rocksdb/db
Vijay Nadimpalli 4c49e38f15 MultiGet batching in memtable (#5818)
Summary:
RocksDB has a MultiGet() API that implements batched key lookup for higher performance (https://github.com/facebook/rocksdb/blob/master/include/rocksdb/db.h#L468). Currently, batching is implemented in BlockBasedTableReader::MultiGet() for SST file lookups. One of the ways it improves performance is by pipelining bloom filter lookups (by prefetching required cachelines for all the keys in the batch, and then doing the probe) and thus hiding the cache miss latency. The same concept can be extended to the memtable as well. This PR involves implementing a pipelined bloom filter lookup in DynamicBloom, and implementing MemTable::MultiGet() that can leverage it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5818

Test Plan:
Existing tests

Performance Test:
Ran the below command which fills up the memtable and makes sure there are no flushes and then call multiget. Ran it on master and on the new change and see atleast 1% performance improvement across all the test runs I did. Sometimes the improvement was upto 5%.

TEST_TMPDIR=/data/users/$USER/benchmarks/feature/ numactl -C 10 ./db_bench -benchmarks="fillseq,multireadrandom" -num=600000 -compression_type="none" -level_compaction_dynamic_level_bytes -write_buffer_size=200000000 -target_file_size_base=200000000 -max_bytes_for_level_base=16777216 -reads=90000 -threads=1 -compression_type=none -cache_size=4194304000 -batch_size=32 -disable_auto_compactions=true -bloom_bits=10 -cache_index_and_filter_blocks=true -pin_l0_filter_and_index_blocks_in_cache=true -multiread_batched=true -multiread_stride=4 -statistics -memtable_whole_key_filtering=true -memtable_bloom_size_ratio=10

Differential Revision: D17578869

Pulled By: vjnadimpalli

fbshipit-source-id: 23dc651d9bf49db11d22375bf435708875a1f192
2019-10-10 09:39:39 -07:00
..
compaction Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
db_impl MultiGet batching in memtable (#5818) 2019-10-10 09:39:39 -07:00
arena_wrapped_db_iter.cc Apply formatter on recent 45 commits. (#5827) 2019-09-19 12:34:17 -07:00
arena_wrapped_db_iter.h Refactor ArenaWrappedDBIter into separate files (#5801) 2019-09-13 13:50:43 -07:00
builder.cc Divide file_reader_writer.h and .cc (#5803) 2019-09-16 10:33:51 -07:00
builder.h Move some logging related files to logging/ (#5387) 2019-05-31 17:23:59 -07:00
c.cc Remove snap_refresh_nanos option (#5826) 2019-09-18 20:26:04 -07:00
c_test.c Add C binding for secondary instance (#5505) 2019-06-27 08:58:54 -07:00
column_family.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
column_family.h Bump up memory order of ref counting of ColumnFamilyData (#5723) 2019-08-20 10:34:33 -07:00
column_family_test.cc Refactor trimming logic for immutable memtables (#5022) 2019-08-23 13:55:34 -07:00
compact_files_test.cc Organizing rocksdb/db directory 2019-05-31 11:57:01 -07:00
compacted_db_impl.cc New API to get all merge operands for a Key (#5604) 2019-08-06 14:26:44 -07:00
compacted_db_impl.h Use delete to disable automatic generated methods. (#5009) 2019-09-11 18:09:00 -07:00
comparator_db_test.cc Move some memory related files from util/ to memory/ (#5382) 2019-05-30 17:44:09 -07:00
convenience.cc Do readahead in VerifyChecksum() (#5713) 2019-08-16 16:42:56 -07:00
corruption_test.cc Do readahead in VerifyChecksum() (#5713) 2019-08-16 16:42:56 -07:00
cuckoo_table_db_test.cc Organizing rocksdb/db directory 2019-05-31 11:57:01 -07:00
db_basic_test.cc MultiGet batching in memtable (#5818) 2019-10-10 09:39:39 -07:00
db_blob_index_test.cc Refactor ArenaWrappedDBIter into separate files (#5801) 2019-09-13 13:50:43 -07:00
db_block_cache_test.cc Charge block cache for cache internal usage (#5797) 2019-09-16 15:26:21 -07:00
db_bloom_filter_test.cc Unordered Writes (#5218) 2019-05-13 17:47:21 -07:00
db_compaction_filter_test.cc upgrade gtest 1.7.0 => 1.8.1 for json result writing 2019-09-09 11:24:11 -07:00
db_compaction_test.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
db_dynamic_level_test.cc Fix flaky DBDynamicLevelTest.DynamicLevelMaxBytesBase2 (#4668) 2018-11-12 16:42:16 -08:00
