liying919 opened a new pull request, #1860:
URL: https://github.com/apache/incubator-celeborn/pull/1860
<!--
Thanks for sending a pull request! Here are some tips for you:
- Make sure the PR title start w/ a JIRA ticket, e.g. '[CELEBORN-XXXX]
Your PR title ...'.
- Be sure to keep the PR description updated to reflect all changes.
- Please write your PR title to summarize what this PR proposes.
- If possible, provide a concise example to reproduce the issue for a
faster review.
-->
### What changes were proposed in this pull request?
Don't stop LocalFlusher when notify error.
### Why are the changes needed?
If LocalDeviceMonitor find non-critical error(e.g. disk full usage) count
exceeds threshold and notify error to observed device. LocalFlusher will do
stopAndCleanFlusher, which will interrupt flush threads. Then if the disk
recover from the error, new disk buffer pushed into the flush queue cannot be
flushed. It always causes high memory usage, which would cause
pausePushDataAndReplicate, and can't recover from it .
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
Manual.
1. Run a spark job with shuffle.
2. Copy data in a worker to trigger full disk error.
3. See logs as below
5. Confirm flush threads are still running.
6. Submit another spark job with shuffle, and found disk buffer increase and
decrease while flushing disk.
--
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]
