rocksdb/table/block_based
Peter Dillinger 280b9f371a Fix auto_prefix_mode performance with partitioned filters (#10012)
Summary:
Essentially refactored the RangeMayExist implementation in
FullFilterBlockReader to FilterBlockReaderCommon so that it applies to
partitioned filters as well. (The function is not called for the
block-based filter case.) RangeMayExist is essentially a series of checks
around a possible PrefixMayExist, and I'm confident those checks should
be the same for partitioned as for full filters. (I think it's likely
that bugs remain in those checks, but this change is overall a simplifying
one.)

Added auto_prefix_mode support to db_bench

Other small fixes as well

Fixes https://github.com/facebook/rocksdb/issues/10003

Pull Request resolved: https://github.com/facebook/rocksdb/pull/10012

Test Plan:
Expanded unit test that uses statistics to check for filter
optimization, fails without the production code changes here

Performance: populate two DBs with
```
TEST_TMPDIR=/dev/shm/rocksdb_nonpartitioned ./db_bench -benchmarks=fillrandom -num=10000000 -disable_wal=1 -write_buffer_size=30000000 -bloom_bits=16 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -prefix_size=8
TEST_TMPDIR=/dev/shm/rocksdb_partitioned ./db_bench -benchmarks=fillrandom -num=10000000 -disable_wal=1 -write_buffer_size=30000000 -bloom_bits=16 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -prefix_size=8 -partition_index_and_filters
```

Observe no measurable change in non-partitioned performance
```
TEST_TMPDIR=/dev/shm/rocksdb_nonpartitioned ./db_bench -benchmarks=seekrandom[-X1000] -num=10000000 -readonly -bloom_bits=16 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -prefix_size=8 -auto_prefix_mode -cache_index_and_filter_blocks=1 -cache_size=1000000000 -duration 20
```
Before: seekrandom [AVG 15 runs] : 11798 (± 331) ops/sec
After: seekrandom [AVG 15 runs] : 11724 (± 315) ops/sec

Observe big improvement with partitioned (also supported by bloom use statistics)
```
TEST_TMPDIR=/dev/shm/rocksdb_partitioned ./db_bench -benchmarks=seekrandom[-X1000] -num=10000000 -readonly -bloom_bits=16 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -prefix_size=8 -partition_index_and_filters -auto_prefix_mode -cache_index_and_filter_blocks=1 -cache_size=1000000000 -duration 20
```
Before: seekrandom [AVG 12 runs] : 2942 (± 57) ops/sec
After: seekrandom [AVG 12 runs] : 7489 (± 184) ops/sec

