[
https://issues.apache.org/jira/browse/FLINK-17979?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arvid Heise updated FLINK-17979:
--------------------------------
Release Note: While recovering from unaligned checkpoints, users can now
change the parallelism of the job. This change allows users to quickly upscale
the job under backpressure.
> Support rescaling for Unaligned Checkpoints
> -------------------------------------------
>
> Key: FLINK-17979
> URL: https://issues.apache.org/jira/browse/FLINK-17979
> Project: Flink
> Issue Type: Sub-task
> Components: Runtime / Checkpointing
> Reporter: Roman Khachatryan
> Priority: Major
> Fix For: 1.13.0
>
>
> This is one of the limitations of Unaligned Checkpoints MVP.
> (see [Unaligned checkpoints: recovery &
> rescaling|https://docs.google.com/document/d/1T2WB163uf8xt6Eu2JS0Jyy2XZyF4YpnzGiHlo6twrks/edit?usp=sharing]
> for possible options)
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
