diff --git a/daemons/controld/controld_messages.c b/daemons/controld/controld_messages.c index c8f6c4a1b2..676a94fa62 100644 --- a/daemons/controld/controld_messages.c +++ b/daemons/controld/controld_messages.c @@ -1,1337 +1,1337 @@ /* * 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 General Public License version 2 * or later (GPLv2+) WITHOUT ANY WARRANTY. */ #include #include #include #include #include #include #include #include #include #include #include static enum crmd_fsa_input handle_message(xmlNode *msg, enum crmd_fsa_cause cause); static void handle_response(xmlNode *stored_msg); static enum crmd_fsa_input handle_request(xmlNode *stored_msg, enum crmd_fsa_cause cause); static enum crmd_fsa_input handle_shutdown_request(xmlNode *stored_msg); static void send_msg_via_ipc(xmlNode * msg, const char *sys); /* debug only, can wrap all it likes */ static int last_data_id = 0; void register_fsa_error_adv(enum crmd_fsa_cause cause, enum crmd_fsa_input input, fsa_data_t * cur_data, void *new_data, const char *raised_from) { /* save the current actions if any */ if (controld_globals.fsa_actions != A_NOTHING) { register_fsa_input_adv(cur_data ? cur_data->fsa_cause : C_FSA_INTERNAL, I_NULL, cur_data ? cur_data->data : NULL, controld_globals.fsa_actions, TRUE, __func__); } /* reset the action list */ crm_info("Resetting the current action list"); fsa_dump_actions(controld_globals.fsa_actions, "Drop"); controld_globals.fsa_actions = A_NOTHING; /* register the error */ register_fsa_input_adv(cause, input, new_data, A_NOTHING, TRUE, raised_from); } void register_fsa_input_adv(enum crmd_fsa_cause cause, enum crmd_fsa_input input, void *data, uint64_t with_actions, gboolean prepend, const char *raised_from) { unsigned old_len = g_list_length(controld_globals.fsa_message_queue); fsa_data_t *fsa_data = NULL; if (raised_from == NULL) { raised_from = ""; } if (input == I_NULL && with_actions == A_NOTHING /* && data == NULL */ ) { /* no point doing anything */ crm_err("Cannot add entry to queue: no input and no action"); return; } if (input == I_WAIT_FOR_EVENT) { controld_set_global_flags(controld_fsa_is_stalled); crm_debug("Stalling the FSA pending further input: source=%s cause=%s data=%p queue=%d", raised_from, fsa_cause2string(cause), data, old_len); if (old_len > 0) { fsa_dump_queue(LOG_TRACE); prepend = FALSE; } if (data == NULL) { controld_set_fsa_action_flags(with_actions); fsa_dump_actions(with_actions, "Restored"); return; } /* Store everything in the new event and reset * controld_globals.fsa_actions */ with_actions |= controld_globals.fsa_actions; controld_globals.fsa_actions = A_NOTHING; } last_data_id++; crm_trace("%s %s FSA input %d (%s) due to %s, %s data", raised_from, (prepend? "prepended" : "appended"), last_data_id, fsa_input2string(input), fsa_cause2string(cause), (data? "with" : "without")); fsa_data = calloc(1, sizeof(fsa_data_t)); fsa_data->id = last_data_id; fsa_data->fsa_input = input; fsa_data->fsa_cause = cause; fsa_data->origin = raised_from; fsa_data->data = NULL; fsa_data->data_type = fsa_dt_none; fsa_data->actions = with_actions; if (with_actions != A_NOTHING) { crm_trace("Adding actions %.16llx to input", (unsigned long long) with_actions); } if (data != NULL) { switch (cause) { case C_FSA_INTERNAL: case C_CRMD_STATUS_CALLBACK: case C_IPC_MESSAGE: case C_HA_MESSAGE: CRM_CHECK(((ha_msg_input_t *) data)->msg != NULL, crm_err("Bogus data from %s", raised_from)); crm_trace("Copying %s data from %s as cluster message data", fsa_cause2string(cause), raised_from); fsa_data->data = copy_ha_msg_input(data); fsa_data->data_type = fsa_dt_ha_msg; break; case C_LRM_OP_CALLBACK: crm_trace("Copying %s data from %s as lrmd_event_data_t", fsa_cause2string(cause), raised_from); fsa_data->data = lrmd_copy_event((lrmd_event_data_t *) data); fsa_data->data_type = fsa_dt_lrm; break; case C_TIMER_POPPED: case C_SHUTDOWN: case C_UNKNOWN: case C_STARTUP: crm_crit("Copying %s data (from %s) is not yet implemented", fsa_cause2string(cause), raised_from); crmd_exit(CRM_EX_SOFTWARE); break; } } /* make sure to free it properly later */ if (prepend) { controld_globals.fsa_message_queue = g_list_prepend(controld_globals.fsa_message_queue, fsa_data); } else { controld_globals.fsa_message_queue = g_list_append(controld_globals.fsa_message_queue, fsa_data); } crm_trace("FSA message queue length is %d", g_list_length(controld_globals.fsa_message_queue)); /* fsa_dump_queue(LOG_TRACE); */ if (old_len == g_list_length(controld_globals.fsa_message_queue)) { crm_err("Couldn't add message to the queue"); } if (input != I_WAIT_FOR_EVENT) { controld_trigger_fsa(); } } void fsa_dump_queue(int log_level) { int offset = 0; for (GList *iter = controld_globals.fsa_message_queue; iter != NULL; iter = iter->next) { fsa_data_t *data = (fsa_data_t *) iter->data; do_crm_log_unlikely(log_level, "queue[%d.%d]: input %s raised by %s(%p.%d)\t(cause=%s)", offset++, data->id, fsa_input2string(data->fsa_input), data->origin, data->data, data->data_type, fsa_cause2string(data->fsa_cause)); } } ha_msg_input_t * copy_ha_msg_input(ha_msg_input_t * orig) { ha_msg_input_t *copy = calloc(1, sizeof(ha_msg_input_t)); CRM_ASSERT(copy != NULL); copy->msg = (orig && orig->msg)? copy_xml(orig->msg) : NULL; copy->xml = get_message_xml(copy->msg, PCMK__XE_CRM_XML); return copy; } void delete_fsa_input(fsa_data_t * fsa_data) { lrmd_event_data_t *op = NULL; xmlNode *foo = NULL; if (fsa_data == NULL) { return; } crm_trace("About to free %s data", fsa_cause2string(fsa_data->fsa_cause)); if (fsa_data->data != NULL) { switch (fsa_data->data_type) { case fsa_dt_ha_msg: delete_ha_msg_input(fsa_data->data); break; case fsa_dt_xml: foo = fsa_data->data; free_xml(foo); break; case fsa_dt_lrm: op = (lrmd_event_data_t *) fsa_data->data; lrmd_free_event(op); break; case fsa_dt_none: if (fsa_data->data != NULL) { crm_err("Don't know how to free %s data from %s", fsa_cause2string(fsa_data->fsa_cause), fsa_data->origin); crmd_exit(CRM_EX_SOFTWARE); } break; } crm_trace("%s data freed", fsa_cause2string(fsa_data->fsa_cause)); } free(fsa_data); } /* returns the next message */ fsa_data_t * get_message(void) { fsa_data_t *message = (fsa_data_t *) controld_globals.fsa_message_queue->data; controld_globals.fsa_message_queue = g_list_remove(controld_globals.fsa_message_queue, message); crm_trace("Processing input %d", message->id); return message; } void * fsa_typed_data_adv(fsa_data_t * fsa_data, enum fsa_data_type a_type, const char *caller) { void *ret_val = NULL; if (fsa_data == NULL) { crm_err("%s: No FSA data available", caller); } else if (fsa_data->data == NULL) { crm_err("%s: No message data available. Origin: %s", caller, fsa_data->origin); } else if (fsa_data->data_type != a_type) { crm_crit("%s: Message data was the wrong type! %d vs. requested=%d. Origin: %s", caller, fsa_data->data_type, a_type, fsa_data->origin); CRM_ASSERT(fsa_data->data_type == a_type); } else { ret_val = fsa_data->data; } return ret_val; } /* A_MSG_ROUTE */ void do_msg_route(long long action, enum crmd_fsa_cause cause, enum crmd_fsa_state cur_state, enum crmd_fsa_input current_input, fsa_data_t * msg_data) { ha_msg_input_t *input = fsa_typed_data(fsa_dt_ha_msg); route_message(msg_data->fsa_cause, input->msg); } void route_message(enum crmd_fsa_cause cause, xmlNode * input) { ha_msg_input_t fsa_input; enum crmd_fsa_input result = I_NULL; fsa_input.msg = input; CRM_CHECK(cause == C_IPC_MESSAGE || cause == C_HA_MESSAGE, return); /* try passing the buck first */ if (relay_message(input, cause == C_IPC_MESSAGE)) { return; } /* handle locally */ result = handle_message(input, cause); /* done or process later? */ switch (result) { case I_NULL: case I_CIB_OP: case I_ROUTER: case I_NODE_JOIN: case I_JOIN_REQUEST: case I_JOIN_RESULT: break; default: /* Defering local processing of message */ register_fsa_input_later(cause, result, &fsa_input); return; } if (result != I_NULL) { /* add to the front of the queue */ register_fsa_input(cause, result, &fsa_input); } } gboolean relay_message(xmlNode * msg, gboolean originated_locally) { enum crm_ais_msg_types dest = crm_msg_ais; bool is_for_dc = false; bool is_for_dcib = false; bool is_for_te = false; bool is_for_crm = false; bool is_for_cib = false; bool is_local = false; bool broadcast = false; const char *host_to = NULL; const char *sys_to = NULL; const char *sys_from = NULL; const char *type = NULL; const char *task = NULL; const char *ref = NULL; crm_node_t *node_to = NULL; CRM_CHECK(msg != NULL, return TRUE); host_to = crm_element_value(msg, PCMK__XA_CRM_HOST_TO); sys_to = crm_element_value(msg, PCMK__XA_CRM_SYS_TO); sys_from = crm_element_value(msg, PCMK__XA_CRM_SYS_FROM); type = crm_element_value(msg, PCMK__XA_T); task = crm_element_value(msg, PCMK__XA_CRM_TASK); ref = crm_element_value(msg, PCMK_XA_REFERENCE); broadcast = pcmk__str_empty(host_to); if (ref == NULL) { ref = "without reference ID"; } if (pcmk__str_eq(task, CRM_OP_HELLO, pcmk__str_casei)) { crm_trace("Received hello %s from %s (no processing needed)", ref, pcmk__s(sys_from, "unidentified source")); crm_log_xml_trace(msg, "hello"); return TRUE; } // Require message type (set by create_request()) if (!pcmk__str_eq(type, PCMK__VALUE_CRMD, pcmk__str_none)) { crm_warn("Ignoring invalid message %s with type '%s' " "(not '" PCMK__VALUE_CRMD "')", ref, pcmk__s(type, "")); crm_log_xml_trace(msg, "ignored"); return TRUE; } // Require a destination subsystem (also set by create_request()) if (sys_to == NULL) { crm_warn("Ignoring invalid message %s with no " PCMK__XA_CRM_SYS_TO, ref); crm_log_xml_trace(msg, "ignored"); return TRUE; } // Get the message type appropriate to the destination subsystem if (is_corosync_cluster()) { dest = text2msg_type(sys_to); if ((dest < crm_msg_ais) || (dest > crm_msg_stonith_ng)) { /* Unrecognized value, use a sane default * * @TODO Maybe we should bail instead */ dest = crm_msg_crmd; } } is_for_dc = (strcasecmp(CRM_SYSTEM_DC, sys_to) == 0); is_for_dcib = (strcasecmp(CRM_SYSTEM_DCIB, sys_to) == 0); is_for_te = (strcasecmp(CRM_SYSTEM_TENGINE, sys_to) == 0); is_for_cib = (strcasecmp(CRM_SYSTEM_CIB, sys_to) == 0); is_for_crm = (strcasecmp(CRM_SYSTEM_CRMD, sys_to) == 0); // Check whether message should be processed locally is_local = false; if (broadcast) { if (is_for_dc || is_for_te) { is_local = false; } else if (is_for_crm) { if (pcmk__strcase_any_of(task, CRM_OP_NODE_INFO, PCMK__CONTROLD_CMD_NODES, NULL)) { /* Node info requests do not specify a host, which is normally * treated as "all hosts", because the whole point is that the * client may not know the local node name. Always handle these * requests locally. */ is_local = true; } else { is_local = !originated_locally; } } else { is_local = true; } } else if (pcmk__str_eq(controld_globals.our_nodename, host_to, pcmk__str_casei)) { is_local = true; } else if (is_for_crm && pcmk__str_eq(task, CRM_OP_LRM_DELETE, pcmk__str_casei)) { xmlNode *msg_data = get_message_xml(msg, PCMK__XE_CRM_XML); const char *mode = crm_element_value(msg_data, PCMK__XA_MODE); if (pcmk__str_eq(mode, PCMK__VALUE_CIB, pcmk__str_none)) { // Local delete of an offline node's resource history is_local = true; } } // Check whether message should be relayed if (is_for_dc || is_for_dcib || is_for_te) { if (AM_I_DC) { if (is_for_te) { crm_trace("Route message %s locally as transition request", ref); crm_log_xml_trace(msg, sys_to); send_msg_via_ipc(msg, sys_to); return TRUE; // No further processing of message is needed } crm_trace("Route message %s locally as DC request", ref); return FALSE; // More to be done by caller } if (originated_locally && !pcmk__strcase_any_of(sys_from, CRM_SYSTEM_PENGINE, CRM_SYSTEM_TENGINE, NULL)) { crm_trace("Relay message %s to DC (via %s)", ref, pcmk__s(host_to, "broadcast")); crm_log_xml_trace(msg, "relayed"); if (!broadcast) { node_to = pcmk__get_node(0, host_to, NULL, pcmk__node_search_cluster); } send_cluster_message(node_to, dest, msg, TRUE); return TRUE; } /* Transition engine and scheduler messages are sent only to the DC on * the same node. If we are no longer the DC, discard this message. */ crm_trace("Ignoring message %s because we are no longer DC", ref); crm_log_xml_trace(msg, "ignored"); return TRUE; // No further processing of message is needed } if (is_local) { if (is_for_crm || is_for_cib) { crm_trace("Route message %s locally as controller request", ref); return FALSE; // More to be done by caller } crm_trace("Relay message %s locally to %s", ref, sys_to); crm_log_xml_trace(msg, "IPC-relay"); send_msg_via_ipc(msg, sys_to); return TRUE; } if (!broadcast) { node_to = pcmk__search_node_caches(0, host_to, pcmk__node_search_cluster); if (node_to == NULL) { crm_warn("Ignoring message %s because node %s is unknown", ref, host_to); crm_log_xml_trace(msg, "ignored"); return TRUE; } } crm_trace("Relay message %s to %s", ref, pcmk__s(host_to, "all peers")); crm_log_xml_trace(msg, "relayed"); send_cluster_message(node_to, dest, msg, TRUE); return TRUE; } // Return true if field contains a positive integer static bool authorize_version(xmlNode *message_data, const char *field, const char *client_name, const char *ref, const char *uuid) { const char *version = crm_element_value(message_data, field); long long version_num; if ((pcmk__scan_ll(version, &version_num, -1LL) != pcmk_rc_ok) || (version_num < 0LL)) { crm_warn("Rejected IPC hello from %s: '%s' is not a valid protocol %s " CRM_XS " ref=%s uuid=%s", client_name, ((version == NULL)? "" : version), field, (ref? ref : "none"), uuid); return false; } return true; } /*! * \internal * \brief Check whether a client IPC message is acceptable * * If a given client IPC message is a hello, "authorize" it by ensuring it has * valid information such as a protocol version, and return false indicating * that nothing further needs to be done with the message. If the message is not * a hello, just return true to indicate it needs further processing. * * \param[in] client_msg XML of IPC message * \param[in,out] curr_client If IPC is not proxied, client that sent message * \param[in] proxy_session If IPC is proxied, the session ID * * \return true if message needs further processing, false if it doesn't */ bool controld_authorize_ipc_message(const xmlNode *client_msg, pcmk__client_t *curr_client, const char *proxy_session) { xmlNode *message_data = NULL; const char *client_name = NULL; const char *op = crm_element_value(client_msg, PCMK__XA_CRM_TASK); const char *ref = crm_element_value(client_msg, PCMK_XA_REFERENCE); const char *uuid = (curr_client? curr_client->id : proxy_session); if (uuid == NULL) { crm_warn("IPC message from client rejected: No client identifier " CRM_XS " ref=%s", (ref? ref : "none")); goto rejected; } if (!pcmk__str_eq(CRM_OP_HELLO, op, pcmk__str_casei)) { // Only hello messages need to be authorized return true; } message_data = get_message_xml(client_msg, PCMK__XE_CRM_XML); - client_name = crm_element_value(message_data, "client_name"); + client_name = crm_element_value(message_data, PCMK__XA_CLIENT_NAME); if (pcmk__str_empty(client_name)) { crm_warn("IPC hello from client rejected: No client name", CRM_XS " ref=%s uuid=%s", (ref? ref : "none"), uuid); goto rejected; } - if (!authorize_version(message_data, "major_version", client_name, ref, - uuid)) { + if (!authorize_version(message_data, PCMK__XA_MAJOR_VERSION, client_name, + ref, uuid)) { goto rejected; } - if (!authorize_version(message_data, "minor_version", client_name, ref, - uuid)) { + if (!authorize_version(message_data, PCMK__XA_MINOR_VERSION, client_name, + ref, uuid)) { goto rejected; } crm_trace("Validated IPC hello from client %s", client_name); crm_log_xml_trace(client_msg, "hello"); if (curr_client) { curr_client->userdata = strdup(client_name); } controld_trigger_fsa(); return false; rejected: crm_log_xml_trace(client_msg, "rejected"); if (curr_client) { qb_ipcs_disconnect(curr_client->ipcs); } return false; } static enum crmd_fsa_input handle_message(xmlNode *msg, enum crmd_fsa_cause cause) { const char *type = NULL; CRM_CHECK(msg != NULL, return I_NULL); type = crm_element_value(msg, PCMK__XA_SUBT); if (pcmk__str_eq(type, PCMK__VALUE_REQUEST, pcmk__str_none)) { return handle_request(msg, cause); } if (pcmk__str_eq(type, PCMK__VALUE_RESPONSE, pcmk__str_none)) { handle_response(msg); return I_NULL; } crm_warn("Ignoring message with unknown " PCMK__XA_SUBT" '%s'", pcmk__s(type, "")); crm_log_xml_trace(msg, "bad"); return I_NULL; } static enum crmd_fsa_input handle_failcount_op(xmlNode * stored_msg) { const char *rsc = NULL; const char *uname = NULL; const char *op = NULL; char *interval_spec = NULL; guint interval_ms = 0; gboolean is_remote_node = FALSE; xmlNode *xml_op = get_message_xml(stored_msg, PCMK__XE_CRM_XML); if (xml_op) { xmlNode *xml_rsc = first_named_child(xml_op, PCMK_XE_PRIMITIVE); xmlNode *xml_attrs = first_named_child(xml_op, PCMK__XE_ATTRIBUTES); if (xml_rsc) { rsc = ID(xml_rsc); } if (xml_attrs) { op = crm_element_value(xml_attrs, CRM_META "_" PCMK__META_CLEAR_FAILURE_OP); crm_element_value_ms(xml_attrs, CRM_META "_" PCMK__META_CLEAR_FAILURE_INTERVAL, &interval_ms); } } uname = crm_element_value(xml_op, PCMK__META_ON_NODE); if ((rsc == NULL) || (uname == NULL)) { crm_log_xml_warn(stored_msg, "invalid failcount op"); return I_NULL; } if (crm_element_value(xml_op, PCMK__XA_ROUTER_NODE)) { is_remote_node = TRUE; } crm_debug("Clearing failures for %s-interval %s on %s " "from attribute manager, CIB, and executor state", pcmk__readable_interval(interval_ms), rsc, uname); if (interval_ms) { interval_spec = crm_strdup_printf("%ums", interval_ms); } update_attrd_clear_failures(uname, rsc, op, interval_spec, is_remote_node); free(interval_spec); controld_cib_delete_last_failure(rsc, uname, op, interval_ms); lrm_clear_last_failure(rsc, uname, op, interval_ms); return I_NULL; } static enum crmd_fsa_input handle_lrm_delete(xmlNode *stored_msg) { const char *mode = NULL; xmlNode *msg_data = get_message_xml(stored_msg, PCMK__XE_CRM_XML); CRM_CHECK(msg_data != NULL, return I_NULL); /* CRM_OP_LRM_DELETE has two distinct modes. The default behavior is to * relay the operation to the affected node, which will unregister the * resource from the local executor, clear the resource's history from the * CIB, and do some bookkeeping in the controller. * * However, if the affected node is offline, the client will specify * mode=PCMK__VALUE_CIB which means the controller receiving the operation * should clear the resource's history from the CIB and nothing else. This * is used to clear shutdown locks. */ mode = crm_element_value(msg_data, PCMK__XA_MODE); if (!pcmk__str_eq(mode, PCMK__VALUE_CIB, pcmk__str_none)) { // Relay to affected node crm_xml_add(stored_msg, PCMK__XA_CRM_SYS_TO, CRM_SYSTEM_LRMD); return I_ROUTER; } else { // Delete CIB history locally (compare with do_lrm_delete()) const char *from_sys = NULL; const char *user_name = NULL; const char *rsc_id = NULL; const char *node = NULL; xmlNode *rsc_xml = NULL; int rc = pcmk_rc_ok; rsc_xml = first_named_child(msg_data, PCMK_XE_PRIMITIVE); CRM_CHECK(rsc_xml != NULL, return I_NULL); rsc_id = ID(rsc_xml); from_sys = crm_element_value(stored_msg, PCMK__XA_CRM_SYS_FROM); node = crm_element_value(msg_data, PCMK__META_ON_NODE); user_name = pcmk__update_acl_user(stored_msg, PCMK__XA_CRM_USER, NULL); crm_debug("Handling " CRM_OP_LRM_DELETE " for %s on %s locally%s%s " "(clearing CIB resource history only)", rsc_id, node, (user_name? " for user " : ""), (user_name? user_name : "")); rc = controld_delete_resource_history(rsc_id, node, user_name, cib_dryrun|cib_sync_call); if (rc == pcmk_rc_ok) { rc = controld_delete_resource_history(rsc_id, node, user_name, crmd_cib_smart_opt()); } /* Notify client. Also notify tengine if mode=PCMK__VALUE_CIB and * op=CRM_OP_LRM_DELETE. */ if (from_sys) { lrmd_event_data_t *op = NULL; const char *from_host = crm_element_value(stored_msg, PCMK__XA_SRC); const char *transition; if (strcmp(from_sys, CRM_SYSTEM_TENGINE)) { transition = crm_element_value(msg_data, PCMK__XA_TRANSITION_KEY); } else { transition = crm_element_value(stored_msg, PCMK__XA_TRANSITION_KEY); } crm_info("Notifying %s on %s that %s was%s deleted", from_sys, (from_host? from_host : "local node"), rsc_id, ((rc == pcmk_rc_ok)? "" : " not")); op = lrmd_new_event(rsc_id, PCMK_ACTION_DELETE, 0); op->type = lrmd_event_exec_complete; op->user_data = strdup(transition? transition : FAKE_TE_ID); op->params = pcmk__strkey_table(free, free); g_hash_table_insert(op->params, strdup(PCMK_XA_CRM_FEATURE_SET), strdup(CRM_FEATURE_SET)); controld_rc2event(op, rc); controld_ack_event_directly(from_host, from_sys, NULL, op, rsc_id); lrmd_free_event(op); controld_trigger_delete_refresh(from_sys, rsc_id); } return I_NULL; } } /*! * \brief Handle a CRM_OP_REMOTE_STATE message by updating remote peer cache * * \param[in] msg Message XML * * \return Next FSA input */ static enum crmd_fsa_input handle_remote_state(const xmlNode *msg) { const char *conn_host = NULL; const char *remote_uname = ID(msg); crm_node_t *remote_peer; bool remote_is_up = false; int rc = pcmk_rc_ok; rc = pcmk__xe_get_bool_attr(msg, PCMK__XA_IN_CCM, &remote_is_up); CRM_CHECK(remote_uname && rc == pcmk_rc_ok, return I_NULL); remote_peer = crm_remote_peer_get(remote_uname); CRM_CHECK(remote_peer, return I_NULL); pcmk__update_peer_state(__func__, remote_peer, remote_is_up ? CRM_NODE_MEMBER : CRM_NODE_LOST, 0); conn_host = crm_element_value(msg, PCMK__XA_CONN_HOST); if (conn_host) { pcmk__str_update(&remote_peer->conn_host, conn_host); } else if (remote_peer->conn_host) { free(remote_peer->conn_host); remote_peer->conn_host = NULL; } return I_NULL; } /*! * \brief Handle a CRM_OP_PING message * * \param[in] msg Message XML * * \return Next FSA input */ static enum crmd_fsa_input handle_ping(const xmlNode *msg) { const char *value = NULL; xmlNode *ping = NULL; xmlNode *reply = NULL; // Build reply ping = create_xml_node(NULL, PCMK__XE_PING_RESPONSE); value = crm_element_value(msg, PCMK__XA_CRM_SYS_TO); crm_xml_add(ping, PCMK__XA_CRM_SUBSYSTEM, value); // Add controller state value = fsa_state2string(controld_globals.fsa_state); crm_xml_add(ping, PCMK__XA_CRMD_STATE, value); crm_notice("Current ping state: %s", value); // CTS needs this // Add controller health // @TODO maybe do some checks to determine meaningful status crm_xml_add(ping, PCMK_XA_RESULT, "ok"); // Send reply reply = create_reply(msg, ping); free_xml(ping); if (reply != NULL) { (void) relay_message(reply, TRUE); free_xml(reply); } // Nothing further to do return I_NULL; } /*! * \brief Handle a PCMK__CONTROLD_CMD_NODES message * * \param[in] request Message XML * * \return Next FSA input */ static enum crmd_fsa_input handle_node_list(const xmlNode *request) { GHashTableIter iter; crm_node_t *node = NULL; xmlNode *reply = NULL; xmlNode *reply_data = NULL; // Create message data for reply reply_data = create_xml_node(NULL, PCMK_XE_NODES); g_hash_table_iter_init(&iter, crm_peer_cache); while (g_hash_table_iter_next(&iter, NULL, (gpointer *) & node)) { xmlNode *xml = create_xml_node(reply_data, PCMK_XE_NODE); crm_xml_add_ll(xml, PCMK_XA_ID, (long long) node->id); // uint32_t crm_xml_add(xml, PCMK_XA_UNAME, node->uname); crm_xml_add(xml, PCMK__XA_IN_CCM, node->state); } // Create and send reply reply = create_reply(request, reply_data); free_xml(reply_data); if (reply) { (void) relay_message(reply, TRUE); free_xml(reply); } // Nothing further to do return I_NULL; } /*! * \brief Handle a CRM_OP_NODE_INFO request * * \param[in] msg Message XML * * \return Next FSA input */ static enum crmd_fsa_input handle_node_info_request(const xmlNode *msg) { const char *value = NULL; crm_node_t *node = NULL; int node_id = 0; xmlNode *reply = NULL; xmlNode *reply_data = NULL; // Build reply reply_data = create_xml_node(NULL, PCMK_XE_NODE); crm_xml_add(reply_data, PCMK__XA_CRM_SUBSYSTEM, CRM_SYSTEM_CRMD); // Add whether current partition has quorum pcmk__xe_set_bool_attr(reply_data, PCMK_XA_HAVE_QUORUM, pcmk_is_set(controld_globals.flags, controld_has_quorum)); // Check whether client requested node info by ID and/or name crm_element_value_int(msg, PCMK_XA_ID, &node_id); if (node_id < 0) { node_id = 0; } value = crm_element_value(msg, PCMK_XA_UNAME); // Default to local node if none given if ((node_id == 0) && (value == NULL)) { value = controld_globals.our_nodename; } node = pcmk__search_node_caches(node_id, value, pcmk__node_search_any); if (node) { crm_xml_add(reply_data, PCMK_XA_ID, node->uuid); crm_xml_add(reply_data, PCMK_XA_UNAME, node->uname); crm_xml_add(reply_data, PCMK__XA_CRMD, node->state); pcmk__xe_set_bool_attr(reply_data, PCMK__XA_REMOTE_NODE, pcmk_is_set(node->flags, crm_remote_node)); } // Send reply reply = create_reply(msg, reply_data); free_xml(reply_data); if (reply != NULL) { (void) relay_message(reply, TRUE); free_xml(reply); } // Nothing further to do return I_NULL; } static void verify_feature_set(xmlNode *msg) { const char *dc_version = crm_element_value(msg, PCMK_XA_CRM_FEATURE_SET); if (dc_version == NULL) { /* All we really know is that the DC feature set is older than 3.1.0, * but that's also all that really matters. */ dc_version = "3.0.14"; } if (feature_set_compatible(dc_version, CRM_FEATURE_SET)) { crm_trace("Local feature set (%s) is compatible with DC's (%s)", CRM_FEATURE_SET, dc_version); } else { crm_err("Local feature set (%s) is incompatible with DC's (%s)", CRM_FEATURE_SET, dc_version); // Nothing is likely to improve without administrator involvement