[
https://issues.apache.org/jira/browse/FLINK-13245?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16890630#comment-16890630
]
zhijiang commented on FLINK-13245:
----------------------------------
[~azagrebin] I totally agree with your above point. The first priority should
make the current fine grained recovery work in release-1.9. As we confirmed
before, the consumption notification via network is just best-effort atm, not
always reliable especially when the network connection is not established
during consumer failed.
I remembered that the JM would always release partitions while restarting
producer tasks before, maybe I missed some parts while reviewing the relevant
PRs of partition lifecycle feature. I am sorry for not giving this potential
issue from network stack before.
We could solve the current issue in FLINK-13771 now, and further address the
semantics of partition release and refactor the network behavior if necessary
in release-1.10.
> Network stack is leaking files
> ------------------------------
>
> Key: FLINK-13245
> URL: https://issues.apache.org/jira/browse/FLINK-13245
> Project: Flink
> Issue Type: Bug
> Components: Runtime / Network
> Affects Versions: 1.9.0
> Reporter: Chesnay Schepler
> Assignee: zhijiang
> Priority: Blocker
> Labels: pull-request-available
> Fix For: 1.9.0
>
> Time Spent: 10m
> Remaining Estimate: 0h
>
> There's file leak in the network stack / shuffle service.
> When running the {{SlotCountExceedingParallelismTest}} on Windows a large
> number of {{.channel}} files continue to reside in a
> {{flink-netty-shuffle-XXX}} directory.
> From what I've gathered so far these files are still being used by a
> {{BoundedBlockingSubpartition}}. The cleanup logic in this class uses
> ref-counting to ensure we don't release data while a reader is still present.
> However, at the end of the job this count has not reached 0, and thus nothing
> is being released.
> The same issue is also present on the {{ResultPartition}} level; the
> {{ReleaseOnConsumptionResultPartition}} also are being released while the
> ref-count is greater than 0.
> Overall it appears like there's some issue with the notifications for
> partitions being consumed.
> It is feasible that this issue has recently caused issues on Travis where the
> build were failing due to a lack of disk space.
--
This message was sent by Atlassian JIRA
(v7.6.14#76016)
