[
https://issues.apache.org/jira/browse/YARN-8292?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16484257#comment-16484257
]
Eric Payne commented on YARN-8292:
----------------------------------
{quote}Actually this is required after the change.
{quote}
Yes, I see now.
{quote}TestPreemptionForQueueWithPriorities
{quote}
{{TestPreemptionForQueueWithPriorities}} passes for me in my local environment.
{quote}doPreempt = Resources.lessThan(rc, clusterResource,
Resources
.componentwiseMin(toObtainAfterPreemption, Resources.none()),
Resources.componentwiseMin(toObtainByPartition, Resources.none()));
{quote}
I don't think we want the above code to {{componentwiseMin}} the {{toObtain}}
values with 0, since that will set _all_ positive resource entities to 0.
{quote}Can we address this in a separate JIRA if we cannot come with some
simple solution?
{quote}
In my tests, the current implementation of preemption does not seem to work
anyway when extensible resources are enabled, so this seems to be a larger
problem. You are right that it should be its own JIRA.
I give my +1 here. [~jlowe] / [~sunilg], do you have additional comments?
> Fix the dominant resource preemption cannot happen when some of the resource
> vector becomes negative
> ----------------------------------------------------------------------------------------------------
>
> Key: YARN-8292
> URL: https://issues.apache.org/jira/browse/YARN-8292
> Project: Hadoop YARN
> Issue Type: Bug
> Components: yarn
> Reporter: Sumana Sathish
> Assignee: Wangda Tan
> Priority: Critical
> Attachments: YARN-8292.001.patch, YARN-8292.002.patch,
> YARN-8292.003.patch, YARN-8292.004.patch, YARN-8292.005.patch,
> YARN-8292.006.patch
>
>
> This is an example of the problem:
>
> {code}
> // guaranteed, max, used, pending
> "root(=[30:18:6 30:18:6 12:12:6 1:1:1]);" + //root
> "-a(=[10:6:2 10:6:2 6:6:3 0:0:0]);" + // a
> "-b(=[10:6:2 10:6:2 6:6:3 0:0:0]);" + // b
> "-c(=[10:6:2 10:6:2 0:0:0 1:1:1])"; // c
> {code}
> There're 3 resource types. Total resource of the cluster is 30:18:6
> For both of a/b, there're 3 containers running, each of container is 2:2:1.
> Queue c uses 0 resource, and have 1:1:1 pending resource.
> Under existing logic, preemption cannot happen.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
