mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 16:30:56 +00:00
68a8e6b8fa
Summary: This diff update the code to pin the merge operator operands while the merge operation is done, so that we can eliminate the memcpy cost, to do that we need a new public API for FullMerge that replace the std::deque<std::string> with std::vector<Slice> This diff is stacked on top of D56493 and D56511 In this diff we - Update FullMergeV2 arguments to be encapsulated in MergeOperationInput and MergeOperationOutput which will make it easier to add new arguments in the future - Replace std::deque<std::string> with std::vector<Slice> to pass operands - Replace MergeContext std::deque with std::vector (based on a simple benchmark I ran https://gist.github.com/IslamAbdelRahman/78fc86c9ab9f52b1df791e58943fb187) - Allow FullMergeV2 output to be an existing operand ``` [Everything in Memtable | 10K operands | 10 KB each | 1 operand per key] DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --merge_keys=10000 --num=10000 --disable_auto_compactions --value_size=10240 --write_buffer_size=1000000000 [FullMergeV2] readseq : 0.607 micros/op 1648235 ops/sec; 16121.2 MB/s readseq : 0.478 micros/op 2091546 ops/sec; 20457.2 MB/s readseq : 0.252 micros/op 3972081 ops/sec; 38850.5 MB/s readseq : 0.237 micros/op 4218328 ops/sec; 41259.0 MB/s readseq : 0.247 micros/op 4043927 ops/sec; 39553.2 MB/s [master] readseq : 3.935 micros/op 254140 ops/sec; 2485.7 MB/s readseq : 3.722 micros/op 268657 ops/sec; 2627.7 MB/s readseq : 3.149 micros/op 317605 ops/sec; 3106.5 MB/s readseq : 3.125 micros/op 320024 ops/sec; 3130.1 MB/s readseq : 4.075 micros/op 245374 ops/sec; 2400.0 MB/s ``` ``` [Everything in Memtable | 10K operands | 10 KB each | 10 operand per key] DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --merge_keys=1000 --num=10000 --disable_auto_compactions --value_size=10240 --write_buffer_size=1000000000 [FullMergeV2] readseq : 3.472 micros/op 288018 ops/sec; 2817.1 MB/s readseq : 2.304 micros/op 434027 ops/sec; 4245.2 MB/s readseq : 1.163 micros/op 859845 ops/sec; 8410.0 MB/s readseq : 1.192 micros/op 838926 ops/sec; 8205.4 MB/s readseq : 1.250 micros/op 800000 ops/sec; 7824.7 MB/s [master] readseq : 24.025 micros/op 41623 ops/sec; 407.1 MB/s readseq : 18.489 micros/op 54086 ops/sec; 529.0 MB/s readseq : 18.693 micros/op 53495 ops/sec; 523.2 MB/s readseq : 23.621 micros/op 42335 ops/sec; 414.1 MB/s readseq : 18.775 micros/op 53262 ops/sec; 521.0 MB/s ``` ``` [Everything in Block cache | 10K operands | 10 KB each | 1 operand per key] [FullMergeV2] $ DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --num=100000 --db="/dev/shm/merge-random-10K-10KB" --cache_size=1000000000 --use_existing_db --disable_auto_compactions readseq : 14.741 micros/op 67837 ops/sec; 663.5 MB/s readseq : 1.029 micros/op 971446 ops/sec; 9501.6 MB/s readseq : 0.974 micros/op 1026229 ops/sec; 10037.4 MB/s readseq : 0.965 micros/op 1036080 ops/sec; 10133.8 MB/s readseq : 0.943 micros/op 1060657 ops/sec; 10374.2 MB/s [master] readseq : 16.735 micros/op 59755 ops/sec; 584.5 MB/s readseq : 3.029 micros/op 330151 ops/sec; 3229.2 MB/s readseq : 3.136 micros/op 318883 ops/sec; 3119.0 MB/s readseq : 3.065 micros/op 326245 ops/sec; 3191.0 MB/s readseq : 3.014 micros/op 331813 ops/sec; 3245.4 MB/s ``` ``` [Everything in Block cache | 10K operands | 10 KB each | 10 operand per key] DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --num=100000 --db="/dev/shm/merge-random-10-operands-10K-10KB" --cache_size=1000000000 --use_existing_db --disable_auto_compactions [FullMergeV2] readseq : 24.325 micros/op 41109 ops/sec; 402.1 MB/s readseq : 1.470 micros/op 680272 ops/sec; 6653.7 MB/s readseq : 1.231 micros/op 812347 ops/sec; 7945.5 MB/s readseq : 1.091 micros/op 916590 ops/sec; 8965.1 MB/s readseq : 1.109 micros/op 901713 ops/sec; 8819.6 MB/s [master] readseq : 27.257 micros/op 36687 ops/sec; 358.8 MB/s readseq : 4.443 micros/op 225073 ops/sec; 2201.4 MB/s readseq : 5.830 micros/op 171526 ops/sec; 1677.7 MB/s readseq : 4.173 micros/op 239635 ops/sec; 2343.8 MB/s readseq : 4.150 micros/op 240963 ops/sec; 2356.8 MB/s ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: yhchiang, andrewkr, sdong Reviewed By: sdong Subscribers: lovro, andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D57075 |
