[
https://issues.apache.org/jira/browse/KUDU-2322?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16372447#comment-16372447
]
Todd Lipcon commented on KUDU-2322:
-----------------------------------
[~mpercy] can you take a look at this? It seems if a follower's logs have been
GCed we should probably evict it more aggressively rather than waiting on a new
NON_VOTER to copy. Or at least we should not log once per inbound write :)
> Leader spews logs when follower falls behind log GC
> ---------------------------------------------------
>
> Key: KUDU-2322
> URL: https://issues.apache.org/jira/browse/KUDU-2322
> Project: Kudu
> Issue Type: Bug
> Components: consensus
> Affects Versions: 1.7.0
> Reporter: Todd Lipcon
> Priority: Critical
>
> I'm running a YCSB-based write stress test and found that one of the
> followers fell behind enough that its logs got GCed by the leader. At this
> point, the leader started logging about 100 messages per second indicating
> that it could not obtain a request for this peer.
> I believe this is a regression since 1.6, since before 3-4-3 replication we
> would have evicted the replica as soon as it fell behind GC.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
