JingsongLi commented on PR #9397:
URL: https://github.com/apache/paimon/pull/9397#issuecomment-5449833836

   **[P2] Make preserved multipart cleanup safe to repeat**
   
   `FormatTableCommit.commit` already aborts these messages in its catch path 
(`FormatTableCommit.java:372-382`). `FlinkFormatTableDataStreamSink.close` then 
catches the rethrown commit failure and calls 
`tableCommit.abort(commitMessages)` again 
(`FlinkFormatTableDataStreamSink.java:136-140`). Because the new 
`BaseMultiPartUploadCommitter.discardStaging` propagates `abortMultipartUpload` 
failures, the second abort after a successful first abort (or after an 
already-completed upload) can return `NoSuchUpload` on S3/OSS/Jindo and escape 
from the Flink catch before the original exception is rethrown. The job still 
fails, but the actual publish/commit failure is replaced by a cleanup error.
   
   Please either make absent/finished multipart staging cleanup idempotent, or 
catch the Flink-side abort failure and suppress it onto the original exception, 
and add a double-abort regression that verifies the original cause is retained.


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to