[ 
https://issues.apache.org/jira/browse/YARN-7494?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16574680#comment-16574680
 ] 

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

Thanks [~cheersyang] and [~leftnoteasy]

Almost fixed all comments.

5) It's better to add getMultiNodeSortingPolicyName CSQueue, inside 
FiCaSchedulerApp, you can check the instanceof. With this we can limit the 
changes to CS.

Sunil: We initially had it for only CS. But during our discussion with 
[~cheersyang] we thought its better be generic so that FS can use with ease. 
And less if checks in FicaSchedulerApp.

6) RegularContainerAllocator#allocate, when the change needed?

Earlier for each node heartbeat, we were doing precheck. and then allocate was 
been invoked. In multi-node mode, we should try to do precheck and allocate in 
same loop of sorted nodes so that if one check fails,next node could be looked 
sooner.

7) Instead of adding MultiNodeSortingManager to RMContext, can we limit changes 
inside Scheduler?

Here also We initially had it for only CS. But during this patch review with 
[~cheersyang], we thought this might be better for a common approach. 

> 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-7494.010.patch, YARN-7494.11.patch, 
> YARN-7494.12.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-unsubscr...@hadoop.apache.org
For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org

Reply via email to