You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@yunikorn.apache.org by "Peter Bacsko (Jira)" <ji...@apache.org> on 2023/05/04 09:50:00 UTC

[jira] [Resolved] (YUNIKORN-1720) Improve the performance of node.preAllocateCheck()

     [ https://issues.apache.org/jira/browse/YUNIKORN-1720?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Peter Bacsko resolved YUNIKORN-1720.
------------------------------------
    Fix Version/s: 1.3.0
       Resolution: Fixed

merged to master

> Improve the performance of node.preAllocateCheck()
> --------------------------------------------------
>
>                 Key: YUNIKORN-1720
>                 URL: https://issues.apache.org/jira/browse/YUNIKORN-1720
>             Project: Apache YuniKorn
>          Issue Type: Sub-task
>            Reporter: Eli Schiff
>            Assignee: Eli Schiff
>            Priority: Major
>              Labels: pull-request-available
>             Fix For: 1.3.0
>
>
> The node.preAllocateCheck() function gets run a lot during the scheduling cycle. The function is effectively a boolean function, either the node can be allocated on or it cannot. Instead of returning a bool it returns nil for true and a full error message for false. The thing is, that error message is never read anywhere. From what I can tell, the only thing the code does is check if there is an error message but not the contents. By removing the error message code, it should improve performance.



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@yunikorn.apache.org
For additional commands, e-mail: dev-help@yunikorn.apache.org