rocksdb/db
Baptiste Lemaire 9dc887ece0 Memtable "MemPurge" prototype (#8454)
Summary:
Implement an experimental feature called "MemPurge", which consists in purging "garbage" bytes out of a memtable and reuse the memtable struct instead of making it immutable and eventually flushing its content to storage.
The prototype is by default deactivated and is not intended for use. It is intended for correctness and validation testing. At the moment, the "MemPurge" feature can be switched on by using the `options.experimental_allow_mempurge` flag. For this early stage, when the allow_mempurge flag is set to `true`, all the flush operations will be rerouted to perform a MemPurge. This is a temporary design decision that will give us the time to explore meaningful heuristics to use MemPurge at the right time for relevant workloads . Moreover, the current MemPurge operation only supports `Puts`, `Deletes`, `DeleteRange` operations, and handles `Iterators` as well as `CompactionFilter`s that are invoked at flush time .
Three unit tests are added to `db_flush_test.cc` to test if MemPurge works correctly (and checks that the previously mentioned operations are fully supported thoroughly tested).
One noticeable design decision is the timing of the MemPurge operation in the memtable workflow: for this prototype, the mempurge happens when the memtable is switched (and usually made immutable). This is an inefficient process because it implies that the entirety of the MemPurge operation happens while holding the db_mutex. Future commits will make the MemPurge operation a background task (akin to the regular flush operation) and aim at drastically enhancing the performance of this operation. The MemPurge is also not fully "WAL-compatible" yet, but when the WAL is full, or when the regular MemPurge operation fails (or when the purged memtable still needs to be flushed), a regular flush operation takes place. Later commits will also correct these behaviors.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/8454

Reviewed By: anand1976

Differential Revision: D29433971

Pulled By: bjlemaire

fbshipit-source-id: 6af48213554e35048a7e03816955100a80a26dc5
2021-07-02 05:23:02 -07:00
..
blob Add BlobMetaData retrieval methods (#8273) 2021-06-28 08:13:29 -07:00
compaction Call OnCompactionCompleted API in case of DisableManualCompaction (#8469) 2021-07-01 19:18:55 -07:00
db_impl Memtable "MemPurge" prototype (#8454) 2021-07-02 05:23:02 -07:00
arena_wrapped_db_iter.cc Rename ImmutableOptions variables (#8409) 2021-06-16 16:51:38 -07:00
arena_wrapped_db_iter.h Rename ImmutableOptions variables (#8409) 2021-06-16 16:51:38 -07:00
builder.cc Memtable "MemPurge" prototype (#8454) 2021-07-02 05:23:02 -07:00
builder.h Added memtable garbage statistics (#8411) 2021-06-18 04:57:27 -07:00
c.cc Memtable "MemPurge" prototype (#8454) 2021-07-02 05:23:02 -07:00
c_test.c Expose CompressionOptions::parallel_threads through C API (#8302) 2021-05-17 22:53:04 -07:00
column_family.cc Memtable "MemPurge" prototype (#8454) 2021-07-02 05:23:02 -07:00
column_family.h Memtable "MemPurge" prototype (#8454) 2021-07-02 05:23:02 -07:00
column_family_test.cc Add CreateFrom methods to Env/FileSystem (#8174) 2021-06-15 03:43:48 -07:00
compact_files_test.cc Compaction should not move data to up level (#8116) 2021-03-29 17:10:42 -07:00
comparator_db_test.cc
convenience.cc Make ImmutableOptions struct that inherits from ImmutableCFOptions and ImmutableDBOptions (#8262) 2021-05-05 14:00:17 -07:00
corruption_test.cc Add CreateFrom methods to Env/FileSystem (#8174) 2021-06-15 03:43:48 -07:00
cuckoo_table_db_test.cc Revert "Turn on memtable bloom filter by default. (#6584)" (#7939) 2021-02-06 22:34:30 -08:00
db_basic_test.cc Initial support for secondary cache in LRUCache (#8271) 2021-05-13 22:58:40 -07:00
db_block_cache_test.cc Cache warming data blocks during flush (#8242) 2021-06-17 21:56:47 -07:00