controld_set_fsa_input_flags(R_STAYDOWN); crmd_exit(CRM_EX_FATAL); } } // DC gets own shutdown all-clear static enum crmd_fsa_input handle_shutdown_self_ack(xmlNode *stored_msg) { const char *host_from = crm_element_value(stored_msg, PCMK__XA_SRC); if (pcmk_is_set(controld_globals.fsa_input_register, R_SHUTDOWN)) { // The expected case -- we initiated own shutdown sequence crm_info("Shutting down controller"); return I_STOP; } if (pcmk__str_eq(host_from, controld_globals.dc_name, pcmk__str_casei)) { // Must be logic error -- DC confirming its own unrequested shutdown crm_err("Shutting down controller immediately due to " "unexpected shutdown confirmation"); return I_TERMINATE; } if (controld_globals.fsa_state != S_STOPPING) { // Shouldn't happen -- non-DC confirming unrequested shutdown crm_err("Starting new DC election because %s is " "confirming shutdown we did not request", (host_from? host_from : "another node")); return I_ELECTION; } // Shouldn't happen, but we are already stopping anyway crm_debug("Ignoring unexpected shutdown confirmation from %s", (host_from? host_from : "another node")); return I_NULL; } // Non-DC gets shutdown all-clear from DC static enum crmd_fsa_input handle_shutdown_ack(xmlNode *stored_msg) { const char *host_from = crm_element_value(stored_msg, PCMK__XA_SRC); if (host_from == NULL) { crm_warn("Ignoring shutdown request without origin specified"); return I_NULL; } if (pcmk__str_eq(host_from, controld_globals.dc_name, pcmk__str_null_matches|pcmk__str_casei)) { if (pcmk_is_set(controld_globals.fsa_input_register, R_SHUTDOWN)) { crm_info("Shutting down controller after confirmation from %s", host_from); } else { crm_err("Shutting down controller after unexpected " "shutdown request from %s", host_from); controld_set_fsa_input_flags(R_STAYDOWN); } return I_STOP; } crm_warn("Ignoring shutdown request from %s because DC is %s", host_from, controld_globals.dc_name); return I_NULL; } static enum crmd_fsa_input handle_request(xmlNode *stored_msg, enum crmd_fsa_cause cause) { xmlNode *msg = NULL; const char *op = crm_element_value(stored_msg, PCMK__XA_CRM_TASK); /* Optimize this for the DC - it has the most to do */ crm_log_xml_trace(stored_msg, "request"); if (op == NULL) { crm_warn("Ignoring request without " PCMK__XA_CRM_TASK); return I_NULL; } if (strcmp(op, CRM_OP_SHUTDOWN_REQ) == 0) { const char *from = crm_element_value(stored_msg, PCMK__XA_SRC); crm_node_t *node = pcmk__search_node_caches(0, from, pcmk__node_search_cluster); pcmk__update_peer_expected(__func__, node, CRMD_JOINSTATE_DOWN); if(AM_I_DC == FALSE) { return I_NULL; /* Done */ } } /*========== DC-Only Actions ==========*/ if (AM_I_DC) { if (strcmp(op, CRM_OP_JOIN_ANNOUNCE) == 0) { return I_NODE_JOIN; } else if (strcmp(op, CRM_OP_JOIN_REQUEST) == 0) { return I_JOIN_REQUEST; } else if (strcmp(op, CRM_OP_JOIN_CONFIRM) == 0) { return I_JOIN_RESULT; } else if (strcmp(op, CRM_OP_SHUTDOWN) == 0) { return handle_shutdown_self_ack(stored_msg); } else if (strcmp(op, CRM_OP_SHUTDOWN_REQ) == 0) { // Another controller wants to shut down its node return handle_shutdown_request(stored_msg); } } /*========== common actions ==========*/ if (strcmp(op, CRM_OP_NOVOTE) == 0) { ha_msg_input_t fsa_input; fsa_input.msg = stored_msg; register_fsa_input_adv(C_HA_MESSAGE, I_NULL, &fsa_input, A_ELECTION_COUNT | A_ELECTION_CHECK, FALSE, __func__); } else if (strcmp(op, CRM_OP_REMOTE_STATE) == 0) { /* a remote connection host is letting us know the node state */ return handle_remote_state(stored_msg); } else if (strcmp(op, CRM_OP_THROTTLE) == 0) { throttle_update(stored_msg); if (AM_I_DC && (controld_globals.transition_graph != NULL) && !controld_globals.transition_graph->complete) { crm_debug("The throttle changed. Trigger a graph."); trigger_graph(); } return I_NULL; } else if (strcmp(op, CRM_OP_CLEAR_FAILCOUNT) == 0) { return handle_failcount_op(stored_msg); } else if (strcmp(op, CRM_OP_VOTE) == 0) { /* count the vote and decide what to do after that */ ha_msg_input_t fsa_input; fsa_input.msg = stored_msg; register_fsa_input_adv(C_HA_MESSAGE, I_NULL, &fsa_input, A_ELECTION_COUNT | A_ELECTION_CHECK, FALSE, __func__); /* Sometimes we _must_ go into S_ELECTION */ if (controld_globals.fsa_state == S_HALT) { crm_debug("Forcing an election from S_HALT"); return I_ELECTION; } } else if (strcmp(op, CRM_OP_JOIN_OFFER) == 0) { verify_feature_set(stored_msg); crm_debug("Raising I_JOIN_OFFER: join-%s", crm_element_value(stored_msg, PCMK__XA_JOIN_ID)); return I_JOIN_OFFER; } else if (strcmp(op, CRM_OP_JOIN_ACKNAK) == 0) { crm_debug("Raising I_JOIN_RESULT: join-%s", crm_element_value(stored_msg, PCMK__XA_JOIN_ID)); return I_JOIN_RESULT; } else if (strcmp(op, CRM_OP_LRM_DELETE) == 0) { return handle_lrm_delete(stored_msg); } else if ((strcmp(op, CRM_OP_LRM_FAIL) == 0) || (strcmp(op, CRM_OP_LRM_REFRESH) == 0) // @COMPAT || (strcmp(op, CRM_OP_REPROBE) == 0)) { crm_xml_add(stored_msg, PCMK__XA_CRM_SYS_TO, CRM_SYSTEM_LRMD); return I_ROUTER; } else if (strcmp(op, CRM_OP_NOOP) == 0) { return I_NULL; } else if (strcmp(op, CRM_OP_PING) == 0) { return handle_ping(stored_msg); } else if (strcmp(op, CRM_OP_NODE_INFO) == 0) { return handle_node_info_request(stored_msg); } else if (strcmp(op, CRM_OP_RM_NODE_CACHE) == 0) { int id = 0; const char *name = NULL; crm_element_value_int(stored_msg, PCMK_XA_ID, &id); name = crm_element_value(stored_msg, PCMK_XA_UNAME); if(cause == C_IPC_MESSAGE) { msg = create_request(CRM_OP_RM_NODE_CACHE, NULL, NULL, CRM_SYSTEM_CRMD, CRM_SYSTEM_CRMD, NULL); if (send_cluster_message(NULL, crm_msg_crmd, msg, TRUE) == FALSE) { crm_err("Could not instruct peers to remove references to node %s/%u", name, id); } else { crm_notice("Instructing peers to remove references to node %s/%u", name, id); } free_xml(msg); } else { reap_crm_member(id, name); /* If we're forgetting this node, also forget any failures to fence * it, so we don't carry that over to any node added later with the * same name. */ st_fail_count_reset(name); } } else if (strcmp(op, CRM_OP_MAINTENANCE_NODES) == 0) { xmlNode *xml = get_message_xml(stored_msg, PCMK__XE_CRM_XML); remote_ra_process_maintenance_nodes(xml); } else if (strcmp(op, PCMK__CONTROLD_CMD_NODES) == 0) { return handle_node_list(stored_msg); /*========== (NOT_DC)-Only Actions ==========*/ } else if (!AM_I_DC) { if (strcmp(op, CRM_OP_SHUTDOWN) == 0) { return handle_shutdown_ack(stored_msg); } } else { crm_err("Unexpected request (%s) sent to %s", op, AM_I_DC ? "the DC" : "non-DC node"); crm_log_xml_err(stored_msg, "Unexpected"); } return I_NULL; } static void handle_response(xmlNode *stored_msg) { const char *op = crm_element_value(stored_msg, PCMK__XA_CRM_TASK); crm_log_xml_trace(stored_msg, "reply"); if (op == NULL) { crm_warn("Ignoring reply without " PCMK__XA_CRM_TASK); } else if (AM_I_DC && strcmp(op, CRM_OP_PECALC) == 0) { // Check whether scheduler answer been superseded by subsequent request const char *msg_ref = crm_element_value(stored_msg, PCMK_XA_REFERENCE); if (msg_ref == NULL) { crm_err("%s - Ignoring calculation with no reference", op); } else if (pcmk__str_eq(msg_ref, controld_globals.fsa_pe_ref, pcmk__str_none)) { ha_msg_input_t fsa_input; controld_stop_sched_timer(); fsa_input.msg = stored_msg; register_fsa_input_later(C_IPC_MESSAGE, I_PE_SUCCESS, &fsa_input); } else { crm_info("%s calculation %s is obsolete", op, msg_ref); } } else if (strcmp(op, CRM_OP_VOTE) == 0 || strcmp(op, CRM_OP_SHUTDOWN_REQ) == 0 || strcmp(op, CRM_OP_SHUTDOWN) == 0) { } else { const char *host_from = crm_element_value(stored_msg, PCMK__XA_SRC); crm_err("Unexpected response (op=%s, src=%s) sent to the %s", op, host_from, AM_I_DC ? "DC" : "controller"); } } static enum crmd_fsa_input handle_shutdown_request(xmlNode * stored_msg) { /* handle here to avoid potential version issues * where the shutdown message/procedure may have * been changed in later versions. * * This way the DC is always in control of the shutdown */ char *now_s = NULL; const char *host_from = crm_element_value(stored_msg, PCMK__XA_SRC); if (host_from == NULL) { /* we're shutting down and the DC */ host_from = controld_globals.our_nodename; } crm_info("Creating shutdown request for %s (state=%s)", host_from, fsa_state2string(controld_globals.fsa_state)); crm_log_xml_trace(stored_msg, "message"); now_s = pcmk__ttoa(time(NULL)); update_attrd(host_from, PCMK__NODE_ATTR_SHUTDOWN, now_s, NULL, FALSE); free(now_s); /* will be picked up by the TE as long as its running */ return I_NULL; } static void send_msg_via_ipc(xmlNode * msg, const char *sys) { pcmk__client_t *client_channel = NULL; CRM_CHECK(sys != NULL, return); client_channel = pcmk__find_client_by_id(sys); if (crm_element_value(msg, PCMK__XA_SRC) == NULL) { crm_xml_add(msg, PCMK__XA_SRC, controld_globals.our_nodename); } if (client_channel != NULL) { /* Transient clients such as crmadmin */ pcmk__ipc_send_xml(client_channel, 0, msg, crm_ipc_server_event); } else if (pcmk__str_eq(sys, CRM_SYSTEM_TENGINE, pcmk__str_none)) { xmlNode *data = get_message_xml(msg, PCMK__XE_CRM_XML); process_te_message(msg, data); } else if (pcmk__str_eq(sys, CRM_SYSTEM_LRMD, pcmk__str_none)) { fsa_data_t fsa_data; ha_msg_input_t fsa_input; fsa_input.msg = msg; fsa_input.xml = get_message_xml(msg, PCMK__XE_CRM_XML); fsa_data.id = 0; fsa_data.actions = 0; fsa_data.data = &fsa_input; fsa_data.fsa_input = I_MESSAGE; fsa_data.fsa_cause = C_IPC_MESSAGE; fsa_data.origin = __func__; fsa_data.data_type = fsa_dt_ha_msg; do_lrm_invoke(A_LRM_INVOKE, C_IPC_MESSAGE, controld_globals.fsa_state, I_MESSAGE, &fsa_data); } else if (crmd_is_proxy_session(sys)) { crmd_proxy_send(sys, msg); } else { crm_info("Received invalid request: unknown subsystem '%s'", sys); } } void delete_ha_msg_input(ha_msg_input_t * orig) { if (orig == NULL) { return; } free_xml(orig->msg); free(orig); } /*! * \internal * \brief Notify the cluster of a remote node state change * * \param[in] node_name Node's name * \param[in] node_up true if node is up, false if down */ void broadcast_remote_state_message(const char *node_name, bool node_up) { xmlNode *msg = create_request(CRM_OP_REMOTE_STATE, NULL, NULL, CRM_SYSTEM_CRMD, CRM_SYSTEM_CRMD, NULL); crm_info("Notifying cluster of Pacemaker Remote node %s %s", node_name, node_up? "coming up" : "going down"); crm_xml_add(msg, PCMK_XA_ID, node_name); pcmk__xe_set_bool_attr(msg, PCMK__XA_IN_CCM, node_up); if (node_up) { crm_xml_add(msg, PCMK__XA_CONN_HOST, controld_globals.our_nodename); } send_cluster_message(NULL, crm_msg_crmd, msg, TRUE); free_xml(msg); } diff --git a/daemons/fenced/fenced_commands.c b/daemons/fenced/fenced_commands.c index b1705d50c5..2f7afe0bf8 100644 --- a/daemons/fenced/fenced_commands.c +++ b/daemons/fenced/fenced_commands.c @@ -1,3689 +1,3689 @@ /* * 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 GHashTable *device_list = NULL; GHashTable *topology = NULL; static GList *cmd_list = NULL; static GHashTable *fenced_handlers = NULL; struct device_search_s { /* target of fence action */ char *host; /* requested fence action */ char *action; /* timeout to use if a device is queried dynamically for possible targets */ int per_device_timeout; /* number of registered fencing devices at time of request */ int replies_needed; /* number of device replies received so far */ int replies_received; /* whether the target is eligible to perform requested action (or off) */ bool allow_suicide; /* private data to pass to search callback function */ void *user_data; /* function to call when all replies have been received */ void (*callback) (GList * devices, void *user_data); /* devices capable of performing requested action (or off if remapping) */ GList *capable; /* Whether to perform searches that support the action */ uint32_t support_action_only; }; static gboolean stonith_device_dispatch(gpointer user_data); static void st_child_done(int pid, const pcmk__action_result_t *result, void *user_data); static void search_devices_record_result(struct device_search_s *search, const char *device, gboolean can_fence); static int get_agent_metadata(const char *agent, xmlNode **metadata); static void read_action_metadata(stonith_device_t *device); static enum fenced_target_by unpack_level_kind(const xmlNode *level); typedef struct async_command_s { int id; int pid; int fd_stdout; int options; int default_timeout; /* seconds */ int timeout; /* seconds */ int start_delay; // seconds (-1 means disable static/random fencing delays) int delay_id; char *op; char *origin; char *client; char *client_name; char *remote_op_id; char *target; uint32_t target_nodeid; char *action; char *device; GList *device_list; GList *next_device_iter; // device_list entry for next device to execute void *internal_user_data; void (*done_cb) (int pid, const pcmk__action_result_t *result, void *user_data); guint timer_sigterm; guint timer_sigkill; /*! If the operation timed out, this is the last signal * we sent to the process to get it to terminate */ int last_timeout_signo; stonith_device_t *active_on; stonith_device_t *activating_on; } async_command_t; static xmlNode *construct_async_reply(const async_command_t *cmd, const pcmk__action_result_t *result); static gboolean is_action_required(const char *action, const stonith_device_t *device) { return (device != NULL) && device->automatic_unfencing && pcmk__str_eq(action, PCMK_ACTION_ON, pcmk__str_none); } static int get_action_delay_max(const stonith_device_t *device, const char *action) { const char *value = NULL; guint delay_max = 0U; if (!pcmk__is_fencing_action(action)) { return 0; } value = g_hash_table_lookup(device->params, PCMK_STONITH_DELAY_MAX); if (value) { pcmk_parse_interval_spec(value, &delay_max); delay_max /= 1000; } return (int) delay_max; } static int get_action_delay_base(const stonith_device_t *device, const char *action, const char *target) { char *hash_value = NULL; guint delay_base = 0U; if (!pcmk__is_fencing_action(action)) { return 0; } hash_value = g_hash_table_lookup(device->params, PCMK_STONITH_DELAY_BASE); if (hash_value) { char *value = strdup(hash_value); char *valptr = value; CRM_ASSERT(value != NULL); if (target != NULL) { for (char *val = strtok(value, "; \t"); val != NULL; val = strtok(NULL, "; \t")) { char *mapval = strchr(val, ':'); if (mapval == NULL || mapval[1] == 0) { crm_err("pcmk_delay_base: empty value in mapping", val); continue; } if (mapval != val && strncasecmp(target, val, (size_t)(mapval - val)) == 0) { value = mapval + 1; crm_debug("pcmk_delay_base mapped to %s for %s", value, target); break; } } } if (strchr(value, ':') == 0) { pcmk_parse_interval_spec(value, &delay_base); delay_base /= 1000; } free(valptr); } return (int) delay_base; } /*! * \internal * \brief Override STONITH timeout with pcmk_*_timeout if available * * \param[in] device STONITH device to use * \param[in] action STONITH action name * \param[in] default_timeout Timeout to use if device does not have * a pcmk_*_timeout parameter for action * * \return Value of pcmk_(action)_timeout if available, otherwise default_timeout * \note For consistency, it would be nice if reboot/off/on timeouts could be * set the same way as start/stop/monitor timeouts, i.e. with an * entry in the fencing resource configuration. However that * is insufficient because fencing devices may be registered directly via * the fencer's register_device() API instead of going through the CIB * (e.g. stonith_admin uses it for its -R option, and the executor uses it * to ensure a device is registered when a command is issued). As device * properties, pcmk_*_timeout parameters can be grabbed by the fencer when * the device is registered, whether by CIB change or API call. */ static int get_action_timeout(const stonith_device_t *device, const char *action, int default_timeout) { if (action && device && device->params) { char buffer[64] = { 0, }; const char *value = NULL; /* If "reboot" was requested but the device does not support it, * we will remap to "off", so check timeout for "off" instead */ if (pcmk__str_eq(action, PCMK_ACTION_REBOOT, pcmk__str_none) && !pcmk_is_set(device->flags, st_device_supports_reboot)) { crm_trace("%s doesn't support reboot, using timeout for off instead", device->id); action = PCMK_ACTION_OFF; } /* If the device config specified an action-specific timeout, use it */ snprintf(buffer, sizeof(buffer), "pcmk_%s_timeout", action); value = g_hash_table_lookup(device->params, buffer); if (value) { return atoi(value); } } return default_timeout; } /*! * \internal * \brief Get the currently executing device for a fencing operation * * \param[in] cmd Fencing operation to check * * \return Currently executing device for \p cmd if any, otherwise NULL */ static stonith_device_t * cmd_device(const async_command_t *cmd) { if ((cmd == NULL) || (cmd->device == NULL) || (device_list == NULL)) { return NULL; } return g_hash_table_lookup(device_list, cmd->device); } /*! * \internal * \brief Return the configured reboot action for a given device * * \param[in] device_id Device ID * * \return Configured reboot action for \p device_id */ const char * fenced_device_reboot_action(const char *device_id) { const char *action = NULL; if ((device_list != NULL) && (device_id != NULL)) { stonith_device_t *device = g_hash_table_lookup(device_list, device_id); if ((device != NULL) && (device->params != NULL)) { action = g_hash_table_lookup(device->params, "pcmk_reboot_action"); } } return pcmk__s(action, PCMK_ACTION_REBOOT); } /*! * \internal * \brief Check whether a given device supports the "on" action * * \param[in] device_id Device ID * * \return true if \p device_id supports "on", otherwise false */ bool fenced_device_supports_on(const char *device_id) { if ((device_list != NULL) && (device_id != NULL)) { stonith_device_t *device = g_hash_table_lookup(device_list, device_id); if (device != NULL) { return pcmk_is_set(device->flags, st_device_supports_on); } } return false; } static void free_async_command(async_command_t * cmd) { if (!cmd) { return; } if (cmd->delay_id) { g_source_remove(cmd->delay_id); } cmd_list = g_list_remove(cmd_list, cmd); g_list_free_full(cmd->device_list, free); free(cmd->device); free(cmd->action); free(cmd->target); free(cmd->remote_op_id); free(cmd->client); free(cmd->client_name); free(cmd->origin); free(cmd->op); free(cmd); } /*! * \internal * \brief Create a new asynchronous fencing operation from request XML * * \param[in] msg Fencing request XML (from IPC or CPG) * * \return Newly allocated fencing operation on success, otherwise NULL * * \note This asserts on memory errors, so a NULL return indicates an * unparseable message. */ static async_command_t * create_async_command(xmlNode *msg) { xmlNode *op = NULL; async_command_t *cmd = NULL; if (msg == NULL) { return NULL; } op = get_xpath_object("//@" F_STONITH_ACTION, msg, LOG_ERR); if (op == NULL) { return NULL; } cmd = calloc(1, sizeof(async_command_t)); CRM_ASSERT(cmd != NULL); // All messages must include these cmd->action = crm_element_value_copy(op, F_STONITH_ACTION); cmd->op = crm_element_value_copy(msg, F_STONITH_OPERATION); cmd->client = crm_element_value_copy(msg, F_STONITH_CLIENTID); if ((cmd->action == NULL) || (cmd->op == NULL) || (cmd->client == NULL)) { free_async_command(cmd); return NULL; } crm_element_value_int(msg, F_STONITH_CALLID, &(cmd->id)); crm_element_value_int(msg, F_STONITH_CALLOPTS, &(cmd->options)); crm_element_value_int(msg, F_STONITH_DELAY, &(cmd->start_delay)); crm_element_value_int(msg, F_STONITH_TIMEOUT, &(cmd->default_timeout)); cmd->timeout = cmd->default_timeout; cmd->origin = crm_element_value_copy(msg, PCMK__XA_SRC); cmd->remote_op_id = crm_element_value_copy(msg, F_STONITH_REMOTE_OP_ID); cmd->client_name = crm_element_value_copy(msg, F_STONITH_CLIENTNAME); cmd->target = crm_element_value_copy(op, F_STONITH_TARGET); cmd->device = crm_element_value_copy(op, F_STONITH_DEVICE); cmd->done_cb = st_child_done; // Track in global command list cmd_list = g_list_append(cmd_list, cmd); return cmd; } static int get_action_limit(stonith_device_t * device) { const char *value = NULL; int action_limit = 1; value = g_hash_table_lookup(device->params, PCMK_STONITH_ACTION_LIMIT); if ((value == NULL) || (pcmk__scan_min_int(value, &action_limit, INT_MIN) != pcmk_rc_ok) || (action_limit == 0)) { action_limit = 1; } return action_limit; } static int get_active_cmds(stonith_device_t * device) { int counter = 0; GList *gIter = NULL; GList *gIterNext = NULL; CRM_CHECK(device != NULL, return 0); for (gIter = cmd_list; gIter != NULL; gIter = gIterNext) { async_command_t *cmd = gIter->data; gIterNext = gIter->next; if (cmd->active_on == device) { counter++; } } return counter; } static void fork_cb(int pid, void *user_data) { async_command_t *cmd = (async_command_t *) user_data; stonith_device_t * device = /* in case of a retry we've done the move from activating_on to active_on already */ cmd->activating_on?cmd->activating_on:cmd->active_on; CRM_ASSERT(device); crm_debug("Operation '%s' [%d]%s%s using %s now running with %ds timeout", cmd->action, pid, ((cmd->target == NULL)? "" : " targeting "), pcmk__s(cmd->target, ""), device->id, cmd->timeout); cmd->active_on = device; cmd->activating_on = NULL; } static int get_agent_metadata_cb(gpointer data) { stonith_device_t *device = data; guint period_ms; switch (get_agent_metadata(device->agent, &device->agent_metadata)) { case pcmk_rc_ok: if (device->agent_metadata) { read_action_metadata(device); stonith__device_parameter_flags(&(device->flags), device->id, device->agent_metadata); } return G_SOURCE_REMOVE; case EAGAIN: period_ms = pcmk__mainloop_timer_get_period(device->timer); if (period_ms < 160 * 1000) { mainloop_timer_set_period(device->timer, 2 * period_ms); } return G_SOURCE_CONTINUE; default: return G_SOURCE_REMOVE; } } /*! * \internal * \brief Call a command's action callback for an internal (not library) result * * \param[in,out] cmd Command to report result for * \param[in] execution_status Execution status to use for result * \param[in] exit_status Exit status to use for result * \param[in] exit_reason Exit reason to use for result */ static void report_internal_result(async_command_t *cmd, int exit_status, int execution_status, const char *exit_reason) { pcmk__action_result_t result = PCMK__UNKNOWN_RESULT; pcmk__set_result(&result, exit_status, execution_status, exit_reason); cmd->done_cb(0, &result, cmd); pcmk__reset_result(&result); } static gboolean stonith_device_execute(stonith_device_t * device) { int exec_rc = 0; const char *action_str = NULL; const char *host_arg = NULL; async_command_t *cmd = NULL; stonith_action_t *action = NULL; int active_cmds = 0; int action_limit = 0; GList *gIter = NULL; GList *gIterNext = NULL; CRM_CHECK(device != NULL, return FALSE); active_cmds = get_active_cmds(device); action_limit = get_action_limit(device); if (action_limit > -1 && active_cmds >= action_limit) { crm_trace("%s is over its action limit of %d (%u active action%s)", device->id, action_limit, active_cmds, pcmk__plural_s(active_cmds)); return TRUE; } for (gIter = device->pending_ops; gIter != NULL; gIter = gIterNext) { async_command_t *pending_op = gIter->data; gIterNext = gIter->next; if (pending_op && pending_op->delay_id) { crm_trace("Operation '%s'%s%s using %s was asked to run too early, " "waiting for start delay of %ds", pending_op->action, ((pending_op->target == NULL)? "" : " targeting "), pcmk__s(pending_op->target, ""), device->id, pending_op->start_delay); continue; } device->pending_ops = g_list_remove_link(device->pending_ops, gIter); g_list_free_1(gIter); cmd = pending_op; break; } if (cmd == NULL) { crm_trace("No actions using %s are needed", device->id); return TRUE; } if (pcmk__str_any_of(device->agent, STONITH_WATCHDOG_AGENT, STONITH_WATCHDOG_AGENT_INTERNAL, NULL)) { if (pcmk__is_fencing_action(cmd->action)) { if (node_does_watchdog_fencing(stonith_our_uname)) { pcmk__panic(__func__); goto done; } } else { crm_info("Faking success for %s watchdog operation", cmd->action); report_internal_result(cmd, CRM_EX_OK, PCMK_EXEC_DONE, NULL); goto done; } } #if SUPPORT_CIBSECRETS exec_rc = pcmk__substitute_secrets(device->id, device->params); if (exec_rc != pcmk_rc_ok) { if (pcmk__str_eq(cmd->action, PCMK_ACTION_STOP, pcmk__str_none)) { crm_info("Proceeding with stop operation for %s " "despite being unable to load CIB secrets (%s)", device->id, pcmk_rc_str(exec_rc)); } else { crm_err("Considering %s unconfigured " "because unable to load CIB secrets: %s", device->id, pcmk_rc_str(exec_rc)); report_internal_result(cmd, CRM_EX_ERROR, PCMK_EXEC_NO_SECRETS, "Failed to get CIB secrets"); goto done; } } #endif action_str = cmd->action; if (pcmk__str_eq(cmd->action, PCMK_ACTION_REBOOT, pcmk__str_none) && !pcmk_is_set(device->flags, st_device_supports_reboot)) { crm_notice("Remapping 'reboot' action%s%s using %s to 'off' " "because agent '%s' does not support reboot", ((cmd->target == NULL)? "" : " targeting "), pcmk__s(cmd->target, ""), device->id, device->agent); action_str = PCMK_ACTION_OFF; } if (pcmk_is_set(device->flags, st_device_supports_parameter_port)) { host_arg = "port"; } else if (pcmk_is_set(device->flags, st_device_supports_parameter_plug)) { host_arg = "plug"; } action = stonith__action_create(device->agent, action_str, cmd->target, cmd->target_nodeid, cmd->timeout, device->params, device->aliases, host_arg); /* for async exec, exec_rc is negative for early error exit otherwise handling of success/errors is done via callbacks */ cmd->activating_on = device; exec_rc = stonith__execute_async(action, (void *)cmd, cmd->done_cb, fork_cb); if (exec_rc < 0) { cmd->activating_on = NULL; cmd->done_cb(0, stonith__action_result(action), cmd); stonith__destroy_action(action); } done: /* Device might get triggered to work by multiple fencing commands * simultaneously. Trigger the device again to make sure any * remaining concurrent commands get executed. */ if (device->pending_ops) { mainloop_set_trigger(device->work); } return TRUE; } static gboolean stonith_device_dispatch(gpointer user_data) { return stonith_device_execute(user_data); } static gboolean start_delay_helper(gpointer data) { async_command_t *cmd = data; stonith_device_t *device = cmd_device(cmd); cmd->delay_id = 0; if (device) { mainloop_set_trigger(device->work); } return FALSE; } static void schedule_stonith_command(async_command_t * cmd, stonith_device_t * device) { int delay_max = 0; int delay_base = 0; int requested_delay = cmd->start_delay; CRM_CHECK(cmd != NULL, return); CRM_CHECK(device != NULL, return); if (cmd->device) { free(cmd->device); } if (device->include_nodeid && (cmd->target != NULL)) { crm_node_t *node = pcmk__get_node(0, cmd->target, NULL, pcmk__node_search_cluster); cmd->target_nodeid = node->id; } cmd->device = strdup(device->id); cmd->timeout = get_action_timeout(device, cmd->action, cmd->default_timeout); if (cmd->remote_op_id) { crm_debug("Scheduling '%s' action%s%s using %s for remote peer %s " "with op id %.8s and timeout %ds", cmd->action, (cmd->target == NULL)? "" : " targeting ", pcmk__s(cmd->target, ""), device->id, cmd->origin, cmd->remote_op_id, cmd->timeout); } else { crm_debug("Scheduling '%s' action%s%s using %s for %s with timeout %ds", cmd->action, (cmd->target == NULL)? "" : " targeting ", pcmk__s(cmd->target, ""), device->id, cmd->client, cmd->timeout); } device->pending_ops = g_list_append(device->pending_ops, cmd); mainloop_set_trigger(device->work); // Value -1 means disable any static/random fencing delays if (requested_delay < 0) { return; } delay_max = get_action_delay_max(device, cmd->action); delay_base = get_action_delay_base(device, cmd->action, cmd->target); if (delay_max == 0) { delay_max = delay_base; } if (delay_max < delay_base) { crm_warn(PCMK_STONITH_DELAY_BASE " (%ds) is larger than " PCMK_STONITH_DELAY_MAX " (%ds) for %s using %s " "(limiting to maximum delay)", delay_base, delay_max, cmd->action, device->id); delay_base = delay_max; } if (delay_max > 0) { // coverity[dontcall] It doesn't matter here if rand() is predictable cmd->start_delay += ((delay_max != delay_base)?