[
https://issues.apache.org/jira/browse/FLINK-37375?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17937112#comment-17937112
]
Jufang He commented on FLINK-37375:
-----------------------------------
[~zakelly] In the current design, Flink does not need to obtain the results of
asynchronous processing, nor does the processing result require state recovery.
The main purpose of this feature is to place user-defined, time-consuming
processing logic (such as uploading business data to DFS) into the checkpoint
asynchronous phase to improve task throughput. I think this new method could
perhaps be named asyncOperateOnCheckpoint. WDYT?
Thank you for your suggestions. I have revised the documentation and submitted
a PR. You can refer to the implementation logic in the PR.
> Checkpoint supports the Operator to customize asynchronous snapshot state
> -------------------------------------------------------------------------
>
> Key: FLINK-37375
> URL: https://issues.apache.org/jira/browse/FLINK-37375
> Project: Flink
> Issue Type: Bug
> Components: Runtime / Checkpointing
> Affects Versions: 1.20.1
> Reporter: Jufang He
> Priority: Major
> Labels: pull-request-available
>
> In some Flink task operators, slow operations such as file uploads or data
> flushing may be performed during the synchronous phase of Checkpoint. Due to
> performance issues with external storage components, the synchronous phase
> may take too long to execute, significantly impacting the job's throughput.
> For example, during our internal use of Paimon, we observed that uploading
> files to HDFS during the Checkpoint synchronous phase could encounter random
> HDFS slow node issues, leading to a substantial negative impact on task
> throughput.
> To address this issue, I propose supporting a generic operator custom
> asynchronous snapshot feature, allowing users to move time-consuming logic to
> the asynchronous phase of Checkpoint, thereby minimizing the blocking of the
> main thread and improving task throughput. For instance, the Paimon writer
> operator could write data locally during the Checkpoint synchronous phase and
> upload files to remote storage during the asynchronous phase. Beyond the
> Paimon data upload scenario, other operator logic may also experience slow
> execution during the synchronous phase. This approach aims to uniformly
> optimize such issues.
> I drafted a flip for this issue:
> [https://docs.google.com/document/d/1lwxLEQjD6jVhZUBMRGhzQNWKSvdbPbYNQsV265gR4kw]
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
