facebook/rocksdb v9.7.4 on GitHub

9.7.4 (10/31/2024)

Fix a leak of obsolete blob files left open until DB::Close(). This bug was introduced in version 9.4.0.

OPTIONS file to be loaded by remote worker is now preserved so that it does not get purged by the primary host. A similar technique as how we are preserving new SST files from getting purged is used for this. min_options_file_numbers_ is tracked like pending_outputs_ is tracked.

Fix a bug for surfacing write unix time: Iterator::GetProperty("rocksdb.iterator.write-time") for non-L0 files.

Several DB option settings could be lost through GetOptionsFromString(), possibly elsewhere as well. Affected options, now fixed:background_close_inactive_wals, write_dbid_to_manifest, write_identity_file, prefix_seek_opt_in_only
Fix under counting of allocated memory in the compressed secondary cache due to looking at the compressed block size rather than the actual memory allocated, which could be larger due to internal fragmentation.
Skip insertion of compressed blocks in the secondary cache if the lowest_used_cache_tier DB option is kVolatileTier.

Make Cache a customizable class that can be instantiated by the object registry.
Add new option prefix_seek_opt_in_only that makes iterators generally safer when you might set a prefix_extractor. When prefix_seek_opt_in_only=true, which is expected to be the future default, prefix seek is only used when prefix_same_as_start or auto_prefix_mode are set. Also, prefix_same_as_start and auto_prefix_mode now allow prefix filtering even with total_order_seek=true.
Add a new table property "rocksdb.key.largest.seqno" which records the largest sequence number of all keys in file. It is verified to be zero during SST file ingestion.

Changed the semantics of the BlobDB configuration option blob_garbage_collection_force_threshold to define
a threshold for the overall garbage ratio of all blob files currently eligible for garbage collection (accordin
g to blob_garbage_collection_age_cutoff). This can provide better control over space amplification at the cos
t of slightly higher write amplification.
Set write_dbid_to_manifest=true by default. This means DB ID will now be preserved through backups, checkpo
ints, etc. by default. Also add write_identity_file option which can be set to false for anticipated future b
ehavior.
In FIFO compaction, compactions for changing file temperature (configured by option file_temperature_age_thr esholds) will compact one file at a time, instead of merging multiple eligible file together (#13018).
Support ingesting db generated files using hard link, i.e. IngestExternalFileOptions::move_files/link_files a
nd IngestExternalFileOptions::allow_db_generated_files.
Add a new file ingestion option IngestExternalFileOptions::link_files to hard link input files and preserve
original files links after ingestion.
DB::Close now untracks files in SstFileManager, making avaialble any space used
by them. Prior to this change they would be orphaned until the DB is re-opened.

Fix a bug in CompactRange() where result files may not be compacted in any future compaction. This can only h
appen when users configure CompactRangeOptions::change_level to true and the change level step of manual compac
tion fails (#13009).
Fix handling of dynamic change of prefix_extractor with memtable prefix filter. Previously, prefix seek cou
ld mix different prefix interpretations between memtable and SST files. Now the latest prefix_extractor at th
e time of iterator creation or refresh is respected.
Fix a bug with manual_wal_flush and auto error recovery from WAL failure that may cause CFs to be inconsisten
t (#12995). The fix will set potential WAL write failure as fatal error when manual_wal_flush is true, and disa
bles auto error recovery from these errors.