db_bloom_filter_test.cc Add table properties for number of entries added to filters (#8323) 2021-05-21 17:11:32 -07:00
db_compaction_filter_test.cc Allow applying CompactionFilter outside of compaction (#8243) 2021-05-07 16:01:40 -07:00
db_compaction_test.cc Fix DeleteFilesInRange may cause inconsistent compaction error (#8434) 2021-06-22 09:17:37 -07:00
db_dynamic_level_test.cc
db_encryption_test.cc
db_filesnapshot.cc Fix GetLiveFiles() returning OPTIONS-000000 (#8268) 2021-05-05 12:54:46 -07:00
db_flush_test.cc Memtable "MemPurge" prototype (#8454) 2021-07-02 05:23:02 -07:00
db_info_dumper.cc
db_info_dumper.h
db_inplace_update_test.cc
db_io_failure_test.cc
db_iter.cc Rename ImmutableOptions variables (#8409) 2021-06-16 16:51:38 -07:00
db_iter.h Rename ImmutableOptions variables (#8409) 2021-06-16 16:51:38 -07:00
db_iter_stress_test.cc Make ImmutableOptions struct that inherits from ImmutableCFOptions and ImmutableDBOptions (#8262) 2021-05-05 14:00:17 -07:00
db_iter_test.cc Rename ImmutableOptions variables (#8409) 2021-06-16 16:51:38 -07:00
db_iterator_test.cc Instantiate tests DBIteratorTestForPinnedData (#8051) 2021-03-12 12:31:29 -08:00
db_kv_checksum_test.cc Integrity protection for live updates to WriteBatch (#7748) 2021-01-29 12:18:58 -08:00
db_log_iter_test.cc
db_logical_block_size_cache_test.cc
db_memtable_test.cc Make ImmutableOptions struct that inherits from ImmutableCFOptions and ImmutableDBOptions (#8262) 2021-05-05 14:00:17 -07:00
db_merge_operand_test.cc Support for Merge in Integrated BlobDB with base values (#8292) 2021-06-10 12:58:37 -07:00
db_merge_operator_test.cc
db_options_test.cc Add ObjectRegistry to ConfigOptions (#8166) 2021-05-11 06:47:22 -07:00
db_properties_test.cc Assert unlimited max_open_files for FIFO compaction. (#8172) 2021-04-14 12:05:47 -07:00
db_range_del_test.cc Fix manual compaction max_compaction_bytes under-calculated issue (#8269) 2021-05-21 14:03:44 -07:00
db_secondary_test.cc Add remote compaction public API (#8300) 2021-05-19 21:41:31 -07:00
db_sst_test.cc Fix flaky failure in DBSSTest.DBWithSstFileManagerForBlobFilesWithGC (#8196) 2021-04-15 20:18:57 -07:00
db_statistics_test.cc
db_table_properties_test.cc
db_tailing_iter_test.cc
db_test.cc Fix TSAN issue (#8477) 2021-07-01 11:53:18 -07:00
db_test2.cc Call OnCompactionCompleted API in case of DisableManualCompaction (#8469) 2021-07-01 19:18:55 -07:00
db_test_util.cc Add CreateFrom methods to Env/FileSystem (#8174) 2021-06-15 03:43:48 -07:00
db_test_util.h Cache warming data blocks during flush (#8242) 2021-06-17 21:56:47 -07:00
db_universal_compaction_test.cc Revert "Turn on memtable bloom filter by default. (#6584)" (#7939) 2021-02-06 22:34:30 -08:00
db_wal_test.cc Use DbSessionId as cache key prefix when secondary cache is enabled (#8360) 2021-06-10 11:02:43 -07:00
db_with_timestamp_basic_test.cc Fix a bug in key comparison when index type is kBinarySearchWithFirstKey (#8062) 2021-03-15 17:44:52 -07:00
db_with_timestamp_compaction_test.cc
db_write_buffer_manager_test.cc Stall writes in WriteBufferManager when memory_usage exceeds buffer_size (#7898) 2021-04-21 13:54:02 -07:00
db_write_test.cc
dbformat.cc
dbformat.h Fix some typos in comments (#8066) 2021-03-25 21:18:08 -07:00
dbformat_test.cc
deletefile_test.cc
error_handler.cc All the NoSpace() errors will be handled by regular SetBGError and RecoverFromNoSpace() (#8376) 2021-06-11 14:48:28 -07:00
error_handler.h Fix some typos in comments (#8066) 2021-03-25 21:18:08 -07:00
error_handler_fs_test.cc All the NoSpace() errors will be handled by regular SetBGError and RecoverFromNoSpace() (#8376) 2021-06-11 14:48:28 -07:00
event_helpers.cc Add table properties for number of entries added to filters (#8323) 2021-05-21 17:11:32 -07:00
event_helpers.h
experimental.cc
external_sst_file_basic_test.cc Sync ingested files only if reopen is supported by the FS (#8296) 2021-05-18 19:33:55 -07:00
