rocksdb/table/sst_file_dumper.h
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

102 lines
3.7 KiB
C++

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#pragma once
#ifndef ROCKSDB_LITE
#include <memory>
#include <string>
#include "db/dbformat.h"
#include "file/writable_file_writer.h"
#include "options/cf_options.h"
#include "rocksdb/advanced_options.h"
namespace ROCKSDB_NAMESPACE {
class SstFileDumper {
public:
explicit SstFileDumper(const Options& options, const std::string& file_name,
Temperature file_temp, size_t readahead_size,
bool verify_checksum, bool output_hex,
bool decode_blob_index,
const EnvOptions& soptions = EnvOptions(),
bool silent = false);
Status ReadSequential(bool print_kv, uint64_t read_num, bool has_from,
const std::string& from_key, bool has_to,
const std::string& to_key,
bool use_from_as_prefix = false);
Status ReadTableProperties(
std::shared_ptr<const TableProperties>* table_properties);
uint64_t GetReadNumber() { return read_num_; }
TableProperties* GetInitTableProperties() { return table_properties_.get(); }
Status VerifyChecksum();
Status DumpTable(const std::string& out_filename);
Status getStatus() { return init_result_; }
Status ShowAllCompressionSizes(
size_t block_size,
const std::vector<std::pair<CompressionType, const char*>>&
compression_types,
int32_t compress_level_from, int32_t compress_level_to,
uint32_t max_dict_bytes, uint32_t zstd_max_train_bytes,
uint64_t max_dict_buffer_bytes, bool use_zstd_dict_trainer);
Status ShowCompressionSize(size_t block_size, CompressionType compress_type,
const CompressionOptions& compress_opt);
private:
// Get the TableReader implementation for the sst file
Status GetTableReader(const std::string& file_path);
Status ReadTableProperties(uint64_t table_magic_number,
RandomAccessFileReader* file, uint64_t file_size,
FilePrefetchBuffer* prefetch_buffer);
Status CalculateCompressedTableSize(const TableBuilderOptions& tb_options,
size_t block_size,
uint64_t* num_data_blocks,
uint64_t* compressed_table_size);
Status SetTableOptionsByMagicNumber(uint64_t table_magic_number);
Status SetOldTableOptions();
// Helper function to call the factory with settings specific to the
// factory implementation
Status NewTableReader(const ImmutableOptions& ioptions,
const EnvOptions& soptions,
const InternalKeyComparator& internal_comparator,
uint64_t file_size,
std::unique_ptr<TableReader>* table_reader);
std::string file_name_;
uint64_t read_num_;
Temperature file_temp_;
bool output_hex_;
bool decode_blob_index_;
EnvOptions soptions_;
// less verbose in stdout/stderr
bool silent_;
// options_ and internal_comparator_ will also be used in
// ReadSequential internally (specifically, seek-related operations)
Options options_;
Status init_result_;
std::unique_ptr<TableReader> table_reader_;
std::unique_ptr<RandomAccessFileReader> file_;
const ImmutableOptions ioptions_;
const MutableCFOptions moptions_;
ReadOptions read_options_;
InternalKeyComparator internal_comparator_;
std::unique_ptr<TableProperties> table_properties_;
};
} // namespace ROCKSDB_NAMESPACE
#endif // ROCKSDB_LITE