dolysis
/
rocksdb
mirror of https://github.com/facebook/rocksdb.git
3
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
rocksdb/table
History
Changyu Bi cc23b46da1 Support using ZDICT_finalizeDictionary to generate zstd dictionary (#9857) 
Summary:
An untrained dictionary is currently simply the concatenation of several samples. The ZSTD API, ZDICT_finalizeDictionary(), can improve such a dictionary's effectiveness at low cost. This PR changes how dictionary is created by calling the ZSTD ZDICT_finalizeDictionary() API instead of creating raw content dictionary (when max_dict_buffer_bytes > 0), and pass in all buffered uncompressed data blocks as samples.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/9857

Test Plan:
#### db_bench test for cpu/memory of compression+decompression and space saving on synthetic data:
Set up: change the parameter [here](fb9a167a55/tools/db_bench_tool.cc (L1766)) to 16384 to make synthetic data more compressible.
```
# linked local ZSTD with version 1.5.2
# DEBUG_LEVEL=0 ROCKSDB_NO_FBCODE=1 ROCKSDB_DISABLE_ZSTD=1  EXTRA_CXXFLAGS="-DZSTD_STATIC_LINKING_ONLY -DZSTD -I/data/users/changyubi/install/include/" EXTRA_LDFLAGS="-L/data/users/changyubi/install/lib/ -l:libzstd.a" make -j32 db_bench

dict_bytes=16384
train_bytes=1048576
echo "========== No Dictionary =========="
TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=filluniquerandom,compact -num=10000000 -compression_type=zstd -compression_max_dict_bytes=0 -block_size=4096 -max_background_jobs=24 -memtablerep=vector -allow_concurrent_memtable_write=false -disable_wal=true -max_write_buffer_number=8 >/dev/null 2>&1
TEST_TMPDIR=/dev/shm /usr/bin/time ./db_bench -use_existing_db=true -benchmarks=compact -compression_type=zstd -compression_max_dict_bytes=0 -block_size=4096 2>&1 | grep elapsed
du -hc /dev/shm/dbbench/*sst | grep total

echo "========== Raw Content Dictionary =========="
TEST_TMPDIR=/dev/shm ./db_bench_main -benchmarks=filluniquerandom,compact -num=10000000 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -block_size=4096 -max_background_jobs=24 -memtablerep=vector -allow_concurrent_memtable_write=false -disable_wal=true -max_write_buffer_number=8 >/dev/null 2>&1
TEST_TMPDIR=/dev/shm /usr/bin/time ./db_bench_main -use_existing_db=true -benchmarks=compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -block_size=4096 2>&1 | grep elapsed
du -hc /dev/shm/dbbench/*sst | grep total

echo "========== FinalizeDictionary =========="
TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=filluniquerandom,compact -num=10000000 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -compression_use_zstd_dict_trainer=false -block_size=4096 -max_background_jobs=24 -memtablerep=vector -allow_concurrent_memtable_write=false -disable_wal=true -max_write_buffer_number=8 >/dev/null 2>&1
TEST_TMPDIR=/dev/shm /usr/bin/time ./db_bench -use_existing_db=true -benchmarks=compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -compression_use_zstd_dict_trainer=false -block_size=4096 2>&1 | grep elapsed
du -hc /dev/shm/dbbench/*sst | grep total

echo "========== TrainDictionary =========="
TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=filluniquerandom,compact -num=10000000 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -block_size=4096 -max_background_jobs=24 -memtablerep=vector -allow_concurrent_memtable_write=false -disable_wal=true -max_write_buffer_number=8 >/dev/null 2>&1
TEST_TMPDIR=/dev/shm /usr/bin/time ./db_bench -use_existing_db=true -benchmarks=compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -block_size=4096 2>&1 | grep elapsed
du -hc /dev/shm/dbbench/*sst | grep total

# Result: TrainDictionary is much better on space saving, but FinalizeDictionary seems to use less memory.
# before compression data size: 1.2GB
dict_bytes=16384
max_dict_buffer_bytes =  1048576
                    space   cpu/memory
No Dictionary       468M    14.93user 1.00system 0:15.92elapsed 100%CPU (0avgtext+0avgdata 23904maxresident)k
Raw Dictionary      251M    15.81user 0.80system 0:16.56elapsed 100%CPU (0avgtext+0avgdata 156808maxresident)k
FinalizeDictionary  236M    11.93user 0.64system 0:12.56elapsed 100%CPU (0avgtext+0avgdata 89548maxresident)k
TrainDictionary     84M     7.29user 0.45system 0:07.75elapsed 100%CPU (0avgtext+0avgdata 97288maxresident)k
```

