[
https://issues.apache.org/jira/browse/FLINK-28826?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17576375#comment-17576375
]
Yingjie Cao commented on FLINK-28826:
-------------------------------------
Merged into master via 05de0a295efe06ff342a211071fc3810fdd53a2e.
> Avoid notifying too frequently when recycling buffers for
> BatchShuffleReadBufferPool
> ------------------------------------------------------------------------------------
>
> Key: FLINK-28826
> URL: https://issues.apache.org/jira/browse/FLINK-28826
> Project: Flink
> Issue Type: Sub-task
> Components: Runtime / Network
> Affects Versions: 1.16.0
> Reporter: Yuxin Tan
> Assignee: Yuxin Tan
> Priority: Major
> Labels: pull-request-available
> Fix For: 1.16.0
>
>
> When recycling buffers in BatchShuffleReadBufferPool, the number of buffers
> may be larger than numBuffersPerRequest, which may cause too frequent
> notifications that the buffers are already available.
> So we should modify the condition of notifications that the buffer is
> available to solve this problem.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