db_encryption_test.cc Fix EncryptedEnv assert (#5735) 2019-09-05 17:21:42 -07:00
db_filesnapshot.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
db_flush_test.cc Ref and unref cfd before and after calling WaitForFlushMemTables (#5513) 2019-07-01 14:12:02 -07:00
db_info_dumper.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
db_info_dumper.h
db_inplace_update_test.cc
db_io_failure_test.cc Disable DBIOFailureTest.NoSpaceCompactRange in LITE (#4596) 2018-10-29 14:36:31 -07:00
db_iter.cc Improve readability of DBIter's two seek functions (#5794) 2019-09-16 21:05:07 -07:00
db_iter.h Apply formatter on recent 45 commits. (#5827) 2019-09-19 12:34:17 -07:00
db_iter_stress_test.cc Move some memory related files from util/ to memory/ (#5382) 2019-05-30 17:44:09 -07:00
db_iter_test.cc Move some memory related files from util/ to memory/ (#5382) 2019-05-30 17:44:09 -07:00
db_iterator_test.cc Fix data block upper bound checking for iterator reseek case (#5883) 2019-10-03 20:53:29 -07:00
db_log_iter_test.cc Apply modernize-use-override (2nd iteration) 2019-02-14 14:41:36 -08:00
db_memtable_test.cc upgrade gtest 1.7.0 => 1.8.1 for json result writing 2019-09-09 11:24:11 -07:00
db_merge_operand_test.cc New API to get all merge operands for a Key (#5604) 2019-08-06 14:26:44 -07:00
db_merge_operator_test.cc New API to get all merge operands for a Key (#5604) 2019-08-06 14:26:44 -07:00
db_options_test.cc upgrade gtest 1.7.0 => 1.8.1 for json result writing 2019-09-09 11:24:11 -07:00
db_properties_test.cc Refactor/consolidate legacy Bloom implementation details (#5784) 2019-09-16 16:17:09 -07:00
db_range_del_test.cc Fix merging range tombstone covering put during flush/compaction (#5406) 2019-06-04 10:24:14 -07:00
db_sst_test.cc Fix bugs in WAL trash file handling (#5520) 2019-07-06 21:07:32 -07:00
db_statistics_test.cc Make statistics's stats_level change thread-safe (#5030) 2019-03-01 10:42:09 -08:00
db_table_properties_test.cc upgrade gtest 1.7.0 => 1.8.1 for json result writing 2019-09-09 11:24:11 -07:00
db_tailing_iter_test.cc Remove managed iterator 2018-07-17 14:43:18 -07:00
db_test.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
db_test2.cc Add a unit test to reproduce a corruption bug (#5851) 2019-09-26 16:18:42 -07:00
db_test_util.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
db_test_util.h Support loading custom objects in unit tests (#5676) 2019-08-09 15:12:08 -07:00
db_universal_compaction_test.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
db_wal_test.cc Adding DB::GetCurrentWalFile() API as a repliction/backup helper (#5765) 2019-09-04 12:10:17 -07:00
db_write_test.cc Move some memory related files from util/ to memory/ (#5382) 2019-05-30 17:44:09 -07:00
dbformat.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
dbformat.h Use delete to disable automatic generated methods. (#5009) 2019-09-11 18:09:00 -07:00
dbformat_test.cc Move some logging related files to logging/ (#5387) 2019-05-31 17:23:59 -07:00
deletefile_test.cc Refactor deletefile_test.cc (#5822) 2019-09-18 16:58:21 -07:00
error_handler.cc Make format 2019-05-31 15:24:43 -07:00
error_handler.h Fix typos in comments (#4456) 2018-10-04 20:46:50 -07:00
error_handler_test.cc Move test related files under util/ to test_util/ (#5377) 2019-05-30 11:25:51 -07:00
event_helpers.cc Fix wrong info log printing for num_range_deletions (#5617) 2019-07-23 19:38:16 -07:00
event_helpers.h Move some logging related files to logging/ (#5387) 2019-05-31 17:23:59 -07:00
experimental.cc Organizing rocksdb/db directory 2019-05-31 11:57:01 -07:00
external_sst_file_basic_test.cc Allow ingesting overlapping files (#5539) 2019-09-13 14:49:47 -07:00
external_sst_file_ingestion_job.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
external_sst_file_ingestion_job.h Allow ingesting overlapping files (#5539) 2019-09-13 14:49:47 -07:00
external_sst_file_test.cc Fix a bug in file ingestion (#5760) 2019-08-30 18:29:07 -07:00
fault_injection_test.cc Move some logging related files to logging/ (#5387) 2019-05-31 17:23:59 -07:00
file_indexer.cc