#### Benchmark on 10 sample SST files for spacing saving and CPU time on compression:
FinalizeDictionary is comparable to TrainDictionary in terms of space saving, and takes less time in compression.
```
dict_bytes=16384
train_bytes=1048576

for sst_file in `ls ../temp/myrock-sst/`
do
  echo "********** $sst_file **********"
  echo "========== No Dictionary =========="
  ./sst_dump --file="../temp/myrock-sst/$sst_file" --command=recompress --compression_level_from=6 --compression_level_to=6 --compression_types=kZSTD

  echo "========== Raw Content Dictionary =========="
  ./sst_dump --file="../temp/myrock-sst/$sst_file" --command=recompress --compression_level_from=6 --compression_level_to=6 --compression_types=kZSTD --compression_max_dict_bytes=$dict_bytes

  echo "========== FinalizeDictionary =========="
  ./sst_dump --file="../temp/myrock-sst/$sst_file" --command=recompress --compression_level_from=6 --compression_level_to=6 --compression_types=kZSTD --compression_max_dict_bytes=$dict_bytes --compression_zstd_max_train_bytes=$train_bytes --compression_use_zstd_finalize_dict

  echo "========== TrainDictionary =========="
  ./sst_dump --file="../temp/myrock-sst/$sst_file" --command=recompress --compression_level_from=6 --compression_level_to=6 --compression_types=kZSTD --compression_max_dict_bytes=$dict_bytes --compression_zstd_max_train_bytes=$train_bytes
done

                         010240.sst (Size/Time) 011029.sst              013184.sst              021552.sst              185054.sst              185137.sst              191666.sst              7560381.sst             7604174.sst             7635312.sst
No Dictionary           28165569 / 2614419      32899411 / 2976832      32977848 / 3055542      31966329 / 2004590      33614351 / 1755877      33429029 / 1717042      33611933 / 1776936      33634045 / 2771417      33789721 / 2205414      33592194 / 388254
Raw Content Dictionary  28019950 / 2697961      33748665 / 3572422      33896373 / 3534701      26418431 / 2259658      28560825 / 1839168      28455030 / 1846039      28494319 / 1861349      32391599 / 3095649      33772142 / 2407843      33592230 / 474523
FinalizeDictionary      27896012 / 2650029      33763886 / 3719427      33904283 / 3552793      26008225 / 2198033      28111872 / 1869530      28014374 / 1789771      28047706 / 1848300      32296254 / 3204027      33698698 / 2381468      33592344 / 517433
TrainDictionary         28046089 / 2740037      33706480 / 3679019      33885741 / 3629351      25087123 / 2204558      27194353 / 1970207      27234229 / 1896811      27166710 / 1903119      32011041 / 3322315      32730692 / 2406146      33608631 / 570593
```

