[ 
https://issues.apache.org/jira/browse/YARN-2933?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14268756#comment-14268756
 ] 

Sunil G commented on YARN-2933:
-------------------------------

Hi [~mayank_bansal] and [~wangda]

This is a very needed implementation w.r.t node labels in preemption scenario. 
However I have a concern, please discard if this is been considered already.

An application's(if not specified any labels during submission time) 
containers,  may fall in to nodes where it can be labelled or not labelled. Am 
I correct?  if so, with this implementation, preemption will always happen to 
those containers which are running in a non-labelled node. This may not be 
accurate. So is it possible to do preemption only for applications which are 
submitted without any node labels?

-Sunil

> Capacity Scheduler preemption policy should only consider capacity without 
> labels temporarily
> ---------------------------------------------------------------------------------------------
>
>                 Key: YARN-2933
>                 URL: https://issues.apache.org/jira/browse/YARN-2933
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: capacityscheduler
>            Reporter: Wangda Tan
>            Assignee: Mayank Bansal
>         Attachments: YARN-2933-1.patch, YARN-2933-2.patch, YARN-2933-3.patch, 
> YARN-2933-4.patch, YARN-2933-5.patch
>
>
> Currently, we have capacity enforcement on each queue for each label in 
> CapacityScheduler, but we don't have preemption policy to support that. 
> YARN-2498 is targeting to support preemption respect node labels, but we have 
> some gaps in code base, like queues/FiCaScheduler should be able to get 
> usedResource/pendingResource, etc. by label. These items potentially need to 
> refactor CS which we need spend some time carefully think about.
> For now, what immediately we can do is allow calculate ideal_allocation and 
> preempt containers only for resources on nodes without labels, to avoid 
> regression like: A cluster has some nodes with labels and some not, assume 
> queueA isn't satisfied for resource without label, but for now, preemption 
> policy may preempt resource from nodes with labels for queueA, that is not 
> correct.
> Again, it is just a short-term enhancement, YARN-2498 will consider 
> preemption respecting node-labels for Capacity Scheduler which is our final 
> target. 



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Reply via email to