rocksdb/utilities/write_batch_with_index
Changyu Bi 08dc5cacd9 Check op count in WBWI vs WB when ingesting WBWI (#13722)
Summary:
Large txn commit optimization requires all updates are added to a transaction's WriteBatchWithIndex. However, some usage of transactions may add updates directly to the WBWI's underlying write batch. In these cases, we should not attempt to ingest the WBWI since it will drop these updates. This PR adds sanity checking for this.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/13722

Test Plan:
- added checks in unit test and stress test
- manually check LOG files for the new unit test

Reviewed By: hx235

Differential Revision: D77247688

Pulled By: cbi42

fbshipit-source-id: 3d1c0c6e64d6d7dfd5578bc4d77abe44cac1e419
2025-06-25 13:32:08 -07:00
..
write_batch_with_index.cc Check op count in WBWI vs WB when ingesting WBWI (#13722) 2025-06-25 13:32:08 -07:00
write_batch_with_index_internal.cc Reverse the order of updates to the same key in WriteBatchWithIndex (#13387) 2025-02-10 17:15:47 -08:00
write_batch_with_index_internal.h Experimental API IngestWriteBatchWithIndex() (#13550) 2025-04-17 12:06:40 -07:00
write_batch_with_index_test.cc Check op count in WBWI vs WB when ingesting WBWI (#13722) 2025-06-25 13:32:08 -07:00