[
https://issues.apache.org/jira/browse/YARN-596?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14006676#comment-14006676
]
Sandy Ryza commented on YARN-596:
---------------------------------
The current patch uses the queue's policy to preemptContainerPreCheck. We
should the parent's policy. (Consider the case of a leaf queue with FIFO under
a parent queue with DRF - we should use DRF to decide whether we should skip
the leaf queue).
Also, we should add a new method to SchedulingPolicy instead of checking with
instanceof.
{code}
+ if (Resources.fitsIn(getResourceUsage(), getFairShare())) {
+ return false;
+ } else {
+ return true;
+ }
{code}
Can just use "return Resources.fitsIn(getResourceUsage(), getFairShare())".
> In fair scheduler, intra-application container priorities affect
> inter-application preemption decisions
> -------------------------------------------------------------------------------------------------------
>
> Key: YARN-596
> URL: https://issues.apache.org/jira/browse/YARN-596
> Project: Hadoop YARN
> Issue Type: Bug
> Components: scheduler
> Affects Versions: 2.0.3-alpha
> Reporter: Sandy Ryza
> Assignee: Sandy Ryza
> Attachments: YARN-596.patch, YARN-596.patch, YARN-596.patch,
> YARN-596.patch, YARN-596.patch, YARN-596.patch
>
>
> In the fair scheduler, containers are chosen for preemption in the following
> way:
> All containers for all apps that are in queues that are over their fair share
> are put in a list.
> The list is sorted in order of the priority that the container was requested
> in.
> This means that an application can shield itself from preemption by
> requesting it's containers at higher priorities, which doesn't really make
> sense.
> Also, an application that is not over its fair share, but that is in a queue
> that is over it's fair share is just as likely to have containers preempted
> as an application that is over its fair share.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
