; const char *subt = NULL; xmlNode *local_data = NULL; gboolean op_merged = FALSE; CRM_CHECK((op != NULL), return); // This is a no-op if timers have already been cleared clear_remote_op_timers(op); if (op->notify_sent) { // Most likely, this is a timed-out action that eventually completed crm_notice("Operation '%s'%s%s by %s for %s@%s%s: " "Result arrived too late " CRM_XS " id=%.8s", op->action, (op->target? " targeting " : ""), (op->target? op->target : ""), (op->delegate? op->delegate : "unknown node"), op->client_name, op->originator, (op_merged? " (merged)" : ""), op->id); return; } set_fencing_completed(op); undo_op_remap(op); if (data == NULL) { data = create_xml_node(NULL, "remote-op"); local_data = data; } else if (op->delegate == NULL) { switch (op->result.execution_status) { case PCMK_EXEC_NO_FENCE_DEVICE: break; case PCMK_EXEC_INVALID: if (op->result.exit_status != CRM_EX_EXPIRED) { op->delegate = delegate_from_xml(data); } break; default: op->delegate = delegate_from_xml(data); break; } } if (dup || (crm_element_value(data, F_STONITH_MERGED) != NULL)) { op_merged = true; } /* Tell everyone the operation is done, we will continue * with doing the local notifications once we receive * the broadcast back. */ subt = crm_element_value(data, PCMK__XA_SUBT); if (!dup && !pcmk__str_eq(subt, "broadcast", pcmk__str_casei)) { /* Defer notification until the bcast message arrives */ fenced_broadcast_op_result(op, op_merged); free_xml(local_data); return; } if (pcmk__result_ok(&op->result) || dup || !pcmk__str_eq(op->originator, stonith_our_uname, pcmk__str_casei)) { level = LOG_NOTICE; } do_crm_log(level, "Operation '%s'%s%s by %s for %s@%s%s: %s (%s%s%s) " CRM_XS " id=%.8s", op->action, (op->target? " targeting " : ""), (op->target? op->target : ""), (op->delegate? op->delegate : "unknown node"), op->client_name, op->originator, (op_merged? " (merged)" : ""), crm_exit_str(op->result.exit_status), pcmk_exec_status_str(op->result.execution_status), ((op->result.exit_reason == NULL)? "" : ": "), ((op->result.exit_reason == NULL)? "" : op->result.exit_reason), op->id); handle_local_reply_and_notify(op, data); if (!dup) { finalize_op_duplicates(op, data); } /* Free non-essential parts of the record * Keep the record around so we can query the history */ if (op->query_results) { g_list_free_full(op->query_results, free_remote_query); op->query_results = NULL; } if (op->request) { free_xml(op->request); op->request = NULL; } free_xml(local_data); } /*! * \internal * \brief Finalize a watchdog fencer op after the waiting time expires * * \param[in,out] userdata Fencer operation that completed * * \return G_SOURCE_REMOVE (which tells glib not to restart timer) */ static gboolean remote_op_watchdog_done(gpointer userdata) { remote_fencing_op_t *op = userdata; op->op_timer_one = 0; crm_notice("Self-fencing (%s) by %s for %s assumed complete " CRM_XS " id=%.8s", op->action, op->target, op->client_name, op->id); op->state = st_done; pcmk__set_result(&op->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); finalize_op(op, NULL, false); return G_SOURCE_REMOVE; } static gboolean remote_op_timeout_one(gpointer userdata) { remote_fencing_op_t *op = userdata; op->op_timer_one = 0; crm_notice("Peer's '%s' action targeting %s for client %s timed out " CRM_XS " id=%.8s", op->action, op->target, op->client_name, op->id); pcmk__set_result(&op->result, CRM_EX_ERROR, PCMK_EXEC_TIMEOUT, "Peer did not return fence result within timeout"); // The requested delay has been applied for the first device if (op->client_delay > 0) { op->client_delay = 0; crm_trace("Try another device for '%s' action targeting %s " "for client %s without delay " CRM_XS " id=%.8s", op->action, op->target, op->client_name, op->id); } // Try another device, if appropriate request_peer_fencing(op, NULL); return G_SOURCE_REMOVE; } /*! * \internal * \brief Finalize a remote fencer operation that timed out * * \param[in,out] op Fencer operation that timed out * \param[in] reason Readable description of what step timed out */ static void finalize_timed_out_op(remote_fencing_op_t *op, const char *reason) { crm_debug("Action '%s' targeting %s for client %s timed out " CRM_XS " id=%.8s", op->action, op->target, op->client_name, op->id); if (op->phase == st_phase_on) { /* A remapped reboot operation timed out in the "on" phase, but the * "off" phase completed successfully, so quit trying any further * devices, and return success. */ op->state = st_done; pcmk__set_result(&op->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); } else { op->state = st_failed; pcmk__set_result(&op->result, CRM_EX_ERROR, PCMK_EXEC_TIMEOUT, reason); } finalize_op(op, NULL, false); } /*! * \internal * \brief Finalize a remote fencer operation that timed out * * \param[in,out] userdata Fencer operation that timed out * * \return G_SOURCE_REMOVE (which tells glib not to restart timer) */ static gboolean remote_op_timeout(gpointer userdata) { remote_fencing_op_t *op = userdata; op->op_timer_total = 0; if (op->state == st_done) { crm_debug("Action '%s' targeting %s for client %s already completed " CRM_XS " id=%.8s", op->action, op->target, op->client_name, op->id); } else { finalize_timed_out_op(userdata, "Fencing did not complete within a " "total timeout based on the " "configured timeout and retries for " "any devices attempted"); } return G_SOURCE_REMOVE; } static gboolean remote_op_query_timeout(gpointer data) { remote_fencing_op_t *op = data; op->query_timer = 0; if (op->state == st_done) { crm_debug("Operation %.8s targeting %s already completed", op->id, op->target); } else if (op->state == st_exec) { crm_debug("Operation %.8s targeting %s already in progress", op->id, op->target); } else if (op->query_results) { // Query succeeded, so attempt the actual fencing crm_debug("Query %.8s targeting %s complete (state=%s)", op->id, op->target, stonith_op_state_str(op->state)); request_peer_fencing(op, NULL); } else { crm_debug("Query %.8s targeting %s timed out (state=%s)", op->id, op->target, stonith_op_state_str(op->state)); finalize_timed_out_op(op, "No capable peers replied to device query " "within timeout"); } return G_SOURCE_REMOVE; } static gboolean topology_is_empty(stonith_topology_t *tp) { int i; if (tp == NULL) { return TRUE; } for (i = 0; i < ST_LEVEL_MAX; i++) { if (tp->levels[i] != NULL) { return FALSE; } } return TRUE; } /*! * \internal * \brief Add a device to an operation's automatic unfencing list * * \param[in,out] op Operation to modify * \param[in] device Device ID to add */ static void add_required_device(remote_fencing_op_t *op, const char *device) { GList *match = g_list_find_custom(op->automatic_list, device, sort_strings); if (!match) { op->automatic_list = g_list_prepend(op->automatic_list, strdup(device)); } } /*! * \internal * \brief Remove a device from the automatic unfencing list * * \param[in,out] op Operation to modify * \param[in] device Device ID to remove */ static void remove_required_device(remote_fencing_op_t *op, const char *device) { GList *match = g_list_find_custom(op->automatic_list, device, sort_strings); if (match) { op->automatic_list = g_list_remove(op->automatic_list, match->data); } } /* deep copy the device list */ static void set_op_device_list(remote_fencing_op_t * op, GList *devices) { GList *lpc = NULL; if (op->devices_list) { g_list_free_full(op->devices_list, free); op->devices_list = NULL; } for (lpc = devices; lpc != NULL; lpc = lpc->next) { op->devices_list = g_list_append(op->devices_list, strdup(lpc->data)); } op->devices = op->devices_list; } /*! * \internal * \brief Check whether a node matches a topology target * * \param[in] tp Topology table entry to check * \param[in] node Name of node to check * * \return TRUE if node matches topology target */ static gboolean topology_matches(const stonith_topology_t *tp, const char *node) { regex_t r_patt; CRM_CHECK(node && tp && tp->target, return FALSE); switch (tp->kind) { case fenced_target_by_attribute: /* This level targets by attribute, so tp->target is a NAME=VALUE pair * of a permanent attribute applied to targeted nodes. The test below * relies on the locally cached copy of the CIB, so if fencing needs to * be done before the initial CIB is received or after a malformed CIB * is received, then the topology will be unable to be used. */ if (node_has_attr(node, tp->target_attribute, tp->target_value)) { crm_notice("Matched %s with %s by attribute", node, tp->target); return TRUE; } break; case fenced_target_by_pattern: /* This level targets node names matching a pattern, so tp->target * (and tp->target_pattern) is a regular expression. */ if (regcomp(&r_patt, tp->target_pattern, REG_EXTENDED|REG_NOSUB)) { crm_info("Bad regex '%s' for fencing level", tp->target); } else { int status = regexec(&r_patt, node, 0, NULL, 0); regfree(&r_patt); if (status == 0) { crm_notice("Matched %s with %s by name", node, tp->target); return TRUE; } } break; case fenced_target_by_name: crm_trace("Testing %s against %s", node, tp->target); return pcmk__str_eq(tp->target, node, pcmk__str_casei); default: break; } crm_trace("No match for %s with %s", node, tp->target); return FALSE; } stonith_topology_t * find_topology_for_host(const char *host) { GHashTableIter tIter; stonith_topology_t *tp = g_hash_table_lookup(topology, host); if(tp != NULL) { crm_trace("Found %s for %s in %d entries", tp->target, host, g_hash_table_size(topology)); return tp; } g_hash_table_iter_init(&tIter, topology); while (g_hash_table_iter_next(&tIter, NULL, (gpointer *) & tp)) { if (topology_matches(tp, host)) { crm_trace("Found %s for %s in %d entries", tp->target, host, g_hash_table_size(topology)); return tp; } } crm_trace("No matches for %s in %d topology entries", host, g_hash_table_size(topology)); return NULL; } /*! * \internal * \brief Set fencing operation's device list to target's next topology level * * \param[in,out] op Remote fencing operation to modify * \param[in] empty_ok If true, an operation without a target (i.e. * queries) or a target without a topology will get a * pcmk_rc_ok return value instead of ENODEV * * \return Standard Pacemaker return value */ static int advance_topology_level(remote_fencing_op_t *op, bool empty_ok) { stonith_topology_t *tp = NULL; if (op->target) { tp = find_topology_for_host(op->target); } if (topology_is_empty(tp)) { return empty_ok? pcmk_rc_ok : ENODEV; } CRM_ASSERT(tp->levels != NULL); stonith__set_call_options(op->call_options, op->id, st_opt_topology); /* This is a new level, so undo any remapping left over from previous */ undo_op_remap(op); do { op->level++; } while (op->level < ST_LEVEL_MAX && tp->levels[op->level] == NULL); if (op->level < ST_LEVEL_MAX) { crm_trace("Attempting fencing level %d targeting %s (%d devices) " "for client %s@%s (id=%.8s)", op->level, op->target, g_list_length(tp->levels[op->level]), op->client_name, op->originator, op->id); set_op_device_list(op, tp->levels[op->level]); // The requested delay has been applied for the first fencing level if ((op->level > 1) && (op->client_delay > 0)) { op->client_delay = 0; } if ((g_list_next(op->devices_list) != NULL) && pcmk__str_eq(op->action, PCMK_ACTION_REBOOT, pcmk__str_none)) { /* A reboot has been requested for a topology level with multiple * devices. Instead of rebooting the devices sequentially, we will * turn them all off, then turn them all on again. (Think about * switched power outlets for redundant power supplies.) */ op_phase_off(op); } return pcmk_rc_ok; } crm_info("All %sfencing options targeting %s for client %s@%s failed " CRM_XS " id=%.8s", (stonith_watchdog_timeout_ms > 0)?"non-watchdog ":"", op->target, op->client_name, op->originator, op->id); return ENODEV; } /*! * \internal * \brief If fencing operation is a duplicate, merge it into the other one * * \param[in,out] op Fencing operation to check */ static void merge_duplicates(remote_fencing_op_t *op) { GHashTableIter iter; remote_fencing_op_t *other = NULL; time_t now = time(NULL); g_hash_table_iter_init(&iter, stonith_remote_op_list); while (g_hash_table_iter_next(&iter, NULL, (void **)&other)) { const char *other_action = op_requested_action(other); if (!strcmp(op->id, other->id)) { continue; // Don't compare against self } if (other->state > st_exec) { crm_trace("%.8s not duplicate of %.8s: not in progress", op->id, other->id); continue; } if (!pcmk__str_eq(op->target, other->target, pcmk__str_casei)) { crm_trace("%.8s not duplicate of %.8s: node %s vs. %s", op->id, other->id, op->target, other->target); continue; } if (!pcmk__str_eq(op->action, other_action, pcmk__str_none)) { crm_trace("%.8s not duplicate of %.8s: action %s vs. %s", op->id, other->id, op->action, other_action); continue; } if (pcmk__str_eq(op->client_name, other->client_name, pcmk__str_casei)) { crm_trace("%.8s not duplicate of %.8s: same client %s", op->id, other->id, op->client_name); continue; } if (pcmk__str_eq(other->target, other->originator, pcmk__str_casei)) { crm_trace("%.8s not duplicate of %.8s: suicide for %s", op->id, other->id, other->target); continue; } if (!fencing_peer_active(pcmk__get_node(0, other->originator, NULL, pcmk__node_search_cluster))) { crm_notice("Failing action '%s' targeting %s originating from " "client %s@%s: Originator is dead " CRM_XS " id=%.8s", other->action, other->target, other->client_name, other->originator, other->id); crm_trace("%.8s not duplicate of %.8s: originator dead", op->id, other->id); other->state = st_failed; continue; } if ((other->total_timeout > 0) && (now > (other->total_timeout + other->created))) { crm_trace("%.8s not duplicate of %.8s: old (%ld vs. %ld + %d)", op->id, other->id, now, other->created, other->total_timeout); continue; } /* There is another in-flight request to fence the same host * Piggyback on that instead. If it fails, so do we. */ other->duplicates = g_list_append(other->duplicates, op); if (other->total_timeout == 0) { other->total_timeout = op->total_timeout = TIMEOUT_MULTIPLY_FACTOR * get_op_total_timeout(op, NULL); crm_trace("Best guess as to timeout used for %.8s: %d", other->id, other->total_timeout); } crm_notice("Merging fencing action '%s' targeting %s originating from " "client %s with identical request from %s@%s " CRM_XS " original=%.8s duplicate=%.8s total_timeout=%ds", op->action, op->target, op->client_name, other->client_name, other->originator, op->id, other->id, other->total_timeout); report_timeout_period(op, other->total_timeout); op->state = st_duplicate; } } static uint32_t fencing_active_peers(void) { uint32_t count = 0; crm_node_t *entry; GHashTableIter gIter; g_hash_table_iter_init(&gIter, crm_peer_cache); while (g_hash_table_iter_next(&gIter, NULL, (void **)&entry)) { if(fencing_peer_active(entry)) { count++; } } return count; } /*! * \internal * \brief Process a manual confirmation of a pending fence action * * \param[in] client IPC client that sent confirmation * \param[in,out] msg Request XML with manual confirmation * * \return Standard Pacemaker return code */ int fenced_handle_manual_confirmation(const pcmk__client_t *client, xmlNode *msg) { remote_fencing_op_t *op = NULL; xmlNode *dev = get_xpath_object("//@" PCMK__XA_ST_TARGET, msg, LOG_ERR); CRM_CHECK(dev != NULL, return EPROTO); crm_notice("Received manual confirmation that %s has been fenced", pcmk__s(crm_element_value(dev, PCMK__XA_ST_TARGET), "unknown target")); op = initiate_remote_stonith_op(client, msg, TRUE); if (op == NULL) { return EPROTO; } op->state = st_done; set_fencing_completed(op); op->delegate = strdup("a human"); // For the fencer's purposes, the fencing operation is done pcmk__set_result(&op->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); finalize_op(op, msg, false); /* For the requester's purposes, the operation is still pending. The * actual result will be sent asynchronously via the operation's done_cb(). */ return EINPROGRESS; } /*! * \internal * \brief Create a new remote stonith operation * * \param[in] client ID of local stonith client that initiated the operation * \param[in] request The request from the client that started the operation * \param[in] peer TRUE if this operation is owned by another stonith peer * (an operation owned by one peer is stored on all peers, * but only the owner executes it; all nodes get the results * once the owner finishes execution) */ void * create_remote_stonith_op(const char *client, xmlNode *request, gboolean peer) { remote_fencing_op_t *op = NULL; xmlNode *dev = get_xpath_object("//@" PCMK__XA_ST_TARGET, request, LOG_NEVER); int call_options = 0; const char *operation = NULL; init_stonith_remote_op_hash_table(&stonith_remote_op_list); /* If this operation is owned by another node, check to make * sure we haven't already created this operation. */ if (peer && dev) { const char *op_id = crm_element_value(dev, PCMK__XA_ST_REMOTE_OP); CRM_CHECK(op_id != NULL, return NULL); op = g_hash_table_lookup(stonith_remote_op_list, op_id); if (op) { crm_debug("Reusing existing remote fencing op %.8s for %s", op_id, ((client == NULL)? "unknown client" : client)); return op; } } op = calloc(1, sizeof(remote_fencing_op_t)); CRM_ASSERT(op != NULL); crm_element_value_int(request, PCMK__XA_ST_TIMEOUT, &(op->base_timeout)); // Value -1 means disable any static/random fencing delays crm_element_value_int(request, PCMK__XA_ST_DELAY, &(op->client_delay)); if (peer && dev) { op->id = crm_element_value_copy(dev, PCMK__XA_ST_REMOTE_OP); } else { op->id = crm_generate_uuid(); } g_hash_table_replace(stonith_remote_op_list, op->id, op); op->state = st_query; op->replies_expected = fencing_active_peers(); op->action = crm_element_value_copy(dev, F_STONITH_ACTION); op->originator = crm_element_value_copy(dev, F_STONITH_ORIGIN); op->delegate = crm_element_value_copy(dev, F_STONITH_DELEGATE); /* May not be set */ op->created = time(NULL); if (op->originator == NULL) { /* Local or relayed request */ op->originator = strdup(stonith_our_uname); } CRM_LOG_ASSERT(client != NULL); if (client) { op->client_id = strdup(client); } /* For a RELAY operation, set fenced on the client. */ operation = crm_element_value(request, PCMK__XA_ST_OP); if (pcmk__str_eq(operation, STONITH_OP_RELAY, pcmk__str_none)) { op->client_name = crm_strdup_printf("%s.%lu", crm_system_name, (unsigned long) getpid()); } else { op->client_name = crm_element_value_copy(request, PCMK__XA_ST_CLIENTNAME); } op->target = crm_element_value_copy(dev, PCMK__XA_ST_TARGET); op->request = copy_xml(request); /* TODO: Figure out how to avoid this */ crm_element_value_int(request, PCMK__XA_ST_CALLOPT, &call_options); op->call_options = call_options; crm_element_value_int(request, PCMK__XA_ST_CALLID, &(op->client_callid)); crm_trace("%s new fencing op %s ('%s' targeting %s for client %s, " "base timeout %d, %u %s expected)", (peer && dev)? "Recorded" : "Generated", op->id, op->action, op->target, op->client_name, op->base_timeout, op->replies_expected, pcmk__plural_alt(op->replies_expected, "reply", "replies")); if (op->call_options & st_opt_cs_nodeid) { int nodeid; crm_node_t *node; pcmk__scan_min_int(op->target, &nodeid, 0); node = pcmk__search_node_caches(nodeid, NULL, pcmk__node_search_any |pcmk__node_search_known); /* Ensure the conversion only happens once */ stonith__clear_call_options(op->call_options, op->id, st_opt_cs_nodeid); if (node && node->uname) { free(op->target); op->target = strdup(node->uname); } else { crm_warn("Could not expand nodeid '%s' into a host name", op->target); } } /* check to see if this is a duplicate operation of another in-flight operation */ merge_duplicates(op); if (op->state != st_duplicate) { /* kick history readers */ fenced_send_notification(T_STONITH_NOTIFY_HISTORY, NULL, NULL); } /* safe to trim as long as that doesn't touch pending ops */ stonith_fence_history_trim(); return op; } /*! * \internal * \brief Create a peer fencing operation from a request, and initiate it * * \param[in] client IPC client that made request (NULL to get from request) * \param[in] request Request XML * \param[in] manual_ack Whether this is a manual action confirmation * * \return Newly created operation on success, otherwise NULL */ remote_fencing_op_t * initiate_remote_stonith_op(const pcmk__client_t *client, xmlNode *request, gboolean manual_ack) { int query_timeout = 0; xmlNode *query = NULL; const char *client_id = NULL; remote_fencing_op_t *op = NULL; const char *relay_op_id = NULL; const char *operation = NULL; if (client) { client_id = client->id; } else { client_id = crm_element_value(request, PCMK__XA_ST_CLIENTID); } CRM_LOG_ASSERT(client_id != NULL); op = create_remote_stonith_op(client_id, request, FALSE); op->owner = TRUE; if (manual_ack) { return op; } CRM_CHECK(op->action, return NULL); if (advance_topology_level(op, true) != pcmk_rc_ok) { op->state = st_failed; } switch (op->state) { case st_failed: // advance_topology_level() exhausted levels pcmk__set_result(&op->result, CRM_EX_ERROR, PCMK_EXEC_ERROR, "All topology levels failed"); crm_warn("Could not request peer fencing (%s) targeting %s " CRM_XS " id=%.8s", op->action, op->target, op->id); finalize_op(op, NULL, false); return op; case st_duplicate: crm_info("Requesting peer fencing (%s) targeting %s (duplicate) " CRM_XS " id=%.8s", op->action, op->target, op->id); return op; default: crm_notice("Requesting peer fencing (%s) targeting %s " CRM_XS " id=%.8s state=%s base_timeout=%d", op->action, op->target, op->id, stonith_op_state_str(op->state), op->base_timeout); } query = stonith_create_op(op->client_callid, op->id, STONITH_OP_QUERY, NULL, op->call_options); crm_xml_add(query, PCMK__XA_ST_REMOTE_OP, op->id); crm_xml_add(query, PCMK__XA_ST_TARGET, op->target); crm_xml_add(query, F_STONITH_ACTION, op_requested_action(op)); crm_xml_add(query, F_STONITH_ORIGIN, op->originator); crm_xml_add(query, PCMK__XA_ST_CLIENTID, op->client_id); crm_xml_add(query, PCMK__XA_ST_CLIENTNAME, op->client_name); crm_xml_add_int(query, PCMK__XA_ST_TIMEOUT, op->base_timeout); /* In case of RELAY operation, RELAY information is added to the query to delete the original operation of RELAY. */ operation = crm_element_value(request, PCMK__XA_ST_OP); if (pcmk__str_eq(operation, STONITH_OP_RELAY, pcmk__str_none)) { relay_op_id = crm_element_value(request, PCMK__XA_ST_REMOTE_OP); if (relay_op_id) { crm_xml_add(query, PCMK__XA_ST_REMOTE_OP_RELAY, relay_op_id); } } send_cluster_message(NULL, crm_msg_stonith_ng, query, FALSE); free_xml(query); query_timeout = op->base_timeout * TIMEOUT_MULTIPLY_FACTOR; op->query_timer = g_timeout_add((1000 * query_timeout), remote_op_query_timeout, op); return op; } enum find_best_peer_options { /*! Skip checking the target peer for capable fencing devices */ FIND_PEER_SKIP_TARGET = 0x0001, /*! Only check the target peer for capable fencing devices */ FIND_PEER_TARGET_ONLY = 0x0002, /*! Skip peers and devices that are not verified */ FIND_PEER_VERIFIED_ONLY = 0x0004, }; static peer_device_info_t * find_best_peer(const char *device, remote_fencing_op_t * op, enum find_best_peer_options options) { GList *iter = NULL; gboolean verified_devices_only = (options & FIND_PEER_VERIFIED_ONLY) ? TRUE : FALSE; if (!device && pcmk_is_set(op->call_options, st_opt_topology)) { return NULL; } for (iter = op->query_results; iter != NULL; iter = iter->next) { peer_device_info_t *peer = iter->data; crm_trace("Testing result from %s targeting %s with %d device%s: %d %x", peer->host, op->target, peer->ndevices, pcmk__plural_s(peer->ndevices), peer->tried, options); if ((options & FIND_PEER_SKIP_TARGET) && pcmk__str_eq(peer->host, op->target, pcmk__str_casei)) { continue; } if ((options & FIND_PEER_TARGET_ONLY) && !pcmk__str_eq(peer->host, op->target, pcmk__str_casei)) { continue; } if (pcmk_is_set(op->call_options, st_opt_topology)) { if (grab_peer_device(op, peer, device, verified_devices_only)) { return peer; } } else if (!peer->tried && count_peer_devices(op, peer, verified_devices_only, fenced_support_flag(op->action))) { /* No topology: Use the current best peer */ crm_trace("Simple fencing"); return peer; } } return NULL; } static peer_device_info_t * stonith_choose_peer(remote_fencing_op_t * op) { const char *device = NULL; peer_device_info_t *peer = NULL; uint32_t active = fencing_active_peers(); do { if (op->devices) { device = op->devices->data; crm_trace("Checking for someone to fence (%s) %s using %s", op->action, op->target, device); } else { crm_trace("Checking for someone to fence (%s) %s", op->action, op->target); } /* Best choice is a peer other than the target with verified access */ peer = find_best_peer(device, op, FIND_PEER_SKIP_TARGET|FIND_PEER_VERIFIED_ONLY); if (peer) { crm_trace("Found verified peer %s for %s", peer->host, device?device:""); return peer; } if(op->query_timer != 0 && op->replies < QB_MIN(op->replies_expected, active)) { crm_trace("Waiting before looking for unverified devices to fence %s", op->target); return NULL; } /* If no other peer has verified access, next best is unverified access */ peer = find_best_peer(device, op, FIND_PEER_SKIP_TARGET); if (peer) { crm_trace("Found best unverified peer %s", peer->host); return peer; } /* If no other peer can do it, last option is self-fencing * (which is never allowed for the "on" phase of a remapped reboot) */ if (op->phase != st_phase_on) { peer = find_best_peer(device, op, FIND_PEER_TARGET_ONLY); if (peer) { crm_trace("%s will fence itself", peer->host); return peer; } } /* Try the next fencing level if there is one (unless we're in the "on" * phase of a remapped "reboot", because we ignore errors in that case) */ } while ((op->phase != st_phase_on) && pcmk_is_set(op->call_options, st_opt_topology) && (advance_topology_level(op, false) == pcmk_rc_ok)); if ((stonith_watchdog_timeout_ms > 0) && pcmk__is_fencing_action(op->action) && pcmk__str_eq(device, STONITH_WATCHDOG_ID, pcmk__str_none) && node_does_watchdog_fencing(op->target)) { crm_info("Couldn't contact watchdog-fencing target-node (%s)", op->target); /* check_watchdog_fencing_and_wait will log additional info */ } else { crm_notice("Couldn't find anyone to fence (%s) %s using %s", op->action, op->target, (device? device : "any device")); } return NULL; } static int get_device_timeout(const remote_fencing_op_t *op, const peer_device_info_t *peer, const char *device, bool with_delay) { device_properties_t *props; int delay = 0; if (!peer || !device) { return op->base_timeout; } props = g_hash_table_lookup(peer->devices, device); if (!props) { return op->base_timeout; } // op->client_delay < 0 means disable any static/random fencing delays if (with_delay && (op->client_delay >= 0)) { // delay_base is eventually limited by delay_max delay = (props->delay_max[op->phase] > 0 ? props->delay_max[op->phase] : props->delay_base[op->phase]); } return (props->custom_action_timeout[op->phase]? props->custom_action_timeout[op->phase] : op->base_timeout) + delay; } struct timeout_data { const remote_fencing_op_t *op; const peer_device_info_t *peer; int total_timeout; }; /*! * \internal * \brief Add timeout to a total if device has not been executed yet * * \param[in] key GHashTable key (device ID) * \param[in] value GHashTable value (device properties) * \param[in,out] user_data Timeout data */ static void add_device_timeout(gpointer key, gpointer value, gpointer user_data) { const char *device_id = key; device_properties_t *props = value; struct timeout_data *timeout = user_data; if (!props->executed[timeout->op->phase] && !props->disallowed[timeout->op->phase]) { timeout->total_timeout += get_device_timeout(timeout->op, timeout->peer, device_id, true); } } static int get_peer_timeout(const remote_fencing_op_t *op, const peer_device_info_t *peer) { struct timeout_data timeout; timeout.op = op; timeout.peer = peer; timeout.total_timeout = 0; g_hash_table_foreach(peer->devices, add_device_timeout, &timeout); return (timeout.total_timeout? timeout.total_timeout : op->base_timeout); } static int get_op_total_timeout(const remote_fencing_op_t *op, const peer_device_info_t *chosen_peer) { long long total_timeout = 0; stonith_topology_t *tp = find_topology_for_host(op->target); if (pcmk_is_set(op->call_options, st_opt_topology) && tp) { int i; GList *device_list = NULL; GList *iter = NULL; GList *auto_list = NULL; if (pcmk__str_eq(op->action, PCMK_ACTION_ON, pcmk__str_none) && (op->automatic_list != NULL)) { auto_list = g_list_copy(op->automatic_list); } /* Yep, this looks scary, nested loops all over the place. * Here is what is going on. * Loop1: Iterate through fencing levels. * Loop2: If a fencing level has devices, loop through each device * Loop3: For each device in a fencing level, see what peer owns it * and what that peer has reported the timeout is for the device. */ for (i = 0; i < ST_LEVEL_MAX; i++) { if (!tp->levels[i]) { continue; } for (device_list = tp->levels[i]; device_list; device_list = device_list->next) { /* in case of watchdog-device we add the timeout to the budget regardless of if we got a reply or not */ if ((stonith_watchdog_timeout_ms > 0) && pcmk__is_fencing_action(op->action) && pcmk__str_eq(device_list->data, STONITH_WATCHDOG_ID, pcmk__str_none) && node_does_watchdog_fencing(op->target)) { total_timeout += stonith_watchdog_timeout_ms / 1000; continue; } for (iter = op->query_results; iter != NULL; iter = iter->next) { const peer_device_info_t *peer = iter->data; if (auto_list) { GList *match = g_list_find_custom(auto_list, device_list->data, sort_strings); if (match) { auto_list = g_list_remove(auto_list, match->data); } } if (find_peer_device(op, peer, device_list->data, fenced_support_flag(op->action))) { total_timeout += get_device_timeout(op, peer, device_list->data, true); break; } } /* End Loop3: match device with peer that owns device, find device's timeout period */ } /* End Loop2: iterate through devices at a specific level */ } /*End Loop1: iterate through fencing levels */ //Add only exists automatic_list device timeout if (auto_list) { for (iter = auto_list; iter != NULL; iter = iter->next) { GList *iter2 = NULL; for (iter2 = op->query_results; iter2 != NULL; iter = iter2->next) { peer_device_info_t *peer = iter2->data; if (find_peer_device(op, peer, iter->data, st_device_supports_on)) { total_timeout += get_device_timeout(op, peer, iter->data, true); break; } } } } g_list_free(auto_list); } else if (chosen_peer) { total_timeout = get_peer_timeout(op, chosen_peer); } else { total_timeout = op->base_timeout; } if (total_timeout <= 0) { total_timeout = op->base_timeout; } /* Take any requested fencing delay into account to prevent it from eating * up the total timeout. */ if (op->client_delay > 0) { total_timeout += op->client_delay; } return (int) QB_MIN(total_timeout, INT_MAX); } static void report_timeout_period(remote_fencing_op_t * op, int op_timeout) { GList *iter = NULL; xmlNode *update = NULL; const char *client_node = NULL; const char *client_id = NULL; const char *call_id = NULL; if (op->call_options & st_opt_sync_call) { /* There is no reason to report the timeout for a synchronous call. It * is impossible to use the reported timeout to do anything when the client * is blocking for the response. This update is only important for * async calls that require a callback to report the results in. */ return; } else if (!op->request) { return; } crm_trace("Reporting timeout for %s (id=%.8s)", op->client_name, op->id); - client_node = crm_element_value(op->request, F_STONITH_CLIENTNODE); + client_node = crm_element_value(op->request, PCMK__XA_ST_CLIENTNODE); call_id = crm_element_value(op->request, PCMK__XA_ST_CALLID); client_id = crm_element_value(op->request, PCMK__XA_ST_CLIENTID); if (!client_node || !call_id || !client_id) { return; } if (pcmk__str_eq(client_node, stonith_our_uname, pcmk__str_casei)) { // Client is connected to this node, so send update directly to them do_stonith_async_timeout_update(client_id, call_id, op_timeout); return; } /* The client is connected to another node, relay this update to them */ update = stonith_create_op(op->client_callid, op->id, STONITH_OP_TIMEOUT_UPDATE, NULL, 0); crm_xml_add(update, PCMK__XA_ST_REMOTE_OP, op->id); crm_xml_add(update, PCMK__XA_ST_CLIENTID, client_id); crm_xml_add(update, PCMK__XA_ST_CALLID, call_id); crm_xml_add_int(update, PCMK__XA_ST_TIMEOUT, op_timeout); send_cluster_message(pcmk__get_node(0, client_node, NULL, pcmk__node_search_cluster), crm_msg_stonith_ng, update, FALSE); free_xml(update); for (iter = op->duplicates; iter != NULL; iter = iter->next) { remote_fencing_op_t *dup = iter->data; crm_trace("Reporting timeout for duplicate %.8s to client %s", dup->id, dup->client_name); report_timeout_period(iter->data, op_timeout); } } /*! * \internal * \brief Advance an operation to the next device in its topology * * \param[in,out] op Fencer operation to advance * \param[in] device ID of device that just completed * \param[in,out] msg If not NULL, XML reply of last delegated operation */ static void advance_topology_device_in_level(remote_fencing_op_t *op, const char *device, xmlNode *msg) { /* Advance to the next device at this topology level, if any */ if (op->devices) { op->devices = op->devices->next; } /* Handle automatic unfencing if an "on" action was requested */ if ((op->phase == st_phase_requested) && pcmk__str_eq(op->action, PCMK_ACTION_ON, pcmk__str_none)) { /* If the device we just executed was required, it's not anymore */ remove_required_device(op, device); /* If there are no more devices at this topology level, run through any * remaining devices with automatic unfencing */ if (op->devices == NULL) { op->devices = op->automatic_list; } } if ((op->devices == NULL) && (op->phase == st_phase_off)) { /* We're done with this level and with required devices, but we had * remapped "reboot" to "off", so start over with "on". If any devices * need to be turned back on, op->devices will be non-NULL after this. */ op_phase_on(op); } // This function is only called if the previous device succeeded pcmk__set_result(&op->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); if (op->devices) { /* Necessary devices remain, so execute the next one */ crm_trace("Next targeting %s on behalf of %s@%s", op->target, op->client_name, op->originator); // The requested delay has been applied for the first device if (op->client_delay > 0) { op->client_delay = 0; } request_peer_fencing(op, NULL); } else { /* We're done with all devices and phases, so finalize operation */ crm_trace("Marking complex fencing op targeting %s as complete", op->target); op->state = st_done; finalize_op(op, msg, false); } } static gboolean check_watchdog_fencing_and_wait(remote_fencing_op_t * op) { if (node_does_watchdog_fencing(op->target)) { guint timeout_ms = QB_MIN(stonith_watchdog_timeout_ms, UINT_MAX); crm_notice("Waiting %s for %s to self-fence (%s) for " "client %s " CRM_XS " id=%.8s", pcmk__readable_interval(timeout_ms), op->target, op->action, op->client_name, op->id); if (op->op_timer_one) { g_source_remove(op->op_timer_one); } op->op_timer_one = g_timeout_add(timeout_ms, remote_op_watchdog_done, op); return TRUE; } else { crm_debug("Skipping fallback to watchdog-fencing as %s is " "not in host-list", op->target); } return FALSE; } /*! * \internal * \brief Ask a peer to execute a fencing operation * * \param[in,out] op Fencing operation to be executed * \param[in,out] peer If NULL or topology is in use, choose best peer to * execute the fencing, otherwise use this peer */ static void request_peer_fencing(remote_fencing_op_t *op, peer_device_info_t *peer) { const char *device = NULL; int timeout; CRM_CHECK(op != NULL, return); crm_trace("Action %.8s targeting %s for %s is %s", op->id, op->target, op->client_name, stonith_op_state_str(op->state)); if ((op->phase == st_phase_on) && (op->devices != NULL)) { /* We are in the "on" phase of a remapped topology reboot. If this * device has pcmk_reboot_action="off", or doesn't support the "on" * action, skip it. * * We can't check device properties at this point because we haven't * chosen a peer for this stage yet. Instead, we check the local node's * knowledge about the device. If different versions of the fence agent * are installed on different nodes, there's a chance this could be * mistaken, but the worst that could happen is we don't try turning the * node back on when we should. */ device = op->devices->data; if (pcmk__str_eq(fenced_device_reboot_action(device), PCMK_ACTION_OFF, pcmk__str_none)) { crm_info("Not turning %s back on using %s because the device is " "configured to stay off (pcmk_reboot_action='off')", op->target, device); advance_topology_device_in_level(op, device, NULL); return; } if (!fenced_device_supports_on(device)) { crm_info("Not turning %s back on using %s because the agent " "doesn't support 'on'", op->target, device); advance_topology_device_in_level(op, device, NULL); return; } } timeout = op->base_timeout; if ((peer == NULL) && !pcmk_is_set(op->call_options, st_opt_topology)) { peer = stonith_choose_peer(op); } if (!op->op_timer_total) { op->total_timeout = TIMEOUT_MULTIPLY_FACTOR * get_op_total_timeout(op, peer); op->op_timer_total = g_timeout_add(1000 * op->total_timeout, remote_op_timeout, op); report_timeout_period(op, op->total_timeout); crm_info("Total timeout set to %d for peer's fencing targeting %s for %s" CRM_XS "id=%.8s", op->total_timeout, op->target, op->client_name, op->id); } if (pcmk_is_set(op->call_options, st_opt_topology) && op->devices) { /* Ignore the caller's peer preference if topology is in use, because * that peer might not have access to the required device. With * topology, stonith_choose_peer() removes the device from further * consideration, so the timeout must be calculated beforehand. * * @TODO Basing the total timeout on the caller's preferred peer (above) * is less than ideal. */ peer = stonith_choose_peer(op); device = op->devices->data; /* Fencing timeout sent to peer takes no delay into account. * The peer will add a dedicated timer for any delay upon * schedule_stonith_command(). */ timeout = get_device_timeout(op, peer, device, false); } if (peer) { int timeout_one = 0; xmlNode *remote_op = stonith_create_op(op->client_callid, op->id, STONITH_OP_FENCE, NULL, 0); if (op->client_delay > 0) { /* Take requested fencing delay into account to prevent it from * eating up the timeout. */ timeout_one = TIMEOUT_MULTIPLY_FACTOR * op->client_delay; } crm_xml_add(remote_op, PCMK__XA_ST_REMOTE_OP, op->id); crm_xml_add(remote_op, PCMK__XA_ST_TARGET, op->target); crm_xml_add(remote_op, F_STONITH_ACTION, op->action); crm_xml_add(remote_op, F_STONITH_ORIGIN, op->originator); crm_xml_add(remote_op, PCMK__XA_ST_CLIENTID, op->client_id); crm_xml_add(remote_op, PCMK__XA_ST_CLIENTNAME, op->client_name); crm_xml_add_int(remote_op, PCMK__XA_ST_TIMEOUT, timeout); crm_xml_add_int(remote_op, PCMK__XA_ST_CALLOPT, op->call_options); crm_xml_add_int(remote_op, PCMK__XA_ST_DELAY, op->client_delay); if (device) { timeout_one += TIMEOUT_MULTIPLY_FACTOR * get_device_timeout(op, peer, device, true); crm_notice("Requesting that %s perform '%s' action targeting %s " "using %s " CRM_XS " for client %s (%ds)", peer->host, op->action, op->target, device, op->client_name, timeout_one); crm_xml_add(remote_op, F_STONITH_DEVICE, device); } else { timeout_one += TIMEOUT_MULTIPLY_FACTOR * get_peer_timeout(op, peer); crm_notice("Requesting that %s perform '%s' action targeting %s " CRM_XS " for client %s (%ds, %lds)", peer->host, op->action, op->target, op->client_name, timeout_one, stonith_watchdog_timeout_ms); } op->state = st_exec; if (op->op_timer_one) { g_source_remove(op->op_timer_one); op->op_timer_one = 0; } if (!