[
https://issues.apache.org/jira/browse/YARN-999?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16766687#comment-16766687
]
Íñigo Goiri commented on YARN-999:
----------------------------------
Just to make sure we are in the same page, I added [^YARN-291.000.patch] with a
WIP.
This basically shows a unit test that makes sure we get the expected behavior.
In the scheduler side, I did a very hacky approach for preemption just for the
unit test.
Trying to figure out the best way to do the preemption following events or so.
> In case of long running tasks, reduce node resource should balloon out
> resource quickly by calling preemption API and suspending running task.
> -----------------------------------------------------------------------------------------------------------------------------------------------
>
> Key: YARN-999
> URL: https://issues.apache.org/jira/browse/YARN-999
> Project: Hadoop YARN
> Issue Type: Sub-task
> Components: graceful, nodemanager, scheduler
> Reporter: Junping Du
> Priority: Major
> Attachments: YARN-291.000.patch
>
>
> In current design and implementation, when we decrease resource on node to
> less than resource consumption of current running tasks, tasks can still be
> running until the end. But just no new task get assigned on this node
> (because AvailableResource < 0) until some tasks are finished and
> AvailableResource > 0 again. This is good for most cases but in case of long
> running task, it could be too slow for resource setting to actually work so
> preemption could be hired here.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
