You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by "Congxian Qiu(klion26) (Jira)" <ji...@apache.org> on 2020/01/16 02:56:00 UTC

[jira] [Commented] (FLINK-15603) Show "barrier lag" in checkpoint statistics

    [ https://issues.apache.org/jira/browse/FLINK-15603?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17016484#comment-17016484 ] 

Congxian Qiu(klion26) commented on FLINK-15603:
-----------------------------------------------

And we may add some debug log in {{CheckpointBarrierAligner}} when received a barrier and when barrier align complete such as {{CheckpointBarrierTracker}}, this can be helpful when debugging checkpoint problem.

> Show "barrier lag" in checkpoint statistics
> -------------------------------------------
>
>                 Key: FLINK-15603
>                 URL: https://issues.apache.org/jira/browse/FLINK-15603
>             Project: Flink
>          Issue Type: Improvement
>          Components: Runtime / Web Frontend
>            Reporter: Stephan Ewen
>            Priority: Critical
>              Labels: usability
>             Fix For: 1.11.0
>
>
> One of the most important metrics is missing in the checkpoint stats: "barrier lag", meaning the time it between when the checkpoint was triggered and when the barriers arrive at a task.
> That time is critical to identify if a checkpoint takes too long because of backpressure or other contention.
> You can implicitly calculate this by "end_to_end_time - sync_time - async_time", but it is much more obvious for users that something is up when this number is explicitly shown.



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