((stonith_watchdog_timeout_ms > 0) && (pcmk__str_eq(device, STONITH_WATCHDOG_ID, pcmk__str_none) || (pcmk__str_eq(peer->host, op->target, pcmk__str_casei) && pcmk__is_fencing_action(op->action))) && check_watchdog_fencing_and_wait(op))) { /* Some thoughts about self-fencing cases reaching this point: - Actually check in check_watchdog_fencing_and_wait shouldn't fail if STONITH_WATCHDOG_ID is chosen as fencing-device and it being present implies watchdog-fencing is enabled anyway - If watchdog-fencing is disabled either in general or for a specific target - detected in check_watchdog_fencing_and_wait - for some other kind of self-fencing we can't expect a success answer but timeout is fine if the node doesn't come back in between - Delicate might be the case where we have watchdog-fencing enabled for a node but the watchdog-fencing-device isn't explicitly chosen for suicide. Local pe-execution in sbd may detect the node as unclean and lead to timely suicide. Otherwise the selection of PCMK_OPT_STONITH_WATCHDOG_TIMEOUT at least is questionable. */ /* coming here we're not waiting for watchdog timeout - thus engage timer with timout evaluated before */ op->op_timer_one = g_timeout_add((1000 * timeout_one), remote_op_timeout_one, op); } send_cluster_message(pcmk__get_node(0, peer->host, NULL, pcmk__node_search_cluster), crm_msg_stonith_ng, remote_op, FALSE); peer->tried = TRUE; free_xml(remote_op); return; } else if (op->phase == st_phase_on) { /* A remapped "on" cannot be executed, but the node was already * turned off successfully, so ignore the error and continue. */ crm_warn("Ignoring %s 'on' failure (no capable peers) targeting %s " "after successful 'off'", device, op->target); advance_topology_device_in_level(op, device, NULL); return; } else if (op->owner == FALSE) { crm_err("Fencing (%s) targeting %s for client %s is not ours to control", op->action, op->target, op->client_name); } else if (op->query_timer == 0) { /* We've exhausted all available peers */ crm_info("No remaining peers capable of fencing (%s) %s for client %s " CRM_XS " state=%s", op->action, op->target, op->client_name, stonith_op_state_str(op->state)); CRM_CHECK(op->state < st_done, return); finalize_timed_out_op(op, "All nodes failed, or are unable, to " "fence target"); } else if(op->replies >= op->replies_expected || op->replies >= fencing_active_peers()) { /* if the operation never left the query state, * but we have all the expected replies, then no devices * are available to execute the fencing operation. */ if(stonith_watchdog_timeout_ms > 0 && pcmk__str_eq(device, STONITH_WATCHDOG_ID, pcmk__str_null_matches)) { if (check_watchdog_fencing_and_wait(op)) { return; } } if (op->state == st_query) { crm_info("No peers (out of %d) have devices capable of fencing " "(%s) %s for client %s " CRM_XS " state=%s", op->replies, op->action, op->target, op->client_name, stonith_op_state_str(op->state)); pcmk__reset_result(&op->result); pcmk__set_result(&op->result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, NULL); } else { if (pcmk_is_set(op->call_options, st_opt_topology)) { pcmk__reset_result(&op->result); pcmk__set_result(&op->result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, NULL); } /* ... else use existing result from previous failed attempt * (topology is not in use, and no devices remain to be attempted). * Overwriting the result with PCMK_EXEC_NO_FENCE_DEVICE would * prevent finalize_op() from setting the correct delegate if * needed. */ crm_info("No peers (out of %d) are capable of fencing (%s) %s " "for client %s " CRM_XS " state=%s", op->replies, op->action, op->target, op->client_name, stonith_op_state_str(op->state)); } op->state = st_failed; finalize_op(op, NULL, false); } else { crm_info("Waiting for additional peers capable of fencing (%s) %s%s%s " "for client %s " CRM_XS " id=%.8s", op->action, op->target, (device? " using " : ""), (device? device : ""), op->client_name, op->id); } } /*! * \internal * \brief Comparison function for sorting query results * * \param[in] a GList item to compare * \param[in] b GList item to compare * * \return Per the glib documentation, "a negative integer if the first value * comes before the second, 0 if they are equal, or a positive integer * if the first value comes after the second." */ static gint sort_peers(gconstpointer a, gconstpointer b) { const peer_device_info_t *peer_a = a; const peer_device_info_t *peer_b = b; return (peer_b->ndevices - peer_a->ndevices); } /*! * \internal * \brief Determine if all the devices in the topology are found or not * * \param[in] op Fencing operation with topology to check */ static gboolean all_topology_devices_found(const remote_fencing_op_t *op) { GList *device = NULL; GList *iter = NULL; device_properties_t *match = NULL; stonith_topology_t *tp = NULL; gboolean skip_target = FALSE; int i; tp = find_topology_for_host(op->target); if (!tp) { return FALSE; } if (pcmk__is_fencing_action(op->action)) { /* Don't count the devices on the target node if we are killing * the target node. */ skip_target = TRUE; } for (i = 0; i < ST_LEVEL_MAX; i++) { for (device = tp->levels[i]; device; device = device->next) { match = NULL; for (iter = op->query_results; iter && !match; iter = iter->next) { peer_device_info_t *peer = iter->data; if (skip_target && pcmk__str_eq(peer->host, op->target, pcmk__str_casei)) { continue; } match = find_peer_device(op, peer, device->data, st_device_supports_none); } if (!match) { return FALSE; } } } return TRUE; } /*! * \internal * \brief Parse action-specific device properties from XML * * \param[in] xml XML element containing the properties * \param[in] peer Name of peer that sent XML (for logs) * \param[in] device Device ID (for logs) * \param[in] action Action the properties relate to (for logs) * \param[in,out] op Fencing operation that properties are being parsed for * \param[in] phase Phase the properties relate to * \param[in,out] props Device properties to update */ static void parse_action_specific(const xmlNode *xml, const char *peer, const char *device, const char *action, remote_fencing_op_t *op, enum st_remap_phase phase, device_properties_t *props) { props->custom_action_timeout[phase] = 0; crm_element_value_int(xml, PCMK__XA_ST_ACTION_TIMEOUT, &props->custom_action_timeout[phase]); if (props->custom_action_timeout[phase]) { crm_trace("Peer %s with device %s returned %s action timeout %d", peer, device, action, props->custom_action_timeout[phase]); } props->delay_max[phase] = 0; crm_element_value_int(xml, PCMK__XA_ST_DELAY_MAX, &props->delay_max[phase]); if (props->delay_max[phase]) { crm_trace("Peer %s with device %s returned maximum of random delay %d for %s", peer, device, props->delay_max[phase], action); } props->delay_base[phase] = 0; crm_element_value_int(xml, PCMK__XA_ST_DELAY_BASE, &props->delay_base[phase]); if (props->delay_base[phase]) { crm_trace("Peer %s with device %s returned base delay %d for %s", peer, device, props->delay_base[phase], action); } /* Handle devices with automatic unfencing */ if (pcmk__str_eq(action, PCMK_ACTION_ON, pcmk__str_none)) { int required = 0; crm_element_value_int(xml, PCMK__XA_ST_REQUIRED, &required); if (required) { crm_trace("Peer %s requires device %s to execute for action %s", peer, device, action); add_required_device(op, device); } } /* If a reboot is remapped to off+on, it's possible that a node is allowed * to perform one action but not another. */ if (pcmk__xe_attr_is_true(xml, PCMK__XA_ST_ACTION_DISALLOWED)) { props->disallowed[phase] = TRUE; crm_trace("Peer %s is disallowed from executing %s for device %s", peer, action, device); } } /*! * \internal * \brief Parse one device's properties from peer's XML query reply * * \param[in] xml XML node containing device properties * \param[in,out] op Operation that query and reply relate to * \param[in,out] peer Peer's device information * \param[in] device ID of device being parsed */ static void add_device_properties(const xmlNode *xml, remote_fencing_op_t *op, peer_device_info_t *peer, const char *device) { xmlNode *child; int verified = 0; device_properties_t *props = calloc(1, sizeof(device_properties_t)); int flags = st_device_supports_on; /* Old nodes that don't set the flag assume they support the on action */ /* Add a new entry to this peer's devices list */ CRM_ASSERT(props != NULL); g_hash_table_insert(peer->devices, strdup(device), props); /* Peers with verified (monitored) access will be preferred */ crm_element_value_int(xml, PCMK__XA_ST_MONITOR_VERIFIED, &verified); if (verified) { crm_trace("Peer %s has confirmed a verified device %s", peer->host, device); props->verified = TRUE; } crm_element_value_int(xml, F_STONITH_DEVICE_SUPPORT_FLAGS, &flags); props->device_support_flags = flags; /* Parse action-specific device properties */ parse_action_specific(xml, peer->host, device, op_requested_action(op), op, st_phase_requested, props); for (child = pcmk__xml_first_child(xml); child != NULL; child = pcmk__xml_next(child)) { /* Replies for "reboot" operations will include the action-specific * values for "off" and "on" in child elements, just in case the reboot * winds up getting remapped. */ if (pcmk__str_eq(pcmk__xe_id(child), PCMK_ACTION_OFF, pcmk__str_none)) { parse_action_specific(child, peer->host, device, PCMK_ACTION_OFF, op, st_phase_off, props); } else if (pcmk__str_eq(pcmk__xe_id(child), PCMK_ACTION_ON, pcmk__str_none)) { parse_action_specific(child, peer->host, device, PCMK_ACTION_ON, op, st_phase_on, props); } } } /*! * \internal * \brief Parse a peer's XML query reply and add it to operation's results * * \param[in,out] op Operation that query and reply relate to * \param[in] host Name of peer that sent this reply * \param[in] ndevices Number of devices expected in reply * \param[in] xml XML node containing device list * * \return Newly allocated result structure with parsed reply */ static peer_device_info_t * add_result(remote_fencing_op_t *op, const char *host, int ndevices, const xmlNode *xml) { peer_device_info_t *peer = calloc(1, sizeof(peer_device_info_t)); xmlNode *child; // cppcheck seems not to understand the abort logic in CRM_CHECK // cppcheck-suppress memleak CRM_CHECK(peer != NULL, return NULL); peer->host = strdup(host); peer->devices = pcmk__strkey_table(free, free); /* Each child element describes one capable device available to the peer */ for (child = pcmk__xml_first_child(xml); child != NULL; child = pcmk__xml_next(child)) { const char *device = pcmk__xe_id(child); if (device) { add_device_properties(child, op, peer, device); } } peer->ndevices = g_hash_table_size(peer->devices); CRM_CHECK(ndevices == peer->ndevices, crm_err("Query claimed to have %d device%s but %d found", ndevices, pcmk__plural_s(ndevices), peer->ndevices)); op->query_results = g_list_insert_sorted(op->query_results, peer, sort_peers); return peer; } /*! * \internal * \brief Handle a peer's reply to our fencing query * * Parse a query result from XML and store it in the remote operation * table, and when enough replies have been received, issue a fencing request. * * \param[in] msg XML reply received * * \return pcmk_ok on success, -errno on error * * \note See initiate_remote_stonith_op() for how the XML query was initially * formed, and stonith_query() for how the peer formed its XML reply. */ int process_remote_stonith_query(xmlNode *msg) { int ndevices = 0; gboolean host_is_target = FALSE; gboolean have_all_replies = FALSE; const char *id = NULL; const char *host = NULL; remote_fencing_op_t *op = NULL; peer_device_info_t *peer = NULL; uint32_t replies_expected; xmlNode *dev = get_xpath_object("//@" PCMK__XA_ST_REMOTE_OP, msg, LOG_ERR); CRM_CHECK(dev != NULL, return -EPROTO); id = crm_element_value(dev, PCMK__XA_ST_REMOTE_OP); CRM_CHECK(id != NULL, return -EPROTO); dev = get_xpath_object("//@" PCMK__XA_ST_AVAILABLE_DEVICES, msg, LOG_ERR); CRM_CHECK(dev != NULL, return -EPROTO); crm_element_value_int(dev, PCMK__XA_ST_AVAILABLE_DEVICES, &ndevices); op = g_hash_table_lookup(stonith_remote_op_list, id); if (op == NULL) { crm_debug("Received query reply for unknown or expired operation %s", id); return -EOPNOTSUPP; } replies_expected = fencing_active_peers(); if (op->replies_expected < replies_expected) { replies_expected = op->replies_expected; } if ((++op->replies >= replies_expected) && (op->state == st_query)) { have_all_replies = TRUE; } host = crm_element_value(msg, PCMK__XA_SRC); host_is_target = pcmk__str_eq(host, op->target, pcmk__str_casei); crm_info("Query result %d of %d from %s for %s/%s (%d device%s) %s", op->replies, replies_expected, host, op->target, op->action, ndevices, pcmk__plural_s(ndevices), id); if (ndevices > 0) { peer = add_result(op, host, ndevices, dev); } pcmk__set_result(&op->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); if (pcmk_is_set(op->call_options, st_opt_topology)) { /* If we start the fencing before all the topology results are in, * it is possible fencing levels will be skipped because of the missing * query results. */ if (op->state == st_query && all_topology_devices_found(op)) { /* All the query results are in for the topology, start the fencing ops. */ crm_trace("All topology devices found"); request_peer_fencing(op, peer); } else if (have_all_replies) { crm_info("All topology query replies have arrived, continuing (%d expected/%d received) ", replies_expected, op->replies); request_peer_fencing(op, NULL); } } else if (op->state == st_query) { int nverified = count_peer_devices(op, peer, TRUE, fenced_support_flag(op->action)); /* We have a result for a non-topology fencing op that looks promising, * go ahead and start fencing before query timeout */ if ((peer != NULL) && !host_is_target && nverified) { /* we have a verified device living on a peer that is not the target */ crm_trace("Found %d verified device%s", nverified, pcmk__plural_s(nverified)); request_peer_fencing(op, peer); } else if (have_all_replies) { crm_info("All query replies have arrived, continuing (%d expected/%d received) ", replies_expected, op->replies); request_peer_fencing(op, NULL); } else { crm_trace("Waiting for more peer results before launching fencing operation"); } } else if ((peer != NULL) && (op->state == st_done)) { crm_info("Discarding query result from %s (%d device%s): " "Operation is %s", peer->host, peer->ndevices, pcmk__plural_s(peer->ndevices), stonith_op_state_str(op->state)); } return pcmk_ok; } /*! * \internal * \brief Handle a peer's reply to a fencing request * * Parse a fencing reply from XML, and either finalize the operation * or attempt another device as appropriate. * * \param[in] msg XML reply received */ void fenced_process_fencing_reply(xmlNode *msg) { const char *id = NULL; const char *device = NULL; remote_fencing_op_t *op = NULL; xmlNode *dev = get_xpath_object("//@" PCMK__XA_ST_REMOTE_OP, msg, LOG_ERR); pcmk__action_result_t result = PCMK__UNKNOWN_RESULT; CRM_CHECK(dev != NULL, return); id = crm_element_value(dev, PCMK__XA_ST_REMOTE_OP); CRM_CHECK(id != NULL, return); dev = stonith__find_xe_with_result(msg); CRM_CHECK(dev != NULL, return); stonith__xe_get_result(dev, &result); device = crm_element_value(dev, F_STONITH_DEVICE); if (stonith_remote_op_list) { op = g_hash_table_lookup(stonith_remote_op_list, id); } if ((op == NULL) && pcmk__result_ok(&result)) { /* Record successful fencing operations */ const char *client_id = crm_element_value(dev, PCMK__XA_ST_CLIENTID); op = create_remote_stonith_op(client_id, dev, TRUE); } if (op == NULL) { /* Could be for an event that began before we started */ /* TODO: Record the op for later querying */ crm_info("Received peer result of unknown or expired operation %s", id); pcmk__reset_result(&result); return; } pcmk__reset_result(&op->result); op->result = result; // The operation takes ownership of the result if (op->devices && device && !pcmk__str_eq(op->devices->data, device, pcmk__str_casei)) { crm_err("Received outdated reply for device %s (instead of %s) to " "fence (%s) %s. Operation already timed out at peer level.", device, (const char *) op->devices->data, op->action, op->target); return; } if (pcmk__str_eq(crm_element_value(msg, PCMK__XA_SUBT), "broadcast", pcmk__str_none)) { if (pcmk__result_ok(&op->result)) { op->state = st_done; } else { op->state = st_failed; } finalize_op(op, msg, false); return; } else if (!pcmk__str_eq(op->originator, stonith_our_uname, pcmk__str_casei)) { /* If this isn't a remote level broadcast, and we are not the * originator of the operation, we should not be receiving this msg. */ crm_err("Received non-broadcast fencing result for operation %.8s " "we do not own (device %s targeting %s)", op->id, device, op->target); return; } if (pcmk_is_set(op->call_options, st_opt_topology)) { const char *device = NULL; const char *reason = op->result.exit_reason; /* We own the op, and it is complete. broadcast the result to all nodes * and notify our local clients. */ if (op->state == st_done) { finalize_op(op, msg, false); return; } device = crm_element_value(msg, F_STONITH_DEVICE); if ((op->phase == 2) && !pcmk__result_ok(&op->result)) { /* A remapped "on" failed, but the node was already turned off * successfully, so ignore the error and continue. */ crm_warn("Ignoring %s 'on' failure (%s%s%s) targeting %s " "after successful 'off'", device, pcmk_exec_status_str(op->result.execution_status), (reason == NULL)? "" : ": ", (reason == NULL)? "" : reason, op->target); pcmk__set_result(&op->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); } else { crm_notice("Action '%s' targeting %s%s%s on behalf of %s@%s: " "%s%s%s%s", op->action, op->target, ((device == NULL)? "" : " using "), ((device == NULL)? "" : device), op->client_name, op->originator, pcmk_exec_status_str(op->result.execution_status), (reason == NULL)? "" : " (", (reason == NULL)? "" : reason, (reason == NULL)? "" : ")"); } if (pcmk__result_ok(&op->result)) { /* An operation completed successfully. Try another device if * necessary, otherwise mark the operation as done. */ advance_topology_device_in_level(op, device, msg); return; } else { /* This device failed, time to try another topology level. If no other * levels are available, mark this operation as failed and report results. */ if (advance_topology_level(op, false) != pcmk_rc_ok) { op->state = st_failed; finalize_op(op, msg, false); return; } } } else if (pcmk__result_ok(&op->result) && (op->devices == NULL)) { op->state = st_done; finalize_op(op, msg, false); return; } else if ((op->result.execution_status == PCMK_EXEC_TIMEOUT) && (op->devices == NULL)) { /* If the operation timed out don't bother retrying other peers. */ op->state = st_failed; finalize_op(op, msg, false); return; } else { /* fall-through and attempt other fencing action using another peer */ } /* Retry on failure */ crm_trace("Next for %s on behalf of %s@%s (result was: %s)", op->target, op->originator, op->client_name, pcmk_exec_status_str(op->result.execution_status)); request_peer_fencing(op, NULL); } gboolean stonith_check_fence_tolerance(int tolerance, const char *target, const char *action) { GHashTableIter iter; time_t now = time(NULL); remote_fencing_op_t *rop = NULL; if (tolerance <= 0 || !stonith_remote_op_list || target == NULL || action == NULL) { return FALSE; } g_hash_table_iter_init(&iter, stonith_remote_op_list); while (g_hash_table_iter_next(&iter, NULL, (void **)&rop)) { if (strcmp(rop->target, target) != 0) { continue; } else if (rop->state != st_done) { continue; /* We don't have to worry about remapped reboots here * because if state is done, any remapping has been undone */ } else if (strcmp(rop->action, action) != 0) { continue; } else if ((rop->completed + tolerance) < now) { continue; } crm_notice("Target %s was fenced (%s) less than %ds ago by %s on behalf of %s", target, action, tolerance, rop->delegate, rop->originator); return TRUE; } return FALSE; } diff --git a/daemons/fenced/pacemaker-fenced.c b/daemons/fenced/pacemaker-fenced.c index 4c83bab943..62e431fc8a 100644 --- a/daemons/fenced/pacemaker-fenced.c +++ b/daemons/fenced/pacemaker-fenced.c @@ -1,998 +1,998 @@ /* * Copyright 2009-2024 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 // PRIu32, PRIx32 #include #include #include #include #include #include #include #include #include #include #include #include #define SUMMARY "daemon for executing fencing devices in a Pacemaker cluster" char *stonith_our_uname = NULL; long long stonith_watchdog_timeout_ms = 0; GList *stonith_watchdog_targets = NULL; static GMainLoop *mainloop = NULL; gboolean stand_alone = FALSE; gboolean stonith_shutdown_flag = FALSE; static qb_ipcs_service_t *ipcs = NULL; static pcmk__output_t *out = NULL; pcmk__supported_format_t formats[] = { PCMK__SUPPORTED_FORMAT_NONE, PCMK__SUPPORTED_FORMAT_TEXT, PCMK__SUPPORTED_FORMAT_XML, { NULL, NULL, NULL } }; static struct { bool no_cib_connect; gchar **log_files; } options; crm_exit_t exit_code = CRM_EX_OK; static void stonith_cleanup(void); static int32_t st_ipc_accept(qb_ipcs_connection_t * c, uid_t uid, gid_t gid) { if (stonith_shutdown_flag) { crm_info("Ignoring new client [%d] during shutdown", pcmk__client_pid(c)); return -ECONNREFUSED; } if (pcmk__new_client(c, uid, gid) == NULL) { return -ENOMEM; } return 0; } /* Exit code means? */ static int32_t st_ipc_dispatch(qb_ipcs_connection_t * qbc, void *data, size_t size) { uint32_t id = 0; uint32_t flags = 0; int call_options = 0; xmlNode *request = NULL; pcmk__client_t *c = pcmk__find_client(qbc); const char *op = NULL; if (c == NULL) { crm_info("Invalid client: %p", qbc); return 0; } request = pcmk__client_data2xml(c, data, &id, &flags); if (request == NULL) { pcmk__ipc_send_ack(c, id, flags, PCMK__XE_NACK, NULL, CRM_EX_PROTOCOL); return 0; } op = crm_element_value(request, PCMK__XA_CRM_TASK); if(pcmk__str_eq(op, CRM_OP_RM_NODE_CACHE, pcmk__str_casei)) { crm_xml_add(request, PCMK__XA_T, T_STONITH_NG); crm_xml_add(request, PCMK__XA_ST_OP, op); crm_xml_add(request, PCMK__XA_ST_CLIENTID, c->id); crm_xml_add(request, PCMK__XA_ST_CLIENTNAME, pcmk__client_name(c)); - crm_xml_add(request, F_STONITH_CLIENTNODE, stonith_our_uname); + crm_xml_add(request, PCMK__XA_ST_CLIENTNODE, stonith_our_uname); send_cluster_message(NULL, crm_msg_stonith_ng, request, FALSE); free_xml(request); return 0; } if (c->name == NULL) { const char *value = crm_element_value(request, PCMK__XA_ST_CLIENTNAME); c->name = crm_strdup_printf("%s.%u", pcmk__s(value, "unknown"), c->pid); } crm_element_value_int(request, PCMK__XA_ST_CALLOPT, &call_options); crm_trace("Flags %#08" PRIx32 "/%#08x for command %" PRIu32 " from client %s", flags, call_options, id, pcmk__client_name(c)); if (pcmk_is_set(call_options, st_opt_sync_call)) { CRM_ASSERT(flags & crm_ipc_client_response); CRM_LOG_ASSERT(c->request_id == 0); /* This means the client has two synchronous events in-flight */ c->request_id = id; /* Reply only to the last one */ } crm_xml_add(request, PCMK__XA_ST_CLIENTID, c->id); crm_xml_add(request, PCMK__XA_ST_CLIENTNAME, pcmk__client_name(c)); - crm_xml_add(request, F_STONITH_CLIENTNODE, stonith_our_uname); + crm_xml_add(request, PCMK__XA_ST_CLIENTNODE, stonith_our_uname); crm_log_xml_trace(request, "ipc-received"); stonith_command(c, id, flags, request, NULL); free_xml(request); return 0; } /* Error code means? */ static int32_t st_ipc_closed(qb_ipcs_connection_t * c) { pcmk__client_t *client = pcmk__find_client(c); if (client == NULL) { return 0; } crm_trace("Connection %p closed", c); pcmk__free_client(client); /* 0 means: yes, go ahead and destroy the connection */ return 0; } static void st_ipc_destroy(qb_ipcs_connection_t * c) { crm_trace("Connection %p destroyed", c); st_ipc_closed(c); } static void stonith_peer_callback(xmlNode * msg, void *private_data) { const char *remote_peer = crm_element_value(msg, PCMK__XA_SRC); const char *op = crm_element_value(msg, PCMK__XA_ST_OP); if (pcmk__str_eq(op, "poke", pcmk__str_none)) { return; } crm_log_xml_trace(msg, "Peer[inbound]"); stonith_command(NULL, 0, 0, msg, remote_peer); } #if SUPPORT_COROSYNC static void stonith_peer_ais_callback(cpg_handle_t handle, const struct cpg_name *groupName, uint32_t nodeid, uint32_t pid, void *msg, size_t msg_len) { uint32_t kind = 0; xmlNode *xml = NULL; const char *from = NULL; char *data = pcmk_message_common_cs(handle, nodeid, pid, msg, &kind, &from); if(data == NULL) { return; } if (kind == crm_class_cluster) { xml = string2xml(data); if (xml == NULL) { crm_err("Invalid XML: '%.120s'", data); free(data); return; } crm_xml_add(xml, PCMK__XA_SRC, from); stonith_peer_callback(xml, NULL); } free_xml(xml); free(data); return; } static