[
https://issues.apache.org/jira/browse/YUNIKORN-1787?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17729766#comment-17729766
]
Craig Condit commented on YUNIKORN-1787:
----------------------------------------
I don't think this is safe. Reservation is not performed in all cases, and it
definitely can be run in different scheduling cycles from the actual
allocation. This has the potential to create some very hard to diagnose
failures in edge cases. That's not to say there is no room for improvement --
we may be able to bypass attempting reservations again for a short period of
time after a failure; this may allow us to make forward progress more quickly.
However, this would come at the expense of deterministic behavior.
> Re-use predicate results for reservation
> ----------------------------------------
>
> Key: YUNIKORN-1787
> URL: https://issues.apache.org/jira/browse/YUNIKORN-1787
> Project: Apache YuniKorn
> Issue Type: Sub-task
> Components: core - scheduler, shim - kubernetes
> Reporter: Peter Bacsko
> Assignee: Peter Bacsko
> Priority: Major
>
> As mentioned in
> https://issues.apache.org/jira/browse/YUNIKORN-1378?focusedCommentId=17720232&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-17720232,
> we don't need to run predicates again for reservation.
> If the cluster is busy and no suitable node were found for the request, we
> check if the predicate that failed is a reservation predicate. If it is, then
> there's no reason to run the reservation predicates.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
