[
https://issues.apache.org/jira/browse/MAPREDUCE-2697?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13097284#comment-13097284
]
Arun C Murthy commented on MAPREDUCE-2697:
------------------------------------------
Forgot to add - the crux of the solution is that we limit the amount of
'overhead' for applications in the cluster to a percent defined by
yarn.capacity-scheduler.maximum-am-resource-percent. Thus, the #concurrent apps
scales well with cluster capacity and #apps don't have to 'configured' by
admins.
> Enhance CS to cap concurrently running jobs
> -------------------------------------------
>
> Key: MAPREDUCE-2697
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-2697
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Components: mrv2
> Reporter: Arun C Murthy
> Assignee: Arun C Murthy
> Fix For: 0.23.0
>
> Attachments: MAPREDUCE-2697.patch, MAPREDUCE-2697.patch,
> MAPREDUCE-2697.patch
>
>
> Enhance CS to cap concurrently running jobs ala 0.20.203
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