void stonith_peer_cs_destroy(gpointer user_data) { crm_crit("Lost connection to cluster layer, shutting down"); stonith_shutdown(0); } #endif void do_local_reply(const xmlNode *notify_src, pcmk__client_t *client, int call_options) { /* send callback to originating child */ int local_rc = pcmk_rc_ok; int rid = 0; uint32_t ipc_flags = crm_ipc_server_event; if (pcmk_is_set(call_options, st_opt_sync_call)) { CRM_LOG_ASSERT(client->request_id); rid = client->request_id; client->request_id = 0; ipc_flags = crm_ipc_flags_none; } local_rc = pcmk__ipc_send_xml(client, rid, notify_src, ipc_flags); if (local_rc == pcmk_rc_ok) { crm_trace("Sent response %d to client %s", rid, pcmk__client_name(client)); } else { crm_warn("%synchronous reply to client %s failed: %s", (pcmk_is_set(call_options, st_opt_sync_call)? "S" : "As"), pcmk__client_name(client), pcmk_rc_str(local_rc)); } } uint64_t get_stonith_flag(const char *name) { if (pcmk__str_eq(name, T_STONITH_NOTIFY_FENCE, pcmk__str_casei)) { return st_callback_notify_fence; } else if (pcmk__str_eq(name, STONITH_OP_DEVICE_ADD, pcmk__str_casei)) { return st_callback_device_add; } else if (pcmk__str_eq(name, STONITH_OP_DEVICE_DEL, pcmk__str_casei)) { return st_callback_device_del; } else if (pcmk__str_eq(name, T_STONITH_NOTIFY_HISTORY, pcmk__str_casei)) { return st_callback_notify_history; } else if (pcmk__str_eq(name, T_STONITH_NOTIFY_HISTORY_SYNCED, pcmk__str_casei)) { return st_callback_notify_history_synced; } return st_callback_unknown; } static void stonith_notify_client(gpointer key, gpointer value, gpointer user_data) { const xmlNode *update_msg = user_data; pcmk__client_t *client = value; const char *type = NULL; CRM_CHECK(client != NULL, return); CRM_CHECK(update_msg != NULL, return); type = crm_element_value(update_msg, PCMK__XA_SUBT); CRM_CHECK(type != NULL, crm_log_xml_err(update_msg, "notify"); return); if (client->ipcs == NULL) { crm_trace("Skipping client with NULL channel"); return; } if (pcmk_is_set(client->flags, get_stonith_flag(type))) { int rc = pcmk__ipc_send_xml(client, 0, update_msg, crm_ipc_server_event); if (rc != pcmk_rc_ok) { crm_warn("%s notification of client %s failed: %s " CRM_XS " id=%.8s rc=%d", type, pcmk__client_name(client), pcmk_rc_str(rc), client->id, rc); } else { crm_trace("Sent %s notification to client %s", type, pcmk__client_name(client)); } } } void do_stonith_async_timeout_update(const char *client_id, const char *call_id, int timeout) { pcmk__client_t *client = NULL; xmlNode *notify_data = NULL; if (!timeout || !call_id || !client_id) { return; } client = pcmk__find_client_by_id(client_id); if (!client) { return; } notify_data = create_xml_node(NULL, T_STONITH_TIMEOUT_VALUE); crm_xml_add(notify_data, PCMK__XA_T, T_STONITH_TIMEOUT_VALUE); crm_xml_add(notify_data, PCMK__XA_ST_CALLID, call_id); crm_xml_add_int(notify_data, PCMK__XA_ST_TIMEOUT, timeout); crm_trace("timeout update is %d for client %s and call id %s", timeout, client_id, call_id); if (client) { pcmk__ipc_send_xml(client, 0, notify_data, crm_ipc_server_event); } free_xml(notify_data); } /*! * \internal * \brief Notify relevant IPC clients of a fencing operation result * * \param[in] type Notification type * \param[in] result Result of fencing operation (assume success if NULL) * \param[in] data If not NULL, add to notification as call data */ void fenced_send_notification(const char *type, const pcmk__action_result_t *result, xmlNode *data) { /* TODO: Standardize the contents of data */ xmlNode *update_msg = create_xml_node(NULL, "notify"); CRM_LOG_ASSERT(type != NULL); crm_xml_add(update_msg, PCMK__XA_T, T_STONITH_NOTIFY); crm_xml_add(update_msg, PCMK__XA_SUBT, type); crm_xml_add(update_msg, PCMK__XA_ST_OP, type); stonith__xe_set_result(update_msg, result); if (data != NULL) { add_message_xml(update_msg, PCMK__XA_ST_CALLDATA, data); } crm_trace("Notifying clients"); pcmk__foreach_ipc_client(stonith_notify_client, update_msg); free_xml(update_msg); crm_trace("Notify complete"); } /*! * \internal * \brief Send notifications for a configuration change to subscribed clients * * \param[in] op Notification type (STONITH_OP_DEVICE_ADD, * STONITH_OP_DEVICE_DEL, STONITH_OP_LEVEL_ADD, or * STONITH_OP_LEVEL_DEL) * \param[in] result Operation result * \param[in] desc Description of what changed * \param[in] active Current number of devices or topologies in use */ static void send_config_notification(const char *op, const pcmk__action_result_t *result, const char *desc, int active) { xmlNode *notify_data = create_xml_node(NULL, op); CRM_CHECK(notify_data != NULL, return); crm_xml_add(notify_data, F_STONITH_DEVICE, desc); crm_xml_add_int(notify_data, F_STONITH_ACTIVE, active); fenced_send_notification(op, result, notify_data); free_xml(notify_data); } /*! * \internal * \brief Send notifications for a device change to subscribed clients * * \param[in] op Notification type (STONITH_OP_DEVICE_ADD or * STONITH_OP_DEVICE_DEL) * \param[in] result Operation result * \param[in] desc ID of device that changed */ void fenced_send_device_notification(const char *op, const pcmk__action_result_t *result, const char *desc) { send_config_notification(op, result, desc, g_hash_table_size(device_list)); } /*! * \internal * \brief Send notifications for a topology level change to subscribed clients * * \param[in] op Notification type (STONITH_OP_LEVEL_ADD or * STONITH_OP_LEVEL_DEL) * \param[in] result Operation result * \param[in] desc String representation of level ([]) */ void fenced_send_level_notification(const char *op, const pcmk__action_result_t *result, const char *desc) { send_config_notification(op, result, desc, g_hash_table_size(topology)); } /*! * \internal * \brief Check whether a node does watchdog-fencing * * \param[in] node Name of node to check * * \return TRUE if node found in stonith_watchdog_targets * or stonith_watchdog_targets is empty indicating * all nodes are doing watchdog-fencing */ gboolean node_does_watchdog_fencing(const char *node) { return ((stonith_watchdog_targets == NULL) || pcmk__str_in_list(node, stonith_watchdog_targets, pcmk__str_casei)); } void stonith_shutdown(int nsig) { crm_info("Terminating with %d clients", pcmk__ipc_client_count()); stonith_shutdown_flag = TRUE; if (mainloop != NULL && g_main_loop_is_running(mainloop)) { g_main_loop_quit(mainloop); } } static void stonith_cleanup(void) { fenced_cib_cleanup(); if (ipcs) { qb_ipcs_destroy(ipcs); } crm_peer_destroy(); pcmk__client_cleanup(); free_stonith_remote_op_list(); free_topology_list(); free_device_list(); free_metadata_cache(); fenced_unregister_handlers(); free(stonith_our_uname); stonith_our_uname = NULL; } static gboolean stand_alone_cpg_cb(const gchar *option_name, const gchar *optarg, gpointer data, GError **error) { stand_alone = FALSE; options.no_cib_connect = true; return TRUE; } struct qb_ipcs_service_handlers ipc_callbacks = { .connection_accept = st_ipc_accept, .connection_created = NULL, .msg_process = st_ipc_dispatch, .connection_closed = st_ipc_closed, .connection_destroyed = st_ipc_destroy }; /*! * \internal * \brief Callback for peer status changes * * \param[in] type What changed * \param[in] node What peer had the change * \param[in] data Previous value of what changed */ static void st_peer_update_callback(enum crm_status_type type, crm_node_t * node, const void *data) { if ((type != crm_status_processes) && !pcmk_is_set(node->flags, crm_remote_node)) { /* * This is a hack until we can send to a nodeid and/or we fix node name lookups * These messages are ignored in stonith_peer_callback() */ xmlNode *query = create_xml_node(NULL, "stonith_command"); crm_xml_add(query, PCMK__XA_T, T_STONITH_NG); crm_xml_add(query, PCMK__XA_ST_OP, "poke"); crm_debug("Broadcasting our uname because of node %u", node->id); send_cluster_message(NULL, crm_msg_stonith_ng, query, FALSE); free_xml(query); } } static pcmk__cluster_option_t fencer_options[] = { /* name, old name, type, allowed values, * default value, validator, * context, * short description, * long description */ { PCMK_STONITH_HOST_ARGUMENT, NULL, "string", NULL, "port", NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "An alternate parameter to supply instead of 'port'"), N_("Some devices do not support the standard 'port' parameter or may " "provide additional ones. Use this to specify an alternate, device-" "specific, parameter that should indicate the machine to be " "fenced. A value of \"none\" can be used to tell the cluster not " "to supply any additional parameters."), }, { PCMK_STONITH_HOST_MAP, NULL, "string", NULL, "", NULL, pcmk__opt_context_none, N_("A mapping of node names to port numbers for devices that do not " "support node names."), N_("For example, \"node1:1;node2:2,3\" would tell the cluster to use " "port 1 for node1 and ports 2 and 3 for node2."), }, { PCMK_STONITH_HOST_LIST, NULL, "string", NULL, "", NULL, pcmk__opt_context_none, N_("A list of nodes that can be targeted by this device (optional " "unless pcmk_host_list=\"static-list\")"), N_("For example, \"node1,node2,node3\"."), }, { PCMK_STONITH_HOST_CHECK, NULL, "select", "dynamic-list, static-list, status, none", "dynamic-list", NULL, pcmk__opt_context_none, N_("How to determine which nodes can be targeted by the device"), N_("Use \"dynamic-list\" to query the device via the 'list' command; " "\"static-list\" to check the pcmk_host_list attribute; " "\"status\" to query the device via the 'status' command; or " "\"none\" to assume every device can fence every node."), }, { PCMK_STONITH_DELAY_MAX, NULL, "time", NULL, "0s", NULL, pcmk__opt_context_none, N_("Enable a base delay for fencing actions and specify base delay " "value."), N_("Enable a delay of no more than the time specified before executing " "fencing actions. Pacemaker derives the overall delay by taking " "the value of pcmk_delay_base and adding a random delay value such " "that the sum is kept below this maximum."), }, { PCMK_STONITH_DELAY_BASE, NULL, "string", NULL, "0s", NULL, pcmk__opt_context_none, N_("Enable a base delay for fencing actions and specify base delay " "value."), N_("This enables a static delay for fencing actions, which can help " "avoid \"death matches\" where two nodes try to fence each other " "at the same time. If pcmk_delay_max is also used, a random delay " "will be added such that the total delay is kept below that value. " "This can be set to a single time value to apply to any node " "targeted by this device (useful if a separate device is " "configured for each target), or to a node map (for example, " "\"node1:1s;node2:5\") to set a different value for each target."), }, { PCMK_STONITH_ACTION_LIMIT, NULL, "integer", NULL, "1", NULL, pcmk__opt_context_none, N_("The maximum number of actions can be performed in parallel on this " "device"), N_("Cluster property concurrent-fencing=\"true\" needs to be " "configured first. Then use this to specify the maximum number of " "actions can be performed in parallel on this device. A value of " "-1 means an unlimited number of actions can be performed in " "parallel."), }, { "pcmk_reboot_action", NULL, "string", NULL, PCMK_ACTION_REBOOT, NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "An alternate command to run instead of 'reboot'"), N_("Some devices do not support the standard commands or may provide " "additional ones. Use this to specify an alternate, device-" "specific, command that implements the 'reboot' action."), }, { "pcmk_reboot_timeout", NULL, "time", NULL, "60s", NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "Specify an alternate timeout to use for 'reboot' actions instead " "of stonith-timeout"), N_("Some devices need much more/less time to complete than normal. " "Use this to specify an alternate, device-specific, timeout for " "'reboot' actions."), }, { "pcmk_reboot_retries", NULL, "integer", NULL, "2", NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "The maximum number of times to try the 'reboot' command within " "the timeout period"), N_("Some devices do not support multiple connections. Operations may " "\"fail\" if the device is busy with another task. In that case, " "Pacemaker will automatically retry the operation if there is time " "remaining. Use this option to alter the number of times Pacemaker " "tries a 'reboot' action before giving up."), }, { "pcmk_off_action", NULL, "string", NULL, PCMK_ACTION_OFF, NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "An alternate command to run instead of 'off'"), N_("Some devices do not support the standard commands or may provide " "additional ones. Use this to specify an alternate, device-" "specific, command that implements the 'off' action."), }, { "pcmk_off_timeout", NULL, "time", NULL, "60s", NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "Specify an alternate timeout to use for 