external_sst_file_ingestion_job.cc Sync ingested files only if reopen is supported by the FS (#8296) 2021-05-18 19:33:55 -07:00
external_sst_file_ingestion_job.h Use SystemClock* instead of std::shared_ptr<SystemClock> in lower level routines (#8033) 2021-03-15 04:34:11 -07:00
external_sst_file_test.cc Deflake ExternalSSTFileTest.PickedLevelBug (#8307) 2021-05-20 09:29:57 -07:00
fault_injection_test.cc
file_indexer.cc
file_indexer.h
file_indexer_test.cc
filename_test.cc
flush_job.cc Memtable "MemPurge" prototype (#8454) 2021-07-02 05:23:02 -07:00
flush_job.h Use SST file manager to track blob files as well (#8037) 2021-03-17 20:44:49 -07:00
flush_job_test.cc Use DbSessionId as cache key prefix when secondary cache is enabled (#8360) 2021-06-10 11:02:43 -07:00
flush_scheduler.cc
flush_scheduler.h Include C++ standard library headers instead of C compatibility headers (#8068) 2021-03-19 12:09:47 -07:00
forward_iterator.cc Fix some typos in comments (#8066) 2021-03-25 21:18:08 -07:00
forward_iterator.h
forward_iterator_bench.cc
import_column_family_job.cc
import_column_family_job.h Use SystemClock* instead of std::shared_ptr<SystemClock> in lower level routines (#8033) 2021-03-15 04:34:11 -07:00
import_column_family_test.cc
internal_stats.cc Pin CacheEntryStatsCollector to fix performance bug (#8385) 2021-06-14 08:15:11 -07:00
internal_stats.h Pin CacheEntryStatsCollector to fix performance bug (#8385) 2021-06-14 08:15:11 -07:00
job_context.h Rename ImmutableOptions variables (#8409) 2021-06-16 16:51:38 -07:00
kv_checksum.h Integrity protection for live updates to WriteBatch (#7748) 2021-01-29 12:18:58 -08:00
listener_test.cc
log_format.h
log_reader.cc
log_reader.h
log_test.cc
log_writer.cc Using existing crc32c checksum in checksum handoff for Manifest and WAL (#8412) 2021-06-25 00:47:17 -07:00
log_writer.h Include C++ standard library headers instead of C compatibility headers (#8068) 2021-03-19 12:09:47 -07:00
logs_with_prep_tracker.cc
logs_with_prep_tracker.h Include C++ standard library headers instead of C compatibility headers (#8068) 2021-03-19 12:09:47 -07:00
lookup_key.h
malloc_stats.cc
malloc_stats.h
manual_compaction_test.cc
memtable.cc Make ImmutableOptions struct that inherits from ImmutableCFOptions and ImmutableDBOptions (#8262) 2021-05-05 14:00:17 -07:00
memtable.h Memtable "MemPurge" prototype (#8454) 2021-07-02 05:23:02 -07:00
memtable_list.cc Fix some typos in comments (#8066) 2021-03-25 21:18:08 -07:00
memtable_list.h
memtable_list_test.cc Use DbSessionId as cache key prefix when secondary cache is enabled (#8360) 2021-06-10 11:02:43 -07:00
merge_context.h Add Merge Operator support to WriteBatchWithIndex (#8135) 2021-05-10 12:50:25 -07:00
merge_helper.cc Add support for Merge with base value during Compaction in IntegratedBlobDB (#8445) 2021-06-24 18:11:30 -07:00
merge_helper.h Add support for Merge with base value during Compaction in IntegratedBlobDB (#8445) 2021-06-24 18:11:30 -07:00
merge_helper_test.cc
merge_operator.cc
merge_test.cc
obsolete_files_test.cc Print blob file checksums as hex (#8437) 2021-06-22 09:49:44 -07:00
options_file_test.cc
output_validator.cc
output_validator.h Add remote compaction public API (#8300) 2021-05-19 21:41:31 -07:00
perf_context_test.cc Use SystemClock* instead of std::shared_ptr<SystemClock> in lower level routines (#8033) 2021-03-15 04:34:11 -07:00
periodic_work_scheduler.cc Use SystemClock* instead of std::shared_ptr<SystemClock> in lower level routines (#8033) 2021-03-15 04:34:11 -07:00
periodic_work_scheduler.h
periodic_work_scheduler_test.cc
pinned_iterators_manager.h
plain_table_db_test.cc Make ImmutableOptions struct that inherits from ImmutableCFOptions and ImmutableDBOptions (#8262) 2021-05-05 14:00:17 -07:00
pre_release_callback.h
prefix_test.cc Use SystemClock* instead of std::shared_ptr<SystemClock> in lower level routines (#8033) 2021-03-15 04:34:11 -07:00
