mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-27 20:43:57 +00:00
c6b1f6d182
Summary: sst_dump --command=check can now compare number of keys in a file with num_entries in table property and reports corruption is there is a mismatch. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12322 Test Plan: - new unit test for API `SstFileDumper::ReadSequential` - ran sst_dump on a good and a bad file: ``` sst_dump --file=./32316112.sst options.env is 0x7f68bfcb5000 Process ./32316112.sst Sst file format: block-based from [] to [] sst_dump --file=./32316115.sst options.env is 0x7f6d0d2b5000 Process ./32316115.sst Sst file format: block-based from [] to [] ./32316115.sst: Corruption: Table property has num_entries = 6050408 but scanning the table returns 6050406 records. ``` Reviewed By: jowlyzhang Differential Revision: D53320481 Pulled By: cbi42 fbshipit-source-id: d84c996346a9575a5a2ea5f5fb09a9d3ee672cd6
105 lines
4.1 KiB
C++
105 lines
4.1 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
|
|
|
|
#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);
|
|
|
|
// read_num_limit limits the total number of keys read. If read_num_limit = 0,
|
|
// then there is no limit. If read_num_limit = 0 or
|
|
// std::numeric_limits<uint64_t>::max(), has_from and has_to are false, then
|
|
// the number of keys read is compared with `num_entries` field in table
|
|
// properties. A Corruption status is returned if they do not match.
|
|
Status ReadSequential(bool print_kv, uint64_t read_num_limit, 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_;
|
|
|
|
ImmutableOptions ioptions_;
|
|
const MutableCFOptions moptions_;
|
|
ReadOptions read_options_;
|
|
InternalKeyComparator internal_comparator_;
|
|
std::unique_ptr<TableProperties> table_properties_;
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|
|
|