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

Posted to issues@flink.apache.org by "Stephan Ewen (Jira)" <ji...@apache.org> on 2021/05/21 16:59:00 UTC

[jira] [Updated] (FLINK-22753) Activate log-based Checkpoints for StateFun

     [ https://issues.apache.org/jira/browse/FLINK-22753?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Stephan Ewen updated FLINK-22753:
---------------------------------
    Description: 
Once available, we should use log-based checkpointing in StateFun, to have predictable checkpointing times and predictably low end-to-end exactly-once latencies.

This is blocked on the implementation of [FLIP-158: Generalized incremental checkpoints|https://cwiki.apache.org/confluence/display/FLINK/FLIP-158%3A+Generalized+incremental+checkpoints]  (FLINK-21352)

  was:Once available, we should use log-based checkpointing in StateFun, to have predictable checkpointing times and predictably low end-to-end exactly-once latencies.


> Activate log-based Checkpoints for StateFun
> -------------------------------------------
>
>                 Key: FLINK-22753
>                 URL: https://issues.apache.org/jira/browse/FLINK-22753
>             Project: Flink
>          Issue Type: Sub-task
>          Components: Stateful Functions
>            Reporter: Stephan Ewen
>            Priority: Major
>
> Once available, we should use log-based checkpointing in StateFun, to have predictable checkpointing times and predictably low end-to-end exactly-once latencies.
> This is blocked on the implementation of [FLIP-158: Generalized incremental checkpoints|https://cwiki.apache.org/confluence/display/FLINK/FLIP-158%3A+Generalized+incremental+checkpoints]  (FLINK-21352)



--
This message was sent by Atlassian Jira
(v8.3.4#803005)