C0urante opened a new pull request, #13181: URL: https://github.com/apache/kafka/pull/13181
The [Jira](https://issues.apache.org/jira/browse/KAFKA-14610) contains a more detailed description of the motivation for this change. To summarize, if there are bursty topic partitions, offset sync starvation can occur since MM2 limits the number of in-flight syncs at one time. The fix here is to enqueue the latest applicable offset for any to-be-synced topic partition in the `commitRecord` method, immediately fire off all syncs that can be published in that method, and then periodically re-check for new syncs in `commit` in case there are syncs that could not be published due to, e.g., a burst of throughput on a topic partition. ### Committer Checklist (excluded from commit message) - [ ] Verify design and implementation - [ ] Verify test coverage and CI build status - [ ] Verify documentation (including upgrade notes) -- 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: jira-unsubscr...@kafka.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
