mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-28 15:33:54 +00:00
b26b395e0a
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 |
||
---|---|---|
.. | ||
agg_merge | ||
backup | ||
blob_db | ||
cassandra | ||
checkpoint | ||
compaction_filters | ||
convenience | ||
leveldb_options | ||
memory | ||
merge_operators | ||
option_change_migration | ||
options | ||
persistent_cache | ||
simulator_cache | ||
table_properties_collectors | ||
trace | ||
transactions | ||
ttl | ||
write_batch_with_index | ||
cache_dump_load.cc | ||
cache_dump_load_impl.cc | ||
cache_dump_load_impl.h | ||
compaction_filters.cc | ||
counted_fs.cc | ||
counted_fs.h | ||
debug.cc | ||
env_mirror.cc | ||
env_mirror_test.cc | ||
env_timed.cc | ||
env_timed.h | ||
env_timed_test.cc | ||
fault_injection_env.cc | ||
fault_injection_env.h | ||
fault_injection_fs.cc | ||
fault_injection_fs.h | ||
fault_injection_secondary_cache.cc | ||
fault_injection_secondary_cache.h | ||
memory_allocators.h | ||
merge_operators.cc | ||
merge_operators.h | ||
object_registry.cc | ||
object_registry_test.cc | ||
types_util.cc | ||
types_util_test.cc | ||
util_merge_operators_test.cc | ||
wal_filter.cc |