You are viewing a plain text version of this content. The canonical link for it is here.
Posted to yarn-issues@hadoop.apache.org by "Qi Zhu (Jira)" <ji...@apache.org> on 2021/05/05 03:06:00 UTC
[jira] [Comment Edited] (YARN-9927) RM multi-thread event
processing mechanism
[ https://issues.apache.org/jira/browse/YARN-9927?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17339383#comment-17339383 ]
Qi Zhu edited comment on YARN-9927 at 5/5/21, 3:05 AM:
-------------------------------------------------------
Great review and investigation!
Thanks very much [~ebadger] [~ebadger] .
I agree with you that we should do some stress test done via SLS or manually. And the more generic way of event handling is a great improvement in YARN.
I will investigate how to use SLS to confirm the improvement.
And about the test, i will change it to test both the multi-thread and the single one.
was (Author: zhuqi):
Great review and investigation!
Thanks very much [~ebadger] [~ebadger] .
I agree with you that we should do some stress test done via SLS or manually. And the more generic way of event handling is a great improvement in YARN.
And about the test, i will change it to test both the multi-thread and the single one.
> RM multi-thread event processing mechanism
> ------------------------------------------
>
> Key: YARN-9927
> URL: https://issues.apache.org/jira/browse/YARN-9927
> Project: Hadoop YARN
> Issue Type: Sub-task
> Components: yarn
> Affects Versions: 3.0.0, 2.9.2
> Reporter: hcarrot
> Assignee: Qi Zhu
> Priority: Major
> Attachments: RM multi-thread event processing mechanism.pdf, YARN-9927.001.patch, YARN-9927.002.patch, YARN-9927.003.patch, YARN-9927.004.patch, YARN-9927.005.patch
>
>
> Recently, we have observed serious event blocking in RM event dispatcher queue. After analysis of RM event monitoring data and RM event processing logic, we found that
> 1) environment: a cluster with thousands of nodes
> 2) RMNodeStatusEvent dominates 90% time consumption of RM event scheduler
> 3) Meanwhile, RM event processing is in a single-thread mode, and It results in the low headroom of RM event scheduler, thus performance of RM.
> So we proposed a RM multi-thread event processing mechanism to improve RM performance.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org