freemandealer opened a new pull request, #60977:
URL: https://github.com/apache/doris/pull/60977
Problem:
In a rare restart window, BE can rebuild file-cache metadata in memory
while
the corresponding cache files are not yet durable on disk. If that
metadata is
also restored via LRU dump/load, blocks may appear as DOWNLOADED even
though
the local files are missing. Subsequent reads then produce false-positive
cache
hits, fail on local read, and repeatedly fall back to S3. This preserves
correctness but causes avoidable cache thrashing and latency jitter.
Root cause:
The read path treated DOWNLOADED as a valid local hit source and fell back
to
remote reads on failure, but it did not actively invalidate stale metadata
when
the local cache file was gone.
### What problem does this PR solve?
Issue Number: close #xxx
Related PR: #xxx
Problem Summary:
### Release note
None
### Check List (For Author)
- Test <!-- At least one of them must be included. -->
- [ ] Regression test
- [ ] Unit Test
- [ ] Manual test (add detailed scripts or steps below)
- [ ] No need to test or manual test. Explain why:
- [ ] This is a refactor/code format and no logic has been changed.
- [ ] Previous test can cover this change.
- [ ] No code files have been changed.
- [ ] Other reason <!-- Add your reason? -->
- Behavior changed:
- [ ] No.
- [ ] Yes. <!-- Explain the behavior change -->
- Does this need documentation?
- [ ] No.
- [ ] Yes. <!-- Add document PR link here. eg:
https://github.com/apache/doris-website/pull/1214 -->
### Check List (For Reviewer who merge this PR)
- [ ] Confirm the release note
- [ ] Confirm test cases
- [ ] Confirm document
- [ ] Add branch pick label <!-- Add branch pick label that this PR should
merge into -->
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