#### Decompression/Read test:
With FinalizeDictionary/TrainDictionary, some data structure used for decompression are in stored in dictionary, so they are expected to be faster in terms of decompression/reads.
```
dict_bytes=16384
train_bytes=1048576
echo "No Dictionary"
TEST_TMPDIR=/dev/shm/ ./db_bench -benchmarks=filluniquerandom,compact -compression_type=zstd -compression_max_dict_bytes=0 > /dev/null 2>&1
TEST_TMPDIR=/dev/shm/ ./db_bench -use_existing_db=true -benchmarks=readrandom -cache_size=0 -compression_type=zstd -compression_max_dict_bytes=0 2>&1 | grep MB/s

echo "Raw Dictionary"
TEST_TMPDIR=/dev/shm/ ./db_bench -benchmarks=filluniquerandom,compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes > /dev/null 2>&1
TEST_TMPDIR=/dev/shm/ ./db_bench -use_existing_db=true -benchmarks=readrandom -cache_size=0 -compression_type=zstd  -compression_max_dict_bytes=$dict_bytes 2>&1 | grep MB/s

echo "FinalizeDict"
TEST_TMPDIR=/dev/shm/ ./db_bench -benchmarks=filluniquerandom,compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -compression_use_zstd_dict_trainer=false  > /dev/null 2>&1
TEST_TMPDIR=/dev/shm/ ./db_bench -use_existing_db=true -benchmarks=readrandom -cache_size=0 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -compression_use_zstd_dict_trainer=false 2>&1 | grep MB/s

echo "Train Dictionary"
TEST_TMPDIR=/dev/shm/ ./db_bench -benchmarks=filluniquerandom,compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes > /dev/null 2>&1
TEST_TMPDIR=/dev/shm/ ./db_bench -use_existing_db=true -benchmarks=readrandom -cache_size=0 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes 2>&1 | grep MB/s

No Dictionary
readrandom   :      12.183 micros/op 82082 ops/sec 12.183 seconds 1000000 operations;    9.1 MB/s (1000000 of 1000000 found)
Raw Dictionary
readrandom   :      12.314 micros/op 81205 ops/sec 12.314 seconds 1000000 operations;    9.0 MB/s (1000000 of 1000000 found)
FinalizeDict
readrandom   :       9.787 micros/op 102180 ops/sec 9.787 seconds 1000000 operations;   11.3 MB/s (1000000 of 1000000 found)
Train Dictionary
readrandom   :       9.698 micros/op 103108 ops/sec 9.699 seconds 1000000 operations;   11.4 MB/s (1000000 of 1000000 found)
```

