[
https://issues.apache.org/jira/browse/RATIS-727?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16956918#comment-16956918
]
Lokesh Jain commented on RATIS-727:
-----------------------------------
> Has the client tried the other servers?
This is from a heap dump so I do not know if the client retried other servers.
We can possibly look at logs for the client behaviour. I agree RATIS-574 could
have contributed to these many retries.
> server cannot handle 7 requests at the same time
The server can handle the requests. The problem is that all these attempts
contribute to garbage. Ideally for a NotLeaderException the request should not
be retried on the same server again.
> Garbage collection due to same request retries on a follower
> ------------------------------------------------------------
>
> Key: RATIS-727
> URL: https://issues.apache.org/jira/browse/RATIS-727
> Project: Ratis
> Issue Type: Bug
> Components: client
> Reporter: Lokesh Jain
> Priority: Major
>
> In a heap dump it could be seen that a client request retries on the same
> follower multiple times and every time the request is rejected with a
> NotLeaderException. In case of Ozone it is a WriteChunk request which leads
> to garbage collection of 16MB for every request. In the heap dump a client
> request retries multiple times leading to garbage collection of ~100MB.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
