db_stress: deep clean directory before checkpoint (#7039)
Summary: We see crash test occassionally fails with "A checkpoint operation failed with: Invalid argument: Directory exists". The suspicious is that the directory fails to be deleted because some trash files. Deep clean the directory after a DestroyDB() call. Also add more debugging printf in case it fails. Also, preserve the DB if verification fails. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7039 Test Plan: Run db_stress with low --checkpoint_one_in value Reviewed By: riversand963 Differential Revision: D22271694 fbshipit-source-id: 6a9b2abb664fc69a4dc666741df4f6b23703cd6dmain
parent
5be2cb6948
commit
2d1d51d385
Loading…
Reference in new issue