Closed hx235 closed 1 week ago
@hx235 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.
@hx235 has updated the pull request. You must reimport the pull request before landing.
@hx235 has updated the pull request. You must reimport the pull request before landing.
@hx235 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.
@hx235 has updated the pull request. You must reimport the pull request before landing.
@hx235 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.
@hx235 merged this pull request in facebook/rocksdb@41c6b4549ab0dccfb15b7af038f7803cbe8c5f23.
Context/Summary: https://github.com/facebook/rocksdb/pull/12713 adjusted the error injection in ReadAsync. See original behavior here https://github.com/facebook/rocksdb/blob/71f9e6b5b36e3223e8dba29df75e4e5008818d16/utilities/fault_injection_fs.cc#L456-L484
The PR returns the injected error instead of the ReadAsync() status. It also allows cb to be call in
TestFSRandomAccessFile
layer when ReadAsync() and the cb can called withinFSRandomAccessFile
layer so cb can be double called. It appears to be the root-cause of the following frequent errorAddressSanitizer: heap-use-after-free on rocksdb::RandomAccessFileReader::ReadAsync
though I don't have a confirmed repro yet. Considering this change to mostly revert to previous behavior, it should be safe to proceed anyway.Test: Monitor CI