You are viewing a plain text version of this content. The canonical link for it is here.
Posted to yarn-issues@hadoop.apache.org by "Wei Yan (JIRA)" <ji...@apache.org> on 2014/08/20 23:23:27 UTC

[jira] [Updated] (YARN-2395) Fair Scheduler : implement fair share preemption at parent queue based on fairSharePreemptionTimeout

     [ https://issues.apache.org/jira/browse/YARN-2395?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Wei Yan updated YARN-2395:
--------------------------

    Attachment: YARN-2395-1.patch

Discussed with Karthik offline. We agree on the solution that each queue can specify its own fairSharePreemptionTimeout. If not specified, the queue will inherits the value from its parent queue.

Another issue here: I removed the old "defaultFairSharePreemptionTimeout" and added a new one "rootFairSharePreemptionTimeout", which configures the timeout value for the root queue. I didn't use the name "defaultFairSharePreemptionTimeout" as it may confuse users that the queue will use this value if not configure, which is not true and the queue will take value from its parent queue.

> Fair Scheduler : implement fair share preemption at parent queue based on fairSharePreemptionTimeout
> ----------------------------------------------------------------------------------------------------
>
>                 Key: YARN-2395
>                 URL: https://issues.apache.org/jira/browse/YARN-2395
>             Project: Hadoop YARN
>          Issue Type: New Feature
>          Components: fairscheduler
>            Reporter: Ashwin Shankar
>            Assignee: Wei Yan
>         Attachments: YARN-2395-1.patch
>
>
> Currently in fair scheduler, the preemption logic considers fair share starvation only at leaf queue level. This jira is created to implement it at the parent queue as well.
> It involves :
> 1. Making "check for fair share starvation" and "amount of resource to preempt"  recursive such that they traverse the queue hierarchy from root to leaf.
> 2. Currently fairSharePreemptionTimeout is a global config. We could make it configurable on a per queue basis,so that we can specify different timeouts for parent queues.



--
This message was sent by Atlassian JIRA
(v6.2#6252)