'off' actions instead of " "stonith-timeout"), N_("Some devices need much more/less time to complete than normal. " "Use this to specify an alternate, device-specific, timeout for " "'off' actions."), }, { "pcmk_off_retries", NULL, "integer", NULL, "2", NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "The maximum number of times to try the 'off' command within the " "timeout period"), N_("Some devices do not support multiple connections. Operations may " "\"fail\" if the device is busy with another task. In that case, " "Pacemaker will automatically retry the operation if there is time " "remaining. Use this option to alter the number of times Pacemaker " "tries a 'off' action before giving up."), }, { "pcmk_on_action", NULL, "string", NULL, PCMK_ACTION_ON, NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "An alternate command to run instead of 'on'"), N_("Some devices do not support the standard commands or may provide " "additional ones. Use this to specify an alternate, device-" "specific, command that implements the 'on' action."), }, { "pcmk_on_timeout", NULL, "time", NULL, "60s", NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "Specify an alternate timeout to use for 'on' actions instead of " "stonith-timeout"), N_("Some devices need much more/less time to complete than normal. " "Use this to specify an alternate, device-specific, timeout for " "'on' actions."), }, { "pcmk_on_retries", NULL, "integer", NULL, "2", NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "The maximum number of times to try the 'on' command within the " "timeout period"), N_("Some devices do not support multiple connections. Operations may " "\"fail\" if the device is busy with another task. In that case, " "Pacemaker will automatically retry the operation if there is time " "remaining. Use this option to alter the number of times Pacemaker " "tries a 'on' action before giving up."), }, { "pcmk_list_action", NULL, "string", NULL, PCMK_ACTION_LIST, NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "An alternate command to run instead of 'list'"), N_("Some devices do not support the standard commands or may provide " "additional ones. Use this to specify an alternate, device-" "specific, command that implements the 'list' action."), }, { "pcmk_list_timeout", NULL, "time", NULL, "60s", NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "Specify an alternate timeout to use for 'list' actions instead of " "stonith-timeout"), N_("Some devices need much more/less time to complete than normal. " "Use this to specify an alternate, device-specific, timeout for " "'list' actions."), }, { "pcmk_list_retries", NULL, "integer", NULL, "2", NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "The maximum number of times to try the 'list' command within the " "timeout period"), N_("Some devices do not support multiple connections. Operations may " "\"fail\" if the device is busy with another task. In that case, " "Pacemaker will automatically retry the operation if there is time " "remaining. Use this option to alter the number of times Pacemaker " "tries a 'list' action before giving up."), }, { "pcmk_monitor_action", NULL, "string", NULL, PCMK_ACTION_MONITOR, NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "An alternate command to run instead of 'monitor'"), N_("Some devices do not support the standard commands or may provide " "additional ones. Use this to specify an alternate, device-" "specific, command that implements the 'monitor' action."), }, { "pcmk_monitor_timeout", NULL, "time", NULL, "60s", NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "Specify an alternate timeout to use for 'monitor' actions instead " "of stonith-timeout"), N_("Some devices need much more/less time to complete than normal. " "Use this to specify an alternate, device-specific, timeout for " "'monitor' actions."), }, { "pcmk_monitor_retries", NULL, "integer", NULL, "2", NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "The maximum number of times to try the 'monitor' command within " "the timeout period"), N_("Some devices do not support multiple connections. Operations may " "\"fail\" if the device is busy with another task. In that case, " "Pacemaker will automatically retry the operation if there is time " "remaining. Use this option to alter the number of times Pacemaker " "tries a 'monitor' action before giving up."), }, { "pcmk_status_action", NULL, "string", NULL, PCMK_ACTION_STATUS, NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "An alternate command to run instead of 'status'"), N_("Some devices do not support the standard commands or may provide " "additional ones. Use this to specify an alternate, device-" "specific, command that implements the 'status' action."), }, { "pcmk_status_timeout", NULL, "time", NULL, "60s", NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "Specify an alternate timeout to use for 'status' actions instead " "of stonith-timeout"), N_("Some devices need much more/less time to complete than normal. " "Use this to specify an alternate, device-specific, timeout for " "'status' actions."), }, { "pcmk_status_retries", NULL, "integer", NULL, "2", NULL, pcmk__opt_context_none, N_("*** Advanced Use Only *** " "The maximum number of times to try the 'status' command within " "the timeout period"), N_("Some devices do not support multiple connections. Operations may " "\"fail\" if the device is busy with another task. In that case, " "Pacemaker will automatically retry the operation if there is time " "remaining. Use this option to alter the number of times Pacemaker " "tries a 'status' action before giving up."), }, }; void fencer_metadata(void) { const char *name = "pacemaker-fenced"; const char *desc_short = N_("Instance attributes available for all " "\"stonith\"-class resources"); const char *desc_long = N_("Instance attributes available for all " "\"stonith\"-class resources and used by " "Pacemaker's fence daemon, formerly known as " "stonithd"); gchar *s = pcmk__format_option_metadata(name, desc_short, desc_long, pcmk__opt_context_none, fencer_options, PCMK__NELEM(fencer_options)); printf("%s", s); g_free(s); } static GOptionEntry entries[] = { { "stand-alone", 's', G_OPTION_FLAG_NONE, G_OPTION_ARG_NONE, &stand_alone, N_("Deprecated (will be removed in a future release)"), NULL }, { "stand-alone-w-cpg", 'c', G_OPTION_FLAG_NO_ARG, G_OPTION_ARG_CALLBACK, stand_alone_cpg_cb, N_("Intended for use in regression testing only"), NULL }, { "logfile", 'l', G_OPTION_FLAG_NONE, G_OPTION_ARG_FILENAME_ARRAY, &options.log_files, N_("Send logs to the additional named logfile"), NULL }, { NULL } }; static GOptionContext * build_arg_context(pcmk__common_args_t *args, GOptionGroup **group) { GOptionContext *context = NULL; context = pcmk__build_arg_context(args, "text (default), xml", group, "[metadata]"); pcmk__add_main_args(context, entries); return context; } int main(int argc, char **argv) { int rc = pcmk_rc_ok; crm_cluster_t *cluster = NULL; crm_ipc_t *old_instance = NULL; GError *error = NULL; GOptionGroup *output_group = NULL; pcmk__common_args_t *args = pcmk__new_common_args(SUMMARY); gchar **processed_args = pcmk__cmdline_preproc(argv, "l"); GOptionContext *context = build_arg_context(args, &output_group); crm_log_preinit(NULL, argc, argv); pcmk__register_formats(output_group, formats); if (!g_option_context_parse_strv(context, &processed_args, &error)) { exit_code = CRM_EX_USAGE; goto done; } rc = pcmk__output_new(&out, args->output_ty, args->output_dest, argv); if (rc != pcmk_rc_ok) { exit_code = CRM_EX_ERROR; g_set_error(&error, PCMK__EXITC_ERROR, exit_code, "Error creating output format %s: %s", args->output_ty, pcmk_rc_str(rc)); goto done; } if (args->version) { out->version(out, false); goto done; } if ((g_strv_length(processed_args) >= 2) && pcmk__str_eq(processed_args[1], "metadata", pcmk__str_none)) { fencer_metadata(); goto done; } // Open additional log files pcmk__add_logfiles(options.log_files, out); crm_log_init(NULL, LOG_INFO + args->verbosity, TRUE, (args->verbosity > 0), argc, argv, FALSE); crm_notice("Starting Pacemaker fencer"); old_instance = crm_ipc_new("stonith-ng", 0); if (old_instance == NULL) { /* crm_ipc_new() will have already logged an error message with * crm_err() */ exit_code = CRM_EX_FATAL; goto done; } if (pcmk__connect_generic_ipc(old_instance) == pcmk_rc_ok) { // IPC endpoint already up crm_ipc_close(old_instance); crm_ipc_destroy(old_instance); crm_err("pacemaker-fenced is already active, aborting startup"); goto done; } else { // Not up or not authentic, we'll proceed either way crm_ipc_destroy(old_instance); old_instance = NULL; } mainloop_add_signal(SIGTERM, stonith_shutdown); crm_peer_init(); rc = fenced_scheduler_init(); if (rc != pcmk_rc_ok) { exit_code = CRM_EX_FATAL; g_set_error(&error, PCMK__EXITC_ERROR, exit_code, "Error initializing scheduler data: %s", pcmk_rc_str(rc)); goto done; } cluster = pcmk_cluster_new(); if (!stand_alone) { #if SUPPORT_COROSYNC if (is_corosync_cluster()) { cluster->destroy = stonith_peer_cs_destroy; cluster->cpg.cpg_deliver_fn = stonith_peer_ais_callback; cluster->cpg.cpg_confchg_fn = pcmk_cpg_membership; } #endif // SUPPORT_COROSYNC crm_set_status_callback(&st_peer_update_callback); if (crm_cluster_connect(cluster) == FALSE) { exit_code = CRM_EX_FATAL; crm_crit("Cannot sign in to the cluster... terminating"); goto done; } pcmk__str_update(&stonith_our_uname, cluster->uname); if (!options.no_cib_connect) { setup_cib(); } } else { pcmk__str_update(&stonith_our_uname, "localhost"); crm_warn("Stand-alone mode is deprecated and will be removed " "in a future release"); } init_device_list(); init_topology_list(); pcmk__serve_fenced_ipc(&ipcs, &ipc_callbacks); // Create the mainloop and run it... mainloop = g_main_loop_new(NULL, FALSE); crm_notice("Pacemaker fencer successfully started and accepting connections"); g_main_loop_run(mainloop); done: g_strfreev(processed_args); pcmk__free_arg_context(context); g_strfreev(options.log_files); stonith_cleanup(); pcmk_cluster_free(cluster); fenced_scheduler_cleanup(); pcmk__output_and_clear_error(&error, out); if (out != NULL) { out->finish(out, exit_code, true, NULL); pcmk__output_free(out); } pcmk__unregister_formats(); crm_exit(exit_code); } diff --git a/include/crm/common/xml_names_internal.h b/include/crm/common/xml_names_internal.h index 298b7a69f7..2a6313efac 100644 --- a/include/crm/common/xml_names_internal.h +++ b/include/crm/common/xml_names_internal.h @@ -1,237 +1,238 @@ /* * Copyright 2004-2024 the Pacemaker project contributors * * The version control history for this file may have further details. * * This source code is licensed under the GNU Lesser General Public License * version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY. */ #ifndef PCMK__CRM_COMMON_XML_NAMES_INTERNAL__H # define PCMK__CRM_COMMON_XML_NAMES_INTERNAL__H #ifdef __cplusplus extern "C" { #endif /* * XML element names used only by internal code */ #define PCMK__XE_ACK "ack" #define PCMK__XE_ATTRIBUTES "attributes" #define PCMK__XE_CRM_EVENT "crm_event" #define PCMK__XE_CRM_XML "crm_xml" #define PCMK__XE_DIV "div" #define PCMK__XE_DOWNED "downed" #define PCMK__XE_FAILED "failed" #define PCMK__XE_FAILED_UPDATE "failed_update" #define PCMK__XE_GENERATION_TUPLE "generation_tuple" #define PCMK__XE_LRM "lrm" #define PCMK__XE_LRM_RESOURCE "lrm_resource" #define PCMK__XE_LRM_RESOURCES "lrm_resources" #define PCMK__XE_LRM_RSC_OP "lrm_rsc_op" #define PCMK__XE_MAINTENANCE "maintenance" #define PCMK__XE_META "meta" #define PCMK__XE_NACK "nack" #define PCMK__XE_NODE_STATE "node_state" #define PCMK__XE_OPTIONS "options" #define PCMK__XE_PARAM "param" #define PCMK__XE_PING "ping" #define PCMK__XE_PING_RESPONSE "ping_response" #define PCMK__XE_PSEUDO_EVENT "pseudo_event" #define PCMK__XE_RSC_OP "rsc_op" #define PCMK__XE_SHUTDOWN "shutdown" #define PCMK__XE_SPAN "span" #define PCMK__XE_TICKET_STATE "ticket_state" #define PCMK__XE_TRANSIENT_ATTRIBUTES "transient_attributes" #define PCMK__XE_TRANSITION_GRAPH "transition_graph" #define PCMK__XE_XPATH_QUERY "xpath-query" #define PCMK__XE_XPATH_QUERY_PATH "xpath-query-path" // @COMPAT Deprecated since 1.1.12 #define PCMK__XE_ACL_USER "acl_user" /* @COMPAT Deprecate somehow. It's undocumented and behaves the same as * PCMK__XE_CIB in places where it's recognized. */ #define PCMK__XE_ALL "all" // @COMPAT Deprecated since 2.1.7 #define PCMK__XE_DIFF_ADDED "diff-added" // @COMPAT Deprecated since 2.1.7 #define PCMK__XE_DIFF_REMOVED "diff-removed" // @COMPAT Deprecated since 1.0.8 (commit 4cb100f) #define PCMK__XE_LIFETIME "lifetime" /* @COMPAT Deprecated since 2.0.0; alias for with PCMK_META_PROMOTABLE * set to "true" */ #define PCMK__XE_PROMOTABLE_LEGACY "master" // @COMPAT Support for rkt is deprecated since 2.1.8 #define PCMK__XE_RKT "rkt" // @COMPAT