andreacavalli/rocksdb
0
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

deflake DBCompactionTestWithParam.IntraL0Compaction test (#7065)

Browse Source 
Summary:
This check is flaky because compaction could run between the `Flush()` and the `TestGetTickerCount()`, which would increase the `BLOCK_CACHE_INDEX_MISS` count beyond what the test expects. Verified by adding a `sleep(1)` between those two lines and observing the counter is too high every time. The solution is just to remove this check as it doesn't have any use anyways. The latter check of index miss is sufficient to conclude the newest L0 file (i.e., the one generated by intra-L0) does not have its index block pinned in cache. It'd be nice to simultaneously check the L0 files generated by flush do have their index blocks pinned in cache, but that's not what the line deleted in this PR was checking..
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7065

Reviewed By: pdillinger

Differential Revision: D22340327

Pulled By: ajkr

fbshipit-source-id: e076b2c7228b7fa763dd0c0cb13828e176c1abee
This commit is contained in:
Andrew Kryczka 2020-07-01 14:51:50 -07:00 committed by Facebook GitHub Bot
parent e2fd501d44
commit c25a014792
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
db/db_compaction_test.cc
View File

@ -3223,7 +3223,6 @@ TEST_P(DBCompactionTestWithParam, IntraL0Compaction) {
ASSERT_OK(Put(Key(i + 1), value));
}
ASSERT_OK(Flush());
ASSERT_EQ(i + 1, TestGetTickerCount(options, BLOCK_CACHE_INDEX_MISS));
}
dbfull()->TEST_WaitForCompact();
ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();