(rand() % (delay_max - delay_base)):0) + delay_base; } if (cmd->start_delay > 0) { crm_notice("Delaying '%s' action%s%s using %s for %ds " CRM_XS " timeout=%ds requested_delay=%ds base=%ds max=%ds", cmd->action, (cmd->target == NULL)? "" : " targeting ", pcmk__s(cmd->target, ""), device->id, cmd->start_delay, cmd->timeout, requested_delay, delay_base, delay_max); cmd->delay_id = g_timeout_add_seconds(cmd->start_delay, start_delay_helper, cmd); } } static void free_device(gpointer data) { GList *gIter = NULL; stonith_device_t *device = data; g_hash_table_destroy(device->params); g_hash_table_destroy(device->aliases); for (gIter = device->pending_ops; gIter != NULL; gIter = gIter->next) { async_command_t *cmd = gIter->data; crm_warn("Removal of device '%s' purged operation '%s'", device->id, cmd->action); report_internal_result(cmd, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, "Device was removed before action could be executed"); } g_list_free(device->pending_ops); g_list_free_full(device->targets, free); if (device->timer) { mainloop_timer_stop(device->timer); mainloop_timer_del(device->timer); } mainloop_destroy_trigger(device->work); free_xml(device->agent_metadata); free(device->namespace); if (device->on_target_actions != NULL) { g_string_free(device->on_target_actions, TRUE); } free(device->agent); free(device->id); free(device); } void free_device_list(void) { if (device_list != NULL) { g_hash_table_destroy(device_list); device_list = NULL; } } void init_device_list(void) { if (device_list == NULL) { device_list = pcmk__strkey_table(NULL, free_device); } } static GHashTable * build_port_aliases(const char *hostmap, GList ** targets) { char *name = NULL; int last = 0, lpc = 0, max = 0, added = 0; GHashTable *aliases = pcmk__strikey_table(free, free); if (hostmap == NULL) { return aliases; } max = strlen(hostmap); for (; lpc <= max; lpc++) { switch (hostmap[lpc]) { /* Skip escaped chars */ case '\\': lpc++; break; /* Assignment chars */ case '=': case ':': if (lpc > last) { free(name); name = calloc(1, 1 + lpc - last); memcpy(name, hostmap + last, lpc - last); } last = lpc + 1; break; /* Delimeter chars */ /* case ',': Potentially used to specify multiple ports */ case 0: case ';': case ' ': case '\t': if (name) { char *value = NULL; int k = 0; value = calloc(1, 1 + lpc - last); memcpy(value, hostmap + last, lpc - last); for (int i = 0; value[i] != '\0'; i++) { if (value[i] != '\\') { value[k++] = value[i]; } } value[k] = '\0'; crm_debug("Adding alias '%s'='%s'", name, value); g_hash_table_replace(aliases, name, value); if (targets) { *targets = g_list_append(*targets, strdup(value)); } value = NULL; name = NULL; added++; } else if (lpc > last) { crm_debug("Parse error at offset %d near '%s'", lpc - last, hostmap + last); } last = lpc + 1; break; } if (hostmap[lpc] == 0) { break; } } if (added == 0) { crm_info("No host mappings detected in '%s'", hostmap); } free(name); return aliases; } GHashTable *metadata_cache = NULL; void free_metadata_cache(void) { if (metadata_cache != NULL) { g_hash_table_destroy(metadata_cache); metadata_cache = NULL; } } static void init_metadata_cache(void) { if (metadata_cache == NULL) { metadata_cache = pcmk__strkey_table(free, free); } } int get_agent_metadata(const char *agent, xmlNode ** metadata) { char *buffer = NULL; if (metadata == NULL) { return EINVAL; } *metadata = NULL; if (pcmk__str_eq(agent, STONITH_WATCHDOG_AGENT_INTERNAL, pcmk__str_none)) { return pcmk_rc_ok; } init_metadata_cache(); buffer = g_hash_table_lookup(metadata_cache, agent); if (buffer == NULL) { stonith_t *st = stonith_api_new(); int rc; if (st == NULL) { crm_warn("Could not get agent meta-data: " "API memory allocation failed"); return EAGAIN; } rc = st->cmds->metadata(st, st_opt_sync_call, agent, NULL, &buffer, 10); stonith_api_delete(st); if (rc || !buffer) { crm_err("Could not retrieve metadata for fencing agent %s", agent); return EAGAIN; } g_hash_table_replace(metadata_cache, strdup(agent), buffer); } *metadata = string2xml(buffer); return pcmk_rc_ok; } static gboolean is_nodeid_required(xmlNode * xml) { xmlXPathObjectPtr xpath = NULL; if (stand_alone) { return FALSE; } if (!xml) { return FALSE; } xpath = xpath_search(xml, "//" PCMK_XE_PARAMETER "[@" PCMK_XA_NAME "='nodeid']"); if (numXpathResults(xpath) <= 0) { freeXpathObject(xpath); return FALSE; } freeXpathObject(xpath); return TRUE; } static void read_action_metadata(stonith_device_t *device) { xmlXPathObjectPtr xpath = NULL; int max = 0; int lpc = 0; if (device->agent_metadata == NULL) { return; } xpath = xpath_search(device->agent_metadata, "//action"); max = numXpathResults(xpath); if (max <= 0) { freeXpathObject(xpath); return; } for (lpc = 0; lpc < max; lpc++) { const char *action = NULL; xmlNode *match = getXpathResult(xpath, lpc); CRM_LOG_ASSERT(match != NULL); if(match == NULL) { continue; }; action = crm_element_value(match, PCMK_XA_NAME); if (pcmk__str_eq(action, PCMK_ACTION_LIST, pcmk__str_none)) { stonith__set_device_flags(device->flags, device->id, st_device_supports_list); } else if (pcmk__str_eq(action, PCMK_ACTION_STATUS, pcmk__str_none)) { stonith__set_device_flags(device->flags, device->id, st_device_supports_status); } else if (pcmk__str_eq(action, PCMK_ACTION_REBOOT, pcmk__str_none)) { stonith__set_device_flags(device->flags, device->id, st_device_supports_reboot); } else if (pcmk__str_eq(action, PCMK_ACTION_ON, pcmk__str_none)) { /* "automatic" means the cluster will unfence node when it joins */ /* "required" is a deprecated synonym for "automatic" */ if (pcmk__xe_attr_is_true(match, "automatic") || pcmk__xe_attr_is_true(match, "required")) { device->automatic_unfencing = TRUE; } stonith__set_device_flags(device->flags, device->id, st_device_supports_on); } if ((action != NULL) && pcmk__xe_attr_is_true(match, "on_target")) { pcmk__add_word(&(device->on_target_actions), 64, action); } } freeXpathObject(xpath); } /*! * \internal * \brief Set a pcmk_*_action parameter if not already set * * \param[in,out] params Device parameters * \param[in] action Name of action * \param[in] value Value to use if action is not already set */ static void map_action(GHashTable *params, const char *action, const char *value) { char *key = crm_strdup_printf("pcmk_%s_action", action); if (g_hash_table_lookup(params, key)) { crm_warn("Ignoring %s='%s', see %s instead", STONITH_ATTR_ACTION_OP, value, key); free(key); } else { crm_warn("Mapping %s='%s' to %s='%s'", STONITH_ATTR_ACTION_OP, value, key, value); g_hash_table_insert(params, key, strdup(value)); } } /*! * \internal * \brief Create device parameter table from XML * * \param[in] name Device name (used for logging only) * \param[in] dev XML containing device parameters */ static GHashTable * xml2device_params(const char *name, const xmlNode *dev) { GHashTable *params = xml2list(dev); const char *value; /* Action should never be specified in the device configuration, * but we support it for users who are familiar with other software * that worked that way. */ value = g_hash_table_lookup(params, STONITH_ATTR_ACTION_OP); if (value != NULL) { crm_warn("%s has '%s' parameter, which should never be specified in configuration", name, STONITH_ATTR_ACTION_OP); if (*value == '\0') { crm_warn("Ignoring empty '%s' parameter", STONITH_ATTR_ACTION_OP); } else if (strcmp(value, PCMK_ACTION_REBOOT) == 0) { crm_warn("Ignoring %s='reboot' (see " PCMK_OPT_STONITH_ACTION " cluster property instead)", STONITH_ATTR_ACTION_OP); } else if (strcmp(value, PCMK_ACTION_OFF) == 0) { map_action(params, PCMK_ACTION_REBOOT, value); } else { map_action(params, PCMK_ACTION_OFF, value); map_action(params, PCMK_ACTION_REBOOT, value); } g_hash_table_remove(params, STONITH_ATTR_ACTION_OP); } return params; } static const char * target_list_type(stonith_device_t * dev) { const char *check_type = NULL; check_type = g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_CHECK); if (check_type == NULL) { if (g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_LIST)) { check_type = "static-list"; } else if (g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_MAP)) { check_type = "static-list"; } else if (pcmk_is_set(dev->flags, st_device_supports_list)) { check_type = "dynamic-list"; } else if (pcmk_is_set(dev->flags, st_device_supports_status)) { check_type = "status"; } else { check_type = PCMK__VALUE_NONE; } } return check_type; } static stonith_device_t * build_device_from_xml(xmlNode *dev) { const char *value; stonith_device_t *device = NULL; - char *agent = crm_element_value_copy(dev, "agent"); + char *agent = crm_element_value_copy(dev, PCMK_XA_AGENT); CRM_CHECK(agent != NULL, return device); device = calloc(1, sizeof(stonith_device_t)); CRM_CHECK(device != NULL, {free(agent); return device;}); device->id = crm_element_value_copy(dev, PCMK_XA_ID); device->agent = agent; device->namespace = crm_element_value_copy(dev, "namespace"); device->params = xml2device_params(device->id, dev); value = g_hash_table_lookup(device->params, PCMK_STONITH_HOST_LIST); if (value) { device->targets = stonith__parse_targets(value); } value = g_hash_table_lookup(device->params, PCMK_STONITH_HOST_MAP); device->aliases = build_port_aliases(value, &(device->targets)); value = target_list_type(device); if (!pcmk__str_eq(value, "static-list", pcmk__str_casei) && device->targets) { /* Other than "static-list", dev-> targets is unnecessary. */ g_list_free_full(device->targets, free); device->targets = NULL; } switch (get_agent_metadata(device->agent, &device->agent_metadata)) { case pcmk_rc_ok: if (device->agent_metadata) { read_action_metadata(device); stonith__device_parameter_flags(&(device->flags), device->id, device->agent_metadata); } break; case EAGAIN: if (device->timer == NULL) { device->timer = mainloop_timer_add("get_agent_metadata", 10 * 1000, TRUE, get_agent_metadata_cb, device); } if (!mainloop_timer_running(device->timer)) { mainloop_timer_start(device->timer); } break; default: break; } value = g_hash_table_lookup(device->params, "nodeid"); if (!value) { device->include_nodeid = is_nodeid_required(device->agent_metadata); } value = crm_element_value(dev, "rsc_provides"); if (pcmk__str_eq(value, PCMK__VALUE_UNFENCING, pcmk__str_casei)) { device->automatic_unfencing = TRUE; } if (is_action_required(PCMK_ACTION_ON, device)) { crm_info("Fencing device '%s' requires unfencing", device->id); } if (device->on_target_actions != NULL) { crm_info("Fencing device '%s' requires actions (%s) to be executed " "on target", device->id, (const char *) device->on_target_actions->str); } device->work = mainloop_add_trigger(G_PRIORITY_HIGH, stonith_device_dispatch, device); /* TODO: Hook up priority */ return device; } static void schedule_internal_command(const char *origin, stonith_device_t * device, const char *action, const char *target, int timeout, void *internal_user_data, void (*done_cb) (int pid, const pcmk__action_result_t *result, void *user_data)) { async_command_t *cmd = NULL; cmd = calloc(1, sizeof(async_command_t)); cmd->id = -1; cmd->default_timeout = timeout ? timeout : 60; cmd->timeout = cmd->default_timeout; cmd->action = strdup(action); pcmk__str_update(&cmd->target, target); cmd->device = strdup(device->id); cmd->origin = strdup(origin); cmd->client = strdup(crm_system_name); cmd->client_name = strdup(crm_system_name); cmd->internal_user_data = internal_user_data; cmd->done_cb = done_cb; /* cmd, not internal_user_data, is passed to 'done_cb' as the userdata */ schedule_stonith_command(cmd, device); } // Fence agent status commands use custom exit status codes enum fence_status_code { fence_status_invalid = -1, fence_status_active = 0, fence_status_unknown = 1, fence_status_inactive = 2, }; static void status_search_cb(int pid, const pcmk__action_result_t *result, void *user_data) { async_command_t *cmd = user_data; struct device_search_s *search = cmd->internal_user_data; stonith_device_t *dev = cmd_device(cmd); gboolean can = FALSE; free_async_command(cmd); if (!dev) { search_devices_record_result(search, NULL, FALSE); return; } mainloop_set_trigger(dev->work); if (result->execution_status != PCMK_EXEC_DONE) { crm_warn("Assuming %s cannot fence %s " "because status could not be executed: %s%s%s%s", dev->id, search->host, pcmk_exec_status_str(result->execution_status), ((result->exit_reason == NULL)? "" : " ("), ((result->exit_reason == NULL)? "" : result->exit_reason), ((result->exit_reason == NULL)? "" : ")")); search_devices_record_result(search, dev->id, FALSE); return; } switch (result->exit_status) { case fence_status_unknown: crm_trace("%s reported it cannot fence %s", dev->id, search->host); break; case fence_status_active: case fence_status_inactive: crm_trace("%s reported it can fence %s", dev->id, search->host); can = TRUE; break; default: crm_warn("Assuming %s cannot fence %s " "(status returned unknown code %d)", dev->id, search->host, result->exit_status); break; } search_devices_record_result(search, dev->id, can); } static void dynamic_list_search_cb(int pid, const pcmk__action_result_t *result, void *user_data) { async_command_t *cmd = user_data; struct device_search_s *search = cmd->internal_user_data; stonith_device_t *dev = cmd_device(cmd); gboolean can_fence = FALSE; free_async_command(cmd); /* Host/alias must be in the list output to be eligible to be fenced * * Will cause problems if down'd nodes aren't listed or (for virtual nodes) * if the guest is still listed despite being moved to another machine */ if (!dev) { search_devices_record_result(search, NULL, FALSE); return; } mainloop_set_trigger(dev->work); if (pcmk__result_ok(result)) { crm_info("Refreshing target list for %s", dev->id); g_list_free_full(dev->targets, free); dev->targets = stonith__parse_targets(result->action_stdout); dev->targets_age = time(NULL); } else if (dev->targets != NULL) { if (result->execution_status == PCMK_EXEC_DONE) { crm_info("Reusing most recent target list for %s " "because list returned error code %d", dev->id, result->exit_status); } else { crm_info("Reusing most recent target list for %s " "because list could not be executed: %s%s%s%s", dev->id, pcmk_exec_status_str(result->execution_status), ((result->exit_reason == NULL)? "" : " ("), ((result->exit_reason == NULL)? "" : result->exit_reason), ((result->exit_reason == NULL)? "" : ")")); } } else { // We have never successfully executed list if (result->execution_status == PCMK_EXEC_DONE) { crm_warn("Assuming %s cannot fence %s " "because list returned error code %d", dev->id, search->host, result->exit_status); } else { crm_warn("Assuming %s cannot fence %s " "because list could not be executed: %s%s%s%s", dev->id, search->host, pcmk_exec_status_str(result->execution_status), ((result->exit_reason == NULL)? "" : " ("), ((result->exit_reason == NULL)? "" : result->exit_reason), ((result->exit_reason == NULL)? "" : ")")); } /* Fall back to pcmk_host_check="status" if the user didn't explicitly * specify "dynamic-list". */ if (g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_CHECK) == NULL) { crm_notice("Switching to pcmk_host_check='status' for %s", dev->id); g_hash_table_replace(dev->params, strdup(PCMK_STONITH_HOST_CHECK), strdup("status")); } } if (dev->targets) { const char *alias = g_hash_table_lookup(dev->aliases, search->host); if (!alias) { alias = search->host; } if (pcmk__str_in_list(alias, dev->targets, pcmk__str_casei)) { can_fence = TRUE; } } search_devices_record_result(search, dev->id, can_fence); } /*! * \internal * \brief Returns true if any key in first is not in second or second has a different value for key */ static int device_params_diff(GHashTable *first, GHashTable *second) { char *key = NULL; char *value = NULL; GHashTableIter gIter; g_hash_table_iter_init(&gIter, first); while (g_hash_table_iter_next(&gIter, (void **)&key, (void **)&value)) { if(strstr(key, "CRM_meta") == key) { continue; } else if (strcmp(key, PCMK_XA_CRM_FEATURE_SET) == 0) { continue; } else { char *other_value = g_hash_table_lookup(second, key); if (!other_value || !pcmk__str_eq(other_value, value, pcmk__str_casei)) { crm_trace("Different value for %s: %s != %s", key, other_value, value); return 1; } } } return 0; } /*! * \internal * \brief Checks to see if an identical device already exists in the device_list */ static stonith_device_t * device_has_duplicate(const stonith_device_t *device) { stonith_device_t *dup = g_hash_table_lookup(device_list, device->id); if (!dup) { crm_trace("No match for %s", device->id); return NULL; } else if (!pcmk__str_eq(dup->agent, device->agent, pcmk__str_casei)) { crm_trace("Different agent: %s != %s", dup->agent, device->agent); return NULL; } /* Use calculate_operation_digest() here? */ if (device_params_diff(device->params, dup->params) || device_params_diff(dup->params, device->params)) { return NULL; } crm_trace("Match"); return dup; } int stonith_device_register(xmlNode *dev, gboolean from_cib) { stonith_device_t *dup = NULL; stonith_device_t *device = build_device_from_xml(dev); guint ndevices = 0; int rv = pcmk_ok; CRM_CHECK(device != NULL, return -ENOMEM); /* do we have a watchdog-device? */ if (pcmk__str_eq(device->id, STONITH_WATCHDOG_ID, pcmk__str_none) || pcmk__str_any_of(device->agent, STONITH_WATCHDOG_AGENT, STONITH_WATCHDOG_AGENT_INTERNAL, NULL)) do { if (stonith_watchdog_timeout_ms <= 0) { crm_err("Ignoring watchdog fence device without " PCMK_OPT_STONITH_WATCHDOG_TIMEOUT " set."); rv = -ENODEV; /* fall through to cleanup & return */ } else if (!pcmk__str_any_of(device->agent, STONITH_WATCHDOG_AGENT, STONITH_WATCHDOG_AGENT_INTERNAL, NULL)) { crm_err("Ignoring watchdog fence device with unknown " "agent '%s' unequal '" STONITH_WATCHDOG_AGENT "'.", device->agent?device->agent:""); rv = -ENODEV; /* fall through to cleanup & return */ } else if (!pcmk__str_eq(device->id, STONITH_WATCHDOG_ID, pcmk__str_none)) { crm_err("Ignoring watchdog fence device " "named %s !='"STONITH_WATCHDOG_ID"'.", device->id?device->id:""); rv = -ENODEV; /* fall through to cleanup & return */ } else { if (pcmk__str_eq(device->agent, STONITH_WATCHDOG_AGENT, pcmk__str_none)) { /* this either has an empty list or the targets configured for watchdog-fencing */ g_list_free_full(stonith_watchdog_targets, free); stonith_watchdog_targets = device->targets; device->targets = NULL; } if (node_does_watchdog_fencing(stonith_our_uname)) { g_list_free_full(device->targets, free); device->targets = stonith__parse_targets(stonith_our_uname); g_hash_table_replace(device->params, strdup(PCMK_STONITH_HOST_LIST), strdup(stonith_our_uname)); /* proceed as with any other stonith-device */ break; } crm_debug("Skip registration of watchdog fence device on node not in host-list."); /* cleanup and fall through to more cleanup and return */ device->targets = NULL; stonith_device_remove(device->id, from_cib); } free_device(device); return rv; } while (0); dup = device_has_duplicate(device); if (dup) { ndevices = g_hash_table_size(device_list); crm_debug("Device '%s' already in device list (%d active device%s)", device->id, ndevices, pcmk__plural_s(ndevices)); free_device(device); device = dup; dup = g_hash_table_lookup(device_list, device->id); dup->dirty = FALSE; } else { stonith_device_t *old = g_hash_table_lookup(device_list, device->id); if (from_cib && old && old->api_registered) { /* If the cib is writing over an entry that is shared with a stonith client, * copy any pending ops that currently exist on the old entry to the new one. * Otherwise the pending ops will be reported as failures */ crm_info("Overwriting existing entry for %s from CIB", device->id); device->pending_ops = old->pending_ops; device->api_registered = TRUE; old->pending_ops = NULL; if (device->pending_ops) { mainloop_set_trigger(device->work); } } g_hash_table_replace(device_list, device->id, device); ndevices = g_hash_table_size(device_list); crm_notice("Added '%s' to device list (%d active device%s)", device->id, ndevices, pcmk__plural_s(ndevices)); } if (from_cib) { device->cib_registered = TRUE; } else { device->api_registered = TRUE; } return pcmk_ok; } void stonith_device_remove(const char *id, bool from_cib) { stonith_device_t *device = g_hash_table_lookup(device_list, id); guint ndevices = 0; if (!device) { ndevices = g_hash_table_size(device_list); crm_info("Device '%s' not found (%d active device%s)", id, ndevices, pcmk__plural_s(ndevices)); return; } if (from_cib) { device->cib_registered = FALSE; } else { device->verified = FALSE; device->api_registered = FALSE; } if (!device->cib_registered && !device->api_registered) { g_hash_table_remove(device_list, id); ndevices = g_hash_table_size(device_list); crm_info("Removed '%s' from device list (%d active device%s)", id, ndevices, pcmk__plural_s(ndevices)); } else { crm_trace("Not removing '%s' from device list (%d active) because " "still registered via:%s%s", id, g_hash_table_size(device_list), (device->cib_registered? " cib" : ""), (device->api_registered? " api" : "")); } } /*! * \internal * \brief Return the number of stonith levels registered for a node * * \param[in] tp Node's topology table entry * * \return Number of non-NULL levels in topology entry * \note This function is used only for log messages. */ static int count_active_levels(const stonith_topology_t *tp) { int lpc = 0; int count = 0; for (lpc = 0; lpc < ST_LEVEL_MAX; lpc++) { if (tp->levels[lpc] != NULL) { count++; } } return count; } static void free_topology_entry(gpointer data) { stonith_topology_t *tp = data; int lpc = 0; for (lpc = 0; lpc < ST_LEVEL_MAX; lpc++) { if (tp->levels[lpc] != NULL) { g_list_free_full(tp->levels[lpc], free); } } free(tp->target); free(tp->target_value); free(tp->target_pattern); free(tp->target_attribute); free(tp); } void free_topology_list(void) { if (topology != NULL) { g_hash_table_destroy(topology); topology = NULL; } } void init_topology_list(void) { if (topology == NULL) { topology = pcmk__strkey_table(NULL, free_topology_entry); } } char * stonith_level_key(const xmlNode *level, enum fenced_target_by mode) { if (mode == fenced_target_by_unknown) { mode = unpack_level_kind(level); } switch (mode) { case fenced_target_by_name: return crm_element_value_copy(level, PCMK_XA_TARGET); case fenced_target_by_pattern: return crm_element_value_copy(level, PCMK_XA_TARGET_PATTERN); case fenced_target_by_attribute: return crm_strdup_printf("%s=%s", crm_element_value(level, PCMK_XA_TARGET_ATTRIBUTE), crm_element_value(level, PCMK_XA_TARGET_VALUE)); default: return crm_strdup_printf("unknown-%s", ID(level)); } } /*! * \internal * \brief Parse target identification from topology level XML * * \param[in] level Topology level XML to parse * * \return How to identify target of \p level */ static enum fenced_target_by unpack_level_kind(const xmlNode *level) { if (crm_element_value(level, PCMK_XA_TARGET) != NULL) { return fenced_target_by_name; } if (crm_element_value(level, PCMK_XA_TARGET_PATTERN) != NULL) { return fenced_target_by_pattern; } if (!stand_alone /* if standalone, there's no attribute manager */ && (crm_element_value(level, PCMK_XA_TARGET_ATTRIBUTE) != NULL) && (crm_element_value(level, PCMK_XA_TARGET_VALUE) != NULL)) { return fenced_target_by_attribute; } return fenced_target_by_unknown; } static stonith_key_value_t * parse_device_list(const char *devices) { int lpc = 0; int max = 0; int last = 0; stonith_key_value_t *output = NULL; if (devices == NULL) { return output; } max = strlen(devices); for (lpc = 0; lpc <= max; lpc++) { if (devices[lpc] == ',' || devices[lpc] == 0) { char *line = strndup(devices + last, lpc - last); output = stonith_key_value_add(output, NULL, line); free(line); last = lpc + 1; } } return output; } /*! * \internal * \brief Unpack essential information from topology request XML * * \param[in] xml Request XML to search * \param[out] mode If not NULL, where to store level kind * \param[out] target If not NULL, where to store representation of target * \param[out] id If not NULL, where to store level number * \param[out] desc If not NULL, where to store log-friendly level description * * \return Topology level XML from within \p xml, or NULL if not found * \note The caller is responsible for freeing \p *target and \p *desc if set. */ static xmlNode * unpack_level_request(xmlNode *xml, enum fenced_target_by *mode, char **target, int *id, char **desc) { enum fenced_target_by local_mode = fenced_target_by_unknown; char *local_target = NULL; int local_id = 0; /* The level element can be the top element or lower. If top level, don't * search by xpath, because it might give multiple hits if the XML is the * CIB. */ if ((xml != NULL) && !pcmk__xe_is(xml, PCMK_XE_FENCING_LEVEL)) { xml = get_xpath_object("//" PCMK_XE_FENCING_LEVEL, xml, LOG_WARNING); } if (xml == NULL) { if (desc != NULL) { *desc = crm_strdup_printf("missing"); } } else { local_mode = unpack_level_kind(xml); local_target = stonith_level_key(xml, local_mode); crm_element_value_int(xml, PCMK_XA_INDEX, &local_id); if (desc != NULL) { *desc = crm_strdup_printf("%s[%d]", local_target, local_id); } } if (mode != NULL) { *mode = local_mode; } if (id != NULL) { *id = local_id; } if (target != NULL) { *target = local_target; } else { free(local_target); } return xml; } /*! * \internal * \brief Register a fencing topology level for a target * * Given an XML request specifying the target name, level index, and device IDs * for the level, this will create an entry for the target in the global topology * table if one does not already exist, then append the specified device IDs to * the entry's device list for the specified level. * * \param[in] msg XML request for STONITH level registration * \param[out] desc If not NULL, set to string representation "TARGET[LEVEL]" * \param[out] result Where to set result of registration */ void fenced_register_level(xmlNode *msg, char **desc, pcmk__action_result_t *result) { int id = 0; xmlNode *level; enum fenced_target_by mode; char *target; stonith_topology_t *tp; stonith_key_value_t *dIter = NULL; stonith_key_value_t *devices = NULL; CRM_CHECK((msg != NULL) && (result != NULL), return); level = unpack_level_request(msg, &mode, &target, &id, desc); if (level == NULL) { fenced_set_protocol_error(result); return; } // Ensure an ID was given (even the client API adds an ID) if (pcmk__str_empty(ID(level))) { crm_warn("Ignoring registration for topology level without ID"); free(target); crm_log_xml_trace(level, "Bad level"); pcmk__format_result(result, CRM_EX_INVALID_PARAM, PCMK_EXEC_INVALID, "Topology level is invalid without ID"); return; } // Ensure a valid target was specified if (mode == fenced_target_by_unknown) { crm_warn("Ignoring registration for topology level '%s' " "without valid target", ID(level)); free(target); crm_log_xml_trace(level, "Bad level"); pcmk__format_result(result, CRM_EX_INVALID_PARAM, PCMK_EXEC_INVALID, "Invalid target for topology level '%s'", ID(level)); return; } // Ensure level ID is in allowed range if ((id <= 0) || (id >= ST_LEVEL_MAX)) { crm_warn("Ignoring topology registration for %s with invalid level %d", target, id); free(target); crm_log_xml_trace(level, "Bad level"); pcmk__format_result(result, CRM_EX_INVALID_PARAM, PCMK_EXEC_INVALID, "Invalid level number '%s' for topology level '%s'", pcmk__s(crm_element_value(level, PCMK_XA_INDEX), ""), ID(level)); return; } /* Find or create topology table entry */ tp = g_hash_table_lookup(topology, target); if (tp == NULL) { tp = calloc(1, sizeof(stonith_topology_t)); if (tp == NULL) { pcmk__set_result(result, CRM_EX_ERROR, PCMK_EXEC_ERROR, strerror(ENOMEM)); free(target); return; } tp->kind = mode; tp->target = target; tp->target_value = crm_element_value_copy(level, PCMK_XA_TARGET_VALUE); tp->target_pattern = crm_element_value_copy(level, PCMK_XA_TARGET_PATTERN); tp->target_attribute = crm_element_value_copy(level, PCMK_XA_TARGET_ATTRIBUTE); g_hash_table_replace(topology, tp->target, tp); crm_trace("Added %s (%d) to the topology (%d active entries)", target, (int) mode, g_hash_table_size(topology)); } else { free(target); } if (tp->levels[id] != NULL) { crm_info("Adding to the existing %s[%d] topology entry", tp->target, id); } devices = parse_device_list(crm_element_value(level, PCMK_XA_DEVICES)); for (dIter = devices; dIter; dIter = dIter->next) { const char *device = dIter->value; crm_trace("Adding device '%s' for %s[%d]", device, tp->target, id); tp->levels[id] = g_list_append(tp->levels[id], strdup(device)); } stonith_key_value_freeall(devices, 1, 1); { int nlevels = count_active_levels(tp); crm_info("Target %s has %d active fencing level%s", tp->target, nlevels, pcmk__plural_s(nlevels)); } pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); } /*! * \internal * \brief Unregister a fencing topology level for a target * * Given an XML request specifying the target name and level index (or 0 for all * levels), this will remove any corresponding entry for the target from the * global topology table. * * \param[in] msg XML request for STONITH level registration * \param[out] desc If not NULL, set to string representation "TARGET[LEVEL]" * \param[out] result Where to set result of unregistration */ void fenced_unregister_level(xmlNode *msg, char **desc, pcmk__action_result_t *result) { int id = -1; stonith_topology_t *tp; char *target; xmlNode *level = NULL; CRM_CHECK(result != NULL, return); level = unpack_level_request(msg, NULL, &target, &id, desc); if (level == NULL) { fenced_set_protocol_error(result); return; } // Ensure level ID is in allowed range if ((id < 0) || (id >= ST_LEVEL_MAX)) { crm_warn("Ignoring topology unregistration for %s with invalid level %d", target, id); free(target); crm_log_xml_trace(level, "Bad level"); pcmk__format_result(result, CRM_EX_INVALID_PARAM, PCMK_EXEC_INVALID, "Invalid level number '%s' for topology level %s", pcmk__s(crm_element_value(level, PCMK_XA_INDEX), ""), // Client API doesn't add ID to unregistration XML pcmk__s(ID(level), "")); return; } tp = g_hash_table_lookup(topology, target); if (tp == NULL) { guint nentries = g_hash_table_size(topology); crm_info("No fencing topology found for %s (%d active %s)", target, nentries, pcmk__plural_alt(nentries, "entry", "entries")); } else if (id == 0 && g_hash_table_remove(topology, target)) { guint nentries = g_hash_table_size(topology); crm_info("Removed all fencing topology entries related to %s " "(%d active %s remaining)", target, nentries, pcmk__plural_alt(nentries, "entry", "entries")); } else if (tp->levels[id] != NULL) { guint nlevels; g_list_free_full(tp->levels[id], free); tp->levels[id] = NULL; nlevels = count_active_levels(tp); crm_info("Removed level %d from fencing topology for %s " "(%d active level%s remaining)", id, target, nlevels, pcmk__plural_s(nlevels)); } free(target); pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); } static char * list_to_string(GList *list, const char *delim, gboolean terminate_with_delim) { int max = g_list_length(list); size_t delim_len = delim?strlen(delim):0; size_t alloc_size = 1 + (max?((max-1+(terminate_with_delim?1:0))*delim_len):0); char *rv; GList *gIter; for (gIter = list; gIter != NULL; gIter = gIter->next) { const char *value = (const char *) gIter->data; alloc_size += strlen(value); } rv = calloc(alloc_size, sizeof(char)); if (rv) { char *pos = rv; const char *lead_delim = ""; for (gIter = list; gIter != NULL; gIter = gIter->next) { const char *value = (const char *) gIter->data; pos = &pos[sprintf(pos, "%s%s", lead_delim, value)]; lead_delim = delim; } if (max && terminate_with_delim) { sprintf(pos, "%s", delim); } } return rv; } /*! * \internal * \brief Execute a fence agent action directly (and asynchronously) * * Handle a STONITH_OP_EXEC API message by scheduling a requested agent action * directly on a specified device. Only list, monitor, and status actions are * expected to use this call, though it should work with any agent command. * * \param[in] msg Request XML specifying action * \param[out] result Where to store result of action * * \note If the action is monitor, the device must be registered via the API * (CIB registration is not sufficient), because monitor should not be * possible unless the device is "started" (API registered). */ static void execute_agent_action(xmlNode *msg, pcmk__action_result_t *result) { xmlNode *dev = get_xpath_object("//" F_STONITH_DEVICE, msg, LOG_ERR); xmlNode *op = get_xpath_object("//@" F_STONITH_ACTION, msg, LOG_ERR); const char *id = crm_element_value(dev, F_STONITH_DEVICE); const char *action = crm_element_value(op, F_STONITH_ACTION); async_command_t *cmd = NULL; stonith_device_t *device = NULL; if ((id == NULL) || (action == NULL)) { crm_info("Malformed API action request: device %s, action %s", (id? id : "not specified"), (action? action : "not specified")); fenced_set_protocol_error(result); return; } if (pcmk__str_eq(id, STONITH_WATCHDOG_ID, pcmk__str_none)) { // Watchdog agent actions are implemented internally if (stonith_watchdog_timeout_ms <= 0) { pcmk__set_result(result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, "Watchdog fence device not configured"); return; } else if (pcmk__str_eq(action, PCMK_ACTION_LIST, pcmk__str_none)) { pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); pcmk__set_result_output(result, list_to_string(stonith_watchdog_targets, "\n", TRUE), NULL); return; } else if (pcmk__str_eq(action, PCMK_ACTION_MONITOR, pcmk__str_none)) { pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); return; } } device = g_hash_table_lookup(device_list, id); if (device == NULL) { crm_info("Ignoring API '%s' action request because device %s not found", action, id); pcmk__format_result(result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, "'%s' not found", id); return; } else if (!device->api_registered && (strcmp(action, PCMK_ACTION_MONITOR) == 0)) { // Monitors may run only on "started" (API-registered) devices crm_info("Ignoring API '%s' action request because device %s not active", action, id); pcmk__format_result(result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, "'%s' not active", id); return; } cmd = create_async_command(msg); if (cmd == NULL) { crm_log_xml_warn(msg, "invalid"); fenced_set_protocol_error(result); return; } schedule_stonith_command(cmd, device); pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL); } static void search_devices_record_result(struct device_search_s *search, const char *device, gboolean can_fence) { search->replies_received++; if (can_fence && device) { if (search->support_action_only != st_device_supports_none) { stonith_device_t *dev = g_hash_table_lookup(device_list, device); if (dev && !pcmk_is_set(dev->flags, search->support_action_only)) { return; } } search->capable = g_list_append(search->capable, strdup(device)); } if (search->replies_needed == search->replies_received) { guint ndevices = g_list_length(search->capable); crm_debug("Search found %d device%s that can perform '%s' targeting %s", ndevices, pcmk__plural_s(ndevices), (search->action? search->action : "unknown action"), (search->host? search->host : "any node")); search->callback(search->capable, search->user_data); free(search->host); free(search->action); free(search); } } /*! * \internal * \brief Check whether the local host is allowed to execute a fencing action * * \param[in] device Fence device to check * \param[in] action Fence action to check * \param[in] target Hostname of fence target * \param[in] allow_suicide Whether self-fencing is allowed for this operation * * \return TRUE if local host is allowed to execute action, FALSE otherwise */ static gboolean localhost_is_eligible(const stonith_device_t *device, const char *action, const char *target, gboolean allow_suicide) { gboolean localhost_is_target = pcmk__str_eq(target, stonith_our_uname, pcmk__str_casei); if ((device != NULL) && (action != NULL) && (device->on_target_actions != NULL) && (strstr((const char*) device->on_target_actions->str, action) != NULL)) { if (!localhost_is_target) { crm_trace("Operation '%s' using %s can only be executed for local " "host, not %s", action, device->id, target); return FALSE; } } else if (localhost_is_target && !allow_suicide) { crm_trace("'%s' operation does not support self-fencing", action); return FALSE; } return TRUE; } /*! * \internal * \brief Check if local node is allowed to execute (possibly remapped) action * * \param[in] device Fence device to check * \param[in] action Fence action to check * \param[in] target Node name of fence target * \param[in] allow_self Whether self-fencing is allowed for this operation * * \return true if local node is allowed to execute \p action or any actions it * might be remapped to, otherwise false */ static bool localhost_is_eligible_with_remap(const stonith_device_t *device, const char *action, const char *target, gboolean allow_self) { // Check exact action if (localhost_is_eligible(device, action, target, allow_self)) { return true; } // Check potential remaps if (pcmk__str_eq(action, PCMK_ACTION_REBOOT, pcmk__str_none)) { /* "reboot" might get remapped to "off" then "on", so even if reboot is * disallowed, return true if either of those is allowed. We'll report * the disallowed actions with the results. We never allow self-fencing * for remapped "on" actions because the target is off at that point. */ if (localhost_is_eligible(device, PCMK_ACTION_OFF, target, allow_self) || localhost_is_eligible(device, PCMK_ACTION_ON, target, FALSE)) { return true; } } return false; } static void can_fence_host_with_device(stonith_device_t *dev, struct device_search_s *search) { gboolean can = FALSE; const char *check_type = "Internal bug"; const char *target = NULL; const char *alias = NULL; const char *dev_id = "Unspecified device"; const char *action = (search == NULL)? NULL : search->action; CRM_CHECK((dev != NULL) && (action != NULL), goto search_report_results); if (dev->id != NULL) { dev_id = dev->id; } target = search->host; if (target == NULL) { can = TRUE; check_type = "No target"; goto search_report_results; } /* Answer immediately if the device does not support the action * or the local node is not allowed to perform it */ if (pcmk__str_eq(action, PCMK_ACTION_ON, pcmk__str_none) && !pcmk_is_set(dev->flags, st_device_supports_on)) { check_type = "Agent does not support 'on'"; goto search_report_results; } else if (!localhost_is_eligible_with_remap(dev, action, target, search->allow_suicide)) { check_type = "This node is not allowed to execute action"; goto search_report_results; } // Check eligibility as specified by pcmk_host_check check_type = target_list_type(dev); alias = g_hash_table_lookup(dev->aliases, target); if (pcmk__str_eq(check_type, PCMK__VALUE_NONE, pcmk__str_casei)) { can = TRUE; } else if (pcmk__str_eq(check_type, "static-list", pcmk__str_casei)) { if (pcmk__str_in_list(target, dev->targets, pcmk__str_casei)) { can = TRUE; } else if (g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_MAP) && g_hash_table_lookup(dev->aliases, target)) { can = TRUE; } } else if (pcmk__str_eq(check_type, "dynamic-list", pcmk__str_casei)) { time_t now = time(NULL); if (dev->targets == NULL || dev->targets_age + 60 < now) { int device_timeout = get_action_timeout(dev, PCMK_ACTION_LIST, search->per_device_timeout); if (device_timeout > search->per_device_timeout) { crm_notice("Since the pcmk_list_timeout (%ds) parameter of %s " "is larger than " PCMK_OPT_STONITH_TIMEOUT " (%ds), timeout may occur", device_timeout, dev_id, search->per_device_timeout); } crm_trace("Running '%s' to check whether %s is eligible to fence %s (%s)", check_type, dev_id, target, action); schedule_internal_command(__func__, dev, PCMK_ACTION_LIST, NULL, search->per_device_timeout, search, dynamic_list_search_cb); /* we'll respond to this search request async in the cb */ return; } if (pcmk__str_in_list(((alias == NULL)? target : alias), dev->targets, pcmk__str_casei)) { can = TRUE; } } else if (pcmk__str_eq(check_type, "status", pcmk__str_casei)) { int device_timeout = get_action_timeout(dev, check_type, search->per_device_timeout); if (device_timeout > search->per_device_timeout) { crm_notice("Since the pcmk_status_timeout (%ds) parameter of %s is " "larger than " PCMK_OPT_STONITH_TIMEOUT " (%ds), " "timeout may occur", device_timeout, dev_id, search->per_device_timeout); } crm_trace("Running '%s' to check whether %s is eligible to fence %s (%s)", check_type, dev_id, target, action); schedule_internal_command(__func__, dev, PCMK_ACTION_STATUS, target, search->per_device_timeout, search, status_search_cb); /* we'll respond to this search request async in the cb */ return; } else { crm_err("Invalid value for " PCMK_STONITH_HOST_CHECK ": %s", check_type); check_type = "Invalid " PCMK_STONITH_HOST_CHECK; } search_report_results: crm_info("%s is%s eligible to fence (%s) %s%s%s%s: %s", dev_id, (can? "" : " not"), pcmk__s(action, "unspecified action"), pcmk__s(target, "unspecified target"), (alias == NULL)? "" : " (as '", pcmk__s(alias, ""), (alias == NULL)? "" : "')", check_type); search_devices_record_result(search, ((dev == NULL)? NULL : dev_id), can); } static void search_devices(gpointer key, gpointer value, gpointer user_data) { stonith_device_t *dev = value; struct device_search_s *search = user_data; can_fence_host_with_device(dev, search); } #define DEFAULT_QUERY_TIMEOUT 20 static void get_capable_devices(const char *host, const char *action, int timeout, bool suicide, void *user_data, void (*callback) (GList * devices, void *user_data), uint32_t support_action_only) { struct device_search_s *search; guint ndevices = g_hash_table_size(device_list); if (ndevices == 0) { callback(NULL, user_data); return; } search = calloc(1, sizeof(struct device_search_s)); if (!search) { crm_crit("Cannot search for capable fence devices: %s", strerror(ENOMEM)); callback(NULL, user_data); return; } pcmk__str_update(&search->host, host); pcmk__str_update(&search->action, action); search->per_device_timeout = timeout; search->allow_suicide = suicide; search->callback = callback; search->user_data = user_data; search->support_action_only = support_action_only; /* We are guaranteed this many replies, even if a device is * unregistered while the search is in progress. */ search->replies_needed = ndevices; crm_debug("Searching %d device%s to see which can execute '%s' targeting %s", ndevices, pcmk__plural_s(ndevices), (search->action? search->action : "unknown action"), (search->host? search->host : "any node")); g_hash_table_foreach(device_list, search_devices, search); } struct st_query_data { xmlNode *reply; char *remote_peer; char *client_id; char *target; char *action; int call_options; }; /*! * \internal * \brief Add action-specific attributes to query reply XML * * \param[in,out] xml XML to add attributes to * \param[in] action Fence action * \param[in] device Fence device * \param[in] target Fence target */ static void add_action_specific_attributes(xmlNode *xml, const char *action, const stonith_device_t *device, const char *target) { int action_specific_timeout; int delay_max; int delay_base; CRM_CHECK(xml && action && device, return); if (is_action_required(action, device)) { crm_trace("Action '%s' is required using %s", action, device->id); crm_xml_add_int(xml, F_STONITH_DEVICE_REQUIRED, 1); } action_specific_timeout = get_action_timeout(device, action, 0); if (action_specific_timeout) { crm_trace("Action '%s' has timeout %dms using %s", action, action_specific_timeout, device->id); crm_xml_add_int(xml, F_STONITH_ACTION_TIMEOUT, action_specific_timeout); } delay_max = get_action_delay_max(device, action); if (delay_max > 0) { crm_trace("Action '%s' has maximum random delay %ds using %s", action, delay_max, device->id); crm_xml_add_int(xml, F_STONITH_DELAY_MAX, delay_max); } delay_base = get_action_delay_base(device, action, target); if (delay_base > 0) { crm_xml_add_int(xml, F_STONITH_DELAY_BASE, delay_base); } if ((delay_max > 0) && (delay_base == 0)) { crm_trace("Action '%s' has maximum random delay %ds using %s", action, delay_max, device->id); } else if ((delay_max == 0) && (delay_base > 0)) { crm_trace("Action '%s' has a static delay of %ds using %s", action, delay_base, device->id); } else if ((delay_max > 0) && (delay_base > 0)) { crm_trace("Action '%s' has a minimum delay of %ds and a randomly chosen " "maximum delay of %ds using %s", action, delay_base, delay_max, device->id); } } /*! * \internal * \brief Add "disallowed" attribute to query reply XML if appropriate * * \param[in,out] xml XML to add attribute to * \param[in] action Fence action * \param[in] device Fence device * \param[in] target Fence target * \param[in] allow_suicide Whether self-fencing is allowed */ static void add_disallowed(xmlNode *xml, const char *action, const stonith_device_t *device, const char *target, gboolean allow_suicide) { if (!localhost_is_eligible(device, action, target, allow_suicide)) { crm_trace("Action '%s' using %s is disallowed for local host", action, device->id); pcmk__xe_set_bool_attr(xml, F_STONITH_ACTION_DISALLOWED, true); } } /*! * \internal * \brief Add child element with action-specific values to query reply XML * * \param[in,out] xml XML to add attribute to * \param[in] action Fence action * \param[in] device Fence device * \param[in] target Fence target * \param[in] allow_suicide Whether self-fencing is allowed */ static void add_action_reply(xmlNode *xml, const char *action, const stonith_device_t *device, const char *target, gboolean allow_suicide) { xmlNode *child = create_xml_node(xml, F_STONITH_ACTION); crm_xml_add(child, PCMK_XA_ID, action); add_action_specific_attributes(child, action, device, target); add_disallowed(child, action, device, target, allow_suicide); } /*! * \internal * \brief Send a reply to a CPG peer or IPC client * * \param[in] reply XML reply to send * \param[in] call_options Send synchronously if st_opt_sync_call is set * \param[in] remote_peer If not NULL, name of peer node to send CPG reply * \param[in,out] client If not NULL, client to send IPC reply */ static void stonith_send_reply(const xmlNode *reply, int call_options, const char *remote_peer, pcmk__client_t *client) { CRM_CHECK((reply != NULL) && ((remote_peer != NULL) || (client != NULL)), return); if (remote_peer == NULL) { do_local_reply(reply, client, call_options); } else { send_cluster_message(pcmk__get_node(0, remote_peer, NULL, pcmk__node_search_cluster), crm_msg_stonith_ng, reply, FALSE); } } static void stonith_query_capable_device_cb(GList * devices, void *user_data) { struct st_query_data *query = user_data; int available_devices = 0; xmlNode *dev = NULL; xmlNode *list = NULL; GList *lpc = NULL; pcmk__client_t *client = NULL; if (query->client_id != NULL) { client = pcmk__find_client_by_id(query->client_id); if ((client == NULL) && (query->remote_peer == NULL)) { crm_trace("Skipping reply to %s: no longer a client", query->client_id); goto done; } } /* Pack the results into XML */ list = create_xml_node(NULL, __func__); crm_xml_add(list, F_STONITH_TARGET, query->target); for (lpc = devices; lpc != NULL; lpc = lpc->next) { stonith_device_t *device = g_hash_table_lookup(device_list, lpc->data); const char *action = query->action; if (!device) { /* It is possible the device got unregistered while * determining who can fence the target */ continue; } available_devices++; dev = create_xml_node(list, F_STONITH_DEVICE); crm_xml_add(dev, PCMK_XA_ID, device->id); crm_xml_add(dev, "namespace", device->namespace); - crm_xml_add(dev, "agent", device->agent); + crm_xml_add(dev, PCMK_XA_AGENT, device->agent); crm_xml_add_int(dev, F_STONITH_DEVICE_VERIFIED, device->verified); crm_xml_add_int(dev, F_STONITH_DEVICE_SUPPORT_FLAGS, device->flags); /* If the originating fencer wants to reboot the node, and we have a * capable device that doesn't support "reboot", remap to "off" instead. */ if (!pcmk_is_set(device->flags, st_device_supports_reboot) && pcmk__str_eq(query->action, PCMK_ACTION_REBOOT, pcmk__str_none)) { crm_trace("%s doesn't support reboot, using values for off instead", device->id); action = PCMK_ACTION_OFF; } /* Add action-specific values if available */ add_action_specific_attributes(dev, action, device, query->target); if (pcmk__str_eq(query->action, PCMK_ACTION_REBOOT, pcmk__str_none)) { /* A "reboot" *might* get remapped to "off" then "on", so after * sending the "reboot"-specific values in the main element, we add * sub-elements for "off" and "on" values. * * We short-circuited earlier if "reboot", "off" and "on" are all * disallowed for the local host. However if only one or two are * disallowed, we send