file_indexer.h Move some memory related files from util/ to memory/ (#5382) 2019-05-30 17:44:09 -07:00
file_indexer_test.cc Move some memory related files from util/ to memory/ (#5382) 2019-05-30 17:44:09 -07:00
filename_test.cc Move some logging related files to logging/ (#5387) 2019-05-31 17:23:59 -07:00
flush_job.cc simplify include directive involving inttypes (#5402) 2019-06-06 13:56:07 -07:00
flush_job.h Move some logging related files to logging/ (#5387) 2019-05-31 17:23:59 -07:00
flush_job_test.cc Divide file_reader_writer.h and .cc (#5803) 2019-09-16 10:33:51 -07:00
flush_scheduler.cc Refactor trimming logic for immutable memtables (#5022) 2019-08-23 13:55:34 -07:00
flush_scheduler.h Refactor trimming logic for immutable memtables (#5022) 2019-08-23 13:55:34 -07:00
forward_iterator.cc Add more callers for table reader. (#5454) 2019-06-20 14:31:48 -07:00
forward_iterator.h Move some memory related files from util/ to memory/ (#5382) 2019-05-30 17:44:09 -07:00
forward_iterator_bench.cc simplify include directive involving inttypes (#5402) 2019-06-06 13:56:07 -07:00
import_column_family_job.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
import_column_family_job.h Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
import_column_family_test.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
internal_stats.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
internal_stats.h Rename InternalDBStatsType enum names (#5779) 2019-09-06 17:31:10 -07:00
job_context.h WritePrepared: Fix visible key compacted out by compaction (#4883) 2019-01-15 21:34:38 -08:00
listener_test.cc Move some logging related files to logging/ (#5387) 2019-05-31 17:23:59 -07:00
log_format.h Fix an inaccurate comment (#4315) 2018-08-24 18:13:20 -07:00
log_reader.cc Divide file_reader_writer.h and .cc (#5803) 2019-09-16 10:33:51 -07:00
log_reader.h Divide file_reader_writer.h and .cc (#5803) 2019-09-16 10:33:51 -07:00
log_test.cc Divide file_reader_writer.h and .cc (#5803) 2019-09-16 10:33:51 -07:00
log_writer.cc Divide file_reader_writer.h and .cc (#5803) 2019-09-16 10:33:51 -07:00
log_writer.h Use delete to disable automatic generated methods. (#5009) 2019-09-11 18:09:00 -07:00
logs_with_prep_tracker.cc Skip deleted WALs during recovery 2018-05-03 15:43:09 -07:00
logs_with_prep_tracker.h Skip deleted WALs during recovery 2018-05-03 15:43:09 -07:00
lookup_key.h Avoid user key copying for Get/Put/Write with user-timestamp (#5502) 2019-07-25 15:27:39 -07:00
malloc_stats.cc Support jemalloc compiled with `--with-jemalloc-prefix` (#5521) 2019-07-02 12:07:01 -07:00
malloc_stats.h
manual_compaction_test.cc Move some memory related files from util/ to memory/ (#5382) 2019-05-30 17:44:09 -07:00
memtable.cc MultiGet batching in memtable (#5818) 2019-10-10 09:39:39 -07:00
memtable.h MultiGet batching in memtable (#5818) 2019-10-10 09:39:39 -07:00
memtable_list.cc MultiGet batching in memtable (#5818) 2019-10-10 09:39:39 -07:00
memtable_list.h MultiGet batching in memtable (#5818) 2019-10-10 09:39:39 -07:00
memtable_list_test.cc Refactor trimming logic for immutable memtables (#5022) 2019-08-23 13:55:34 -07:00
merge_context.h Introduce a new MultiGet batching implementation (#5011) 2019-04-11 14:28:26 -07:00
merge_helper.cc Fix merging range tombstone covering put during flush/compaction (#5406) 2019-06-04 10:24:14 -07:00
merge_helper.h Remove v1 RangeDelAggregator (#4778) 2018-12-17 17:33:46 -08:00
merge_helper_test.cc Move some memory related files from util/ to memory/ (#5382) 2019-05-30 17:44:09 -07:00
merge_operator.cc
merge_test.cc Make format 2019-05-31 15:24:43 -07:00
obsolete_files_test.cc Refactor ObsoleteFilesTest to inherit from DBTestBase (#5820) 2019-09-18 11:52:17 -07:00
options_file_test.cc Organizing rocksdb/db directory 2019-05-31 11:57:01 -07:00
perf_context_test.cc Move some memory related files from util/ to memory/ (#5382) 2019-05-30 17:44:09 -07:00
pinned_iterators_manager.h
plain_table_db_test.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
pre_release_callback.h WritePrepared: reduce prepared_mutex_ overhead (#5420) 2019-06-10 11:53:31 -07:00
