rocksdb/tools/ldb_tool.cc
Zhichao Cao 4369f2c7bb Checksum for each SST file and stores in MANIFEST (#6216)
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
2020-02-10 15:52:52 -08:00

141 lines
5.1 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).
//
#ifndef ROCKSDB_LITE
#include "rocksdb/ldb_tool.h"
#include "rocksdb/utilities/ldb_cmd.h"
#include "tools/ldb_cmd_impl.h"
namespace rocksdb {
LDBOptions::LDBOptions() {}
void LDBCommandRunner::PrintHelp(const LDBOptions& ldb_options,
const char* /*exec_name*/) {
std::string ret;
ret.append(ldb_options.print_help_header);
ret.append("\n\n");
ret.append("commands MUST specify --" + LDBCommand::ARG_DB +
"=<full_path_to_db_directory> when necessary\n");
ret.append("\n");
ret.append("commands can optionally specify --" + LDBCommand::ARG_ENV_URI +
"=<uri_of_environment> if necessary\n\n");
ret.append(
"The following optional parameters control if keys/values are "
"input/output as hex or as plain strings:\n");
ret.append(" --" + LDBCommand::ARG_KEY_HEX +
" : Keys are input/output as hex\n");
ret.append(" --" + LDBCommand::ARG_VALUE_HEX +
" : Values are input/output as hex\n");
ret.append(" --" + LDBCommand::ARG_HEX +
" : Both keys and values are input/output as hex\n");
ret.append("\n");
ret.append(
"The following optional parameters control the database "
"internals:\n");
ret.append(
" --" + LDBCommand::ARG_CF_NAME +
"=<string> : name of the column family to operate on. default: default "
"column family\n");
ret.append(" --" + LDBCommand::ARG_TTL +
" with 'put','get','scan','dump','query','batchput'"
" : DB supports ttl and value is internally timestamp-suffixed\n");
ret.append(" --" + LDBCommand::ARG_TRY_LOAD_OPTIONS +
" : Try to load option file from DB.\n");
ret.append(" --" + LDBCommand::ARG_IGNORE_UNKNOWN_OPTIONS +
" : Ignore unknown options when loading option file.\n");
ret.append(" --" + LDBCommand::ARG_BLOOM_BITS + "=<int,e.g.:14>\n");
ret.append(" --" + LDBCommand::ARG_FIX_PREFIX_LEN + "=<int,e.g.:14>\n");
ret.append(" --" + LDBCommand::ARG_COMPRESSION_TYPE +
"=<no|snappy|zlib|bzip2|lz4|lz4hc|xpress|zstd>\n");
ret.append(" --" + LDBCommand::ARG_COMPRESSION_MAX_DICT_BYTES +
"=<int,e.g.:16384>\n");
ret.append(" --" + LDBCommand::ARG_BLOCK_SIZE + "=<block_size_in_bytes>\n");
ret.append(" --" + LDBCommand::ARG_AUTO_COMPACTION + "=<true|false>\n");
ret.append(" --" + LDBCommand::ARG_DB_WRITE_BUFFER_SIZE +
"=<int,e.g.:16777216>\n");
ret.append(" --" + LDBCommand::ARG_WRITE_BUFFER_SIZE +
"=<int,e.g.:4194304>\n");
ret.append(" --" + LDBCommand::ARG_FILE_SIZE + "=<int,e.g.:2097152>\n");
ret.append("\n\n");
ret.append("Data Access Commands:\n");
PutCommand::Help(ret);
GetCommand::Help(ret);
BatchPutCommand::Help(ret);
ScanCommand::Help(ret);
DeleteCommand::Help(ret);
DeleteRangeCommand::Help(ret);
DBQuerierCommand::Help(ret);
ApproxSizeCommand::Help(ret);
CheckConsistencyCommand::Help(ret);
ListFileRangeDeletesCommand::Help(ret);
ret.append("\n\n");
ret.append("Admin Commands:\n");
WALDumperCommand::Help(ret);
CompactorCommand::Help(ret);
ReduceDBLevelsCommand::Help(ret);
ChangeCompactionStyleCommand::Help(ret);
DBDumperCommand::Help(ret);
DBLoaderCommand::Help(ret);
ManifestDumpCommand::Help(ret);
FileChecksumDumpCommand::Help(ret);
ListColumnFamiliesCommand::Help(ret);
CreateColumnFamilyCommand::Help(ret);
DropColumnFamilyCommand::Help(ret);
DBFileDumperCommand::Help(ret);
InternalDumpCommand::Help(ret);
RepairCommand::Help(ret);
BackupCommand::Help(ret);
RestoreCommand::Help(ret);
CheckPointCommand::Help(ret);
WriteExternalSstFilesCommand::Help(ret);
IngestExternalSstFilesCommand::Help(ret);
fprintf(stderr, "%s\n", ret.c_str());
}
int LDBCommandRunner::RunCommand(
int argc, char** argv, Options options, const LDBOptions& ldb_options,
const std::vector<ColumnFamilyDescriptor>* column_families) {
if (argc <= 2) {
PrintHelp(ldb_options, argv[0]);
return 1;
}
LDBCommand* cmdObj = LDBCommand::InitFromCmdLineArgs(
argc, argv, options, ldb_options, column_families);
if (cmdObj == nullptr) {
fprintf(stderr, "Unknown command\n");
PrintHelp(ldb_options, argv[0]);
return 1;
}
if (!cmdObj->ValidateCmdLineOptions()) {
return 1;
}
cmdObj->Run();
LDBCommandExecuteResult ret = cmdObj->GetExecuteState();
fprintf(stderr, "%s\n", ret.ToString().c_str());
delete cmdObj;
return ret.IsFailed() ? 1 : 0;
}
void LDBTool::Run(int argc, char** argv, Options options,
const LDBOptions& ldb_options,
const std::vector<ColumnFamilyDescriptor>* column_families) {
int error_code = LDBCommandRunner::RunCommand(argc, argv, options,
ldb_options, column_families);
exit(error_code);
}
} // namespace rocksdb
#endif // ROCKSDB_LITE