sin/samba-mirror
1
0
Fork 0
mirror of https://github.com/samba-team/samba.git synced 2024-12-23 17:34:34 +03:00
Code

recoverd: Don't continue if the current node gets banned

Browse Source 
Can not continue with recovery or monitoring cluster.

Signed-off-by: Martin Schwenke <martin@meltin.net>
Pair-programmed-with: Amitay Isaacs <amitay@gmail.com>

(This used to be ctdb commit 14399de1dd0bd8dabf1f48b1457e3ccb37589d8a)
This commit is contained in:
Martin Schwenke 2013-06-28 16:31:07 +10:00 committed by Amitay Isaacs
parent b29b6ae39e
commit aa79a656a7
1 changed files with 19 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
ctdb/server/ctdb_recoverd.c
View File

@ -1546,12 +1546,13 @@ static void takeover_fail_callback(struct ctdb_context *ctdb, uint32_t node_pnn,
}
static void ban_misbehaving_nodes(struct ctdb_recoverd *rec)
static void ban_misbehaving_nodes(struct ctdb_recoverd *rec, bool *self_ban)
{
struct ctdb_context *ctdb = rec->ctdb;
int i;
struct ctdb_banning_state *ban_state;
*self_ban = false;
for (i=0; i<ctdb->num_nodes; i++) {
if (ctdb->nodes[i]->ban_state == NULL) {
continue;
@ -1566,6 +1567,11 @@ static void ban_misbehaving_nodes(struct ctdb_recoverd *rec)
ctdb->tunable.recovery_ban_period));
ctdb_ban_node(rec, ctdb->nodes[i]->pnn, ctdb->tunable.recovery_ban_period);
ban_state->count = 0;
/* Banning ourself? */
if (ctdb->nodes[i]->pnn == rec->ctdb->pnn) {
*self_ban = true;
}
}
}
@ -1585,13 +1591,18 @@ static int do_recovery(struct ctdb_recoverd *rec,
uint32_t *nodes;
struct timeval start_time;
uint32_t culprit = (uint32_t)-1;
bool self_ban;
DEBUG(DEBUG_NOTICE, (__location__ " Starting do_recovery\n"));
/* if recovery fails, force it again */
rec->need_recovery = true;
ban_misbehaving_nodes(rec);
ban_misbehaving_nodes(rec, &self_ban);
if (self_ban) {
DEBUG(DEBUG_NOTICE, ("This node was banned, aborting recovery\n"));
return -1;
}
if (ctdb->tunable.verify_recovery_lock != 0) {
DEBUG(DEBUG_ERR,("Taking out recovery lock from recovery daemon\n"));
@ -3333,7 +3344,7 @@ static void main_loop(struct ctdb_context *ctdb, struct ctdb_recoverd *rec,
struct ctdb_vnn_map *remote_vnnmap=NULL;
int32_t debug_level;
int i, j, ret;
bool self_ban;
/* verify that the main daemon is still running */
@ -3411,7 +3422,11 @@ static void main_loop(struct ctdb_context *ctdb, struct ctdb_recoverd *rec,
/* remember our own node flags */
rec->node_flags = nodemap->nodes[pnn].flags;
ban_misbehaving_nodes(rec);
ban_misbehaving_nodes(rec, &self_ban);
if (self_ban) {
DEBUG(DEBUG_NOTICE, ("This node was banned, restart main_loop\n"));
return;
}
/* if the local daemon is STOPPED or BANNED, we verify that the databases are
also frozen and thet the recmode is set to active.