You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/tools/sst_dump_tool.cc

668 lines
22 KiB

// 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 "tools/sst_dump_tool_imp.h"
10 years ago
#ifndef __STDC_FORMAT_MACROS
#define __STDC_FORMAT_MACROS
#endif
#include <inttypes.h>
#include <iostream>
#include <map>
#include <memory>
#include <sstream>
#include <vector>
#include "db/memtable.h"
#include "db/write_batch_internal.h"
#include "options/cf_options.h"
#include "rocksdb/db.h"
#include "rocksdb/env.h"
#include "rocksdb/iterator.h"
#include "rocksdb/slice_transform.h"
#include "rocksdb/status.h"
#include "rocksdb/table_properties.h"
#include "rocksdb/utilities/ldb_cmd.h"
#include "table/block.h"
#include "table/block_based_table_builder.h"
#include "table/block_based_table_factory.h"
#include "table/block_builder.h"
#include "table/format.h"
#include "table/meta_blocks.h"
#include "table/plain_table_factory.h"
#include "table/table_reader.h"
#include "util/compression.h"
#include "util/random.h"
#include "port/port.h"
namespace rocksdb {
SstFileReader::SstFileReader(const std::string& file_path,
bool verify_checksum,
bool output_hex)
:file_name_(file_path), read_num_(0), verify_checksum_(verify_checksum),
output_hex_(output_hex), ioptions_(options_),
internal_comparator_(BytewiseComparator()) {
fprintf(stdout, "Process %s\n", file_path.c_str());
Disable pre-fetching of index and filter blocks for sst_dump_tool. Summary: BlockBasedTable pre-fetches the filter and index blocks on Open call. This is an optimistic optimization targeted for runtime scenario. The optimization is unnecessary for sst_dump_tool - Added a provision to disable pre-fetching of index and filter blocks in BlockBasedTable - Disabled pre-fetching for the sst_dump tool Stack for reference : #01 0x00000000005ed944 in snappy::InternalUncompress<snappy::SnappyArrayWriter> () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:148 #02 0x00000000005edeee in snappy::RawUncompress () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:947 #03 0x00000000004e0b4d in rocksdb::UncompressBlockContents () from /data/users/paultuckfield/rocksdb/./util/compression.h:69 #04 0x00000000004e145c in rocksdb::ReadBlockContents () from /data/users/paultuckfield/rocksdb/table/format.cc:334 #05 0x00000000004ca424 in rocksdb::(anonymous namespace)::ReadBlockFromFile () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:70 #06 0x00000000004cccad in rocksdb::BlockBasedTable::CreateIndexReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:173 #07 0x00000000004d17e5 in rocksdb::BlockBasedTable::Open () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:553 #08 0x00000000004c8184 in rocksdb::BlockBasedTableFactory::NewTableReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_factory.cc:51 #09 0x0000000000598463 in rocksdb::SstFileReader::NewTableReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:69 #10 0x00000000005986c2 in rocksdb::SstFileReader::SstFileReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:26 #11 0x0000000000599047 in rocksdb::SSTDumpTool::Run () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:332 #12 0x0000000000409b06 in main () from /data/users/paultuckfield/rocksdb/tools/sst_dump.cc:12 Test Plan: - Added a unit test to trigger the code. - Also did some manual verification. - Passed all unit tests task #6296048 Reviewers: igor, rven, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D34041
10 years ago
init_result_ = GetTableReader(file_name_);
}
10 years ago
extern const uint64_t kBlockBasedTableMagicNumber;
extern const uint64_t kLegacyBlockBasedTableMagicNumber;
extern const uint64_t kPlainTableMagicNumber;
extern const uint64_t kLegacyPlainTableMagicNumber;
const char* testFileName = "test_file_name";
