[
https://issues.apache.org/jira/browse/FLINK-19852?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17232483#comment-17232483
]
Xintong Song commented on FLINK-19852:
--------------------------------------
[~gaoyunhaii] and I also had a discussion around this issue. We have similar
opinion as yours, that the least invasive fix might be to have iterative tasks
cache the pages and do not re-allocate them on each iteration.
> Managed memory released check can block IterativeTask
> -----------------------------------------------------
>
> Key: FLINK-19852
> URL: https://issues.apache.org/jira/browse/FLINK-19852
> Project: Flink
> Issue Type: Bug
> Components: Runtime / Task
> Affects Versions: 1.11.0, 1.10.2, 1.12.0, 1.11.1, 1.11.2
> Reporter: shaomeng.wang
> Priority: Critical
> Attachments: image-2020-10-28-17-48-28-395.png,
> image-2020-10-28-17-48-48-583.png
>
>
> UnsafeMemoryBudget#reserveMemory, called on TempBarrier, needs time to wait
> on GC of all allocated/released managed memory at every iteration.
>
> stack:
> !image-2020-10-28-17-48-48-583.png!
> new TempBarrier in BatchTask
> !image-2020-10-28-17-48-28-395.png!
>
> These will be very slow than before.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