||
|---|---|---|
| .. | ||
| aligned_buffer.h | ||
| allocator.h | ||
| arena.cc | ||
| arena.h | ||
| arena_test.cc | ||
| autovector.h | ||
| autovector_test.cc | ||
| bloom.cc | ||
| bloom_test.cc | ||
| build_version.h | ||
| cache_bench.cc | ||
| cache_test.cc | ||
| channel.h | ||
| coding.cc | ||
| coding.h | ||
| coding_test.cc | ||
| compaction_job_stats_impl.cc | ||
| comparator.cc | ||
| compression.h | ||
| concurrent_arena.cc | ||
| concurrent_arena.h | ||
| crc32c.cc | ||
| crc32c.h | ||
| crc32c_test.cc | ||
| delete_scheduler.cc | ||
| delete_scheduler.h | ||
| delete_scheduler_test.cc | ||
| dynamic_bloom.cc | ||
| dynamic_bloom.h | ||
| dynamic_bloom_test.cc | ||
| env.cc | ||
| env_basic_test.cc | ||
| env_chroot.cc | ||
| env_chroot.h | ||
| env_hdfs.cc | ||
| env_posix.cc | ||
| env_test.cc | ||
| event_logger.cc | ||
| event_logger.h | ||
| event_logger_test.cc | ||
| fault_injection_test_env.cc | ||
| fault_injection_test_env.h | ||
| file_reader_writer.cc | ||
| file_reader_writer.h | ||
| file_reader_writer_test.cc | ||
| file_util.cc | ||
| file_util.h | ||
| filelock_test.cc | ||
| filter_policy.cc | ||
| hash.cc | ||
| hash.h | ||
| heap.h | ||
| heap_test.cc | ||
| histogram.cc | ||
| histogram.h | ||
| histogram_test.cc | ||
| histogram_windowing.cc | ||
| histogram_windowing.h | ||
| instrumented_mutex.cc | ||
| instrumented_mutex.h | ||
| io_posix.cc | ||
| io_posix.h | ||
| iostats_context.cc | ||
| iostats_context_imp.h | ||
| iostats_context_test.cc | ||
| kv_map.h | ||
| log_buffer.cc | ||
| log_buffer.h | ||
| log_write_bench.cc | ||
| logging.cc | ||
| logging.h | ||
| lru_cache.cc | ||
| memenv.cc | ||
| mock_env.cc | ||
| mock_env.h | ||
| mock_env_test.cc | ||
| murmurhash.cc | ||
| murmurhash.h | ||
| mutable_cf_options.cc | ||
| mutable_cf_options.h | ||
| mutexlock.h | ||
| options.cc | ||
| options_helper.cc | ||
| options_helper.h | ||
| options_parser.cc | ||
| options_parser.h | ||
| options_sanity_check.cc | ||
| options_sanity_check.h | ||
| options_settable_test.cc | ||
| options_test.cc | ||
| perf_context.cc | ||
| perf_context_imp.h | ||
| perf_level.cc | ||
| perf_level_imp.h | ||
| perf_step_timer.h | ||
| posix_logger.h | ||
| random.cc | ||
| random.h | ||
| rate_limiter.cc | ||
| rate_limiter.h | ||
| rate_limiter_test.cc | ||
| sharded_cache.cc | ||
| sharded_cache.h | ||
| slice.cc | ||
| slice_transform_test.cc | ||
| sst_file_manager_impl.cc | ||
| sst_file_manager_impl.h | ||
| statistics.cc | ||
| statistics.h | ||
| status.cc | ||
| status_message.cc | ||
| stderr_logger.h | ||
| stop_watch.h | ||
| string_util.cc | ||
| string_util.h | ||
| sync_point.cc | ||
| sync_point.h | ||
| testharness.cc | ||
| testharness.h | ||
| testutil.cc | ||
| testutil.h | ||
| thread_list_test.cc | ||
| thread_local.cc | ||
| thread_local.h | ||
| thread_local_test.cc | ||
| thread_operation.h | ||
| thread_status_impl.cc | ||
| thread_status_updater.cc | ||
| thread_status_updater.h | ||
| thread_status_updater_debug.cc | ||
| thread_status_util.cc | ||
| thread_status_util.h | ||
| thread_status_util_debug.cc | ||
| threadpool.cc | ||
| threadpool.h | ||
| transaction_test_util.cc | ||
| transaction_test_util.h | ||
| xfunc.cc | ||
| xfunc.h | ||
| xxhash.cc | ||
| xxhash.h | ||