Reviewed By: siying

Differential Revision: D36469796

Pulled By: pdillinger

fbshipit-source-id: bcf1e2a68d347b32adb2b27384f945434e7a266d
2022-05-19 13:09:03 -07:00
..
binary_search_index_reader.cc Set Read rate limiter priority dynamically and pass it to FS (#9996) 2022-05-18 19:41:44 -07:00
binary_search_index_reader.h Extend Get/MultiGet deadline support to table open (#6982) 2020-06-29 14:53:17 -07:00
block_based_filter_block_test.cc FilterPolicy API changes for 7.0 (#9501) 2022-02-08 13:56:46 -08:00
block_based_filter_block.cc Remove own ToString() (#9955) 2022-05-06 13:03:58 -07:00
block_based_filter_block.h FilterPolicy API changes for 7.0 (#9501) 2022-02-08 13:56:46 -08:00
block_based_table_builder.cc Rewrite memory-charging feature's option API (#9926) 2022-05-17 15:01:51 -07:00
block_based_table_builder.h Fix segmentation fault in table_options.prepopulate_block_cache when used with partition_filters (#9263) 2021-12-08 12:44:38 -08:00
block_based_table_factory.cc Mark old reserve* option deprecated (#10016) 2022-05-18 22:25:54 -07:00
block_based_table_factory.h Account memory of big memory users in BlockBasedTable in global memory limit (#9748) 2022-04-06 10:33:00 -07:00
block_based_table_iterator.cc Set Read rate limiter priority dynamically and pass it to FS (#9996) 2022-05-18 19:41:44 -07:00
block_based_table_iterator.h Make initial auto readahead_size configurable (#9836) 2022-04-15 17:28:09 -07:00
block_based_table_reader_impl.h Fb 9718 verify checksums is ignored (#9767) 2022-03-29 11:54:54 -07:00
block_based_table_reader_test.cc Rewrite memory-charging feature's option API (#9926) 2022-05-17 15:01:51 -07:00
block_based_table_reader.cc Set Read rate limiter priority dynamically and pass it to FS (#9996) 2022-05-18 19:41:44 -07:00
block_based_table_reader.h Add stats related to async prefetching (#9845) 2022-04-25 21:58:22 -07:00
block_builder.cc Improve data block construction performance (#9040) 2021-10-19 12:36:21 -07:00
block_builder.h Improve data block construction performance (#9040) 2021-10-19 12:36:21 -07:00
block_like_traits.h Change type of cache buffer passed to Cache::CreateCallback() to const void* (#9595) 2022-02-17 21:09:56 -08:00
block_prefetcher.cc Set Read rate limiter priority dynamically and pass it to FS (#9996) 2022-05-18 19:41:44 -07:00
block_prefetcher.h Set Read rate limiter priority dynamically and pass it to FS (#9996) 2022-05-18 19:41:44 -07:00
block_prefix_index.cc Replace namespace name "rocksdb" with ROCKSDB_NAMESPACE (#6433) 2020-02-20 12:09:57 -08:00
block_prefix_index.h Replace namespace name "rocksdb" with ROCKSDB_NAMESPACE (#6433) 2020-02-20 12:09:57 -08:00
block_test.cc Improve / clean up meta block code & integrity (#9163) 2021-11-18 11:43:44 -08:00
block_type.h Fix and detect headers with missing dependencies (#8893) 2021-09-10 10:00:26 -07:00
block.cc Use std::numeric_limits<> (#9954) 2022-05-05 13:08:21 -07:00
block.h Reduce comparator objects init cost in BlockIter (#9611) 2022-05-03 17:37:19 -07:00
cachable_entry.h Meta-internal folly integration with F14FastMap (#9546) 2022-04-13 07:34:01 -07:00
data_block_footer.cc Replace namespace name "rocksdb" with ROCKSDB_NAMESPACE (#6433) 2020-02-20 12:09:57 -08:00
data_block_footer.h Replace namespace name "rocksdb" with ROCKSDB_NAMESPACE (#6433) 2020-02-20 12:09:57 -08:00
data_block_hash_index_test.cc Fast path for detecting unchanged prefix_extractor (#9407) 2022-01-21 11:37:46 -08:00
data_block_hash_index.cc Replace namespace name "rocksdb" with ROCKSDB_NAMESPACE (#6433) 2020-02-20 12:09:57 -08:00
data_block_hash_index.h Replace namespace name "rocksdb" with ROCKSDB_NAMESPACE (#6433) 2020-02-20 12:09:57 -08:00
filter_block_reader_common.cc Fix auto_prefix_mode performance with partitioned filters (#10012) 2022-05-19 13:09:03 -07:00
filter_block_reader_common.h Fix auto_prefix_mode performance with partitioned filters (#10012) 2022-05-19 13:09:03 -07:00
filter_block.h Fix auto_prefix_mode performance with partitioned filters (#10012) 2022-05-19 13:09:03 -07:00
filter_policy_internal.h Fix a major performance bug in 7.0 re: filter compatibility (#9736) 2022-03-23 10:00:54 -07:00
filter_policy.cc Rewrite memory-charging feature's option API (#9926) 2022-05-17 15:01:51 -07:00
flush_block_policy.cc Restore Regex support for ObjectLibrary::Register, rename new APIs to allow old one to be deprecated in the future (#9362) 2022-01-11 06:33:48 -08:00
flush_block_policy.h Make FlushBlockPolicyFactory into a Customizable class (#8432) 2021-07-12 09:04:59 -07:00
full_filter_block_test.cc Fix a major performance bug in 7.0 re: filter compatibility (#9736) 2022-03-23 10:00:54 -07:00
full_filter_block.cc Fix auto_prefix_mode performance with partitioned filters (#10012) 2022-05-19 13:09:03 -07:00
full_filter_block.h Fix auto_prefix_mode performance with partitioned filters (#10012) 2022-05-19 13:09:03 -07:00
hash_index_reader.cc Set Read rate limiter priority dynamically and pass it to FS (#9996) 2022-05-18 19:41:44 -07:00
hash_index_reader.h Extend Get/MultiGet deadline support to table open (#6982) 2020-06-29 14:53:17 -07:00
index_builder.cc Add (& fix) some simple source code checks (#8821) 2021-09-07 21:19:27 -07:00
index_builder.h Remove own ToString() (#9955) 2022-05-06 13:03:58 -07:00
index_reader_common.cc Set Read rate limiter priority dynamically and pass it to FS (#9996) 2022-05-18 19:41:44 -07:00
index_reader_common.h Set Read rate limiter priority dynamically and pass it to FS (#9996) 2022-05-18 19:41:44 -07:00
mock_block_based_table.h Refactor FilterPolicies toward Customizable (#9567) 2022-02-16 08:30:03 -08:00
parsed_full_filter_block.cc Hide FilterBits{Builder,Reader} from public API (#9592) 2022-02-17 16:34:46 -08:00
parsed_full_filter_block.h Use new Insert and Lookup APIs in table reader to support secondary cache (#8315) 2021-05-21 18:29:12 -07:00
partitioned_filter_block_test.cc More refactoring ahead of footer & meta changes (#9240) 2021-12-10 08:13:26 -08:00
partitioned_filter_block.cc Enable READ_BLOCK_COMPACTION_MICROS to track stats (#9722) 2022-03-24 15:06:24 -07:00
partitioned_filter_block.h Meta-internal folly integration with F14FastMap (#9546) 2022-04-13 07:34:01 -07:00
partitioned_index_iterator.cc Set Read rate limiter priority dynamically and pass it to FS (#9996) 2022-05-18 19:41:44 -07:00
partitioned_index_iterator.h Make initial auto readahead_size configurable (#9836) 2022-04-15 17:28:09 -07:00
partitioned_index_reader.cc Set Read rate limiter priority dynamically and pass it to FS (#9996) 2022-05-18 19:41:44 -07:00
partitioned_index_reader.h Meta-internal folly integration with F14FastMap (#9546) 2022-04-13 07:34:01 -07:00
reader_common.cc Remove own ToString() (#9955) 2022-05-06 13:03:58 -07:00
reader_common.h Bring the Configurable options together (#5753) 2020-09-14 17:01:01 -07:00
uncompression_dict_reader.cc Fb 9718 verify checksums is ignored (#9767) 2022-03-29 11:54:54 -07:00
uncompression_dict_reader.h Fb 9718 verify checksums is ignored (#9767) 2022-03-29 11:54:54 -07:00