Disable pre-fetching of index and filter blocks for sst_dump_tool. Summary: BlockBasedTable pre-fetches the filter and index blocks on Open call. This is an optimistic optimization targeted for runtime scenario. The optimization is unnecessary for sst_dump_tool - Added a provision to disable pre-fetching of index and filter blocks in BlockBasedTable - Disabled pre-fetching for the sst_dump tool Stack for reference : #01 0x00000000005ed944 in snappy::InternalUncompress<snappy::SnappyArrayWriter> () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:148 #02 0x00000000005edeee in snappy::RawUncompress () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:947 #03 0x00000000004e0b4d in rocksdb::UncompressBlockContents () from /data/users/paultuckfield/rocksdb/./util/compression.h:69 #04 0x00000000004e145c in rocksdb::ReadBlockContents () from /data/users/paultuckfield/rocksdb/table/format.cc:334 #05 0x00000000004ca424 in rocksdb::(anonymous namespace)::ReadBlockFromFile () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:70 #06 0x00000000004cccad in rocksdb::BlockBasedTable::CreateIndexReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:173 #07 0x00000000004d17e5 in rocksdb::BlockBasedTable::Open () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:553 #08 0x00000000004c8184 in rocksdb::BlockBasedTableFactory::NewTableReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_factory.cc:51 #09 0x0000000000598463 in rocksdb::SstFileReader::NewTableReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:69 #10 0x00000000005986c2 in rocksdb::SstFileReader::SstFileReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:26 #11 0x0000000000599047 in rocksdb::SSTDumpTool::Run () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:332 #12 0x0000000000409b06 in main () from /data/users/paultuckfield/rocksdb/tools/sst_dump.cc:12 Test Plan: - Added a unit test to trigger the code. - Also did some manual verification. - Passed all unit tests task #6296048 Reviewers: igor, rven, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D34041
10 years ago
Status SstFileReader::GetTableReader(const std::string& file_path) {
// Warning about 'magic_number' being uninitialized shows up only in UBsan
// builds. Though access is guarded by 's.ok()' checks, fix the issue to
// avoid any warnings.
uint64_t magic_number = Footer::kInvalidTableMagicNumber;
// read table magic number
Footer footer;
unique_ptr<RandomAccessFile> file;
uint64_t file_size;
Status s = options_.env->NewRandomAccessFile(file_path, &file, soptions_);
if (s.ok()) {
s = options_.env->GetFileSize(file_path, &file_size);
}
file_.reset(new RandomAccessFileReader(std::move(file), file_path));
if (s.ok()) {
s = ReadFooterFromFile(file_.get(), file_size, &footer);
}
if (s.ok()) {
magic_number = footer.table_magic_number();
}
if (s.ok()) {
if (magic_number == kPlainTableMagicNumber ||
magic_number == kLegacyPlainTableMagicNumber) {
soptions_.use_mmap_reads = true;
options_.env->NewRandomAccessFile(file_path, &file, soptions_);
file_.reset(new RandomAccessFileReader(std::move(file), file_path));
}
options_.comparator = &internal_comparator_;
// For old sst format, ReadTableProperties might fail but file can be read
if (ReadTableProperties(magic_number, file_.get(), file_size).ok()) {
SetTableOptionsByMagicNumber(magic_number);
} else {
SetOldTableOptions();
}
}
if (s.ok()) {
s = NewTableReader(ioptions_, soptions_, internal_comparator_, file_size,
&table_reader_);
}
return s;
}
Disable pre-fetching of index and filter blocks for sst_dump_tool. Summary: BlockBasedTable pre-fetches the filter and index blocks on Open call. This is an optimistic optimization targeted for runtime scenario. The optimization is unnecessary for sst_dump_tool - Added a provision to disable pre-fetching of index and filter blocks in BlockBasedTable - Disabled pre-fetching for the sst_dump tool Stack for reference : #01 0x00000000005ed944 in snappy::InternalUncompress<snappy::SnappyArrayWriter> () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:148 #02 0x00000000005edeee in snappy::RawUncompress () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:947 #03 0x00000000004e0b4d in rocksdb::UncompressBlockContents () from /data/users/paultuckfield/rocksdb/./util/compression.h:69 #04 0x00000000004e145c in rocksdb::ReadBlockContents () from /data/users/paultuckfield/rocksdb/table/format.cc:334 #05 0x00000000004ca424 in rocksdb::(anonymous namespace)::ReadBlockFromFile () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:70 #06 0x00000000004cccad in rocksdb::BlockBasedTable::CreateIndexReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:173 #07 0x00000000004d17e5 in rocksdb::BlockBasedTable::Open () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:553 #08 0x00000000004c8184 in rocksdb::BlockBasedTableFactory::NewTableReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_factory.cc:51 #09 0x0000000000598463 in rocksdb::SstFileReader::NewTableReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:69 #10 0x00000000005986c2 in rocksdb::SstFileReader::SstFileReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:26 #11 0x0000000000599047 in rocksdb::SSTDumpTool::Run () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:332 #12 0x0000000000409b06 in main () from /data/users/paultuckfield/rocksdb/tools/sst_dump.cc:12 Test Plan: - Added a unit test to trigger the code. - Also did some manual verification. - Passed all unit tests task #6296048 Reviewers: igor, rven, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D34041