back the results and mark which ones are * disallowed. If "reboot" is disallowed, this might cause problems * with older fencer versions, which won't check for it. Older * versions will ignore "off" and "on", so they are not a problem. */ add_disallowed(dev, action, device, query->target, pcmk_is_set(query->call_options, st_opt_allow_suicide)); add_action_reply(dev, PCMK_ACTION_OFF, device, query->target, pcmk_is_set(query->call_options, st_opt_allow_suicide)); add_action_reply(dev, PCMK_ACTION_ON, device, query->target, FALSE); } /* A query without a target wants device parameters */ if (query->target == NULL) { xmlNode *attrs = create_xml_node(dev, PCMK__XE_ATTRIBUTES); g_hash_table_foreach(device->params, hash2field, attrs); } } crm_xml_add_int(list, F_STONITH_AVAILABLE_DEVICES, available_devices); if (query->target) { crm_debug("Found %d matching device%s for target '%s'", available_devices, pcmk__plural_s(available_devices), query->target); } else { crm_debug("%d device%s installed", available_devices, pcmk__plural_s(available_devices)); } if (list != NULL) { crm_log_xml_trace(list, "Add query results"); add_message_xml(query->reply, F_STONITH_CALLDATA, list); } stonith_send_reply(query->reply, query->call_options, query->remote_peer, client); done: free_xml(query->reply); free(query->remote_peer); free(query->client_id); free(query->target); free(query->action); free(query); free_xml(list); g_list_free_full(devices, free); } /*! * \internal * \brief Log the result of an asynchronous command * * \param[in] cmd Command the result is for * \param[in] result Result of command * \param[in] pid Process ID of command, if available * \param[in] next Alternate device that will be tried if command failed * \param[in] op_merged Whether this command was merged with an earlier one */ static void log_async_result(const async_command_t *cmd, const pcmk__action_result_t *result, int pid, const char *next, bool op_merged) { int log_level = LOG_ERR; int output_log_level = LOG_NEVER; guint devices_remaining = g_list_length(cmd->next_device_iter); GString *msg = g_string_sized_new(80); // Reasonable starting size // Choose log levels appropriately if we have a result if (pcmk__result_ok(result)) { log_level = (cmd->target == NULL)? LOG_DEBUG : LOG_NOTICE; if ((result->action_stdout != NULL) && !pcmk__str_eq(cmd->action, "metadata", pcmk__str_none)) { output_log_level = LOG_DEBUG; } next = NULL; } else { log_level = (cmd->target == NULL)? LOG_NOTICE : LOG_ERR; if ((result->action_stdout != NULL) && !pcmk__str_eq(cmd->action, "metadata", pcmk__str_none)) { output_log_level = LOG_WARNING; } } // Build the log message piece by piece pcmk__g_strcat(msg, "Operation '", cmd->action, "' ", NULL); if (pid != 0) { g_string_append_printf(msg, "[%d] ", pid); } if (cmd->target != NULL) { pcmk__g_strcat(msg, "targeting ", cmd->target, " ", NULL); } if (cmd->device != NULL) { pcmk__g_strcat(msg, "using ", cmd->device, " ", NULL); } // Add exit status or execution status as appropriate if (result->execution_status == PCMK_EXEC_DONE) { g_string_append_printf(msg, "returned %d", result->exit_status); } else { pcmk__g_strcat(msg, "could not be executed: ", pcmk_exec_status_str(result->execution_status), NULL); } // Add exit reason and next device if appropriate if (result->exit_reason != NULL) { pcmk__g_strcat(msg, " (", result->exit_reason, ")", NULL); } if (next != NULL) { pcmk__g_strcat(msg, ", retrying with ", next, NULL); } if (devices_remaining > 0) { g_string_append_printf(msg, " (%u device%s remaining)", (unsigned int) devices_remaining, pcmk__plural_s(devices_remaining)); } g_string_append_printf(msg, " " CRM_XS " %scall %d from %s", (op_merged? "merged " : ""), cmd->id, cmd->client_name); // Log the result do_crm_log(log_level, "%s", msg->str); g_string_free(msg, TRUE); // Log the output (which may have multiple lines), if appropriate if (output_log_level != LOG_NEVER) { char *prefix = crm_strdup_printf("%s[%d]", cmd->device, pid); crm_log_output(output_log_level, prefix, result->action_stdout); free(prefix); } } /*! * \internal * \brief Reply to requester after asynchronous command completion * * \param[in] cmd Command that completed * \param[in] result Result of command * \param[in] pid Process ID of command, if available * \param[in] merged If true, command was merged with another, not executed */ static void send_async_reply(const async_command_t *cmd, const pcmk__action_result_t *result, int pid, bool merged) { xmlNode *reply = NULL; pcmk__client_t *client = NULL; CRM_CHECK((cmd != NULL) && (result != NULL), return); log_async_result(cmd, result, pid, NULL, merged); if (cmd->client != NULL) { client = pcmk__find_client_by_id(cmd->client); if ((client == NULL) && (cmd->origin == NULL)) { crm_trace("Skipping reply to %s: no longer a client", cmd->client); return; } } reply = construct_async_reply(cmd, result); if (merged) { pcmk__xe_set_bool_attr(reply, F_STONITH_MERGED, true); } if (!stand_alone && pcmk__is_fencing_action(cmd->action) && pcmk__str_eq(cmd->origin, cmd->target, pcmk__str_casei)) { /* The target was also the originator, so broadcast the result on its * behalf (since it will be unable to). */ crm_trace("Broadcast '%s' result for %s (target was also originator)", cmd->action, cmd->target); crm_xml_add(reply, PCMK__XA_SUBT, "broadcast"); crm_xml_add(reply, F_STONITH_OPERATION, T_STONITH_NOTIFY); send_cluster_message(NULL, crm_msg_stonith_ng, reply, FALSE); } else { // Reply only to the originator stonith_send_reply(reply, cmd->options, cmd->origin, client); } crm_log_xml_trace(reply, "Reply"); free_xml(reply); if (stand_alone) { /* Do notification with a clean data object */ xmlNode *notify_data = create_xml_node(NULL, T_STONITH_NOTIFY_FENCE); stonith__xe_set_result(notify_data, result); crm_xml_add(notify_data, F_STONITH_TARGET, cmd->target); crm_xml_add(notify_data, F_STONITH_OPERATION, cmd->op); crm_xml_add(notify_data, F_STONITH_DELEGATE, "localhost"); crm_xml_add(notify_data, F_STONITH_DEVICE, cmd->device); crm_xml_add(notify_data, F_STONITH_REMOTE_OP_ID, cmd->remote_op_id); crm_xml_add(notify_data, F_STONITH_ORIGIN, cmd->client); fenced_send_notification(T_STONITH_NOTIFY_FENCE, result, notify_data); fenced_send_notification(T_STONITH_NOTIFY_HISTORY, NULL, NULL); } } static void cancel_stonith_command(async_command_t * cmd) { stonith_device_t *device = cmd_device(cmd); if (device) { crm_trace("Cancel scheduled '%s' action using %s", cmd->action, device->id); device->pending_ops = g_list_remove(device->pending_ops, cmd); } } /*! * \internal * \brief Cancel and reply to any duplicates of a just-completed operation * * Check whether any fencing operations are scheduled to do the same thing as * one that just succeeded. If so, rather than performing the same operation * twice, return the result of this operation for all matching pending commands. * * \param[in,out] cmd Fencing operation that just succeeded * \param[in] result Result of \p cmd * \param[in] pid If nonzero, process ID of agent invocation (for logs) * * \note Duplicate merging will do the right thing for either type of remapped * reboot. If the executing fencer remapped an unsupported reboot to off, * then cmd->action will be "reboot" and will be merged with any other * reboot requests. If the originating fencer remapped a topology reboot * to off then on, we will get here once with cmd->action "off" and once * with "on", and they will be merged separately with similar requests. */ static void reply_to_duplicates(async_command_t *cmd, const pcmk__action_result_t *result, int pid) { GList *next = NULL; for (GList *iter = cmd_list; iter != NULL; iter = next) { async_command_t *cmd_other = iter->data; next = iter->next; // We might delete this entry, so grab next now if (cmd == cmd_other) { continue; } /* A pending operation matches if: * 1. The client connections are different. * 2. The target is the same. * 3. The fencing action is the same. * 4. The device scheduled to execute the action is the same. */ if (pcmk__str_eq(cmd->client, cmd_other->client, pcmk__str_casei) || !pcmk__str_eq(cmd->target, cmd_other->target, pcmk__str_casei) || !pcmk__str_eq(cmd->action, cmd_other->action, pcmk__str_none) || !pcmk__str_eq(cmd->device, cmd_other->device, pcmk__str_casei)) { continue; } crm_notice("Merging fencing action '%s'%s%s originating from " "client %s with identical fencing request from client %s", cmd_other->action, (cmd_other->target == NULL)? "" : " targeting ", pcmk__s(cmd_other->target, ""), cmd_other->client_name, cmd->client_name); // Stop tracking the duplicate, send its result, and cancel it cmd_list = g_list_remove_link(cmd_list, iter); send_async_reply(cmd_other, result, pid, true); cancel_stonith_command(cmd_other); free_async_command(cmd_other); g_list_free_1(iter); } } /*! * \internal * \brief Return the next required device (if any) for an operation * * \param[in,out] cmd Fencing operation that just succeeded * * \return Next device required for action if any, otherwise NULL */ static stonith_device_t * next_required_device(async_command_t *cmd) { for (GList *iter = cmd->next_device_iter; iter != NULL; iter = iter->next) { stonith_device_t *next_device = g_hash_table_lookup(device_list, iter->data); if (is_action_required(cmd->action, next_device)) { /* This is only called for successful actions, so it's OK to skip * non-required devices. */ cmd->next_device_iter = iter->next; return next_device; } } return NULL; } static void st_child_done(int pid, const pcmk__action_result_t *result, void *user_data) { async_command_t *cmd = user_data; stonith_device_t *device = NULL; stonith_device_t *next_device = NULL; CRM_CHECK(cmd != NULL, return); device = cmd_device(cmd); cmd->active_on = NULL; /* The device is ready to do something else now */ if (device) { if (!device->verified && pcmk__result_ok(result) && pcmk__strcase_any_of(cmd->action, PCMK_ACTION_LIST, PCMK_ACTION_MONITOR, PCMK_ACTION_STATUS, NULL)) { device->verified = TRUE; } mainloop_set_trigger(device->work); } if (pcmk__result_ok(result)) { next_device = next_required_device(cmd); } else if ((cmd->next_device_iter != NULL) && !is_action_required(cmd->action, device)) { /* if this device didn't work out, see if there are any others we can try. * if the failed device was 'required', we can't pick another device. */ next_device = g_hash_table_lookup(device_list, cmd->next_device_iter->data); cmd->next_device_iter = cmd->next_device_iter->next; } if (next_device == NULL) { send_async_reply(cmd, result, pid, false); if (pcmk__result_ok(result)) { reply_to_duplicates(cmd, result, pid); } free_async_command(cmd); } else { // This operation requires more fencing log_async_result(cmd, result, pid, next_device->id, false); schedule_stonith_command(cmd, next_device); } } static gint sort_device_priority(gconstpointer a, gconstpointer b) { const stonith_device_t *dev_a = a; const stonith_device_t *dev_b = b; if (dev_a->priority > dev_b->priority) { return -1; } else if (dev_a->priority < dev_b->priority) { return 1; } return 0; } static void stonith_fence_get_devices_cb(GList * devices, void *user_data) { async_command_t *cmd = user_data; stonith_device_t *device = NULL; guint ndevices = g_list_length(devices); crm_info("Found %d matching device%s for target '%s'", ndevices, pcmk__plural_s(ndevices), cmd->target); if (devices != NULL) { /* Order based on priority */ devices = g_list_sort(devices, sort_device_priority); device = g_hash_table_lookup(device_list, devices->data); } if (device == NULL) { // No device found pcmk__action_result_t result = PCMK__UNKNOWN_RESULT; pcmk__format_result(&result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, "No device configured for target '%s'", cmd->target); send_async_reply(cmd, &result, 0, false); pcmk__reset_result(&result); free_async_command(cmd); g_list_free_full(devices, free); } else { // Device found, schedule it for fencing cmd->device_list = devices; cmd->next_device_iter = devices->next; schedule_stonith_command(cmd, device); } } /*! * \internal * \brief Execute a fence action via the local node * * \param[in] msg Fencing request * \param[out] result Where to store result of fence action */ static void fence_locally(xmlNode *msg, pcmk__action_result_t *result) { const char *device_id = NULL; stonith_device_t *device = NULL; async_command_t *cmd = NULL; xmlNode *dev = NULL; CRM_CHECK((msg != NULL) && (result != NULL), return); dev = get_xpath_object("//@" F_STONITH_TARGET, msg, LOG_ERR); cmd = create_async_command(msg); if (cmd == NULL) { crm_log_xml_warn(msg, "invalid"); fenced_set_protocol_error(result); return; } device_id = crm_element_value(dev, F_STONITH_DEVICE); if (device_id != NULL) { device = g_hash_table_lookup(device_list, device_id); if (device == NULL) { crm_err("Requested device '%s' is not available", device_id); pcmk__format_result(result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, "Requested device '%s' not found", device_id); return; } schedule_stonith_command(cmd, device); } else { const char *host = crm_element_value(dev, F_STONITH_TARGET); if (pcmk_is_set(cmd->options, st_opt_cs_nodeid)) { int nodeid = 0; crm_node_t *node = NULL; pcmk__scan_min_int(host, &nodeid, 0); node = pcmk__search_node_caches(nodeid, NULL, pcmk__node_search_any |pcmk__node_search_known); if (node != NULL) { host = node->uname; } } /* If we get to here, then self-fencing is implicitly allowed */ get_capable_devices(host, cmd->action, cmd->default_timeout, TRUE, cmd, stonith_fence_get_devices_cb, fenced_support_flag(cmd->action)); } pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL); } /*! * \internal * \brief Build an XML reply for a fencing operation * * \param[in] request Request that reply is for * \param[in] data If not NULL, add to reply as call data * \param[in] result Full result of fencing operation * * \return Newly created XML reply * \note The caller is responsible for freeing the result. * \note This has some overlap with construct_async_reply(), but that copies * values from an async_command_t, whereas this one copies them from the * request. */ xmlNode * fenced_construct_reply(const xmlNode *request, xmlNode *data, const pcmk__action_result_t *result) { xmlNode *reply = NULL; reply = create_xml_node(NULL, T_STONITH_REPLY); crm_xml_add(reply, "st_origin", __func__); crm_xml_add(reply, PCMK__XA_T, T_STONITH_NG); stonith__xe_set_result(reply, result); if (request == NULL) { /* Most likely, this is the result of a stonith operation that was * initiated before we came up. Unfortunately that means we lack enough * information to provide clients with a full result. * * @TODO Maybe synchronize this information at start-up? */ crm_warn("Missing request information for client notifications for " "operation with result '%s' (initiated before we came up?)", pcmk_exec_status_str(result->execution_status)); } else { const char *name = NULL; const char *value = NULL; // Attributes to copy from request to reply const char *names[] = { F_STONITH_OPERATION, F_STONITH_CALLID, F_STONITH_CLIENTID, F_STONITH_CLIENTNAME, F_STONITH_REMOTE_OP_ID, F_STONITH_CALLOPTS }; for (int lpc = 0; lpc < PCMK__NELEM(names); lpc++) { name = names[lpc]; value = crm_element_value(request, name); crm_xml_add(reply, name, value); } if (data != NULL) { add_message_xml(reply, F_STONITH_CALLDATA, data); } } return reply; } /*! * \internal * \brief Build an XML reply to an asynchronous fencing command * * \param[in] cmd Fencing command that reply is for * \param[in] result Command result */ static xmlNode * construct_async_reply(const async_command_t *cmd, const pcmk__action_result_t *result) { xmlNode *reply = create_xml_node(NULL, T_STONITH_REPLY); crm_xml_add(reply, "st_origin", __func__); crm_xml_add(reply, PCMK__XA_T, T_STONITH_NG); crm_xml_add(reply, F_STONITH_OPERATION, cmd->op); crm_xml_add(reply, F_STONITH_DEVICE, cmd->device); crm_xml_add(reply, F_STONITH_REMOTE_OP_ID, cmd->remote_op_id); crm_xml_add(reply, F_STONITH_CLIENTID, cmd->client); crm_xml_add(reply, F_STONITH_CLIENTNAME, cmd->client_name); crm_xml_add(reply, F_STONITH_TARGET, cmd->target); crm_xml_add(reply, F_STONITH_ACTION, cmd->op); crm_xml_add(reply, F_STONITH_ORIGIN, cmd->origin); crm_xml_add_int(reply, F_STONITH_CALLID, cmd->id); crm_xml_add_int(reply, F_STONITH_CALLOPTS, cmd->options); stonith__xe_set_result(reply, result); return reply; } bool fencing_peer_active(crm_node_t *peer) { if (peer == NULL) { return FALSE; } else if (peer->uname == NULL) { return FALSE; } else if (pcmk_is_set(peer->processes, crm_get_cluster_proc())) { return TRUE; } return FALSE; } void set_fencing_completed(remote_fencing_op_t *op) { struct timespec tv; qb_util_timespec_from_epoch_get(&tv); op->completed = tv.tv_sec; op->completed_nsec = tv.tv_nsec; } /*! * \internal * \brief Look for alternate node needed if local node shouldn't fence target * * \param[in] target Node that must be fenced * * \return Name of an alternate node that should fence \p target if any, * or NULL otherwise */ static const char * check_alternate_host(const char *target) { if (pcmk__str_eq(target, stonith_our_uname, pcmk__str_casei)) { GHashTableIter gIter; crm_node_t *entry = NULL; g_hash_table_iter_init(&gIter, crm_peer_cache); while (g_hash_table_iter_next(&gIter, NULL, (void **)&entry)) { if (fencing_peer_active(entry) && !pcmk__str_eq(entry->uname, target, pcmk__str_casei)) { crm_notice("Forwarding self-fencing request to %s", entry->uname); return entry->uname; } } crm_warn("Will handle own fencing because no peer can"); } return NULL; } static void remove_relay_op(xmlNode * request) { xmlNode *dev = get_xpath_object("//@" F_STONITH_ACTION, request, LOG_TRACE); const char *relay_op_id = NULL; const char *op_id = NULL; const char *client_name = NULL; const char *target = NULL; remote_fencing_op_t *relay_op = NULL; if (dev) { target = crm_element_value(dev, F_STONITH_TARGET); } relay_op_id = crm_element_value(request, F_STONITH_REMOTE_OP_ID_RELAY); op_id = crm_element_value(request, F_STONITH_REMOTE_OP_ID); client_name = crm_element_value(request, F_STONITH_CLIENTNAME); /* Delete RELAY operation. */ if (relay_op_id && target && pcmk__str_eq(target, stonith_our_uname, pcmk__str_casei)) { relay_op = g_hash_table_lookup(stonith_remote_op_list, relay_op_id); if (relay_op) { GHashTableIter iter; remote_fencing_op_t *list_op = NULL; g_hash_table_iter_init(&iter, stonith_remote_op_list); /* If the operation to be deleted is registered as a duplicate, delete the registration. */ while (g_hash_table_iter_next(&iter, NULL, (void **)&list_op)) { GList *dup_iter = NULL; if (list_op != relay_op) { for (dup_iter = list_op->duplicates; dup_iter != NULL; dup_iter = dup_iter->next) { remote_fencing_op_t *other = dup_iter->data; if (other == relay_op) { other->duplicates = g_list_remove(other->duplicates, relay_op); break; } } } } crm_debug("Deleting relay op %s ('%s'%s%s for %s), " "replaced by op %s ('%s'%s%s for %s)", relay_op->id, relay_op->action, (relay_op->target == NULL)? "" : " targeting ", pcmk__s(relay_op->target, ""), relay_op->client_name, op_id, relay_op->action, (target == NULL)? "" : " targeting ", pcmk__s(target, ""), client_name); g_hash_table_remove(stonith_remote_op_list, relay_op_id); } } } /*! * \internal * \brief Check whether an API request was sent by a privileged user * * API commands related to fencing configuration may be done only by privileged * IPC users (i.e. root or hacluster), because all other users should go through * the CIB to have ACLs applied. If no client was given, this is a peer request, * which is always allowed. * * \param[in] c IPC client that sent request (or NULL if sent by CPG peer) * \param[in] op Requested API operation (for logging only) * * \return true if sender is peer or privileged client, otherwise false */ static inline bool is_privileged(const pcmk__client_t *c, const char *op) { if ((c == NULL) || pcmk_is_set(c->flags, pcmk__client_privileged)) { return true; } else { crm_warn("Rejecting IPC request '%s' from unprivileged client %s", pcmk__s(op, ""), pcmk__client_name(c)); return false; } } // CRM_OP_REGISTER static xmlNode * handle_register_request(pcmk__request_t *request) { xmlNode *reply = create_xml_node(NULL, "reply"); CRM_ASSERT(request->ipc_client != NULL); crm_xml_add(reply, F_STONITH_OPERATION, CRM_OP_REGISTER); crm_xml_add(reply, F_STONITH_CLIENTID, request->ipc_client->id); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); pcmk__set_request_flags(request, pcmk__request_reuse_options); return reply; } // STONITH_OP_EXEC static xmlNode * handle_agent_request(pcmk__request_t *request) { execute_agent_action(request->xml, &request->result); if (request->result.execution_status == PCMK_EXEC_PENDING) { return NULL; } return fenced_construct_reply(request->xml, NULL, &request->result); } // STONITH_OP_TIMEOUT_UPDATE static xmlNode * handle_update_timeout_request(pcmk__request_t *request) { const char *call_id = crm_element_value(request->xml, F_STONITH_CALLID); const char *client_id = crm_element_value(request->xml, F_STONITH_CLIENTID); int op_timeout = 0; crm_element_value_int(request->xml, F_STONITH_TIMEOUT, &op_timeout); do_stonith_async_timeout_update(client_id, call_id, op_timeout); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); return NULL; } // STONITH_OP_QUERY static xmlNode * handle_query_request(pcmk__request_t *request) { int timeout = 0; xmlNode *dev = NULL; const char *action = NULL; const char *target = NULL; const char *client_id = crm_element_value(request->xml, F_STONITH_CLIENTID); struct st_query_data *query = NULL; if (request->peer != NULL) { // Record it for the future notification create_remote_stonith_op(client_id, request->xml, TRUE); } /* Delete the DC node RELAY operation. */ remove_relay_op(request->xml); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); dev = get_xpath_object("//@" F_STONITH_ACTION, request->xml, LOG_NEVER); if (dev != NULL) { const char *device = crm_element_value(dev, F_STONITH_DEVICE); if (pcmk__str_eq(device, "manual_ack", pcmk__str_casei)) { return NULL; // No query or reply necessary } target = crm_element_value(dev, F_STONITH_TARGET); action = crm_element_value(dev, F_STONITH_ACTION); } crm_log_xml_trace(request->xml, "Query"); query = calloc(1, sizeof(struct st_query_data)); CRM_ASSERT(query != NULL); query->reply = fenced_construct_reply(request->xml, NULL, &request->result); pcmk__str_update(&query->remote_peer, request->peer); pcmk__str_update(&query->client_id, client_id); pcmk__str_update(&query->target, target); pcmk__str_update(&query->action, action); query->call_options = request->call_options; crm_element_value_int(request->xml, F_STONITH_TIMEOUT, &timeout); get_capable_devices(target, action, timeout, pcmk_is_set(query->call_options, st_opt_allow_suicide), query, stonith_query_capable_device_cb, st_device_supports_none); return NULL; } // T_STONITH_NOTIFY static xmlNode * handle_notify_request(pcmk__request_t *request) { const char *flag_name = NULL; CRM_ASSERT(request->ipc_client != NULL); flag_name = crm_element_value(request->xml, F_STONITH_NOTIFY_ACTIVATE); if (flag_name != NULL) { crm_debug("Enabling %s callbacks for client %s", flag_name, pcmk__request_origin(request)); pcmk__set_client_flags(request->ipc_client, get_stonith_flag(flag_name)); } flag_name = crm_element_value(request->xml, F_STONITH_NOTIFY_DEACTIVATE); if (flag_name != NULL) { crm_debug("Disabling %s callbacks for client %s", flag_name, pcmk__request_origin(request)); pcmk__clear_client_flags(request->ipc_client, get_stonith_flag(flag_name)); } pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); pcmk__set_request_flags(request, pcmk__request_reuse_options); return pcmk__ipc_create_ack(request->ipc_flags, "ack", NULL, CRM_EX_OK); } // STONITH_OP_RELAY static xmlNode * handle_relay_request(pcmk__request_t *request) { xmlNode *dev = get_xpath_object("//@" F_STONITH_TARGET, request->xml, LOG_TRACE); crm_notice("Received forwarded fencing request from " "%s %s to fence (%s) peer %s", pcmk__request_origin_type(request), pcmk__request_origin(request), crm_element_value(dev, F_STONITH_ACTION), crm_element_value(dev, F_STONITH_TARGET)); if (initiate_remote_stonith_op(NULL, request->xml, FALSE) == NULL) { fenced_set_protocol_error(&request->result); return fenced_construct_reply(request->xml, NULL, &request->result); } pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL); return NULL; } // STONITH_OP_FENCE static xmlNode * handle_fence_request(pcmk__request_t *request) { if ((request->peer != NULL) || stand_alone) { fence_locally(request->xml, &request->result); } else if (pcmk_is_set(request->call_options, st_opt_manual_ack)) { switch (fenced_handle_manual_confirmation(request->ipc_client, request->xml)) { case pcmk_rc_ok: pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); break; case EINPROGRESS: pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL); break; default: fenced_set_protocol_error(&request->result); break; } } else { const char *alternate_host = NULL; xmlNode *dev = get_xpath_object("//@" F_STONITH_TARGET, request->xml, LOG_TRACE); const char *target = crm_element_value(dev, F_STONITH_TARGET); const char *action = crm_element_value(dev, F_STONITH_ACTION); const char *device = crm_element_value(dev, F_STONITH_DEVICE); if (request->ipc_client != NULL) { int tolerance = 0; crm_notice("Client %s wants to fence (%s) %s using %s", pcmk__request_origin(request), action, target, (device? device : "any device")); crm_element_value_int(dev, F_STONITH_TOLERANCE, &tolerance); if (stonith_check_fence_tolerance(tolerance, target, action)) { pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); return fenced_construct_reply(request->xml, NULL, &request->result); } alternate_host = check_alternate_host(target); } else { crm_notice("Peer %s wants to fence (%s) '%s' with device '%s'", request->peer, action, target, (device == NULL)? "(any)" : device); } if (alternate_host != NULL) { const char *client_id = NULL; remote_fencing_op_t *op = NULL; if (request->ipc_client->id == 0) { client_id = crm_element_value(request->xml, F_STONITH_CLIENTID); } else { client_id = request->ipc_client->id; } /* Create a duplicate fencing operation to relay with the client ID. * When a query response is received, this operation should be * deleted to avoid keeping the duplicate around. */ op = create_remote_stonith_op(client_id, request->xml, FALSE); crm_xml_add(request->xml, F_STONITH_OPERATION, STONITH_OP_RELAY); crm_xml_add(request->xml, F_STONITH_CLIENTID, request->ipc_client->id); crm_xml_add(request->xml, F_STONITH_REMOTE_OP_ID, op->id); send_cluster_message(pcmk__get_node(0, alternate_host, NULL, pcmk__node_search_cluster), crm_msg_stonith_ng, request->xml, FALSE); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL); } else if (initiate_remote_stonith_op(request->ipc_client, request->xml, FALSE) == NULL) { fenced_set_protocol_error(&request->result); } else { pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL); } } if (request->result.execution_status == PCMK_EXEC_PENDING) { return NULL; } return fenced_construct_reply(request->xml, NULL, &request->result); } // STONITH_OP_FENCE_HISTORY static xmlNode * handle_history_request(pcmk__request_t *request) { xmlNode *reply = NULL; xmlNode *data = NULL; stonith_fence_history(request->xml, &data, request->peer, request->call_options); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); if (!pcmk_is_set(request->call_options, st_opt_discard_reply)) { /* When the local node broadcasts its history, it sets * st_opt_discard_reply and doesn't need a reply. */ reply = fenced_construct_reply(request->xml, data, &request->result); } free_xml(data); return reply; } // STONITH_OP_DEVICE_ADD static xmlNode * handle_device_add_request(pcmk__request_t *request) { const char *op = crm_element_value(request->xml, F_STONITH_OPERATION); xmlNode *dev = get_xpath_object("//" F_STONITH_DEVICE, request->xml, LOG_ERR); if (is_privileged(request->ipc_client, op)) { int rc = stonith_device_register(dev, FALSE); pcmk__set_result(&request->result, ((rc == pcmk_ok)? CRM_EX_OK : CRM_EX_ERROR), stonith__legacy2status(rc), ((rc == pcmk_ok)? NULL : pcmk_strerror(rc))); } else { pcmk__set_result(&request->result, CRM_EX_INSUFFICIENT_PRIV, PCMK_EXEC_INVALID, "Unprivileged users must register device via CIB"); } fenced_send_device_notification(op, &request->result, (dev == NULL)? NULL : ID(dev)); return fenced_construct_reply(request->xml, NULL, &request->result); } // STONITH_OP_DEVICE_DEL static xmlNode * handle_device_delete_request(pcmk__request_t *request) { xmlNode *dev = get_xpath_object("//" F_STONITH_DEVICE, request->xml, LOG_ERR); const char *device_id = crm_element_value(dev, PCMK_XA_ID); const char *op = crm_element_value(request->xml, F_STONITH_OPERATION); if (is_privileged(request->ipc_client, op)) { stonith_device_remove(device_id, false); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); } else { pcmk__set_result(&request->result, CRM_EX_INSUFFICIENT_PRIV, PCMK_EXEC_INVALID, "Unprivileged users must delete device via CIB"); } fenced_send_device_notification(op, &request->result, device_id); return fenced_construct_reply(request->xml, NULL, &request->result); } // STONITH_OP_LEVEL_ADD static xmlNode * handle_level_add_request(pcmk__request_t *request) { char *desc = NULL; const char *op = crm_element_value(request->xml, F_STONITH_OPERATION); if (is_privileged(request->ipc_client, op)) { fenced_register_level(request->xml, &desc, &request->result); } else { unpack_level_request(request->xml, NULL, NULL, NULL, &desc); pcmk__set_result(&request->result, CRM_EX_INSUFFICIENT_PRIV, PCMK_EXEC_INVALID, "Unprivileged users must add level via CIB"); } fenced_send_level_notification(op, &request->result, desc); free(desc); return fenced_construct_reply(request->xml, NULL, &request->result); } // STONITH_OP_LEVEL_DEL static xmlNode * handle_level_delete_request(pcmk__request_t *request) { char *desc = NULL; const char *op = crm_element_value(request->xml, F_STONITH_OPERATION); if (is_privileged(request->ipc_client, op)) { fenced_unregister_level(request->xml, &desc, &request->result); } else { unpack_level_request(request->xml, NULL, NULL, NULL, &desc); pcmk__set_result(&request->result, CRM_EX_INSUFFICIENT_PRIV, PCMK_EXEC_INVALID, "Unprivileged users must delete level via CIB"); } fenced_send_level_notification(op, &request->result, desc); free(desc); return fenced_construct_reply(request->xml, NULL, &request->result); } // CRM_OP_RM_NODE_CACHE static xmlNode * handle_cache_request(pcmk__request_t *request) { int node_id = 0; const char *name = NULL; crm_element_value_int(request->xml, PCMK_XA_ID, &node_id); name = crm_element_value(request->xml, PCMK_XA_UNAME); reap_crm_member(node_id, name); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); return NULL; } static xmlNode * handle_unknown_request(pcmk__request_t *request) { crm_err("Unknown IPC request %s from %s %s", request->op, pcmk__request_origin_type(request), pcmk__request_origin(request)); pcmk__format_result(&request->result, CRM_EX_PROTOCOL, PCMK_EXEC_INVALID, "Unknown IPC request type '%s' (bug?)", request->op); return fenced_construct_reply(request->xml, NULL, &request->result); } static void fenced_register_handlers(void) { pcmk__server_command_t handlers[] = { { CRM_OP_REGISTER, handle_register_request }, { STONITH_OP_EXEC, handle_agent_request }, { STONITH_OP_TIMEOUT_UPDATE, handle_update_timeout_request }, { STONITH_OP_QUERY, handle_query_request }, { T_STONITH_NOTIFY, handle_notify_request }, { STONITH_OP_RELAY, handle_relay_request }, { STONITH_OP_FENCE, handle_fence_request }, { STONITH_OP_FENCE_HISTORY, handle_history_request }, { STONITH_OP_DEVICE_ADD, handle_device_add_request }, { STONITH_OP_DEVICE_DEL, handle_device_delete_request }, { STONITH_OP_LEVEL_ADD, handle_level_add_request }, { STONITH_OP_LEVEL_DEL, handle_level_delete_request }, { CRM_OP_RM_NODE_CACHE, handle_cache_request }, { NULL, handle_unknown_request }, }; fenced_handlers = pcmk__register_handlers(handlers); } void fenced_unregister_handlers(void) { if (fenced_handlers != NULL) { g_hash_table_destroy(fenced_handlers); fenced_handlers = NULL; } } static void handle_request(pcmk__request_t *request) { xmlNode *reply = NULL; const char *reason = NULL; if (fenced_handlers == NULL) { fenced_register_handlers(); } reply = pcmk__process_request(request, fenced_handlers); if (reply != NULL) { if (pcmk_is_set(request->flags, pcmk__request_reuse_options) && (request->ipc_client != NULL)) { /* Certain IPC-only commands must reuse the call options from the * original request rather than the ones set by stonith_send_reply() * -> do_local_reply(). */ pcmk__ipc_send_xml(request->ipc_client, request->ipc_id, reply, request->ipc_flags); request->ipc_client->request_id = 0; } else { stonith_send_reply(reply, request->call_options, request->peer, request->ipc_client); } free_xml(reply); } reason = request->result.exit_reason; crm_debug("Processed %s request from %s %s: %s%s%s%s", request->op, pcmk__request_origin_type(request), pcmk__request_origin(request), pcmk_exec_status_str(request->result.execution_status), (reason == NULL)? "" : " (", (reason == NULL)? "" : reason, (reason == NULL)? "" : ")"); } static void handle_reply(pcmk__client_t *client, xmlNode *request, const char *remote_peer) { // Copy, because request might be freed before we want to log this char *op = crm_element_value_copy(request, F_STONITH_OPERATION); if (pcmk__str_eq(op, STONITH_OP_QUERY, pcmk__str_none)) { process_remote_stonith_query(request); } else if (pcmk__str_any_of(op, T_STONITH_NOTIFY, STONITH_OP_FENCE, NULL)) { fenced_process_fencing_reply(request); } else { crm_err("Ignoring unknown %s reply from %s %s", pcmk__s(op, "untyped"), ((client == NULL)? "peer" : "client"), ((client == NULL)? remote_peer : pcmk__client_name(client))); crm_log_xml_warn(request, "UnknownOp"); free(op); return; } crm_debug("Processed %s reply from %s %s", op, ((client == NULL)? "peer" : "client"), ((client == NULL)? remote_peer : pcmk__client_name(client))); free(op); } /*! * \internal * \brief Handle a message from an IPC client or CPG peer * * \param[in,out] client If not NULL, IPC client that sent message * \param[in] id If from IPC client, IPC message ID * \param[in] flags Message flags * \param[in,out] message Message XML * \param[in] remote_peer If not NULL, CPG peer that sent message */ void stonith_command(pcmk__client_t *client, uint32_t id, uint32_t flags, xmlNode *message, const char *remote_peer) { int call_options = st_opt_none; bool is_reply = false; CRM_CHECK(message != NULL, return); if (get_xpath_object("//" T_STONITH_REPLY, message, LOG_NEVER) != NULL) { is_reply = true; } crm_element_value_int(message, F_STONITH_CALLOPTS, &call_options); crm_debug("Processing %ssynchronous %s %s %u from %s %s", pcmk_is_set(call_options, st_opt_sync_call)? "" : "a", crm_element_value(message, F_STONITH_OPERATION), (is_reply? "reply" : "request"), id, ((client == NULL)? "peer" : "client"), ((client == NULL)? remote_peer : pcmk__client_name(client))); if (pcmk_is_set(call_options, st_opt_sync_call)) { CRM_ASSERT(client == NULL || client->request_id == id); } if (is_reply) { handle_reply(client, message, remote_peer); } else { pcmk__request_t request = { .ipc_client = client, .ipc_id = id, .ipc_flags = flags, .peer = remote_peer, .xml = message, .call_options = call_options, .result = PCMK__UNKNOWN_RESULT, }; request.op = crm_element_value_copy(request.xml, F_STONITH_OPERATION); CRM_CHECK(request.op != NULL, return); if (pcmk_is_set(request.call_options, st_opt_sync_call)) { pcmk__set_request_flags(&request, pcmk__request_sync); } handle_request(&request); pcmk__reset_request(&request); } } diff --git a/include/crm/common/options.h b/include/crm/common/options.h index 2b4f23f9f6..e5c0a7f5b4 100644 --- a/include/crm/common/options.h +++ b/include/crm/common/options.h @@ -1,196 +1,198 @@ /* * Copyright 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_OPTIONS__H # define PCMK__CRM_COMMON_OPTIONS__H #ifdef __cplusplus extern "C" { #endif /** * \file * \brief API related to options * \ingroup core */ /* * Cluster options */ #define PCMK_OPT_BATCH_LIMIT "batch-limit" #define PCMK_OPT_CLUSTER_DELAY "cluster-delay" #define PCMK_OPT_CLUSTER_INFRASTRUCTURE "cluster-infrastructure" #define PCMK_OPT_CLUSTER_IPC_LIMIT "cluster-ipc-limit" #define PCMK_OPT_CLUSTER_NAME "cluster-name" #define PCMK_OPT_CLUSTER_RECHECK_INTERVAL "cluster-recheck-interval" #define PCMK_OPT_CONCURRENT_FENCING "concurrent-fencing" #define PCMK_OPT_DC_DEADTIME "dc-deadtime" #define PCMK_OPT_DC_VERSION "dc-version" #define PCMK_OPT_ELECTION_TIMEOUT "election-timeout" #define PCMK_OPT_ENABLE_ACL "enable-acl" #define PCMK_OPT_ENABLE_STARTUP_PROBES "enable-startup-probes" #define PCMK_OPT_FENCE_REACTION "fence-reaction" #define PCMK_OPT_HAVE_WATCHDOG "have-watchdog" #define PCMK_OPT_JOIN_FINALIZATION_TIMEOUT "join-finalization-timeout" #define PCMK_OPT_JOIN_INTEGRATION_TIMEOUT "join-integration-timeout" #define PCMK_OPT_LOAD_THRESHOLD "load-threshold" #define PCMK_OPT_MAINTENANCE_MODE "maintenance-mode" #define PCMK_OPT_MIGRATION_LIMIT "migration-limit" #define PCMK_OPT_NO_QUORUM_POLICY "no-quorum-policy" #define PCMK_OPT_NODE_ACTION_LIMIT "node-action-limit" #define PCMK_OPT_NODE_HEALTH_BASE "node-health-base" #define PCMK_OPT_NODE_HEALTH_GREEN "node-health-green" #define PCMK_OPT_NODE_HEALTH_RED "node-health-red" #define PCMK_OPT_NODE_HEALTH_STRATEGY "node-health-strategy" #define PCMK_OPT_NODE_HEALTH_YELLOW "node-health-yellow" #define PCMK_OPT_NODE_PENDING_TIMEOUT "node-pending-timeout" #define PCMK_OPT_PE_ERROR_SERIES_MAX "pe-error-series-max" #define PCMK_OPT_PE_INPUT_SERIES_MAX "pe-input-series-max" #define PCMK_OPT_PE_WARN_SERIES_MAX "pe-warn-series-max" #define PCMK_OPT_PLACEMENT_STRATEGY "placement-strategy" #define PCMK_OPT_PRIORITY_FENCING_DELAY "priority-fencing-delay" #define PCMK_OPT_SHUTDOWN_ESCALATION "shutdown-escalation" #define PCMK_OPT_SHUTDOWN_LOCK "shutdown-lock" #define PCMK_OPT_SHUTDOWN_LOCK_LIMIT "shutdown-lock-limit" #define PCMK_OPT_START_FAILURE_IS_FATAL "start-failure-is-fatal" #define PCMK_OPT_STARTUP_FENCING "startup-fencing" #define PCMK_OPT_STONITH_ACTION "stonith-action" #define PCMK_OPT_STONITH_ENABLED "stonith-enabled" #define PCMK_OPT_STONITH_MAX_ATTEMPTS "stonith-max-attempts" #define PCMK_OPT_STONITH_TIMEOUT "stonith-timeout" #define PCMK_OPT_STONITH_WATCHDOG_TIMEOUT "stonith-watchdog-timeout" #define PCMK_OPT_STOP_ALL_RESOURCES "stop-all-resources" #define PCMK_OPT_STOP_ORPHAN_ACTIONS "stop-orphan-actions" #define PCMK_OPT_STOP_ORPHAN_RESOURCES "stop-orphan-resources" #define PCMK_OPT_SYMMETRIC_CLUSTER "symmetric-cluster" #define PCMK_OPT_TRANSITION_DELAY "transition-delay" /* * Meta-attributes */ #define PCMK_META_ALLOW_MIGRATE "allow-migrate" #define PCMK_META_ALLOW_UNHEALTHY_NODES "allow-unhealthy-nodes" #define PCMK_META_CLONE_MAX "clone-max" #define PCMK_META_CLONE_MIN "clone-min" #define PCMK_META_CLONE_NODE_MAX "clone-node-max" #define PCMK_META_CONTAINER_ATTR_TARGET "container-attribute-target" #define PCMK_META_CRITICAL "critical" #define PCMK_META_ENABLED "enabled" #define PCMK_META_FAILURE_TIMEOUT "failure-timeout" #define PCMK_META_GLOBALLY_UNIQUE "globally-unique" #define PCMK_META_INTERLEAVE "interleave" #define PCMK_META_INTERVAL "interval" #define PCMK_META_IS_MANAGED "is-managed" #define PCMK_META_INTERVAL_ORIGIN "interval-origin" #define PCMK_META_MAINTENANCE "maintenance" #define PCMK_META_MIGRATION_THRESHOLD "migration-threshold" #define PCMK_META_MULTIPLE_ACTIVE "multiple-active" #define PCMK_META_NOTIFY "notify" #define PCMK_META_ON_FAIL "on-fail" #define PCMK_META_ORDERED "ordered" #define PCMK_META_PRIORITY "priority" #define PCMK_META_PROMOTABLE "promotable" #define PCMK_META_PROMOTED_MAX "promoted-max" #define PCMK_META_PROMOTED_NODE_MAX "promoted-node-max" #define PCMK_META_RECORD_PENDING "record-pending" #define PCMK_META_REMOTE_ADDR "remote-addr" #define PCMK_META_REMOTE_ALLOW_MIGRATE "remote-allow-migrate" #define PCMK_META_REMOTE_CONNECT_TIMEOUT "remote-connect-timeout" #define PCMK_META_REMOTE_NODE "remote-node" #define PCMK_META_REMOTE_PORT "remote-port" #define PCMK_META_REQUIRES "requires" #define PCMK_META_RESOURCE_STICKINESS "resource-stickiness" #define PCMK_META_START_DELAY "start-delay" #define PCMK_META_TARGET_ROLE "target-role" #define PCMK_META_TIMEOUT "timeout" #define PCMK_META_TIMESTAMP_FORMAT "timestamp-format" /* * Remote resource instance attributes */ #define PCMK_REMOTE_RA_ADDR "addr" #define PCMK_REMOTE_RA_PORT "port" #define PCMK_REMOTE_RA_RECONNECT_INTERVAL "reconnect_interval" #define PCMK_REMOTE_RA_SERVER "server" /* * Enumerated values */ #define PCMK_VALUE_ALWAYS "always" #define PCMK_VALUE_AND "and" #define PCMK_VALUE_BALANCED "balanced" #define PCMK_VALUE_BLOCK "block" #define PCMK_VALUE_CIB_BOOTSTRAP_OPTIONS "cib-bootstrap-options" #define PCMK_VALUE_DATE_SPEC "date_spec" #define PCMK_VALUE_DEFAULT "default" #define PCMK_VALUE_DEFINED "defined" #define PCMK_VALUE_DEMOTE "demote" #define PCMK_VALUE_DENY "deny" #define PCMK_VALUE_EQ "eq" #define PCMK_VALUE_EXCLUSIVE "exclusive" #define PCMK_VALUE_FAILED "failed" #define PCMK_VALUE_FALSE "false" #define PCMK_VALUE_FENCE "fence" #define PCMK_VALUE_FREEZE "freeze" #define PCMK_VALUE_GRANTED "granted" #define PCMK_VALUE_GREEN "green" #define PCMK_VALUE_GT "gt" #define PCMK_VALUE_GTE "gte" +#define PCMK_VALUE_HOST "host" #define PCMK_VALUE_IGNORE "ignore" #define PCMK_VALUE_INTEGER "integer" #define PCMK_VALUE_LITERAL "literal" #define PCMK_VALUE_LT "lt" #define PCMK_VALUE_LTE "lte" #define PCMK_VALUE_MANDATORY "Mandatory" #define PCMK_VALUE_MEMBER "member" #define PCMK_VALUE_META "meta" #define PCMK_VALUE_MINIMAL "minimal" #define PCMK_VALUE_NE "ne" #define PCMK_VALUE_NEVER "never" #define PCMK_VALUE_NOT_DEFINED "not_defined" #define PCMK_VALUE_NUMBER "number" #define PCMK_VALUE_ONLINE "online" #define PCMK_VALUE_OPTIONAL "Optional" #define PCMK_VALUE_OR "or" +#define PCMK_VALUE_PANIC "panic" #define PCMK_VALUE_PARAM "param" #define PCMK_VALUE_PENDING "pending" #define PCMK_VALUE_READ "read" #define PCMK_VALUE_RED "red" #define PCMK_VALUE_REMOTE "remote" #define PCMK_VALUE_RESTART "restart" #define PCMK_VALUE_RESTART_CONTAINER "restart-container" #define PCMK_VALUE_REVOKED "revoked" #define PCMK_VALUE_SERIALIZE "Serialize" #define PCMK_VALUE_STANDBY "standby" #define PCMK_VALUE_STRING "string" #define PCMK_VALUE_STOP "stop" #define PCMK_VALUE_SUCCESS "success" #define PCMK_VALUE_TRUE "true" #define PCMK_VALUE_UNKNOWN "unknown" #define PCMK_VALUE_UTILIZATION "utilization" #define PCMK_VALUE_VERSION "version" #define PCMK_VALUE_WRITE "write" #define PCMK_VALUE_YELLOW "yellow" // @COMPAT This will become a deprecated alias for PCMK_VALUE_FENCE (see T279) #define PCMK_VALUE_FENCE_LEGACY "suicide" #ifdef __cplusplus } #endif #endif // PCMK__CRM_COMMON_OPTIONS__H diff --git a/include/crm/msg_xml.h b/include/crm/msg_xml.h index 97e69d6de1..3840175d4f 100644 --- a/include/crm/msg_xml.h +++ b/include/crm/msg_xml.h @@ -1,314 +1,363 @@ /* * 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_MSG_XML__H # define PCMK__CRM_MSG_XML__H # include #if !defined(PCMK_ALLOW_DEPRECATED) || (PCMK_ALLOW_DEPRECATED == 1) #include #endif #ifdef __cplusplus extern "C" { #endif /* This file defines constants for various XML syntax (mainly element and * attribute names). * * For consistency, new constants should start with "PCMK_", followed by: * * "XE" for XML element names * * "XA" for XML attribute names * * "OPT" for cluster option (property) names * * "META" for meta-attribute names * * "VALUE" for enumerated values for various options * * Old names that don't follow this policy should eventually be deprecated and * replaced with names that do. * * Symbols should be public if the user may specify them somewhere (especially * the CIB) or if they're part of a well-defined structure that a user may need * to parse. They should be internal if they're used only internally to * Pacemaker (such as daemon IPC/CPG message XML). * * Constants belong in the following locations: * * Public "XE" and "XA": msg_xml.h * * Internal "XE" and "XA": crm_internal.h * * Public "OPT", "META", and "VALUE": options.h * * Internal "OPT", "META", and "VALUE": options_internal.h * * For meta-attributes that can be specified as either XML attributes or nvpair * names, use "META" unless using both "XA" and "META" constants adds clarity. * An example is operation attributes, which can be specified either as * attributes of the PCMK_XE_OP element or as nvpairs in a meta-attribute set * beneath the PCMK_XE_OP element. */ /* * XML elements */ #define PCMK_XE_ACL_GROUP "acl_group" #define PCMK_XE_ACL_PERMISSION "acl_permission" #define PCMK_XE_ACL_ROLE "acl_role" #define PCMK_XE_ACL_TARGET "acl_target" #define PCMK_XE_ACLS "acls" #define PCMK_XE_ACTION "action" #define PCMK_XE_ACTIONS "actions" +#define PCMK_XE_AGENT "agent" +#define PCMK_XE_AGENT_STATUS "agent-status" +#define PCMK_XE_AGENTS "agents" #define PCMK_XE_ALERT "alert" #define PCMK_XE_ALERTS "alerts" +#define PCMK_XE_ALLOCATIONS "allocations" +#define PCMK_XE_ALLOCATIONS_UTILIZATIONS "allocations_utilizations" #define PCMK_XE_ATTRIBUTE "attribute" +#define PCMK_XE_BAN "ban" +#define PCMK_XE_BANS "bans" #define PCMK_XE_BUNDLE "bundle" +#define PCMK_XE_CAPACITY "capacity" #define PCMK_XE_CHANGE "change" #define PCMK_XE_CHANGE_ATTR "change-attr" #define PCMK_XE_CHANGE_LIST "change-list" #define PCMK_XE_CHANGE_RESULT "change-result" +#define PCMK_XE_CHECK "check" #define PCMK_XE_CIB "cib" #define PCMK_XE_CLONE "clone" #define PCMK_XE_CLUSTER_PROPERTY_SET "cluster_property_set" +#define PCMK_XE_CLUSTER_STATUS "cluster_status" +#define PCMK_XE_COMMAND "command" #define PCMK_XE_CONFIGURATION "configuration" #define PCMK_XE_CONSTRAINTS "constraints" #define PCMK_XE_CONTENT "content" #define PCMK_XE_CRM_CONFIG "crm_config" +#define PCMK_XE_CRM_MON "crm_mon" #define PCMK_XE_DATE_EXPRESSION "date_expression" #define PCMK_XE_DATE_SPEC "date_spec" #define PCMK_XE_DIFF "diff" #define PCMK_XE_DURATION "duration" +#define PCMK_XE_ERROR "error" +#define PCMK_XE_ERRORS "errors" #define PCMK_XE_EXPRESSION "expression" +#define PCMK_XE_FAILURES "failures" #define PCMK_XE_FEATURE "feature" #define PCMK_XE_FEATURES "features" +#define PCMK_XE_FENCE_EVENT "fence_event" +#define PCMK_XE_FENCE_HISTORY "fence_history" #define PCMK_XE_FENCING_LEVEL "fencing-level" #define PCMK_XE_FENCING_TOPOLOGY "fencing-topology" #define PCMK_XE_GROUP "group" #define PCMK_XE_INSTANCE_ATTRIBUTES "instance_attributes" +#define PCMK_XE_ITEM "item" +#define PCMK_XE_LAST_FENCED "last-fenced" +#define PCMK_XE_LIST "list" #define PCMK_XE_LONGDESC "longdesc" #define PCMK_XE_META_ATTRIBUTES "meta_attributes" #define PCMK_XE_NETWORK "network" #define PCMK_XE_NODE "node" +#define PCMK_XE_NODE_ATTRIBUTES "node_attributes" +#define PCMK_XE_NODE_HISTORY "node_history" #define PCMK_XE_NODES "nodes" #define PCMK_XE_NVPAIR "nvpair" #define PCMK_XE_OBJ_REF "obj_ref" #define PCMK_XE_OP "op" #define PCMK_XE_OP_DEFAULTS "op_defaults" -#define PCMK_XE_OPERATION "operation" #define PCMK_XE_OP_EXPRESSION "op_expression" +#define PCMK_XE_OPERATION "operation" +#define PCMK_XE_OPERATIONS "operations" #define PCMK_XE_OPTION "option" +#define PCMK_XE_OUTPUT "output" +#define PCMK_XE_OVERRIDE "override" +#define PCMK_XE_OVERRIDES "overrides" +#define PCMK_XE_PACEMAKER_RESULT "pacemaker-result" #define PCMK_XE_PACEMAKERD "pacemakerd" #define PCMK_XE_PARAMETER "parameter" #define PCMK_XE_PARAMETERS "parameters" #define PCMK_XE_PORT_MAPPING "port-mapping" #define PCMK_XE_POSITION "position" #define PCMK_XE_PRIMITIVE "primitive" #define PCMK_XE_RECIPIENT "recipient" +#define PCMK_XE_REPLICA "replica" #define PCMK_XE_RESOURCE "resource" #define PCMK_XE_RESOURCE_AGENT "resource-agent" +#define PCMK_XE_RESOURCE_AGENT_ACTION "resource-agent-action" +#define PCMK_XE_RESOURCE_CONFIG "resource_config" #define PCMK_XE_RESOURCE_REF "resource_ref" #define PCMK_XE_RESOURCE_SET "resource_set" #define PCMK_XE_RESOURCES "resources" +#define PCMK_XE_RESULT_CODE "result-code" +#define PCMK_XE_REVISED_CLUSTER_STATUS "revised_cluster_status" #define PCMK_XE_ROLE "role" #define PCMK_XE_RSC_ACTION "rsc_action" #define PCMK_XE_RSC_COLOCATION "rsc_colocation" #define PCMK_XE_RSC_DEFAULTS "rsc_defaults" #define PCMK_XE_RSC_EXPRESSION "rsc_expression" #define PCMK_XE_RSC_LOCATION "rsc_location" #define PCMK_XE_RSC_ORDER "rsc_order" #define PCMK_XE_RSC_TICKET "rsc_ticket" #define PCMK_XE_RULE "rule" #define PCMK_XE_SELECT "select" #define PCMK_XE_SELECT_ATTRIBUTES "select_attributes" #define PCMK_XE_SELECT_FENCING "select_fencing" #define PCMK_XE_SELECT_NODES "select_nodes" #define PCMK_XE_SELECT_RESOURCES "select_resources" #define PCMK_XE_SHORTDESC "shortdesc" #define PCMK_XE_SOURCE "source" #define PCMK_XE_STATUS "status" #define PCMK_XE_STORAGE "storage" #define PCMK_XE_STORAGE_MAPPING "storage-mapping" +#define PCMK_XE_SUMMARY "summary" #define PCMK_XE_TAG "tag" #define PCMK_XE_TAGS "tags" #define PCMK_XE_TARGET "target" #define PCMK_XE_TEMPLATE "template" #define PCMK_XE_TICKET "ticket" #define PCMK_XE_TICKETS "tickets" +#define PCMK_XE_TRANSITION "transition" #define PCMK_XE_UTILIZATION "utilization" +#define PCMK_XE_UTILIZATIONS "utilizations" #define PCMK_XE_VERSION "version" /* * XML attributes */ #define PCMK_XA_ACTION "action" #define PCMK_XA_ACTIVE "active" #define PCMK_XA_ADD_HOST "add-host" #define PCMK_XA_ADMIN_EPOCH "admin_epoch" +#define PCMK_XA_AGENT "agent" +#define PCMK_XA_API_VERSION "api-version" #define PCMK_XA_ATTRIBUTE "attribute" #define PCMK_XA_AUTHOR "author" #define PCMK_XA_BLOCKED "blocked" #define PCMK_XA_BOOLEAN_OP "boolean-op" #define PCMK_XA_BUILD "build" +#define PCMK_XA_CACHED "cached" +#define PCMK_XA_CALL "call" #define PCMK_XA_CIB_LAST_WRITTEN "cib-last-written" +#define PCMK_XA_CIB_NODE "cib_node" #define PCMK_XA_CLASS "class" #define PCMK_XA_CLIENT "client" +#define PCMK_XA_CODE "code" #define PCMK_XA_COMPLETED "completed" #define PCMK_XA_CONTROL_PORT "control-port" #define PCMK_XA_CRM_DEBUG_ORIGIN "crm-debug-origin" #define PCMK_XA_CRM_FEATURE_SET "crm_feature_set" #define PCMK_XA_CRM_TIMESTAMP "crm-timestamp" #define PCMK_XA_DAYS "days" #define PCMK_XA_DC_UUID "dc-uuid" #define PCMK_XA_DEFAULT "default" #define PCMK_XA_DELEGATE "delegate" #define PCMK_XA_DESCRIPTION "description" #define PCMK_XA_DEST "dest" #define PCMK_XA_DEVICES "devices" #define PCMK_XA_DISABLED "disabled" #define PCMK_XA_DURATION "duration" #define PCMK_XA_END "end" #define PCMK_XA_EPOCH "epoch" #define PCMK_XA_EXEC_TIME "exec-time" +#define PCMK_XA_EXECUTION_CODE "execution_code" #define PCMK_XA_EXECUTION_DATE "execution-date" +#define PCMK_XA_EXECUTION_MESSAGE "execution_message" #define PCMK_XA_EXIT_REASON "exit-reason" #define PCMK_XA_EXPECTED_UP "expected_up" #define PCMK_XA_EXTENDED_STATUS "extended-status" #define PCMK_XA_FAILED "failed" #define PCMK_XA_FAILURE_IGNORED "failure_ignored" #define PCMK_XA_FEATURE_SET "feature_set" #define PCMK_XA_FEATURES "features" #define PCMK_XA_FIRST "first" #define PCMK_XA_FIRST_ACTION "first-action" #define PCMK_XA_FORMAT "format" #define PCMK_XA_HAVE_QUORUM "have-quorum" #define PCMK_XA_HEALTH "health" #define PCMK_XA_HOST "host" #define PCMK_XA_HOST_INTERFACE "host-interface" #define PCMK_XA_HOST_NETMASK "host-netmask" #define PCMK_XA_HOURS "hours" #define PCMK_XA_ID "id" +#define PCMK_XA_ID_AS_RESOURCE "id_as_resource" #define PCMK_XA_ID_REF "id-ref" #define PCMK_XA_IMAGE "image" #define PCMK_XA_INDEX "index" #define PCMK_XA_INFLUENCE "influence" #define PCMK_XA_INTERNAL_PORT "internal-port" #define PCMK_XA_IP_RANGE_START "ip-range-start" #define PCMK_XA_IS_DC "is_dc" #define PCMK_XA_KIND "kind" #define PCMK_XA_LANG "lang" #define PCMK_XA_LAST_GRANTED "last-granted" #define PCMK_XA_LAST_RC_CHANGE "last-rc-change" #define PCMK_XA_LOCKED_TO "locked_to" #define PCMK_XA_LOSS_POLICY "loss-policy" #define PCMK_XA_MAINTENANCE "maintenance" #define PCMK_XA_MANAGED "managed" +#define PCMK_XA_MESSAGE "message" #define PCMK_XA_MINUTES "minutes" #define PCMK_XA_MIXED_VERSION "mixed_version" #define PCMK_XA_MONTHDAYS "monthdays" #define PCMK_XA_MONTHS "months" #define PCMK_XA_MULTI_STATE "multi_state" #define PCMK_XA_NAME "name" #define PCMK_XA_NETWORK "network" #define PCMK_XA_NEXT_ROLE "next-role" #define PCMK_XA_NO_QUORUM_PANIC "no-quorum-panic" #define PCMK_XA_NODE "node" #define PCMK_XA_NODE_ATTRIBUTE "node-attribute" #define PCMK_XA_NODES_RUNNING_ON "nodes_running_on" #define PCMK_XA_NUM_UPDATES "num_updates" #define PCMK_XA_NUMBER "number" +#define PCMK_XA_NUMBER_RESOURCES "number_resources" #define PCMK_XA_OBJECT_TYPE "object-type" #define PCMK_XA_ONLINE "online" #define PCMK_XA_OP "op" #define PCMK_XA_OPERATION "operation" #define PCMK_XA_OPTIONS "options" #define PCMK_XA_ORIGIN "origin" #define PCMK_XA_ORPHANED "orphaned" #define PCMK_XA_PATH "path" #define PCMK_XA_PENDING "pending" #define PCMK_XA_PORT "port" #define PCMK_XA_PRESENT "present" #define PCMK_XA_PROGRAM "program" #define PCMK_XA_PROMOTED_MAX "promoted-max" +#define PCMK_XA_PROMOTED_ONLY "promoted-only" #define PCMK_XA_PROVIDER "provider" #define PCMK_XA_QUEUE_TIME "queue-time" #define PCMK_XA_RANGE "range" #define PCMK_XA_REASON "reason" #define PCMK_XA_REFERENCE "reference" #define PCMK_XA_RELOADABLE "reloadable" #define PCMK_XA_REMOTE_CLEAR_PORT "remote-clear-port" #define PCMK_XA_REMOTE_TLS_PORT "remote-tls-port" #define PCMK_XA_REPLICAS "replicas" #define PCMK_XA_REPLICAS_PER_HOST "replicas-per-host" #define PCMK_XA_REQUEST "request" #define PCMK_XA_REQUIRE_ALL "require-all" #define PCMK_XA_RESOURCE "resource" #define PCMK_XA_RESOURCE_AGENT "resource_agent" #define PCMK_XA_RESOURCE_DISCOVERY "resource-discovery" #define PCMK_XA_RESOURCES_RUNNING "resources_running" #define PCMK_XA_RESULT "result" #define PCMK_XA_ROLE "role" #define PCMK_XA_RSC "rsc" #define PCMK_XA_RSC_PATTERN "rsc-pattern" #define PCMK_XA_RSC_ROLE "rsc-role" #define PCMK_XA_RUN_COMMAND "run-command" #define PCMK_XA_RUNNING "running" #define PCMK_XA_SCOPE "scope" #define PCMK_XA_SCORE "score" #define PCMK_XA_SCORE_ATTRIBUTE "score-attribute" #define PCMK_XA_SEQUENTIAL "sequential" #define PCMK_XA_SECONDS "seconds" #define PCMK_XA_SHUTDOWN "shutdown" #define PCMK_XA_SOURCE "source" #define PCMK_XA_SOURCE_DIR "source-dir" #define PCMK_XA_SOURCE_DIR_ROOT "source-dir-root" #define PCMK_XA_STANDBY "standby" #define PCMK_XA_STANDBY_ONFAIL "standby_onfail" #define PCMK_XA_START "start" #define PCMK_XA_STATUS "status" #define PCMK_XA_SYMMETRICAL "symmetrical" #define PCMK_XA_TARGET "target" #define PCMK_XA_TARGET_ATTRIBUTE "target-attribute" #define PCMK_XA_TARGET_DIR "target-dir" #define PCMK_XA_TARGET_PATTERN "target-pattern" #define PCMK_XA_TARGET_ROLE "target_role" #define PCMK_XA_TARGET_VALUE "target-value" #define PCMK_XA_TEMPLATE "template" #define PCMK_XA_TICKET "ticket" #define PCMK_XA_TIME "time" #define PCMK_XA_THEN "then" #define PCMK_XA_THEN_ACTION "then-action" #define PCMK_XA_TYPE "type" #define PCMK_XA_UNAME "uname" #define PCMK_XA_UNCLEAN "unclean" #define PCMK_XA_UNIQUE "unique" #define PCMK_XA_UPDATE_CLIENT "update-client" #define PCMK_XA_UPDATE_ORIGIN "update-origin" #define PCMK_XA_UPDATE_USER "update-user" #define PCMK_XA_USER "user" #define PCMK_XA_VALIDATE_WITH "validate-with" #define PCMK_XA_VALUE "value" #define PCMK_XA_VALUE_SOURCE "value-source" #define PCMK_XA_VERSION "version" #define PCMK_XA_WEEKDAYS "weekdays" #define PCMK_XA_WEEKS "weeks" #define PCMK_XA_WEEKYEARS "weekyears" +#define PCMK_XA_WEIGHT "weight" +#define PCMK_XA_WHEN "when" #define PCMK_XA_WITH_QUORUM "with_quorum" #define PCMK_XA_WITH_RSC "with-rsc" #define PCMK_XA_WITH_RSC_ROLE "with-rsc-role" #define PCMK_XA_XPATH "xpath" #define PCMK_XA_YEARDAYS "yeardays" #define PCMK_XA_YEARS "years" # define ID(x) crm_element_value(x, PCMK_XA_ID) #ifdef __cplusplus } #endif #endif diff --git a/include/crm_internal.h b/include/crm_internal.h index e0bc12bcf0..0e33ee6499 100644 --- a/include/crm_internal.h +++ b/include/crm_internal.h @@ -1,259 +1,266 @@ /* * Copyright 2006-2024 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 CRM_INTERNAL__H # define CRM_INTERNAL__H # ifndef PCMK__CONFIG_H # define PCMK__CONFIG_H # include # endif # include /* Our minimum glib dependency is 2.42. Define that as both the minimum and * maximum glib APIs that are allowed (i.e. APIs that were already deprecated * in 2.42, and APIs introduced after 2.42, cannot be used by Pacemaker code). */ #define GLIB_VERSION_MIN_REQUIRED GLIB_VERSION_2_42 #define GLIB_VERSION_MAX_ALLOWED GLIB_VERSION_2_42 # include # include # include /* Public API headers can guard including deprecated API headers with this * symbol, thus preventing internal code (which includes this header) from using * deprecated APIs, while still allowing external code to use them by default. */ #define PCMK_ALLOW_DEPRECATED 0 # include # include # include # include # include # include # include # include # include # include # include # include #define N_(String) (String) #ifdef ENABLE_NLS # define _(String) gettext(String) #else # define _(String) (String) #endif /* * XML element names used only by internal code */ #define PCMK__XE_ATTRIBUTES "attributes" #define PCMK__XE_CRM_EVENT "crm_event" #define PCMK__XE_CRM_XML "crm_xml" #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_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_TICKET_STATE "ticket_state" #define PCMK__XE_TRANSIENT_ATTRIBUTES "transient_attributes" #define PCMK__XE_TRANSITION_GRAPH "transition_graph" // @COMPAT Deprecated since 1.1.12 #define PCMK__XE_ACL_USER "acl_user" /* @TODO 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 2.0.0; alias for with PCMK_META_PROMOTABLE * set to "true" */ #define PCMK__XE_PROMOTABLE_LEGACY "master" // @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_DAMPENING "attr_dampening" #define PCMK__XA_ATTR_FORCE "attrd_is_force_write" #define PCMK__XA_ATTR_INTERVAL "attr_clear_interval" #define PCMK__XA_ATTR_IS_PRIVATE "attr_is_private" #define PCMK__XA_ATTR_IS_REMOTE "attr_is_remote" #define PCMK__XA_ATTR_NAME "attr_name" #define PCMK__XA_ATTR_NODE_ID "attr_host_id" #define PCMK__XA_ATTR_NODE_NAME "attr_host" #define PCMK__XA_ATTR_OPERATION "attr_clear_operation" #define PCMK__XA_ATTR_PATTERN "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_UUID "attr_key" #define PCMK__XA_ATTR_VALUE "attr_value" #define PCMK__XA_ATTR_VERSION "attr_version" #define PCMK__XA_ATTR_WRITER "attr_writer" #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_CONN_HOST "connection_host" #define PCMK__XA_CRMD "crmd" #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_EXPECTED "expected" #define PCMK__XA_FILE "file" #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_IN_CCM "in_ccm" #define PCMK__XA_JOIN "join" #define PCMK__XA_JOIN_ID "join_id" #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_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_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" #define PCMK__XA_REMOTE_NODE "remote_node" /* 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_SCHEMA "schema" #define PCMK__XA_SCHEMAS "schemas" #define PCMK__XA_SRC "src" #define PCMK__XA_SUBT "subt" // subtype #define PCMK__XA_T "t" // type #define PCMK__XA_TASK "task" #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 since 2.1.5 #define PCMK__XA_RSC_INSTANCE "rsc-instance" // @COMPAT Deprecated since 1.1.12 #define PCMK__XA_TAG "tag" // @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" /* * IPC service names that are only used internally */ # define PCMK__SERVER_BASED_RO "cib_ro" # define PCMK__SERVER_BASED_RW "cib_rw" # define PCMK__SERVER_BASED_SHM "cib_shm" /* * IPC commands that can be sent to Pacemaker daemons */ #define PCMK__ATTRD_CMD_PEER_REMOVE "peer-remove" #define PCMK__ATTRD_CMD_UPDATE "update" #define PCMK__ATTRD_CMD_UPDATE_BOTH "update-both" #define PCMK__ATTRD_CMD_UPDATE_DELAY "update-delay" #define PCMK__ATTRD_CMD_QUERY "query" #define PCMK__ATTRD_CMD_REFRESH "refresh" #define PCMK__ATTRD_CMD_FLUSH "flush" #define PCMK__ATTRD_CMD_SYNC "sync" #define PCMK__ATTRD_CMD_SYNC_RESPONSE "sync-response" #define PCMK__ATTRD_CMD_CLEAR_FAILURE "clear-failure" #define PCMK__ATTRD_CMD_CONFIRM "confirm" #define PCMK__CONTROLD_CMD_NODES "list-nodes" #endif /* CRM_INTERNAL__H */ diff --git a/lib/common/attrs.c b/lib/common/attrs.c index 67f253b50a..38e5f33b75 100644 --- a/lib/common/attrs.c +++ b/lib/common/attrs.c @@ -1,98 +1,99 @@ /* * 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 _GNU_SOURCE # define _GNU_SOURCE #endif #include #include #include #include #define OCF_RESKEY_PREFIX "OCF_RESKEY_" #define LRM_TARGET_ENV OCF_RESKEY_PREFIX CRM_META "_" PCMK__META_ON_NODE /*! * \internal * \brief Get the node name that should be used to set node attributes * * If given NULL, "auto", or "localhost" as an argument, check the environment * to detect the node name that should be used to set node attributes. (The * caller might not know the correct name, for example if the target is part of - * a bundle with \c PCMK_META_CONTAINER_ATTR_TARGET set to "host".) + * a bundle with \c PCMK_META_CONTAINER_ATTR_TARGET set to \c PCMK_VALUE_HOST.) * * \param[in] name NULL, "auto" or "localhost" to check environment variables, * or anything else to return NULL * * \return Node name that should be used for node attributes based on the * environment if known, otherwise NULL */ const char * pcmk__node_attr_target(const char *name) { if (name == NULL || pcmk__strcase_any_of(name, "auto", "localhost", NULL)) { char buf[128] = OCF_RESKEY_PREFIX; size_t offset = sizeof(OCF_RESKEY_PREFIX) - 1; char *target_var = crm_meta_name(PCMK_META_CONTAINER_ATTR_TARGET); char *phys_var = crm_meta_name(PCMK__META_PHYSICAL_HOST); const char *target = NULL; const char *host_physical = NULL; snprintf(buf + offset, sizeof(buf) - offset, "%s", target_var); target = getenv(buf); snprintf(buf + offset, sizeof(buf) - offset, "%s", phys_var); host_physical = getenv(buf); // It is important to use the name by which the scheduler knows us - if (host_physical && pcmk__str_eq(target, "host", pcmk__str_casei)) { + if (host_physical + && pcmk__str_eq(target, PCMK_VALUE_HOST, pcmk__str_casei)) { name = host_physical; } else { const char *host_pcmk = getenv(LRM_TARGET_ENV); if (host_pcmk) { name = host_pcmk; } } free(target_var); free(phys_var); // TODO? Call get_local_node_name() if name == NULL // (currently would require linkage against libcrmcluster) return name; } else { return NULL; } } /*! * \brief Return the name of the node attribute used as a promotion score * * \param[in] rsc_id Resource ID that promotion score is for (or NULL to * check the OCF_RESOURCE_INSTANCE environment variable) * * \return Newly allocated string with the node attribute name (or NULL on * error, including no ID or environment variable specified) * \note It is the caller's responsibility to free() the result. */ char * pcmk_promotion_score_name(const char *rsc_id) { if (pcmk__str_empty(rsc_id)) { rsc_id = getenv("OCF_RESOURCE_INSTANCE"); if (pcmk__str_empty(rsc_id)) { return NULL; } } return crm_strdup_printf("master-%s", rsc_id); } diff --git a/lib/common/ipc_controld.c b/lib/common/ipc_controld.c index 9b16886cc1..ed75032b2e 100644 --- a/lib/common/ipc_controld.c +++ b/lib/common/ipc_controld.c @@ -1,658 +1,660 @@ /* * Copyright 2020-2024 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. */ #include #include #include #include #include #include #include #include #include #include #include #include "crmcommon_private.h" struct controld_api_private_s { char *client_uuid; unsigned int replies_expected; }; /*! * \internal * \brief Get a string representation of a controller API reply type * * \param[in] reply Controller API reply type * * \return String representation of a controller API reply type */ const char * pcmk__controld_api_reply2str(enum pcmk_controld_api_reply reply) { switch (reply) { case pcmk_controld_reply_reprobe: return "reprobe"; case pcmk_controld_reply_info: return "info"; case pcmk_controld_reply_resource: return "resource"; case pcmk_controld_reply_ping: return "ping"; case pcmk_controld_reply_nodes: return "nodes"; default: return "unknown"; } } // \return Standard Pacemaker return code static int new_data(pcmk_ipc_api_t *api) { struct controld_api_private_s *private = NULL; api->api_data = calloc(1, sizeof(struct controld_api_private_s)); if (api->api_data == NULL) { return errno; } private = api->api_data; /* This is set to the PID because that's how it was always done, but PIDs * are not unique because clients can be remote. The value appears to be * unused other than as part of PCMK__XA_CRM_SYS_FROM in IPC requests, which * is only compared against the internal system names (CRM_SYSTEM_TENGINE, * etc.), so it shouldn't be a problem. */ private->client_uuid = pcmk__getpid_s(); /* @TODO Implement a call ID model similar to the CIB, executor, and fencer * IPC APIs, so that requests and replies can be matched, and * duplicate replies can be discarded. */ return pcmk_rc_ok; } static void free_data(void *data) { free(((struct controld_api_private_s *) data)->client_uuid); free(data); } // \return Standard Pacemaker return code static int post_connect(pcmk_ipc_api_t *api) { /* The controller currently requires clients to register via a hello * request, but does not reply back. */ struct controld_api_private_s *private = api->api_data; const char *client_name = crm_system_name? crm_system_name : "client"; xmlNode *hello; int rc; hello = create_hello_message(private->client_uuid, client_name, PCMK__CONTROLD_API_MAJOR, PCMK__CONTROLD_API_MINOR); rc = pcmk__send_ipc_request(api, hello); free_xml(hello); if (rc != pcmk_rc_ok) { crm_info("Could not send IPC hello to %s: %s " CRM_XS " rc=%s", pcmk_ipc_name(api, true), pcmk_rc_str(rc), rc); } else { crm_debug("Sent IPC hello to %s", pcmk_ipc_name(api, true)); } return rc; } static void set_node_info_data(pcmk_controld_api_reply_t *data, xmlNode *msg_data) { data->reply_type = pcmk_controld_reply_info; if (msg_data == NULL) { return; } data->data.node_info.have_quorum = pcmk__xe_attr_is_true(msg_data, PCMK_XA_HAVE_QUORUM); data->data.node_info.is_remote = pcmk__xe_attr_is_true(msg_data, PCMK__XA_REMOTE_NODE); /* Integer node_info.id is currently valid only for Corosync nodes. * * @TODO: Improve handling after crm_node_t is refactored to handle layer- * specific data better. */ crm_element_value_int(msg_data, PCMK_XA_ID, &(data->data.node_info.id)); data->data.node_info.uuid = crm_element_value(msg_data, PCMK_XA_ID); data->data.node_info.uname = crm_element_value(msg_data, PCMK_XA_UNAME); data->data.node_info.state = crm_element_value(msg_data, PCMK__XA_CRMD); } static void set_ping_data(pcmk_controld_api_reply_t *data, xmlNode *msg_data) { data->reply_type = pcmk_controld_reply_ping; if (msg_data == NULL) { return; } data->data.ping.sys_from = crm_element_value(msg_data, PCMK__XA_CRM_SUBSYSTEM); data->data.ping.fsa_state = crm_element_value(msg_data, PCMK__XA_CRMD_STATE); data->data.ping.result = crm_element_value(msg_data, PCMK_XA_RESULT); } static void set_nodes_data(pcmk_controld_api_reply_t *data, xmlNode *msg_data) { pcmk_controld_api_node_t *node_info; data->reply_type = pcmk_controld_reply_nodes; for (xmlNode *node = first_named_child(msg_data, PCMK_XE_NODE); node != NULL; node = crm_next_same_xml(node)) { long long id_ll = 0; node_info = calloc(1, sizeof(pcmk_controld_api_node_t)); crm_element_value_ll(node, PCMK_XA_ID, &id_ll); if (id_ll > 0) { node_info->id = id_ll; } node_info->uname = crm_element_value(node, PCMK_XA_UNAME); node_info->state = crm_element_value(node, PCMK__XA_IN_CCM); data->data.nodes = g_list_prepend(data->data.nodes, node_info); } } static bool reply_expected(pcmk_ipc_api_t *api, const xmlNode *request) { // We only need to handle commands that API functions can send return pcmk__str_any_of(crm_element_value(request, PCMK__XA_CRM_TASK), PCMK__CONTROLD_CMD_NODES, CRM_OP_LRM_DELETE, CRM_OP_LRM_FAIL, CRM_OP_NODE_INFO, CRM_OP_PING, CRM_OP_REPROBE, CRM_OP_RM_NODE_CACHE, NULL); } static bool dispatch(pcmk_ipc_api_t *api, xmlNode *reply) { struct controld_api_private_s *private = api->api_data; crm_exit_t status = CRM_EX_OK; xmlNode *msg_data = NULL; const char *value = NULL; pcmk_controld_api_reply_t reply_data = { pcmk_controld_reply_unknown, NULL, NULL, }; if (pcmk__xe_is(reply, "ack")) { /* ACKs are trivial responses that do not count toward expected replies, * and do not have all the fields that validation requires, so skip that * processing. */ return private->replies_expected > 0; } if (private->replies_expected > 0) { private->replies_expected--; } // Do some basic validation of the reply /* @TODO We should be able to verify that value is always a response, but * currently the controller doesn't always properly set the type. Even * if we fix the controller, we'll still need to handle replies from * old versions (feature set could be used to differentiate). */ value = crm_element_value(reply, PCMK__XA_SUBT); if (!pcmk__str_any_of(value, PCMK__VALUE_REQUEST, PCMK__VALUE_RESPONSE, NULL)) { crm_info("Unrecognizable message from controller: " "invalid message type '%s'", pcmk__s(value, "")); status = CRM_EX_PROTOCOL; goto done; } if (pcmk__str_empty(crm_element_value(reply, PCMK_XA_REFERENCE))) { crm_info("Unrecognizable message from controller: no reference"); status = CRM_EX_PROTOCOL; goto done; } value = crm_element_value(reply, PCMK__XA_CRM_TASK); if (pcmk__str_empty(value)) { crm_info("Unrecognizable message from controller: no command name"); status = CRM_EX_PROTOCOL; goto done; } // Parse useful info from reply reply_data.feature_set = crm_element_value(reply, PCMK_XA_VERSION); reply_data.host_from = crm_element_value(reply, PCMK__XA_SRC); msg_data = get_message_xml(reply, PCMK__XE_CRM_XML); if (!strcmp(value, CRM_OP_REPROBE)) { reply_data.reply_type = pcmk_controld_reply_reprobe; } else if (!strcmp(value, CRM_OP_NODE_INFO)) { set_node_info_data(&reply_data, msg_data); } else if (!strcmp(value, CRM_OP_INVOKE_LRM)) { reply_data.reply_type = pcmk_controld_reply_resource; reply_data.data.resource.node_state = msg_data; } else if (!strcmp(value, CRM_OP_PING)) { set_ping_data(&reply_data, msg_data); } else if (!strcmp(value, PCMK__CONTROLD_CMD_NODES)) { set_nodes_data(&reply_data, msg_data); } else { crm_info("Unrecognizable message from controller: unknown command '%s'", value); status = CRM_EX_PROTOCOL; } done: pcmk__call_ipc_callback(api, pcmk_ipc_event_reply, status, &reply_data); // Free any reply data that was allocated if (pcmk__str_eq(value, PCMK__CONTROLD_CMD_NODES, pcmk__str_casei)) { g_list_free_full(reply_data.data.nodes, free); } return false; // No further replies needed } pcmk__ipc_methods_t * pcmk__controld_api_methods(void) { pcmk__ipc_methods_t *cmds = calloc(1, sizeof(pcmk__ipc_methods_t)); if (cmds != NULL) { cmds->new_data = new_data; cmds->free_data = free_data; cmds->post_connect = post_connect; cmds->reply_expected = reply_expected; cmds->dispatch = dispatch; } return cmds; } /*! * \internal * \brief Create XML for a controller IPC request * * \param[in] api Controller connection * \param[in] op Controller IPC command name * \param[in] node Node name to set as destination host * \param[in] msg_data XML to attach to request as message data * * \return Newly allocated XML for request */ static xmlNode * create_controller_request(const pcmk_ipc_api_t *api, const char *op, const char *node, xmlNode *msg_data) { struct controld_api_private_s *private = NULL; const char *sys_to = NULL; if (api == NULL) { return NULL; } private = api->api_data; if ((node == NULL) && !strcmp(op, CRM_OP_PING)) { sys_to = CRM_SYSTEM_DC; } else { sys_to = CRM_SYSTEM_CRMD; } return create_request(op, msg_data, node, sys_to, (crm_system_name? crm_system_name : "client"), private->client_uuid); } // \return Standard Pacemaker return code static int send_controller_request(pcmk_ipc_api_t *api, const xmlNode *request, bool reply_is_expected) { if (crm_element_value(request, PCMK_XA_REFERENCE) == NULL) { return EINVAL; } if (reply_is_expected) { struct controld_api_private_s *private = api->api_data; private->replies_expected++; } return pcmk__send_ipc_request(api, request); } static xmlNode * create_reprobe_message_data(const char *target_node, const char *router_node) { xmlNode *msg_data; msg_data = create_xml_node(NULL, "data_for_" CRM_OP_REPROBE); crm_xml_add(msg_data, PCMK__META_ON_NODE, target_node); if ((router_node != NULL) && !pcmk__str_eq(router_node, target_node, pcmk__str_casei)) { crm_xml_add(msg_data, PCMK__XA_ROUTER_NODE, router_node); } return msg_data; } /*! * \brief Send a reprobe controller operation * * \param[in,out] api Controller connection * \param[in] target_node Name of node to reprobe * \param[in] router_node Router node for host * * \return Standard Pacemaker return code * \note Event callback will get a reply of type pcmk_controld_reply_reprobe. */ int pcmk_controld_api_reprobe(pcmk_ipc_api_t *api, const char *target_node, const char *router_node) { xmlNode *request; xmlNode *msg_data; int rc = pcmk_rc_ok; if (api == NULL) { return EINVAL; } if (router_node == NULL) { router_node = target_node; } crm_debug("Sending %s IPC request to reprobe %s via %s", pcmk_ipc_name(api, true), pcmk__s(target_node, "local node"), pcmk__s(router_node, "local node")); msg_data = create_reprobe_message_data(target_node, router_node); request = create_controller_request(api, CRM_OP_REPROBE, router_node, msg_data); rc = send_controller_request(api, request, true); free_xml(msg_data); free_xml(request); return rc; } /*! * \brief Send a "node info" controller operation * * \param[in,out] api Controller connection * \param[in] nodeid ID of node to get info for (or 0 for local node) * * \return Standard Pacemaker return code * \note Event callback will get a reply of type pcmk_controld_reply_info. */ int pcmk_controld_api_node_info(pcmk_ipc_api_t *api, uint32_t nodeid) { xmlNode *request; int rc = pcmk_rc_ok; request = create_controller_request(api, CRM_OP_NODE_INFO, NULL, NULL); if (request == NULL) { return EINVAL; } if (nodeid > 0) { crm_xml_set_id(request, "%lu", (unsigned long) nodeid); } rc = send_controller_request(api, request, true); free_xml(request); return rc; } /*! * \brief Ask the controller for status * * \param[in,out] api Controller connection * \param[in] node_name Name of node whose status is desired (NULL for DC) * * \return Standard Pacemaker return code * \note Event callback will get a reply of type pcmk_controld_reply_ping. */ int pcmk_controld_api_ping(pcmk_ipc_api_t *api, const char *node_name) { xmlNode *request; int rc = pcmk_rc_ok; request = create_controller_request(api, CRM_OP_PING, node_name, NULL); if (request == NULL) { return EINVAL; } rc = send_controller_request(api, request, true); free_xml(request); return rc; } /*! * \brief Ask the controller for cluster information * * \param[in,out] api Controller connection * * \return Standard Pacemaker return code * \note Event callback will get a reply of type pcmk_controld_reply_nodes. */ int pcmk_controld_api_list_nodes(pcmk_ipc_api_t *api) { xmlNode *request; int rc = EINVAL; request = create_controller_request(api, PCMK__CONTROLD_CMD_NODES, NULL, NULL); if (request != NULL) { rc = send_controller_request(api, request, true); free_xml(request); } return rc; } // \return Standard Pacemaker return code static int controller_resource_op(pcmk_ipc_api_t *api, const char *op, const char *target_node, const char *router_node, bool cib_only, const char *rsc_id, const char *rsc_long_id, const char *standard, const char *provider, const char *type) { int rc = pcmk_rc_ok; char *key; xmlNode *request, *msg_data, *xml_rsc, *params; if (api == NULL) { return EINVAL; } if (router_node == NULL) { router_node = target_node; } msg_data = create_xml_node(NULL, PCMK__XE_RSC_OP); /* The controller logs the transition key from resource op requests, so we * need to have *something* for it. * @TODO don't use "crm-resource" */ key = pcmk__transition_key(0, getpid(), 0, "xxxxxxxx-xrsc-opxx-xcrm-resourcexxxx"); crm_xml_add(msg_data, PCMK__XA_TRANSITION_KEY, key); free(key); crm_xml_add(msg_data, PCMK__META_ON_NODE, target_node); if (!pcmk__str_eq(router_node, target_node, pcmk__str_casei)) { crm_xml_add(msg_data, PCMK__XA_ROUTER_NODE, router_node); } if (cib_only) { // Indicate that only the CIB needs to be cleaned crm_xml_add(msg_data, PCMK__XA_MODE, PCMK__VALUE_CIB); } xml_rsc = create_xml_node(msg_data, PCMK_XE_PRIMITIVE); crm_xml_add(xml_rsc, PCMK_XA_ID, rsc_id); crm_xml_add(xml_rsc, PCMK__XA_LONG_ID, rsc_long_id); crm_xml_add(xml_rsc, PCMK_XA_CLASS, standard); crm_xml_add(xml_rsc, PCMK_XA_PROVIDER, provider); crm_xml_add(xml_rsc, PCMK_XA_TYPE, type); params = create_xml_node(msg_data, PCMK__XE_ATTRIBUTES); crm_xml_add(params, PCMK_XA_CRM_FEATURE_SET, CRM_FEATURE_SET); // The controller parses the timeout from the request key = crm_meta_name(PCMK_META_TIMEOUT); crm_xml_add(params, key, "60000"); /* 1 minute */ //@TODO pass as arg free(key); request = create_controller_request(api, op, router_node, msg_data); rc = send_controller_request(api, request, true); free_xml(msg_data); free_xml(request); return rc; } /*! * \brief Ask the controller to fail a resource * * \param[in,out] api Controller connection * \param[in] target_node Name of node resource is on * \param[in] router_node Router node for target * \param[in] rsc_id ID of resource to fail * \param[in] rsc_long_id Long ID of resource (if any) * \param[in] standard Standard of resource * \param[in] provider Provider of resource (if any) * \param[in] type Type of resource to fail * * \return Standard Pacemaker return code * \note Event callback will get a reply of type pcmk_controld_reply_resource. */ int pcmk_controld_api_fail(pcmk_ipc_api_t *api, const char *target_node, const char *router_node, const char *rsc_id, const char *rsc_long_id, const char *standard, const char *provider, const char *type) { crm_debug("Sending %s IPC request to fail %s (a.k.a. %s) on %s via %s", pcmk_ipc_name(api, true), pcmk__s(rsc_id, "unknown resource"), pcmk__s(rsc_long_id, "no other names"), pcmk__s(target_node, "unspecified node"), pcmk__s(router_node, "unspecified node")); return controller_resource_op(api, CRM_OP_LRM_FAIL, target_node, router_node, false, rsc_id, rsc_long_id, standard, provider, type); } /*! * \brief Ask the controller to refresh a resource * * \param[in,out] api Controller connection * \param[in] target_node Name of node resource is on * \param[in] router_node Router node for target * \param[in] rsc_id ID of resource to refresh * \param[in] rsc_long_id Long ID of resource (if any) * \param[in] standard Standard of resource * \param[in] provider Provider of resource (if any) * \param[in] type Type of resource * \param[in] cib_only If true, clean resource from CIB only * * \return Standard Pacemaker return code * \note Event callback will get a reply of type pcmk_controld_reply_resource. */ int pcmk_controld_api_refresh(pcmk_ipc_api_t *api, const char *target_node, const char *router_node, const char *rsc_id, const char *rsc_long_id, const char *standard, const char *provider, const char *type, bool cib_only) { crm_debug("Sending %s IPC request to refresh %s (a.k.a. %s) on %s via %s", pcmk_ipc_name(api, true), pcmk__s(rsc_id, "unknown resource"), pcmk__s(rsc_long_id, "no other names"), pcmk__s(target_node, "unspecified node"), pcmk__s(router_node, "unspecified node")); return controller_resource_op(api, CRM_OP_LRM_DELETE, target_node, router_node, cib_only, rsc_id, rsc_long_id, standard, provider, type); } /*! * \brief Get the number of IPC replies currently expected from the controller * * \param[in] api Controller IPC API connection * * \return Number of replies expected */ unsigned int pcmk_controld_api_replies_expected(const pcmk_ipc_api_t *api) { struct controld_api_private_s *private = api->api_data; return private->replies_expected; } /*! * \brief Create XML for a controller IPC "hello" message * * \deprecated This function is deprecated as part of the public C API. */ // \todo make this static to this file when breaking API backward compatibility xmlNode * create_hello_message(const char *uuid, const char *client_name, const char *major_version, const char *minor_version) { xmlNode *hello_node = NULL; xmlNode *hello = NULL; if (pcmk__str_empty(uuid) || pcmk__str_empty(client_name) || pcmk__str_empty(major_version) || pcmk__str_empty(minor_version)) { crm_err("Could not create IPC hello message from %s (UUID %s): " "missing information", client_name? client_name : "unknown client", uuid? uuid : "unknown"); return NULL; } hello_node = create_xml_node(NULL, PCMK__XE_OPTIONS); if (hello_node == NULL) { crm_err("Could not create IPC hello message from %s (UUID %s): " "Message data creation failed", client_name, uuid); return NULL; } - crm_xml_add(hello_node, "major_version", major_version); - crm_xml_add(hello_node, "minor_version", minor_version); - crm_xml_add(hello_node, "client_name", client_name); - crm_xml_add(hello_node, "client_uuid", uuid); + crm_xml_add(hello_node, PCMK__XA_MAJOR_VERSION, major_version); + crm_xml_add(hello_node, PCMK__XA_MINOR_VERSION, minor_version); + crm_xml_add(hello_node, PCMK__XA_CLIENT_NAME, client_name); + + // @TODO Nothing uses this. Drop, or keep for debugging? + crm_xml_add(hello_node, PCMK__XA_CLIENT_UUID, uuid); hello = create_request(CRM_OP_HELLO, hello_node, NULL, NULL, client_name, uuid); if (hello == NULL) { crm_err("Could not create IPC hello message from %s (UUID %s): " "Request creation failed", client_name, uuid); return NULL; } free_xml(hello_node); crm_trace("Created hello message from %s (UUID %s)", client_name, uuid); return hello; } diff --git a/lib/common/options.c b/lib/common/options.c index 74c2cd8bdc..68b8d5ba76 100644 --- a/lib/common/options.c +++ b/lib/common/options.c @@ -1,1157 +1,1158 @@ /* * 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 _GNU_SOURCE # define _GNU_SOURCE #endif #include #include #include #include #include #include #include #include void pcmk__cli_help(char cmd) { if (cmd == 'v' || cmd == '$') { printf("Pacemaker %s\n", PACEMAKER_VERSION); printf("Written by Andrew Beekhof and " "the Pacemaker project contributors\n"); } else if (cmd == '!') { printf("Pacemaker %s (Build: %s): %s\n", PACEMAKER_VERSION, BUILD_VERSION, CRM_FEATURES); } crm_exit(CRM_EX_OK); while(1); // above does not return } /* * Option metadata */ static pcmk__cluster_option_t cluster_options[] = { /* name, old name, type, allowed values, * default value, validator, * context, * short description, * long description */ { PCMK_OPT_DC_VERSION, NULL, "string", NULL, PCMK__VALUE_NONE, NULL, pcmk__opt_context_controld, N_("Pacemaker version on cluster node elected Designated Controller " "(DC)"), N_("Includes a hash which identifies the exact revision the code was " "built from. Used for diagnostic purposes."), }, { PCMK_OPT_CLUSTER_INFRASTRUCTURE, NULL, "string", NULL, "corosync", NULL, pcmk__opt_context_controld, N_("The messaging layer on which Pacemaker is currently running"), N_("Used for informational and diagnostic purposes."), }, { PCMK_OPT_CLUSTER_NAME, NULL, "string", NULL, NULL, NULL, pcmk__opt_context_controld, N_("An arbitrary name for the cluster"), N_("This optional value is mostly for users' convenience as desired " "in administration, but may also be used in Pacemaker " "configuration rules via the #cluster-name node attribute, and " "by higher-level tools and resource agents."), }, { PCMK_OPT_DC_DEADTIME, NULL, "time", NULL, "20s", pcmk__valid_interval_spec, pcmk__opt_context_controld, N_("How long to wait for a response from other nodes during start-up"), N_("The optimal value will depend on the speed and load of your " "network and the type of switches used."), }, { PCMK_OPT_CLUSTER_RECHECK_INTERVAL, NULL, "time", N_("Zero disables polling, while positive values are an interval in " "seconds (unless other units are specified, for example \"5min\")"), "15min", pcmk__valid_interval_spec, pcmk__opt_context_controld, N_("Polling interval to recheck cluster state and evaluate rules " "with date specifications"), N_("Pacemaker is primarily event-driven, and looks ahead to know when " "to recheck cluster state for failure-timeout settings and most " "time-based rules. However, it will also recheck the cluster after " "this amount of inactivity, to evaluate rules with date " "specifications and serve as a fail-safe for certain types of " "scheduler bugs."), }, { - PCMK_OPT_FENCE_REACTION, NULL, "select", PCMK_VALUE_STOP ", panic", + PCMK_OPT_FENCE_REACTION, NULL, "select", + PCMK_VALUE_STOP ", " PCMK_VALUE_PANIC, PCMK_VALUE_STOP, NULL, pcmk__opt_context_controld, N_("How a cluster node should react if notified of its own fencing"), N_("A cluster node may receive notification of a \"succeeded\" " "fencing that targeted it if fencing is misconfigured, or if " "fabric fencing is in use that doesn't cut cluster communication. " "Use \"stop\" to attempt to immediately stop Pacemaker and stay " "stopped, or \"panic\" to attempt to immediately reboot the local " "node, falling back to stop on failure."), }, { PCMK_OPT_ELECTION_TIMEOUT, NULL, "time", NULL, "2min", pcmk__valid_interval_spec, pcmk__opt_context_controld, N_("*** Advanced Use Only ***"), N_("Declare an election failed if it is not decided within this much " "time. If you need to adjust this value, it probably indicates " "the presence of a bug."), }, { PCMK_OPT_SHUTDOWN_ESCALATION, NULL, "time", NULL, "20min", pcmk__valid_interval_spec, pcmk__opt_context_controld, N_("*** Advanced Use Only ***"), N_("Exit immediately if shutdown does not complete within this much " "time. If you need to adjust this value, it probably indicates " "the presence of a bug."), }, { PCMK_OPT_JOIN_INTEGRATION_TIMEOUT, "crmd-integration-timeout", "time", NULL, "3min", pcmk__valid_interval_spec, pcmk__opt_context_controld, N_("*** Advanced Use Only ***"), N_("If you need to adjust this value, it probably indicates " "the presence of a bug."), }, { PCMK_OPT_JOIN_FINALIZATION_TIMEOUT, "crmd-finalization-timeout", "time", NULL, "30min", pcmk__valid_interval_spec, pcmk__opt_context_controld, N_("*** Advanced Use Only ***"), N_("If you need to adjust this value, it probably indicates " "the presence of a bug."), }, { PCMK_OPT_TRANSITION_DELAY, "crmd-transition-delay", "time", NULL, "0s", pcmk__valid_interval_spec, pcmk__opt_context_controld, N_("*** Advanced Use Only *** " "Enabling this option will slow down cluster recovery under all " "conditions"), N_("Delay cluster recovery for this much time to allow for additional " "events to occur. Useful if your configuration is sensitive to " "the order in which ping updates arrive."), }, { PCMK_OPT_NO_QUORUM_POLICY, NULL, "select", PCMK_VALUE_STOP ", " PCMK_VALUE_FREEZE ", " PCMK_VALUE_IGNORE ", " PCMK_VALUE_DEMOTE ", " PCMK_VALUE_FENCE_LEGACY, PCMK_VALUE_STOP, pcmk__valid_no_quorum_policy, pcmk__opt_context_schedulerd, N_("What to do when the cluster does not have quorum"), NULL, }, { PCMK_OPT_SHUTDOWN_LOCK, NULL, "boolean", NULL, PCMK_VALUE_FALSE, pcmk__valid_boolean, pcmk__opt_context_schedulerd, N_("Whether to lock resources to a cleanly shut down node"), N_("When true, resources active on a node when it is cleanly shut down " "are kept \"locked\" to that node (not allowed to run elsewhere) " "until they start again on that node after it rejoins (or for at " "most shutdown-lock-limit, if set). Stonith resources and " "Pacemaker Remote connections are never locked. Clone and bundle " "instances and the promoted role of promotable clones are " "currently never locked, though support could be added in a future " "release."), }, { PCMK_OPT_SHUTDOWN_LOCK_LIMIT, NULL, "time", NULL, "0", pcmk__valid_interval_spec, pcmk__opt_context_schedulerd, N_("Do not lock resources to a cleanly shut down node longer than " "this"), N_("If shutdown-lock is true and this is set to a nonzero time " "duration, shutdown locks will expire after this much time has " "passed since the shutdown was initiated, even if the node has not " "rejoined."), }, { PCMK_OPT_ENABLE_ACL, NULL, "boolean", NULL, PCMK_VALUE_FALSE, pcmk__valid_boolean, pcmk__opt_context_based, N_("Enable Access Control Lists (ACLs) for the CIB"), NULL, }, { PCMK_OPT_SYMMETRIC_CLUSTER, NULL, "boolean", NULL, PCMK_VALUE_TRUE, pcmk__valid_boolean, pcmk__opt_context_schedulerd, N_("Whether resources can run on any node by default"), NULL, }, { PCMK_OPT_MAINTENANCE_MODE, NULL, "boolean", NULL, PCMK_VALUE_FALSE, pcmk__valid_boolean, pcmk__opt_context_schedulerd, N_("Whether the cluster should refrain from monitoring, starting, and " "stopping resources"), NULL, }, { PCMK_OPT_START_FAILURE_IS_FATAL, NULL, "boolean", NULL, PCMK_VALUE_TRUE, pcmk__valid_boolean, pcmk__opt_context_schedulerd, N_("Whether a start failure should prevent a resource from being " "recovered on the same node"), N_("When true, the cluster will immediately ban a resource from a node " "if it fails to start there. When false, the cluster will instead " "check the resource's fail count against its migration-threshold.") }, { PCMK_OPT_ENABLE_STARTUP_PROBES, NULL, "boolean", NULL, PCMK_VALUE_TRUE, pcmk__valid_boolean, pcmk__opt_context_schedulerd, N_("Whether the cluster should check for active resources during " "start-up"), NULL, }, // Fencing-related options { PCMK_OPT_STONITH_ENABLED, NULL, "boolean", NULL, PCMK_VALUE_TRUE, pcmk__valid_boolean, pcmk__opt_context_schedulerd, N_("*** Advanced Use Only *** " "Whether nodes may be fenced as part of recovery"), N_("If false, unresponsive nodes are immediately assumed to be " "harmless, and resources that were active on them may be recovered " "elsewhere. This can result in a \"split-brain\" situation, " "potentially leading to data loss and/or service unavailability."), }, { PCMK_OPT_STONITH_ACTION, NULL, "select", "reboot, off, poweroff", PCMK_ACTION_REBOOT, pcmk__is_fencing_action, pcmk__opt_context_schedulerd, N_("Action to send to fence device when a node needs to be fenced " "(\"poweroff\" is a deprecated alias for \"off\")"), NULL, }, { PCMK_OPT_STONITH_TIMEOUT, NULL, "time", NULL, "60s", pcmk__valid_interval_spec, pcmk__opt_context_schedulerd, N_("How long to wait for on, off, and reboot fence actions to complete " "by default"), NULL, }, { PCMK_OPT_HAVE_WATCHDOG, NULL, "boolean", NULL, PCMK_VALUE_FALSE, pcmk__valid_boolean, pcmk__opt_context_schedulerd, N_("Whether watchdog integration is enabled"), N_("This is set automatically by the cluster according to whether SBD " "is detected to be in use. User-configured values are ignored. " "The value `true` is meaningful if diskless SBD is used and " "`stonith-watchdog-timeout` is nonzero. In that case, if fencing " "is required, watchdog-based self-fencing will be performed via " "SBD without requiring a fencing resource explicitly configured."), }, { /* @COMPAT Currently, unparsable values default to -1 (auto-calculate), * while missing values default to 0 (disable). All values are accepted * (unless the controller finds that the value conflicts with the * SBD_WATCHDOG_TIMEOUT). * * At a compatibility break: properly validate as a timeout, let * either negative values or a particular string like "auto" mean auto- * calculate, and use 0 as the single default for when the option either * is unset or fails to validate. */ PCMK_OPT_STONITH_WATCHDOG_TIMEOUT, NULL, "time", NULL, "0", NULL, pcmk__opt_context_controld, N_("How long before nodes can be assumed to be safely down when " "watchdog-based self-fencing via SBD is in use"), N_("If this is set to a positive value, lost nodes are assumed to " "achieve self-fencing using watchdog-based SBD within this much " "time. This does not require a fencing resource to be explicitly " "configured, though a fence_watchdog resource can be configured, to " "limit use to specific nodes. If this is set to 0 (the default), " "the cluster will never assume watchdog-based self-fencing. If this " "is set to a negative value, the cluster will use twice the local " "value of the `SBD_WATCHDOG_TIMEOUT` environment variable if that " "is positive, or otherwise treat this as 0. WARNING: When used, " "this timeout must be larger than `SBD_WATCHDOG_TIMEOUT` on all " "nodes that use watchdog-based SBD, and Pacemaker will refuse to " "start on any of those nodes where this is not true for the local " "value or SBD is not active. When this is set to a negative value, " "`SBD_WATCHDOG_TIMEOUT` must be set to the same value on all nodes " "that use SBD, otherwise data corruption or loss could occur."), }, { PCMK_OPT_STONITH_MAX_ATTEMPTS, NULL, "integer", NULL, "10", pcmk__valid_positive_int, pcmk__opt_context_controld, N_("How many times fencing can fail before it will no longer be " "immediately re-attempted on a target"), NULL, }, { PCMK_OPT_CONCURRENT_FENCING, NULL, "boolean", NULL, PCMK__CONCURRENT_FENCING_DEFAULT, pcmk__valid_boolean, pcmk__opt_context_schedulerd, N_("Allow performing fencing operations in parallel"), NULL, }, { PCMK_OPT_STARTUP_FENCING, NULL, "boolean", NULL, PCMK_VALUE_TRUE, pcmk__valid_boolean, pcmk__opt_context_schedulerd, N_("*** Advanced Use Only *** " "Whether to fence unseen nodes at start-up"), N_("Setting this to false may lead to a \"split-brain\" situation, " "potentially leading to data loss and/or service unavailability."), }, { PCMK_OPT_PRIORITY_FENCING_DELAY, NULL, "time", NULL, "0", pcmk__valid_interval_spec, pcmk__opt_context_schedulerd, N_("Apply fencing delay targeting the lost nodes with the highest " "total resource priority"), N_("Apply specified delay for the fencings that are targeting the lost " "nodes with the highest total resource priority in case we don't " "have the majority of the nodes in our cluster partition, so that " "the more significant nodes potentially win any fencing match, " "which is especially meaningful under split-brain of 2-node " "cluster. A promoted resource instance takes the base priority + 1 " "on calculation if the base priority is not 0. Any static/random " "delays that are introduced by `pcmk_delay_base/max` configured " "for the corresponding fencing resources will be added to this " "delay. This delay should be significantly greater than, safely " "twice, the maximum `pcmk_delay_base/max`. By default, priority " "fencing delay is disabled."), }, { PCMK_OPT_NODE_PENDING_TIMEOUT, NULL, "time", NULL, "0", pcmk__valid_interval_spec, pcmk__opt_context_schedulerd, N_("How long to wait for a node that has joined the cluster to join " "the controller process group"), N_("Fence nodes that do not join the controller process group within " "this much time after joining the cluster, to allow the cluster " "to continue managing resources. A value of 0 means never fence " "pending nodes. Setting the value to 2h means fence nodes after " "2 hours."), }, { PCMK_OPT_CLUSTER_DELAY, NULL, "time", NULL, "60s", pcmk__valid_interval_spec, pcmk__opt_context_schedulerd, N_("Maximum time for node-to-node communication"), N_("The node elected Designated Controller (DC) will consider an action " "failed if it does not get a response from the node executing the " "action within this time (after considering the action's own " "timeout). The \"correct\" value will depend on the speed and " "load of your network and cluster nodes.") }, // Limits { PCMK_OPT_LOAD_THRESHOLD, NULL, "percentage", NULL, "80%", pcmk__valid_percentage, pcmk__opt_context_controld, N_("Maximum amount of system load that should be used by cluster " "nodes"), N_("The cluster will slow down its recovery process when the amount of " "system resources used (currently CPU) approaches this limit"), }, { PCMK_OPT_NODE_ACTION_LIMIT, NULL, "integer", NULL, "0", pcmk__valid_int, pcmk__opt_context_controld, N_("Maximum number of jobs that can be scheduled per node (defaults to " "2x cores)"), NULL, }, { PCMK_OPT_BATCH_LIMIT, NULL, "integer", NULL, "0", pcmk__valid_int, pcmk__opt_context_schedulerd, N_("Maximum number of jobs that the cluster may execute in parallel " "across all nodes"), N_("The \"correct\" value will depend on the speed and load of your " "network and cluster nodes. If set to 0, the cluster will " "impose a dynamically calculated limit when any node has a " "high load."), }, { PCMK_OPT_MIGRATION_LIMIT, NULL, "integer", NULL, "-1", pcmk__valid_int, pcmk__opt_context_schedulerd, N_("The number of live migration actions that the cluster is allowed " "to execute in parallel on a node (-1 means no limit)"), NULL, }, { PCMK_OPT_CLUSTER_IPC_LIMIT, NULL, "integer", NULL, "500", pcmk__valid_positive_int, pcmk__opt_context_based, N_("Maximum IPC message backlog before disconnecting a cluster daemon"), N_("Raise this if log has \"Evicting client\" messages for cluster " "daemon PIDs (a good value is the number of resources in the " "cluster multiplied by the number of nodes)."), }, // Orphans and stopping { PCMK_OPT_STOP_ALL_RESOURCES, NULL, "boolean", NULL, PCMK_VALUE_FALSE, pcmk__valid_boolean, pcmk__opt_context_schedulerd, N_("Whether the cluster should stop all active resources"), NULL, }, { PCMK_OPT_STOP_ORPHAN_RESOURCES, NULL, "boolean", NULL, PCMK_VALUE_TRUE, pcmk__valid_boolean, pcmk__opt_context_schedulerd, N_("Whether to stop resources that were removed from the " "configuration"), NULL, }, { PCMK_OPT_STOP_ORPHAN_ACTIONS, NULL, "boolean", NULL, PCMK_VALUE_TRUE, pcmk__valid_boolean, pcmk__opt_context_schedulerd, N_("Whether to cancel recurring actions removed from the " "configuration"), NULL, }, { PCMK__OPT_REMOVE_AFTER_STOP, NULL, "boolean", NULL, PCMK_VALUE_FALSE, pcmk__valid_boolean, pcmk__opt_context_schedulerd, N_("*** Deprecated *** " "Whether to remove stopped resources from the executor"), N_("Values other than default are poorly tested and potentially " "dangerous. This option will be removed in a future release."), }, // Storing inputs { PCMK_OPT_PE_ERROR_SERIES_MAX, NULL, "integer", NULL, "-1", pcmk__valid_int, pcmk__opt_context_schedulerd, N_("The number of scheduler inputs resulting in errors to save"), N_("Zero to disable, -1 to store unlimited."), }, { PCMK_OPT_PE_WARN_SERIES_MAX, NULL, "integer", NULL, "5000", pcmk__valid_int, pcmk__opt_context_schedulerd, N_("The number of scheduler inputs resulting in warnings to save"), N_("Zero to disable, -1 to store unlimited."), }, { PCMK_OPT_PE_INPUT_SERIES_MAX, NULL, "integer", NULL, "4000", pcmk__valid_int, pcmk__opt_context_schedulerd, N_("The number of scheduler inputs without errors or warnings to save"), N_("Zero to disable, -1 to store unlimited."), }, // Node health { PCMK_OPT_NODE_HEALTH_STRATEGY, NULL, "select", PCMK__VALUE_NONE ", " PCMK__VALUE_MIGRATE_ON_RED ", " PCMK__VALUE_ONLY_GREEN ", " PCMK__VALUE_PROGRESSIVE ", " PCMK__VALUE_CUSTOM, PCMK__VALUE_NONE, pcmk__validate_health_strategy, pcmk__opt_context_schedulerd, N_("How cluster should react to node health attributes"), N_("Requires external entities to create node attributes (named with " "the prefix \"#health\") with values \"red\", \"yellow\", or " "\"green\".") }, { PCMK_OPT_NODE_HEALTH_BASE, NULL, "integer", NULL, "0", pcmk__valid_int, pcmk__opt_context_schedulerd, N_("Base health score assigned to a node"), N_("Only used when \"node-health-strategy\" is set to " "\"progressive\"."), }, { PCMK_OPT_NODE_HEALTH_GREEN, NULL, "integer", NULL, "0", pcmk__valid_int, pcmk__opt_context_schedulerd, N_("The score to use for a node health attribute whose value is " "\"green\""), N_("Only used when \"node-health-strategy\" is set to \"custom\" or " "\"progressive\"."), }, { PCMK_OPT_NODE_HEALTH_YELLOW, NULL, "integer", NULL, "0", pcmk__valid_int, pcmk__opt_context_schedulerd, N_("The score to use for a node health attribute whose value is " "\"yellow\""), N_("Only used when \"node-health-strategy\" is set to \"custom\" or " "\"progressive\"."), }, { PCMK_OPT_NODE_HEALTH_RED, NULL, "integer", NULL, "-INFINITY", pcmk__valid_int, pcmk__opt_context_schedulerd, N_("The score to use for a node health attribute whose value is " "\"red\""), N_("Only used when \"node-health-strategy\" is set to \"custom\" or " "\"progressive\".") }, // Placement strategy { PCMK_OPT_PLACEMENT_STRATEGY, NULL, "select", PCMK_VALUE_DEFAULT ", " PCMK_VALUE_UTILIZATION ", " PCMK_VALUE_MINIMAL ", " PCMK_VALUE_BALANCED, PCMK_VALUE_DEFAULT, pcmk__valid_placement_strategy, pcmk__opt_context_schedulerd, N_("How the cluster should allocate resources to nodes"), NULL, }, }; /* * Environment variable option handling */ /*! * \internal * \brief Get the value of a Pacemaker environment variable option * * If an environment variable option is set, with either a PCMK_ or (for * backward compatibility) HA_ prefix, log and return the value. * * \param[in] option Environment variable name (without prefix) * * \return Value of environment variable option, or NULL in case of * option name too long or value not found */ const char * pcmk__env_option(const char *option) { const char *const prefixes[] = {"PCMK_", "HA_"}; char env_name[NAME_MAX]; const char *value = NULL; CRM_CHECK(!pcmk__str_empty(option), return NULL); for (int i = 0; i < PCMK__NELEM(prefixes); i++) { int rv = snprintf(env_name, NAME_MAX, "%s%s", prefixes[i], option); if (rv < 0) { crm_err("Failed to write %s%s to buffer: %s", prefixes[i], option, strerror(errno)); return NULL; } if (rv >= sizeof(env_name)) { crm_trace("\"%s%s\" is too long", prefixes[i], option); continue; } value = getenv(env_name); if (value != NULL) { crm_trace("Found %s = %s", env_name, value); return value; } } crm_trace("Nothing found for %s", option); return NULL; } /*! * \brief Set or unset a Pacemaker environment variable option * * Set an environment variable option with a \c "PCMK_" prefix and optionally * an \c "HA_" prefix for backward compatibility. * * \param[in] option Environment variable name (without prefix) * \param[in] value New value (or NULL to unset) * \param[in] compat If false and \p value is not \c NULL, set only * \c "PCMK_