[
https://issues.apache.org/jira/browse/FLINK-27921?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17557893#comment-17557893
]
Anton Kalashnikov commented on FLINK-27921:
-------------------------------------------
[~aitozi], [~guoyangze], This task caused a huge performance drop in many
benchmarks(at least I have checked that this PR is the cause of asyncWait* and
sorted* benchmarks but I assume that other benchmarks' performance drop also
relates to this task). You can check all problematic benchmarks here -
http://codespeed.dak8s.net:8000/changes/
I think this task should be reverted or fixed ASAP since there are too many
benchmarks affected and the drop size is too big(up to 50%).
CC: [~roman], [~smattheis]
> Introduce the checkResourceRequirementsWithDelay in DeclarativeSlotManager
> --------------------------------------------------------------------------
>
> Key: FLINK-27921
> URL: https://issues.apache.org/jira/browse/FLINK-27921
> Project: Flink
> Issue Type: Sub-task
> Components: Runtime / Coordination
> Reporter: Aitozi
> Assignee: Aitozi
> Priority: Major
> Labels: pull-request-available
> Fix For: 1.16.0
>
>
> As discussed in
> [https://github.com/apache/flink/pull/19840#discussion_r884242067] .This
> ticket is meant to introduce the same mechanism to wait for a slight delay
> before process the resource check with {{{}FineGrainedSlotManager{}}}. It
> will reduce the frequency of unnecessary re-allocations
--
This message was sent by Atlassian Jira
(v8.20.7#820007)
