gvsafronov/futriix
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Cluster: improve crash-recovery safety after failover auth vote.

Browse Source 
Add AE_BARRIER to the writable event loop so that slaves requesting
votes can't be served before we re-enter the event loop in the next
iteration, so clusterBeforeSleep() will fsync to disk in time.
Also add the call to explicitly fsync, given that we modified the last
vote epoch variable.
This commit is contained in:
antirez 2018-02-27 10:25:08 +01:00
parent 043763d040
commit 17cbb54919
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/cluster.c
View File

@ -2156,7 +2156,7 @@ void clusterReadHandler(aeEventLoop *el, int fd, void *privdata, int mask) {
* from event handlers that will do stuff with the same link later. */ * from event handlers that will do stuff with the same link later. */
void clusterSendMessage(clusterLink *link, unsigned char *msg, size_t msglen) { void clusterSendMessage(clusterLink *link, unsigned char *msg, size_t msglen) {
if (sdslen(link->sndbuf) == 0 && msglen != 0) if (sdslen(link->sndbuf) == 0 && msglen != 0)
aeCreateFileEvent(server.el,link->fd,AE_WRITABLE, aeCreateFileEvent(server.el,link->fd,AE_WRITABLE|AE_BARRIER,
clusterWriteHandler,link); clusterWriteHandler,link);
link->sndbuf = sdscatlen(link->sndbuf, msg, msglen); link->sndbuf = sdscatlen(link->sndbuf, msg, msglen);
@ -2691,9 +2691,10 @@ void clusterSendFailoverAuthIfNeeded(clusterNode *node, clusterMsg *request) {
} }
/* We can vote for this slave. */ /* We can vote for this slave. */
clusterSendFailoverAuth(node);
server.cluster->lastVoteEpoch = server.cluster->currentEpoch; server.cluster->lastVoteEpoch = server.cluster->currentEpoch;
node->slaveof->voted_time = mstime(); node->slaveof->voted_time = mstime();
clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|CLUSTER_TODO_FSYNC_CONFIG);
clusterSendFailoverAuth(node);
serverLog(LL_WARNING, "Failover auth granted to %.40s for epoch %llu", serverLog(LL_WARNING, "Failover auth granted to %.40s for epoch %llu",
node->name, (unsigned long long) server.cluster->currentEpoch); node->name, (unsigned long long) server.cluster->currentEpoch);
} }