[
https://issues.apache.org/jira/browse/YARN-6516?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15983443#comment-15983443
]
Yufei Gu commented on YARN-6516:
--------------------------------
IIUC, there were only 40 containers in your cluster over time. More likely it
is not a performance issue. Some thoughts and questions:
# Continuous scheduling is unnecessary for a cluster with 2500 nodes. Turn on
the assignmultiple should be enough.
# There were 39 containers for 39 apps in your cluster. I guess these
containers are all for AM. No tasks for apps? That's impossible for MR jobs.
# How did you conclude "assigning a container took 3ms"?
> FairScheduler:the algorithm of assignContainer is so slow for it only can
> assign a thousand containers per second
> -----------------------------------------------------------------------------------------------------------------
>
> Key: YARN-6516
> URL: https://issues.apache.org/jira/browse/YARN-6516
> Project: Hadoop YARN
> Issue Type: Improvement
> Components: fairscheduler
> Affects Versions: 2.7.2
> Reporter: JackZhou
>
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
