rocksdb/tools/sst_dump_tool_imp.h
sdong 4a4b8a1344 sst_dump to reduce number of file reads (#6836)
Summary:
sst_dump can issue many file reads from the file system. This doesn't work well with file systems without a OS cache, especially remote file systems. In order to mitigate this problem, several improvements are done:
1. --readahead_size is added, so that users can specify readahead size when scanning the data.
2. Force a 512KB tail readahead, which prevents three I/Os for footer, meta index and property blocks and hopefully index and filter blocks too.
3. Consoldiate SSTDump's I/Os before opening the file for read. Use the same file prefetch buffer.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6836

Test Plan: Add a test that covers this new feature.

Reviewed By: pdillinger

Differential Revision: D21516607

fbshipit-source-id: 3ae43526286f67b2f4a5bdedfbc92719d579b87e
2020-05-12 18:23:33 -07:00

96 lines
3.3 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 "rocksdb/sst_dump_tool.h"
#include <memory>
#include <string>
#include "db/dbformat.h"
#include "file/writable_file_writer.h"
#include "options/cf_options.h"
namespace ROCKSDB_NAMESPACE {
class SstFileDumper {
public:
explicit SstFileDumper(const Options& options, const std::string& file_name,
size_t readahead_size, bool verify_checksum,
bool output_hex, bool decode_blob_index);
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_; }
int 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);
int 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);
uint64_t CalculateCompressedTableSize(const TableBuilderOptions& tb_options,
size_t block_size,
uint64_t* num_data_blocks);
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 ImmutableCFOptions& 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_;
bool output_hex_;
bool decode_blob_index_;
EnvOptions soptions_;
// 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 ImmutableCFOptions ioptions_;
const MutableCFOptions moptions_;
ReadOptions read_options_;
InternalKeyComparator internal_comparator_;
std::unique_ptr<TableProperties> table_properties_;
};
} // namespace ROCKSDB_NAMESPACE
#endif // ROCKSDB_LITE