4369f2c7bb
Summary: In the current code base, RocksDB generate the checksum for each block and verify the checksum at usage. Current PR enable SST file checksum. After a SST file is generated by Flush or Compaction, RocksDB generate the SST file checksum and store the checksum value and checksum method name in the vs_info and MANIFEST as part for the FileMetadata. Added the enable_sst_file_checksum to Options to enable or disable file checksum. Added sst_file_checksum to Options such that user can plugin their own SST file checksum calculate method via overriding the SstFileChecksum class. The checksum information inlcuding uint32_t checksum value and a checksum name (string). A new tool is added to LDB such that user can dump out a list of file checksum information from MANIFEST. If user enables the file checksum but does not provide the sst_file_checksum instance, RocksDB will use the default crc32checksum implemented in table/sst_file_checksum_crc32c.h Pull Request resolved: https://github.com/facebook/rocksdb/pull/6216 Test Plan: Added the testing case in table_test and ldb_cmd_test to verify checksum is correct in different level. Pass make asan_check. Differential Revision: D19171461 Pulled By: zhichao-cao fbshipit-source-id: b2e53479eefc5bb0437189eaa1941670e5ba8b87
118 lines
3.6 KiB
C++
118 lines
3.6 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 <cassert>
|
|
#include <unordered_map>
|
|
#include "port/port.h"
|
|
#include "rocksdb/file_checksum.h"
|
|
#include "rocksdb/status.h"
|
|
#include "util/crc32c.h"
|
|
#include "util/string_util.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
// This is the class to generate the file checksum based on Crc32. It
|
|
// will be used as the default checksum method for SST file checksum
|
|
class FileChecksumFuncCrc32c : public FileChecksumFunc {
|
|
public:
|
|
std::string Extend(const std::string& init_checksum, const char* data,
|
|
size_t n) override {
|
|
assert(data != nullptr);
|
|
uint32_t checksum_value = StringToUint32(init_checksum);
|
|
return Uint32ToString(crc32c::Extend(checksum_value, data, n));
|
|
}
|
|
|
|
std::string Value(const char* data, size_t n) override {
|
|
assert(data != nullptr);
|
|
return Uint32ToString(crc32c::Value(data, n));
|
|
}
|
|
|
|
std::string ProcessChecksum(const std::string& checksum) override {
|
|
uint32_t checksum_value = StringToUint32(checksum);
|
|
return Uint32ToString(crc32c::Mask(checksum_value));
|
|
}
|
|
|
|
const char* Name() const override { return "FileChecksumCrc32c"; }
|
|
|
|
// Convert a uint32_t type data into a 4 bytes string.
|
|
static std::string Uint32ToString(uint32_t v) {
|
|
std::string s;
|
|
if (port::kLittleEndian) {
|
|
s.append(reinterpret_cast<char*>(&v), sizeof(v));
|
|
} else {
|
|
char buf[sizeof(v)];
|
|
buf[0] = v & 0xff;
|
|
buf[1] = (v >> 8) & 0xff;
|
|
buf[2] = (v >> 16) & 0xff;
|
|
buf[3] = (v >> 24) & 0xff;
|
|
s.append(buf, sizeof(v));
|
|
}
|
|
size_t i = 0, j = s.size() - 1;
|
|
while (i < j) {
|
|
char tmp = s[i];
|
|
s[i] = s[j];
|
|
s[j] = tmp;
|
|
++i;
|
|
--j;
|
|
}
|
|
return s;
|
|
}
|
|
|
|
// Convert a 4 bytes size string into a uint32_t type data.
|
|
static uint32_t StringToUint32(std::string s) {
|
|
assert(s.size() == sizeof(uint32_t));
|
|
size_t i = 0, j = s.size() - 1;
|
|
while (i < j) {
|
|
char tmp = s[i];
|
|
s[i] = s[j];
|
|
s[j] = tmp;
|
|
++i;
|
|
--j;
|
|
}
|
|
uint32_t v = 0;
|
|
if (port::kLittleEndian) {
|
|
memcpy(&v, s.c_str(), sizeof(uint32_t));
|
|
} else {
|
|
const char* buf = s.c_str();
|
|
v |= static_cast<uint32_t>(buf[0]);
|
|
v |= (static_cast<uint32_t>(buf[1]) << 8);
|
|
v |= (static_cast<uint32_t>(buf[2]) << 16);
|
|
v |= (static_cast<uint32_t>(buf[3]) << 24);
|
|
}
|
|
return v;
|
|
}
|
|
};
|
|
|
|
// The default implementaion of FileChecksumList
|
|
class FileChecksumListImpl : public FileChecksumList {
|
|
public:
|
|
FileChecksumListImpl() {}
|
|
void reset() override;
|
|
|
|
size_t size() const override;
|
|
|
|
Status GetAllFileChecksums(
|
|
std::vector<uint64_t>* file_numbers, std::vector<std::string>* checksums,
|
|
std::vector<std::string>* checksum_func_names) override;
|
|
|
|
Status SearchOneFileChecksum(uint64_t file_number, std::string* checksum,
|
|
std::string* checksum_func_name) override;
|
|
|
|
Status InsertOneFileChecksum(uint64_t file_number,
|
|
const std::string& checksum,
|
|
const std::string& checksum_func_name) override;
|
|
|
|
Status RemoveOneFileChecksum(uint64_t file_number) override;
|
|
|
|
private:
|
|
// Key is the file number, the first portion of the value is checksum, the
|
|
// second portion of the value is checksum function name.
|
|
std::unordered_map<uint64_t, std::pair<std::string, std::string>>
|
|
checksum_map_;
|
|
};
|
|
|
|
} // namespace rocksdb
|