range_del_aggregator.cc
range_del_aggregator.h Fix some typos in comments (#8066) 2021-03-25 21:18:08 -07:00
range_del_aggregator_bench.cc Use SystemClock* instead of std::shared_ptr<SystemClock> in lower level routines (#8033) 2021-03-15 04:34:11 -07:00
range_del_aggregator_test.cc
range_tombstone_fragmenter.cc Added memtable garbage statistics (#8411) 2021-06-18 04:57:27 -07:00
range_tombstone_fragmenter.h Added memtable garbage statistics (#8411) 2021-06-18 04:57:27 -07:00
range_tombstone_fragmenter_test.cc
read_callback.h
repair.cc Use DbSessionId as cache key prefix when secondary cache is enabled (#8360) 2021-06-10 11:02:43 -07:00
repair_test.cc Use SST file manager to track blob files as well (#8037) 2021-03-17 20:44:49 -07:00
snapshot_checker.h
snapshot_impl.cc
snapshot_impl.h Fix some typos in comments (#8066) 2021-03-25 21:18:08 -07:00
table_cache.cc Use DbSessionId as cache key prefix when secondary cache is enabled (#8360) 2021-06-10 11:02:43 -07:00
table_cache.h Use DbSessionId as cache key prefix when secondary cache is enabled (#8360) 2021-06-10 11:02:43 -07:00
table_properties_collector.cc Apply sample_for_compression to all block-based tables (#8105) 2021-03-25 15:00:45 -07:00
table_properties_collector.h Make it possible to apply only a subrange of table property collectors (#8298) 2021-05-17 18:28:39 -07:00
table_properties_collector_test.cc Make it possible to apply only a subrange of table property collectors (#8298) 2021-05-17 18:28:39 -07:00
transaction_log_impl.cc
transaction_log_impl.h
trim_history_scheduler.cc
trim_history_scheduler.h
version_builder.cc Handle blob files when options.best_efforts_recovery is true (#8180) 2021-04-19 11:56:14 -07:00
version_builder.h Handle blob files when options.best_efforts_recovery is true (#8180) 2021-04-19 11:56:14 -07:00
version_builder_test.cc Print blob file checksums as hex (#8437) 2021-06-22 09:49:44 -07:00
version_edit.cc Write file temperature information to manifest (#8284) 2021-05-17 15:15:23 -07:00
version_edit.h Write file temperature information to manifest (#8284) 2021-05-17 15:15:23 -07:00
version_edit_handler.cc Fixed manifest_dump issues when printing keys and values containing null characters (#8378) 2021-06-10 12:55:20 -07:00
version_edit_handler.h Fixed manifest_dump issues when printing keys and values containing null characters (#8378) 2021-06-10 12:55:20 -07:00
version_edit_test.cc
version_set.cc Add BlobMetaData retrieval methods (#8273) 2021-06-28 08:13:29 -07:00
version_set.h Remove obsolete method VersionSet::VerifyCompactionFileConsistency (#8449) 2021-06-23 13:28:34 -07:00
version_set_test.cc Print blob file checksums as hex (#8437) 2021-06-22 09:49:44 -07:00
wal_edit.cc
wal_edit.h
wal_edit_test.cc
wal_manager.cc Make types of Immutable/Mutable Options fields match that of the underlying Option (#8176) 2021-04-22 20:43:54 -07:00
wal_manager.h
wal_manager_test.cc Use DbSessionId as cache key prefix when secondary cache is enabled (#8360) 2021-06-10 11:02:43 -07:00
write_batch.cc Use SystemClock* instead of std::shared_ptr<SystemClock> in lower level routines (#8033) 2021-03-15 04:34:11 -07:00
write_batch_base.cc
write_batch_internal.h Integrity protection for live updates to WriteBatch (#7748) 2021-01-29 12:18:58 -08:00
write_batch_test.cc Make ImmutableOptions struct that inherits from ImmutableCFOptions and ImmutableDBOptions (#8262) 2021-05-05 14:00:17 -07:00
write_callback.h
write_callback_test.cc
write_controller.cc Revamp WriteController (#8064) 2021-03-18 09:47:31 -07:00
write_controller.h Revamp WriteController (#8064) 2021-03-18 09:47:31 -07:00
write_controller_test.cc Revamp WriteController (#8064) 2021-03-18 09:47:31 -07:00
write_thread.cc Stall writes in WriteBufferManager when memory_usage exceeds buffer_size (#7898) 2021-04-21 13:54:02 -07:00
write_thread.h typo: fix typo in db/write_thread's state (#8423) 2021-06-18 17:14:51 -07:00