d51dc96a79
Summary: Experiments on column-aware encodings. Supported features: 1) extract data blocks from SST file and encode with specified encodings; 2) Decode encoded data back into row format; 3) Directly extract data blocks and write in row format (without prefix encoding); 4) Get column distribution statistics for column format; 5) Dump data blocks separated by columns in human-readable format. There is still on-going work on this diff. More refactoring is necessary. Test Plan: Wrote tests in `column_aware_encoding_test.cc`. More tests should be added. Reviewers: sdong Reviewed By: sdong Subscribers: arahut, andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D60027
81 lines
2.8 KiB
C++
81 lines
2.8 KiB
C++
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under the BSD-style license found in the
|
|
// LICENSE file in the root directory of this source tree. An additional grant
|
|
// of patent rights can be found in the PATENTS file in the same directory.
|
|
#pragma once
|
|
#ifndef ROCKSDB_LITE
|
|
|
|
#include <string>
|
|
#include <vector>
|
|
#include "db/dbformat.h"
|
|
#include "include/rocksdb/env.h"
|
|
#include "include/rocksdb/immutable_options.h"
|
|
#include "include/rocksdb/listener.h"
|
|
#include "include/rocksdb/options.h"
|
|
#include "include/rocksdb/status.h"
|
|
#include "table/block_based_table_reader.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
struct ColDeclaration;
|
|
struct KVPairColDeclarations;
|
|
|
|
class ColumnAwareEncodingReader {
|
|
public:
|
|
explicit ColumnAwareEncodingReader(const std::string& file_name);
|
|
|
|
void GetKVPairsFromDataBlocks(std::vector<KVPairBlock>* kv_pair_blocks);
|
|
|
|
void EncodeBlocksToRowFormat(WritableFile* out_file,
|
|
CompressionType compression_type,
|
|
const std::vector<KVPairBlock>& kv_pair_blocks,
|
|
std::vector<std::string>* blocks);
|
|
|
|
void DecodeBlocksFromRowFormat(WritableFile* out_file,
|
|
const std::vector<std::string>* blocks);
|
|
|
|
void DumpDataColumns(const std::string& filename,
|
|
const KVPairColDeclarations& kvp_col_declarations,
|
|
const std::vector<KVPairBlock>& kv_pair_blocks);
|
|
|
|
Status EncodeBlocks(const KVPairColDeclarations& kvp_col_declarations,
|
|
WritableFile* out_file, CompressionType compression_type,
|
|
const std::vector<KVPairBlock>& kv_pair_blocks,
|
|
std::vector<std::string>* blocks, bool print_column_stat);
|
|
|
|
void DecodeBlocks(const KVPairColDeclarations& kvp_col_declarations,
|
|
WritableFile* out_file,
|
|
const std::vector<std::string>* blocks);
|
|
|
|
static void GetColDeclarationsPrimary(
|
|
std::vector<ColDeclaration>** key_col_declarations,
|
|
std::vector<ColDeclaration>** value_col_declarations,
|
|
ColDeclaration** value_checksum_declaration);
|
|
|
|
static void GetColDeclarationsSecondary(
|
|
std::vector<ColDeclaration>** key_col_declarations,
|
|
std::vector<ColDeclaration>** value_col_declarations,
|
|
ColDeclaration** value_checksum_declaration);
|
|
|
|
private:
|
|
// Init the TableReader for the sst file
|
|
void InitTableReader(const std::string& file_path);
|
|
|
|
std::string file_name_;
|
|
EnvOptions soptions_;
|
|
|
|
Options options_;
|
|
|
|
Status init_result_;
|
|
std::unique_ptr<BlockBasedTable> table_reader_;
|
|
std::unique_ptr<RandomAccessFileReader> file_;
|
|
|
|
const ImmutableCFOptions ioptions_;
|
|
InternalKeyComparator internal_comparator_;
|
|
std::unique_ptr<TableProperties> table_properties_;
|
|
};
|
|
|
|
} // namespace rocksdb
|
|
|
|
#endif // ROCKSDB_LITE
|