Reviewed By: ajkr

Differential Revision: D35720026

Pulled By: cbi42

fbshipit-source-id: 24d230fdff0fd28a1bb650658798f00dfcfb2a1f
 		2022-05-20 12:09:09 -07:00
..
adaptive More refactoring ahead of footer & meta changes (#9240) 2021-12-10 08:13:26 -08:00
block_based Support using ZDICT_finalizeDictionary to generate zstd dictionary (#9857) 2022-05-20 12:09:09 -07:00
cuckoo Remove own ToString() (#9955) 2022-05-06 13:03:58 -07:00
plain Added GetFactoryCount/Names/Types to ObjectRegistry (#9358) 2022-05-16 09:44:43 -07:00
block_fetcher.cc Remove own ToString() (#9955) 2022-05-06 13:03:58 -07:00
block_fetcher.h More refactoring ahead of footer & meta changes (#9240) 2021-12-10 08:13:26 -08:00
block_fetcher_test.cc Make MemoryAllocator into a Customizable class (#8980) 2021-12-17 04:20:47 -08:00
cleanable_test.cc Eliminate unnecessary (slow) block cache Ref()ing in MultiGet (#9899) 2022-04-26 21:59:24 -07:00
format.cc Set Read rate limiter priority dynamically and pass it to FS (#9996) 2022-05-18 19:41:44 -07:00
format.h Optimize & clean up footer code (#9280) 2021-12-13 17:43:07 -08:00
get_context.cc Support readahead during compaction for blob files (#9187) 2021-11-19 17:53:47 -08:00
get_context.h Cleanup includes in dbformat.h (#8930) 2021-09-29 04:04:40 -07:00
internal_iterator.h Reuse internal auto readhead_size at each Level (expect L0) for Iterations (#9056) 2021-11-10 16:20:04 -08:00
iter_heap.h Replace namespace name "rocksdb" with ROCKSDB_NAMESPACE (#6433) 2020-02-20 12:09:57 -08:00
iterator.cc Eliminate unnecessary (slow) block cache Ref()ing in MultiGet (#9899) 2022-04-26 21:59:24 -07:00
iterator_wrapper.h Reuse internal auto readhead_size at each Level (expect L0) for Iterations (#9056) 2021-11-10 16:20:04 -08:00
merger_test.cc Cleanup multiple implementations of VectorIterator (#8901) 2021-10-06 07:48:31 -07:00
merging_iterator.cc MergingIterator: rearrange fields to reduce paddings (#9024) 2021-10-14 12:01:56 -07:00
merging_iterator.h Cleanup includes in dbformat.h (#8930) 2021-09-29 04:04:40 -07:00
meta_blocks.cc Use std::numeric_limits<> (#9954) 2022-05-05 13:08:21 -07:00
meta_blocks.h Tests for filter compatibility (#9773) 2022-04-06 15:54:40 -07:00
mock_table.cc Add rate limiter priority to ReadOptions (#9424) 2022-02-16 23:18:14 -08:00
mock_table.h Fix some minor issues in the Customizable infrastructure (#8566) 2021-08-19 10:10:47 -07:00
multiget_context.h Multi file concurrency in MultiGet using coroutines and async IO (#9968) 2022-05-19 15:36:27 -07:00
persistent_cache_helper.cc New stable, fixed-length cache keys (#9126) 2021-12-16 17:15:13 -08:00
persistent_cache_helper.h Replace namespace name "rocksdb" with ROCKSDB_NAMESPACE (#6433) 2020-02-20 12:09:57 -08:00
persistent_cache_options.h Use STATIC_AVOID_DESTRUCTION for static objects with non-trivial destructors (#9958) 2022-05-17 09:39:22 -07:00
scoped_arena_iterator.h Replace namespace name "rocksdb" with ROCKSDB_NAMESPACE (#6433) 2020-02-20 12:09:57 -08:00
sst_file_dumper.cc Support using ZDICT_finalizeDictionary to generate zstd dictionary (#9857) 2022-05-20 12:09:09 -07:00
sst_file_dumper.h Support using ZDICT_finalizeDictionary to generate zstd dictionary (#9857) 2022-05-20 12:09:09 -07:00
sst_file_reader.cc Fast path for detecting unchanged prefix_extractor (#9407) 2022-01-21 11:37:46 -08:00
sst_file_reader_test.cc Use the comparator from the sst file table properties in sst_dump_tool (#9491) 2022-02-08 12:15:35 -08:00
sst_file_writer.cc `compression_per_level` should be used for flush and changeable (#9658) 2022-03-07 18:06:19 -08:00
sst_file_writer_collectors.h Remove own ToString() (#9955) 2022-05-06 13:03:58 -07:00
table_builder.h Fast path for detecting unchanged prefix_extractor (#9407) 2022-01-21 11:37:46 -08:00
table_factory.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
table_properties.cc Remove own ToString() (#9955) 2022-05-06 13:03:58 -07:00
table_properties_internal.h Improve / clean up meta block code & integrity (#9163) 2021-11-18 11:43:44 -08:00
table_reader.h Multi file concurrency in MultiGet using coroutines and async IO (#9968) 2022-05-19 15:36:27 -07:00
table_reader_bench.cc Fast path for detecting unchanged prefix_extractor (#9407) 2022-01-21 11:37:46 -08:00
table_reader_caller.h Fix and detect headers with missing dependencies (#8893) 2021-09-10 10:00:26 -07:00
table_test.cc Adjust public APIs to prefer 128-bit SST unique ID (#10009) 2022-05-17 18:43:48 -07:00
two_level_iterator.cc Clarify caching behavior for index and filter partitions (#9068) 2021-10-27 17:23:04 -07:00
two_level_iterator.h Replace namespace name "rocksdb" with ROCKSDB_NAMESPACE (#6433) 2020-02-20 12:09:57 -08:00
unique_id.cc Track SST unique id in MANIFEST and verify (#9990) 2022-05-19 11:04:21 -07:00
unique_id_impl.h Track SST unique id in MANIFEST and verify (#9990) 2022-05-19 11:04:21 -07:00