[
https://issues.apache.org/jira/browse/YUNIKORN-2201?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17790935#comment-17790935
]
Peter Bacsko commented on YUNIKORN-2201:
----------------------------------------
Yes, everything you say is true, but I still believe that there's a reasonable
approach to make the comparisons faster. Obviously this only causes problems if
a certain user runs out of quota and he has a lot of things scheduled. It might
not be an issue at all in real life, because in this test, we're talking about
50000 pods. So having 200-300 asks for every cycle is probably not a big
deal...
> Evaluate the performance impact of Headroom() and CanRunApp()
> -------------------------------------------------------------
>
> Key: YUNIKORN-2201
> URL: https://issues.apache.org/jira/browse/YUNIKORN-2201
> Project: Apache YuniKorn
> Issue Type: Sub-task
> Components: core - scheduler
> Reporter: Peter Bacsko
> Assignee: Peter Bacsko
> Priority: Major
> Attachments: benchmark_maxapps_hit.png, benchmark_nolimit_hit.png,
> benchmark_resourcequota_hit.png
>
>
> {{Manager.CanRunApp()}} and {{Manager.Headroom()}} are constantly called from
> the scheduling cycle.
> We need to see how this affects the overall performance of Yunikorn.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
