[jira] [Commented] (YARN-7494) Add muti node lookup support for better placement

["Sunil Govindan (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/YARN-7494?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16541419#comment-16541419 ] 

Sunil Govindan commented on YARN-7494:
--------------------------------------

Thanks [~cheersyang]. Attaching latest patch with testcase. Also addressed most of the comments. cc [~leftnoteasy]

bq.CapacityScheduler: line 399: this registers policies by names, what if the given policy name is invalid, can we fail the registration in such case?

[CapacitySchedulerConfiguration|eclipse-javadoc:%E2%98%82=hadoop-yarn-server-resourcemanager/src%5C/main%5C/java%3Corg.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity%7BCapacitySchedulerConfiguration.java%E2%98%83CapacitySchedulerConfiguration].getMultiNodePlacementPolicies() does validation to to handle all such invalid policy names (where submitted class is not correct)

 

bq.Queue/FiFoScheduler/FsLeafQueue/FsParentQueue : Not sure why we need this

We need queue.getMultiNodeSortingPolicyName() in places like FicaSchedulerApp. But if we keep this for LeafQueue alone, we ll have impact for ReservationQueue, Auto Created Leaf Queue feature etc. Hence we are now giving this api in Queue level itself so that it become a common api.

> Add muti node lookup support for better placement
> -------------------------------------------------
>
>                 Key: YARN-7494
>                 URL: https://issues.apache.org/jira/browse/YARN-7494
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: capacity scheduler
>            Reporter: Sunil Govindan
>            Assignee: Sunil Govindan
>            Priority: Major
>         Attachments: YARN-7494.001.patch, YARN-7494.002.patch, YARN-7494.003.patch, YARN-7494.004.patch, YARN-7494.005.patch, YARN-7494.006.patch, YARN-7494.007.patch, YARN-7494.008.patch, YARN-7494.009.patch, YARN-7494.v0.patch, YARN-7494.v1.patch, multi-node-designProposal.png
>
>
> Instead of single node, for effectiveness we can consider a multi node lookup based on partition to start with.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org