[
https://issues.apache.org/jira/browse/YARN-1015?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16241212#comment-16241212
]
Arun Suresh commented on YARN-1015:
-----------------------------------
Thanks for the patch [~haibochen]
So couple of comments.
* I assume the scheduler will attempt to allocate OPP containers only after all
reserved containers AND after it has allocated GUAR containers on the node - In
which case, I don't think you should even attempt to promote the container in
call (I was referring to the TODO you added).
* I think a better way to auto-promote would be at the time a guaranteed
container completes, the RM can check if there an OPP containers of the app
which can be promoted - need not be the same app, it can also possibly be
another app from the same queue - or we can go the the other way, and decide to
promote locally at the NM if we know that an app has running opportunistic
container on the same node where it's guaranteed container has completed.
> FS should watch node resource utilization and allocate opportunistic
> containers if appropriate
> ----------------------------------------------------------------------------------------------
>
> Key: YARN-1015
> URL: https://issues.apache.org/jira/browse/YARN-1015
> Project: Hadoop YARN
> Issue Type: Sub-task
> Reporter: Arun C Murthy
> Assignee: Haibo Chen
> Attachments: YARN-1015-YARN-1011.00.patch,
> YARN-1015-YARN-1011.01.patch, YARN-1015-YARN-1011.prelim.patch
>
>
> FS should looks at resource utilization of nodes (provided by NM in
> heartbeat) and allocate opportunistic containers if the resource utilization
> of the node is below its allocation threshold.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
