forked from continuwuation/rocksdb
ac412b1095
Summary: I want to reduce the time from when we call `StopBackup` to `CreateNewBackup` returning `BackupStopped`. We already check for the `stop_backup_` inside `CopyOrCreateFile` and `ReadFileAndComputeChecksum`, but we should add a check at the top of these methods to abort immediately. This could help save some latency from the file system metadata operations, like creating the sequential file and writable file. We also want to update the API documentation for `StopBackup` which currently does not indicate that once it is called, all subsequent requests to create backups will fail. In a follow up PR, we should also add coverage of `StopBackup` to the crash tests. Pull Request resolved: https://github.com/facebook/rocksdb/pull/14129 Test Plan: We were missing unit test coverage for `StopBackup`. I added test cases which cancel backups at different points in time. Once this change is rolled out to production, we can monitor the DB close latencies, which depend on first cancelling ongoing backups Reviewed By: pdillinger Differential Revision: D87356536 Pulled By: archang19 fbshipit-source-id: 687094a41f096f6a156be65b2cce0b5054fb26f2 |
||
|---|---|---|
| .. | ||
| backup_engine.cc | ||
| backup_engine_impl.h | ||
| backup_engine_test.cc | ||