Hui Xiao b26b395e0a Fix CreateCheckpoint not handling failed CleanStagingDirectory well (#12894) ... Summary: **Context/Summary:** `CleanStagingDirectory()` is called when the temporary .tmp folder we use to create checkpoint is not empty to begin with. Expanded fault injection can make this call fail e.g, `Delete file /dev/shm/rocksdb_test/rocksdb_crashtest_blackbox/.checkpoint17.tmp/012393.sst -- IO error: injected metadata write error`. But The result of `CleanStagingDirectory()` is ignored in `CreateCheckpoint()`. So the injected IO error can't be propagated to db stress test and handled correctly. Hence we see `While mkdir: /dev/shm/rocksdb_test/rocksdb_crashtest_blackbox/.checkpoint17.tmp: File exists` when we try to re-use a non-empty .tmp folder for new snapshots. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12894 Test Plan: Monitor CI Reviewed By: ltamasi Differential Revision: D60422849 Pulled By: hx235 fbshipit-source-id: 6f735c98eaa05d2b97ba4f781e0928357a50377a		2024-08-06 11:24:29 -07:00
..
checkpoint_impl.cc	Fix CreateCheckpoint not handling failed CleanStagingDirectory well (#12894)	2024-08-06 11:24:29 -07:00
checkpoint_impl.h	Fix CreateCheckpoint not handling failed CleanStagingDirectory well (#12894)	2024-08-06 11:24:29 -07:00
checkpoint_test.cc	Fix file deletions in DestroyDB not rate limited (#12891)	2024-08-02 19:31:55 -07:00