[
https://issues.apache.org/jira/browse/FLINK-22815?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17356254#comment-17356254
]
Dawid Wysakowicz commented on FLINK-22815:
------------------------------------------
Fixed in:
* master
** e9677357b161df4c06cdb9d5aa0e96e086809035
83471dd624af412b1b4e81cf9c50b6103c9fc5ab
* 1.13
** c4227cc2237373592cbfe4357a9a9223c516ae66
fec1ccea059d53ad70a3f905a20815d069c665a6
> Disable unaligned checkpoints for broadcast partitioning
> --------------------------------------------------------
>
> Key: FLINK-22815
> URL: https://issues.apache.org/jira/browse/FLINK-22815
> Project: Flink
> Issue Type: Bug
> Components: Runtime / Checkpointing
> Affects Versions: 1.13.1, 1.12.4
> Reporter: Dawid Wysakowicz
> Assignee: Dawid Wysakowicz
> Priority: Blocker
> Labels: pull-request-available
> Fix For: 1.11.4, 1.14.0, 1.12.5, 1.13.2
>
>
> Broadcast partitioning can not work with unaligned checkpointing. There
> are no guarantees that records are consumed at the same rate in all
> channels. This can result in some tasks applying state changes
> corresponding to a certain broadcasted event while others don't. In turn
> upon restore, it may lead to an inconsistent state.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