prefix_test.cc Organizing rocksdb/db directory 2019-05-31 11:57:01 -07:00
range_del_aggregator.cc Organizing rocksdb/db directory 2019-05-31 11:57:01 -07:00
range_del_aggregator.h Organizing rocksdb/db directory 2019-05-31 11:57:01 -07:00
range_del_aggregator_bench.cc Move some memory related files from util/ to memory/ (#5382) 2019-05-30 17:44:09 -07:00
range_del_aggregator_test.cc Move test related files under util/ to test_util/ (#5377) 2019-05-30 11:25:51 -07:00
range_tombstone_fragmenter.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
range_tombstone_fragmenter.h Initialized pinned_pos_ and pinned_seq_pos_ in FragmentedRangeTombstoneIterator (#5720) 2019-09-05 17:30:29 -07:00
range_tombstone_fragmenter_test.cc Move test related files under util/ to test_util/ (#5377) 2019-05-30 11:25:51 -07:00
read_callback.h WriteUnPrepared: improve read your own write functionality (#5573) 2019-07-23 08:08:19 -07:00
repair.cc Divide file_reader_writer.h and .cc (#5803) 2019-09-16 10:33:51 -07:00
repair_test.cc Organizing rocksdb/db directory 2019-05-31 11:57:01 -07:00
snapshot_checker.h WritePrepared: fix issue with snapshot released during compaction (#4858) 2019-01-16 09:55:32 -08:00
snapshot_impl.cc
snapshot_impl.h Refresh snapshot list during long compactions (2nd attempt) (#5278) 2019-05-03 17:30:22 -07:00
table_cache.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
table_cache.h Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
table_properties_collector.cc Feature for sampling and reporting compressibility (#4842) 2019-03-18 12:15:34 -07:00
table_properties_collector.h Feature for sampling and reporting compressibility (#4842) 2019-03-18 12:15:34 -07:00
table_properties_collector_test.cc Divide file_reader_writer.h and .cc (#5803) 2019-09-16 10:33:51 -07:00
transaction_log_impl.cc Divide file_reader_writer.h and .cc (#5803) 2019-09-16 10:33:51 -07:00
transaction_log_impl.h reuse scratch buffer in transaction_log_reader (#5702) 2019-08-26 11:26:29 -07:00
trim_history_scheduler.cc Refactor trimming logic for immutable memtables (#5022) 2019-08-23 13:55:34 -07:00
trim_history_scheduler.h Refactor trimming logic for immutable memtables (#5022) 2019-08-23 13:55:34 -07:00
version_builder.cc save a few redundant container lookups (#5875) 2019-10-07 12:28:09 -07:00
version_builder.h Lower the risk for users to run options.force_consistency_checks = true (#5744) 2019-08-29 14:07:37 -07:00
version_builder_test.cc Move some logging related files to logging/ (#5387) 2019-05-31 17:23:59 -07:00
version_edit.cc Persistent globally unique DB ID in manifest (#5725) 2019-09-03 08:52:24 -07:00
version_edit.h Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
version_edit_test.cc upgrade gtest 1.7.0 => 1.8.1 for json result writing 2019-09-09 11:24:11 -07:00
version_set.cc Revert "Merging iterator to avoid child iterator reseek for some cases (#5286)" (#5871) 2019-10-01 11:22:41 -07:00
version_set.h Use delete to disable automatic generated methods. (#5009) 2019-09-11 18:09:00 -07:00
version_set_test.cc upgrade gtest 1.7.0 => 1.8.1 for json result writing 2019-09-09 11:24:11 -07:00
wal_manager.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
wal_manager.h Adding DB::GetCurrentWalFile() API as a repliction/backup helper (#5765) 2019-09-04 12:10:17 -07:00
wal_manager_test.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
write_batch.cc Apply formatter to recent 200+ commits. (#5830) 2019-09-20 12:04:26 -07:00
write_batch_base.cc
write_batch_internal.h Add insert hints for each writebatch (#5728) 2019-09-12 17:15:18 -07:00
write_batch_test.cc upgrade gtest 1.7.0 => 1.8.1 for json result writing 2019-09-09 11:24:11 -07:00
write_callback.h
write_callback_test.cc WritePrepared: reduce prepared_mutex_ overhead (#5420) 2019-06-10 11:53:31 -07:00
write_controller.cc
write_controller.h
write_controller_test.cc Move test related files under util/ to test_util/ (#5377) 2019-05-30 11:25:51 -07:00
write_thread.cc Option to make write group size configurable (#5759) 2019-09-11 18:28:33 -07:00
write_thread.h Option to make write group size configurable (#5759) 2019-09-11 18:28:33 -07:00