[
https://issues.apache.org/jira/browse/YARN-5262?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Jason Lowe updated YARN-5262:
-----------------------------
Fix Version/s: (was: 2.9.0)
2.7.4
2.6.5
2.8.0
Thanks, [~rohithsharma]! I committed this to branch-2.8, branch-2.7, and
branch-2.6 as well.
> Optimize sending RMNodeFinishedContainersPulledByAMEvent for every AM
> heartbeat
> -------------------------------------------------------------------------------
>
> Key: YARN-5262
> URL: https://issues.apache.org/jira/browse/YARN-5262
> Project: Hadoop YARN
> Issue Type: Bug
> Components: resourcemanager
> Reporter: Rohith Sharma K S
> Assignee: Rohith Sharma K S
> Fix For: 2.8.0, 2.6.5, 2.7.4
>
> Attachments: 0001-YARN-5262.patch, 0002-YARN-5262.patch
>
>
> It is observed that RM triggers an one event for every
> ApplicationMaster#allocate request in the following trace. This is not
> necessarily required and it can be optimized such that send only if any
> containers are there to acknowledge to NodeManager.
> {code}
> RMAppAttemptImpl.sendFinishedContainersToNM() line: 1871
> RMAppAttemptImpl.pullJustFinishedContainers() line: 805
> ApplicationMasterService.allocate(AllocateRequest) line: 567
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org
