You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@flink.apache.org by "Yun Tang (Jira)" <ji...@apache.org> on 2023/10/23 13:24:00 UTC

[jira] [Commented] (FLINK-33341) Use available local state for rescaling

    [ https://issues.apache.org/jira/browse/FLINK-33341?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17778665#comment-17778665 ] 

Yun Tang commented on FLINK-33341:
----------------------------------

Current FLIP-291 already supports local recovery with the adaptive scheduler, what's the case here?

> Use available local state for rescaling
> ---------------------------------------
>
>                 Key: FLINK-33341
>                 URL: https://issues.apache.org/jira/browse/FLINK-33341
>             Project: Flink
>          Issue Type: Improvement
>          Components: Runtime / State Backends
>            Reporter: Stefan Richter
>            Assignee: Stefan Richter
>            Priority: Major
>
> Local state is currently only used for recovery. However, it would make sense to also use available local state in rescaling scenarios to reduce the amount of data to download from remote storage.



--
This message was sent by Atlassian Jira
(v8.20.10#820010)