[
https://issues.apache.org/jira/browse/YARN-9335?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16787541#comment-16787541
]
Abhishek Modi commented on YARN-9335:
-------------------------------------
There are two major issues right now. Hbase client has a huge retry time out
which causes threads to get blocked at write entities for async writes. For
sync writes, threads get blocked at synchronized blocks and that will bloat up
the event queue causing huge memory pressure on NM as well as delay in
processing of other events.
> [atsv2] Restrict the number of elements held in NM timeline collector when
> backend is unreachable
> -------------------------------------------------------------------------------------------------
>
> Key: YARN-9335
> URL: https://issues.apache.org/jira/browse/YARN-9335
> Project: Hadoop YARN
> Issue Type: Sub-task
> Reporter: Vrushali C
> Assignee: Abhishek Modi
> Priority: Major
>
> For ATSv2 , if the backend is unreachable, the number/size of data held in
> timeline collector's memory increases significantly. This is not good for the
> NM memory.
> Filing jira to set a limit on how many/much should be retained by the
> timeline collector in memory in case the backend is not reachable.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
