Revision a4d02dc905eb24283d6de2f40214048a811d7f1f authored by Andrew Kryczka on 27 October 2017, 22:43:42 UTC, committed by Andrew Kryczka on 28 October 2017, 02:40:07 UTC
Summary: Problem was in bottommost compaction, when an L0->L0 compaction happened and L0 was bottommost. Then we'd preserve tombstones according to `Compaction::KeyNotExistsBeyondOutputLevel`, while zeroing seqnum according to `CompactionIterator::PrepareOutput`, thus triggering the assertion in `PrepareOutput`. To fix, we can just drop tombstones in L0->L0 when the output is "bottommost", i.e., the compaction includes the oldest L0 file and there's nothing at lower levels. Closes https://github.com/facebook/rocksdb/pull/3085 Differential Revision: D6175742 Pulled By: ajkr fbshipit-source-id: 8ab19a2e001496f362e9eb0a71757e2f6ecfdb3b
1 parent d31d022
| File | Mode | Size |
|---|---|---|
| buckify_rocksdb.py | -rw-r--r-- | 5.0 KB |
| rocks_test_runner.sh | -rwxr-xr-x | 160 bytes |
| targets_builder.py | -rw-r--r-- | 1.9 KB |
| targets_cfg.py | -rw-r--r-- | 2.8 KB |
| util.py | -rw-r--r-- | 3.1 KB |
Computing file changes ...
