fluencelabs/redis
1
0
Fork 0
mirror of https://github.com/fluencelabs/redis synced 2025-03-20 09:30:55 +00:00
Code Issues Projects Releases Wiki Activity

Cluster: more robust FAIL flag cleaup.

Browse Source 
If we have a master in FAIL state that's reachable again, and apparently
no one is going to serve its slots, clear the FAIL flag and let the
cluster continue with its operations again.
This commit is contained in:
antirez 2013-03-05 15:05:32 +01:00
parent 1a02b7440a
commit bac57ad14b
1 changed files with 29 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
src/cluster.c
View File

@ -611,11 +611,38 @@ void markNodeAsFailingIfNeeded(clusterNode *node) {
* Currently we only revert the FAIL state if there are no slaves for this
* node, so that no election was possible. */
void clearNodeFailureIfNeeded(clusterNode *node) {
if (node->flags & REDIS_NODE_FAIL && !node->numslaves) {
int changes = 0;
time_t now = time(NULL);
redisAssert(node->flags & REDIS_NODE_FAIL);
/* For slaves we always clear the FAIL flag if we can contact the
* node again. */
if (node->flags & REDIS_NODE_SLAVE) {
redisLog(REDIS_NOTICE,
"Clear FAIL state for node %.40s: is reachable and has no slaves.",
"Clear FAIL state for node %.40s: slave is already reachable.",
node->name);
node->flags &= ~REDIS_NODE_FAIL;
changes++;
}
/* If it is a master and...
* 1) The FAIL state was set more than 2 times the node timeout + 10 sec.
* 2) It is yet serving slots from our point of view (not failed over).
* Apparently no one is going to fix these slots, clear the FAIL flag. */
if (node->flags & REDIS_NODE_MASTER &&
node->numslots > 0 &&
(now - node->fail_time) > (server.cluster->node_timeout*2+10))
{
redisLog(REDIS_NOTICE,
"Clear FAIL state for node %.40s: is reachable again and nobody is serving its slots after some time.",
node->name);
node->flags &= ~REDIS_NODE_FAIL;
changes++;
}
/* Update state and save config. */
if (changes) {
clusterUpdateState();
clusterSaveConfigOrDie();
}