Deprecated since 1.1.12 #define PCMK__XE_ROLE_REF "role_ref" /* * XML attribute names used only by internal code */ #define PCMK__XA_ATTR_CLEAR_INTERVAL "attr_clear_interval" #define PCMK__XA_ATTR_CLEAR_OPERATION "attr_clear_operation" #define PCMK__XA_ATTR_DAMPENING "attr_dampening" #define PCMK__XA_ATTR_HOST "attr_host" #define PCMK__XA_ATTR_HOST_ID "attr_host_id" #define PCMK__XA_ATTR_IS_PRIVATE "attr_is_private" #define PCMK__XA_ATTR_IS_REMOTE "attr_is_remote" #define PCMK__XA_ATTR_KEY "attr_key" #define PCMK__XA_ATTR_NAME "attr_name" #define PCMK__XA_ATTR_REGEX "attr_regex" #define PCMK__XA_ATTR_RESOURCE "attr_resource" #define PCMK__XA_ATTR_SECTION "attr_section" #define PCMK__XA_ATTR_SET "attr_set" #define PCMK__XA_ATTR_SET_TYPE "attr_set_type" #define PCMK__XA_ATTR_SYNC_POINT "attr_sync_point" #define PCMK__XA_ATTR_USER "attr_user" #define PCMK__XA_ATTR_VALUE "attr_value" #define PCMK__XA_ATTR_VERSION "attr_version" #define PCMK__XA_ATTR_WRITER "attr_writer" #define PCMK__XA_ATTRD_IS_FORCE_WRITE "attrd_is_force_write" #define PCMK__XA_CALL_ID "call-id" #define PCMK__XA_CLIENT_NAME "client_name" #define PCMK__XA_CLIENT_UUID "client_uuid" #define PCMK__XA_CONFIG_ERRORS "config-errors" #define PCMK__XA_CONFIG_WARNINGS "config-warnings" #define PCMK__XA_CONFIRM "confirm" #define PCMK__XA_CONNECTION_HOST "connection_host" #define PCMK__XA_CONTENT "content" #define PCMK__XA_CRMD_STATE "crmd_state" #define PCMK__XA_CRM_HOST_TO "crm_host_to" #define PCMK__XA_CRM_LIMIT_MAX "crm-limit-max" #define PCMK__XA_CRM_LIMIT_MODE "crm-limit-mode" #define PCMK__XA_CRM_SUBSYSTEM "crm_subsystem" #define PCMK__XA_CRM_SYS_FROM "crm_sys_from" #define PCMK__XA_CRM_SYS_TO "crm_sys_to" #define PCMK__XA_CRM_TASK "crm_task" #define PCMK__XA_CRM_TGRAPH_IN "crm-tgraph-in" #define PCMK__XA_CRM_USER "crm_user" #define PCMK__XA_DC_LEAVING "dc-leaving" #define PCMK__XA_DIGEST "digest" #define PCMK__XA_ELECTION_AGE_SEC "election-age-sec" #define PCMK__XA_ELECTION_AGE_NANO_SEC "election-age-nano-sec" #define PCMK__XA_ELECTION_ID "election-id" #define PCMK__XA_ELECTION_OWNER "election-owner" #define PCMK__XA_GRANTED "granted" #define PCMK__XA_GRAPH_ERRORS "graph-errors" #define PCMK__XA_GRAPH_WARNINGS "graph-warnings" #define PCMK__XA_HIDDEN "hidden" #define PCMK__XA_HTTP_EQUIV "http-equiv" #define PCMK__XA_IN_CCM "in_ccm" #define PCMK__XA_JOIN "join" #define PCMK__XA_JOIN_ID "join_id" #define PCMK__XA_LINE "line" #define PCMK__XA_LONG_ID "long-id" #define PCMK__XA_MAJOR_VERSION "major_version" #define PCMK__XA_MINOR_VERSION "minor_version" #define PCMK__XA_MODE "mode" #define PCMK__XA_MOON "moon" #define PCMK__XA_NAMESPACE "namespace" #define PCMK__XA_NODE_FENCED "node_fenced" #define PCMK__XA_NODE_IN_MAINTENANCE "node_in_maintenance" #define PCMK__XA_NODE_START_STATE "node_start_state" #define PCMK__XA_NODE_STATE "node_state" #define PCMK__XA_OP_DIGEST "op-digest" #define PCMK__XA_OP_FORCE_RESTART "op-force-restart" #define PCMK__XA_OP_RESTART_DIGEST "op-restart-digest" #define PCMK__XA_OP_SECURE_DIGEST "op-secure-digest" #define PCMK__XA_OP_SECURE_PARAMS "op-secure-params" #define PCMK__XA_OP_STATUS "op-status" #define PCMK__XA_OPERATION_KEY "operation_key" #define PCMK__XA_PACEMAKERD_STATE "pacemakerd_state" #define PCMK__XA_PASSWORD "password" #define PCMK__XA_PRIORITY "priority" #define PCMK__XA_RC_CODE "rc-code" #define PCMK__XA_REAP "reap" /* Actions to be executed on Pacemaker Remote nodes are routed through the * controller on the cluster node hosting the remote connection. That cluster * node is considered the router node for the action. */ #define PCMK__XA_ROUTER_NODE "router_node" #define PCMK__XA_RSC_ID "rsc-id" #define PCMK__XA_RSC_PROVIDES "rsc_provides" #define PCMK__XA_SCHEMA "schema" #define PCMK__XA_SCHEMAS "schemas" #define PCMK__XA_SRC "src" #define PCMK__XA_ST_ACTION_DISALLOWED "st_action_disallowed" #define PCMK__XA_ST_ACTION_TIMEOUT "st_action_timeout" #define PCMK__XA_ST_AVAILABLE_DEVICES "st-available-devices" #define PCMK__XA_ST_CALLID "st_callid" #define PCMK__XA_ST_CALLDATA "st_calldata" #define PCMK__XA_ST_CALLOPT "st_callopt" #define PCMK__XA_ST_CLIENTID "st_clientid" #define PCMK__XA_ST_CLIENTNAME "st_clientname" +#define PCMK__XA_ST_CLIENTNODE "st_clientnode" #define PCMK__XA_ST_DELAY "st_delay" #define PCMK__XA_ST_DELAY_BASE "st_delay_base" #define PCMK__XA_ST_DELAY_MAX "st_delay_max" #define PCMK__XA_ST_MONITOR_VERIFIED "st_monitor_verified" #define PCMK__XA_ST_OP "st_op" #define PCMK__XA_ST_OUTPUT "st_output" #define PCMK__XA_ST_RC "st_rc" #define PCMK__XA_ST_REMOTE_OP "st_remote_op" #define PCMK__XA_ST_REMOTE_OP_RELAY "st_remote_op_relay" #define PCMK__XA_ST_REQUIRED "st_required" #define PCMK__XA_ST_TARGET "st_target" #define PCMK__XA_ST_TIMEOUT "st_timeout" #define PCMK__XA_ST_TOLERANCE "st_tolerance" #define PCMK__XA_SUBT "subt" // subtype #define PCMK__XA_T "t" // type #define PCMK__XA_TRANSITION_KEY "transition-key" #define PCMK__XA_TRANSITION_MAGIC "transition-magic" #define PCMK__XA_UPTIME "uptime" // @COMPAT Used only with v1 patchsets #define PCMK__XA_CRM_DIFF_MARKER "__crm_diff_marker__" // @COMPAT Deprecated since 2.1.5 #define PCMK__XA_FIRST_INSTANCE "first-instance" // @COMPAT Deprecated since 2.1.7 #define PCMK__XA_ORDERING "ordering" // @COMPAT Deprecated alias for PCMK_XA_PROMOTED_MAX since 2.0.0 #define PCMK__XA_PROMOTED_MAX_LEGACY "masters" // @COMPAT Deprecated alias for PCMK_XA_PROMOTED_ONLY since 2.0.0 #define PCMK__XA_PROMOTED_ONLY_LEGACY "master_only" // @COMPAT Deprecated since 1.1.12 #define PCMK__XA_REF "ref" // @COMPAT Deprecated since 2.1.6 #define PCMK__XA_REPLACE "replace" // @COMPAT Deprecated alias for \c PCMK_XA_AUTOMATIC since 1.1.14 #define PCMK__XA_REQUIRED "required" // @COMPAT Deprecated since 2.1.5 #define PCMK__XA_RSC_INSTANCE "rsc-instance" // @COMPAT Deprecated since 2.1.5 #define PCMK__XA_THEN_INSTANCE "then-instance" // @COMPAT Deprecated since 2.1.5 #define PCMK__XA_WITH_RSC_INSTANCE "with-rsc-instance" #ifdef __cplusplus } #endif #endif // PCMK__CRM_COMMON_XML_NAMES_INTERNAL__H diff --git a/include/crm/fencing/internal.h b/include/crm/fencing/internal.h index 6d9e8dfb2e..1470462941 100644 --- a/include/crm/fencing/internal.h +++ b/include/crm/fencing/internal.h @@ -1,191 +1,190 @@ /* * Copyright 2011-2024 the Pacemaker project contributors * * The version control history for this file may have further details. * * This source code is licensed under the GNU Lesser General Public License * version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY. */ #ifndef STONITH_NG_INTERNAL__H # define STONITH_NG_INTERNAL__H # include # include # include # include # include enum st_device_flags { st_device_supports_none = (0 << 0), st_device_supports_list = (1 << 0), st_device_supports_status = (1 << 1), st_device_supports_reboot = (1 << 2), st_device_supports_parameter_plug = (1 << 3), st_device_supports_parameter_port = (1 << 4), st_device_supports_on = (1 << 5), }; #define stonith__set_device_flags(device_flags, device_id, flags_to_set) do { \ device_flags = pcmk__set_flags_as(__func__, __LINE__, LOG_TRACE, \ "Fence device", device_id, \ (device_flags), (flags_to_set), \ #flags_to_set); \ } while (0) #define stonith__set_call_options(st_call_opts, call_for, flags_to_set) do { \ st_call_opts = pcmk__set_flags_as(__func__, __LINE__, LOG_TRACE, \ "Fencer call", (call_for), \ (st_call_opts), (flags_to_set), \ #flags_to_set); \ } while (0) #define stonith__clear_call_options(st_call_opts, call_for, flags_to_clear) do { \ st_call_opts = pcmk__clear_flags_as(__func__, __LINE__, LOG_TRACE, \ "Fencer call", (call_for), \ (st_call_opts), (flags_to_clear), \ #flags_to_clear); \ } while (0) struct stonith_action_s; typedef struct stonith_action_s stonith_action_t; stonith_action_t *stonith__action_create(const char *agent, const char *action_name, const char *target, uint32_t target_nodeid, int timeout_sec, GHashTable *device_args, GHashTable *port_map, const char *host_arg); void stonith__destroy_action(stonith_action_t *action); pcmk__action_result_t *stonith__action_result(stonith_action_t *action); int stonith__result2rc(const pcmk__action_result_t *result); void stonith__xe_set_result(xmlNode *xml, const pcmk__action_result_t *result); void stonith__xe_get_result(const xmlNode *xml, pcmk__action_result_t *result); xmlNode *stonith__find_xe_with_result(xmlNode *xml); int stonith__execute_async(stonith_action_t *action, void *userdata, void (*done) (int pid, const pcmk__action_result_t *result, void *user_data), void (*fork_cb) (int pid, void *user_data)); int stonith__metadata_async(const char *agent, int timeout_sec, void (*callback)(int pid, const pcmk__action_result_t *result, void *user_data), void *user_data); xmlNode *create_level_registration_xml(const char *node, const char *pattern, const char *attr, const char *value, int level, const stonith_key_value_t *device_list); xmlNode *create_device_registration_xml(const char *id, enum stonith_namespace namespace, const char *agent, const stonith_key_value_t *params, const char *rsc_provides); void stonith__register_messages(pcmk__output_t *out); GList *stonith__parse_targets(const char *hosts); const char *stonith__later_succeeded(const stonith_history_t *event, const stonith_history_t *top_history); stonith_history_t *stonith__sort_history(stonith_history_t *history); void stonith__device_parameter_flags(uint32_t *device_flags, const char *device_name, xmlNode *metadata); # define ST_LEVEL_MAX 10 -# define F_STONITH_CLIENTNODE "st_clientnode" # define F_STONITH_NOTIFY_ACTIVATE "st_notify_activate" # define F_STONITH_NOTIFY_DEACTIVATE "st_notify_deactivate" # define F_STONITH_DELEGATE "st_delegate" # define F_STONITH_DEVICE_SUPPORT_FLAGS "st_device_support_flags" /*! The node initiating the stonith operation. If an operation * is relayed, this is the last node the operation lands on. When * in standalone mode, origin is the client's id that originated the * operation. */ # define F_STONITH_ORIGIN "st_origin" # define F_STONITH_HISTORY_LIST "st_history" # define F_STONITH_DATE "st_date" # define F_STONITH_DATE_NSEC "st_date_nsec" # define F_STONITH_STATE "st_state" # define F_STONITH_ACTIVE "st_active" # define F_STONITH_DIFFERENTIAL "st_differential" # define F_STONITH_DEVICE "st_device_id" # define F_STONITH_ACTION "st_device_action" # define F_STONITH_MERGED "st_op_merged" # define T_STONITH_NG "stonith-ng" # define T_STONITH_REPLY "st-reply" /*! For async operations, an event from the server containing * the total amount of time the server is allowing for the operation * to take place is returned to the client. */ # define T_STONITH_TIMEOUT_VALUE "st-async-timeout-value" # define T_STONITH_NOTIFY "st_notify" # define STONITH_ATTR_ACTION_OP "action" # define STONITH_OP_EXEC "st_execute" # define STONITH_OP_TIMEOUT_UPDATE "st_timeout_update" # define STONITH_OP_QUERY "st_query" # define STONITH_OP_FENCE "st_fence" # define STONITH_OP_RELAY "st_relay" # define STONITH_OP_DEVICE_ADD "st_device_register" # define STONITH_OP_DEVICE_DEL "st_device_remove" # define STONITH_OP_FENCE_HISTORY "st_fence_history" # define STONITH_OP_LEVEL_ADD "st_level_add" # define STONITH_OP_LEVEL_DEL "st_level_remove" # define STONITH_WATCHDOG_AGENT "fence_watchdog" /* Don't change 2 below as it would break rolling upgrade */ # define STONITH_WATCHDOG_AGENT_INTERNAL "#watchdog" # define STONITH_WATCHDOG_ID "watchdog" stonith_history_t *stonith__first_matching_event(stonith_history_t *history, bool (*matching_fn)(stonith_history_t *, void *), void *user_data); bool stonith__event_state_pending(stonith_history_t *history, void *user_data); bool stonith__event_state_eq(stonith_history_t *history, void *user_data); bool stonith__event_state_neq(stonith_history_t *history, void *user_data); int stonith__legacy2status(int rc); int stonith__exit_status(const stonith_callback_data_t *data); int stonith__execution_status(const stonith_callback_data_t *data); const char *stonith__exit_reason(const stonith_callback_data_t *data); int stonith__event_exit_status(const stonith_event_t *event); int stonith__event_execution_status(const stonith_event_t *event); const char *stonith__event_exit_reason(const stonith_event_t *event); char *stonith__event_description(const stonith_event_t *event); gchar *stonith__history_description(const stonith_history_t *event, bool full_history, const char *later_succeeded, uint32_t show_opts); /*! * \internal * \brief Is a fencing operation in pending state? * * \param[in] state State as enum op_state value * * \return A boolean */ static inline bool stonith__op_state_pending(enum op_state state) { return state != st_failed && state != st_done; } gboolean stonith__watchdog_fencing_enabled_for_node(const char *node); gboolean stonith__watchdog_fencing_enabled_for_node_api(stonith_t *st, const char *node); #endif