[
https://issues.apache.org/jira/browse/YARN-408?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13583625#comment-13583625
]
Mayank Bansal commented on YARN-408:
------------------------------------
Yeah sure.
There are two intents to change this value
1. Make it enable by default
2. The algorithm which we use to check for the applications to get the
scheduling opportunity is based on heart beat from the NM , hence if we just
use the number of racks it will not be much of the value add for actually to
achieve the node locality. The intent of using the number of delay is to
actually at least wait for one heart beat from each node in the cluster and
then move task to next locality level.
I defaulted it to number of nodes in one rack generally.
Thanks,
Mayank
> Capacity Scheduler delay scheduling should not be disabled by default
> ---------------------------------------------------------------------
>
> Key: YARN-408
> URL: https://issues.apache.org/jira/browse/YARN-408
> Project: Hadoop YARN
> Issue Type: Bug
> Components: scheduler
> Affects Versions: 3.0.0, 2.0.3-alpha
> Reporter: Mayank Bansal
> Assignee: Mayank Bansal
> Priority: Minor
> Attachments: YARN-408-trunk.patch
>
>
> Capacity Scheduler delay scheduling should not be disabled by default.
> Enabling it to number of nodes in one rack.
> Thanks,
> Mayank
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
