2 monitoring links to all other nodes to detect dead nodes
5 Copyright (C) Ronnie Sahlberg 2007
7 This program is free software; you can redistribute it and/or modify
8 it under the terms of the GNU General Public License as published by
9 the Free Software Foundation; either version 3 of the License, or
10 (at your option) any later version.
12 This program is distributed in the hope that it will be useful,
13 but WITHOUT ANY WARRANTY; without even the implied warranty of
14 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 GNU General Public License for more details.
17 You should have received a copy of the GNU General Public License
18 along with this program; if not, see <http://www.gnu.org/licenses/>.
22 #include "lib/events/events.h"
23 #include "system/filesys.h"
24 #include "system/wait.h"
25 #include "../include/ctdb_private.h"
29 see if any nodes are dead
31 static void ctdb_check_for_dead_nodes(struct event_context *ev, struct timed_event *te,
32 struct timeval t, void *private_data)
34 struct ctdb_context *ctdb = talloc_get_type(private_data, struct ctdb_context);
37 /* send a keepalive to all other nodes, unless */
38 for (i=0;i<ctdb->num_nodes;i++) {
39 struct ctdb_node *node = ctdb->nodes[i];
41 if (node->flags & NODE_FLAGS_DELETED) {
45 if (node->pnn == ctdb->pnn) {
49 if (node->flags & NODE_FLAGS_DISCONNECTED) {
50 /* it might have come alive again */
51 if (node->rx_cnt != 0) {
52 ctdb_node_connected(node);
58 if (node->rx_cnt == 0) {
66 if (node->dead_count >= ctdb->tunable.keepalive_limit) {
67 DEBUG(DEBUG_NOTICE,("dead count reached for node %u\n", node->pnn));
69 ctdb_send_keepalive(ctdb, node->pnn);
70 /* maybe tell the transport layer to kill the
76 DEBUG(DEBUG_DEBUG,("sending keepalive to %u\n", node->pnn));
77 ctdb_send_keepalive(ctdb, node->pnn);
82 event_add_timed(ctdb->ev, ctdb->keepalive_ctx,
83 timeval_current_ofs(ctdb->tunable.keepalive_interval, 0),
84 ctdb_check_for_dead_nodes, ctdb);
88 void ctdb_start_keepalive(struct ctdb_context *ctdb)
90 struct timed_event *te;
92 ctdb->keepalive_ctx = talloc_new(ctdb);
93 CTDB_NO_MEMORY_FATAL(ctdb, ctdb->keepalive_ctx);
95 te = event_add_timed(ctdb->ev, ctdb->keepalive_ctx,
96 timeval_current_ofs(ctdb->tunable.keepalive_interval, 0),
97 ctdb_check_for_dead_nodes, ctdb);
98 CTDB_NO_MEMORY_FATAL(ctdb, te);
100 DEBUG(DEBUG_NOTICE,("Keepalive monitoring has been started\n"));
103 void ctdb_stop_keepalive(struct ctdb_context *ctdb)
105 talloc_free(ctdb->keepalive_ctx);
106 ctdb->keepalive_ctx = NULL;