10 years ago
Status SstFileReader::NewTableReader(
const ImmutableCFOptions& ioptions, const EnvOptions& soptions,
const InternalKeyComparator& internal_comparator, uint64_t file_size,
unique_ptr<TableReader>* table_reader) {
Disable pre-fetching of index and filter blocks for sst_dump_tool. Summary: BlockBasedTable pre-fetches the filter and index blocks on Open call. This is an optimistic optimization targeted for runtime scenario. The optimization is unnecessary for sst_dump_tool - Added a provision to disable pre-fetching of index and filter blocks in BlockBasedTable - Disabled pre-fetching for the sst_dump tool Stack for reference : #01 0x00000000005ed944 in snappy::InternalUncompress<snappy::SnappyArrayWriter> () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:148 #02 0x00000000005edeee in snappy::RawUncompress () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:947 #03 0x00000000004e0b4d in rocksdb::UncompressBlockContents () from /data/users/paultuckfield/rocksdb/./util/compression.h:69 #04 0x00000000004e145c in rocksdb::ReadBlockContents () from /data/users/paultuckfield/rocksdb/table/format.cc:334 #05 0x00000000004ca424 in rocksdb::(anonymous namespace)::ReadBlockFromFile () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:70 #06 0x00000000004cccad in rocksdb::BlockBasedTable::CreateIndexReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:173 #07 0x00000000004d17e5 in rocksdb::BlockBasedTable::Open () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:553 #08 0x00000000004c8184 in rocksdb::BlockBasedTableFactory::NewTableReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_factory.cc:51 #09 0x0000000000598463 in rocksdb::SstFileReader::NewTableReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:69 #10 0x00000000005986c2 in rocksdb::SstFileReader::SstFileReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:26 #11 0x0000000000599047 in rocksdb::SSTDumpTool::Run () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:332 #12 0x0000000000409b06 in main () from /data/users/paultuckfield/rocksdb/tools/sst_dump.cc:12 Test Plan: - Added a unit test to trigger the code. - Also did some manual verification. - Passed all unit tests task #6296048 Reviewers: igor, rven, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D34041
10 years ago
// We need to turn off pre-fetching of index and filter nodes for
// BlockBasedTable
if (BlockBasedTableFactory::kName == options_.table_factory->Name()) {
return options_.table_factory->NewTableReader(
TableReaderOptions(ioptions_, soptions_, internal_comparator_,
/*skip_filters=*/false),
std::move(file_), file_size, &table_reader_, /*enable_prefetch=*/false);
Disable pre-fetching of index and filter blocks for sst_dump_tool. Summary: BlockBasedTable pre-fetches the filter and index blocks on Open call. This is an optimistic optimization targeted for runtime scenario. The optimization is unnecessary for sst_dump_tool - Added a provision to disable pre-fetching of index and filter blocks in BlockBasedTable - Disabled pre-fetching for the sst_dump tool Stack for reference : #01 0x00000000005ed944 in snappy::InternalUncompress<snappy::SnappyArrayWriter> () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:148 #02 0x00000000005edeee in snappy::RawUncompress () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:947 #03 0x00000000004e0b4d in rocksdb::UncompressBlockContents () from /data/users/paultuckfield/rocksdb/./util/compression.h:69 #04 0x00000000004e145c in rocksdb::ReadBlockContents () from /data/users/paultuckfield/rocksdb/table/format.cc:334 #05 0x00000000004ca424 in rocksdb::(anonymous namespace)::ReadBlockFromFile () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:70 #06 0x00000000004cccad in rocksdb::BlockBasedTable::CreateIndexReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:173 #07 0x00000000004d17e5 in rocksdb::BlockBasedTable::Open () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:553 #08 0x00000000004c8184 in rocksdb::BlockBasedTableFactory::NewTableReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_factory.cc:51 #09 0x0000000000598463 in rocksdb::SstFileReader::NewTableReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:69 #10 0x00000000005986c2 in rocksdb::SstFileReader::SstFileReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:26 #11 0x0000000000599047 in rocksdb::SSTDumpTool::Run () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:332 #12 0x0000000000409b06 in main () from /data/users/paultuckfield/rocksdb/tools/sst_dump.cc:12 Test Plan: - Added a unit test to trigger the code. - Also did some manual verification. - Passed all unit tests task #6296048 Reviewers: igor, rven, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D34041
10 years ago
}
// For all other factory implementation
return options_.table_factory->NewTableReader(
TableReaderOptions(ioptions_, soptions_, internal_comparator_),
std::move(file_), file_size, &table_reader_);
Disable pre-fetching of index and filter blocks for sst_dump_tool. Summary: BlockBasedTable pre-fetches the filter and index blocks on Open call. This is an optimistic optimization targeted for runtime scenario. The optimization is unnecessary for sst_dump_tool - Added a provision to disable pre-fetching of index and filter blocks in BlockBasedTable - Disabled pre-fetching for the sst_dump tool Stack for reference : #01 0x00000000005ed944 in snappy::InternalUncompress<snappy::SnappyArrayWriter> () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:148 #02 0x00000000005edeee in snappy::RawUncompress () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:947 #03 0x00000000004e0b4d in rocksdb::UncompressBlockContents () from /data/users/paultuckfield/rocksdb/./util/compression.h:69 #04 0x00000000004e145c in rocksdb::ReadBlockContents () from /data/users/paultuckfield/rocksdb/table/format.cc:334 #05 0x00000000004ca424 in rocksdb::(anonymous namespace)::ReadBlockFromFile () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:70 #06 0x00000000004cccad in rocksdb::BlockBasedTable::CreateIndexReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:173 #07 0x00000000004d17e5 in rocksdb::BlockBasedTable::Open () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:553 #08 0x00000000004c8184 in rocksdb::BlockBasedTableFactory::NewTableReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_factory.cc:51 #09 0x0000000000598463 in rocksdb::SstFileReader::NewTableReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:69 #10 0x00000000005986c2 in rocksdb::SstFileReader::SstFileReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:26 #11 0x0000000000599047 in rocksdb::SSTDumpTool::Run () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:332 #12 0x0000000000409b06 in main () from /data/users/paultuckfield/rocksdb/tools/sst_dump.cc:12 Test Plan: - Added a unit test to trigger the code. - Also did some manual verification. - Passed all unit tests task #6296048 Reviewers: igor, rven, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D34041
10 years ago
}
Status SstFileReader::VerifyChecksum() {
return table_reader_->VerifyChecksum();
}
Status SstFileReader::DumpTable(const std::string& out_filename) {
unique_ptr<WritableFile> out_file;
Env* env = Env::Default();
env->NewWritableFile(out_filename, &out_file, soptions_);
Status s = table_reader_->DumpTable(out_file.get());
out_file->Close();
return s;
}
uint64_t SstFileReader::CalculateCompressedTableSize(
const TableBuilderOptions& tb_options, size_t block_size) {
unique_ptr<WritableFile> out_file;
unique_ptr<Env> env(NewMemEnv(Env::Default()));
env->NewWritableFile(testFileName, &out_file, soptions_);
unique_ptr<WritableFileWriter> dest_writer;
dest_writer.reset(new WritableFileWriter(std::move(out_file), soptions_));
BlockBasedTableOptions table_options;
table_options.block_size = block_size;
BlockBasedTableFactory block_based_tf(table_options);
unique_ptr<TableBuilder> table_builder;
table_builder.reset(block_based_tf.NewTableBuilder(
tb_options,
TablePropertiesCollectorFactory::Context::kUnknownColumnFamily,
dest_writer.get()));
unique_ptr<InternalIterator> iter(table_reader_->NewIterator(ReadOptions()));
for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
if (!iter->status().ok()) {
fputs(iter->status().ToString().c_str(), stderr);
exit(1);
}
table_builder->Add(iter->key(), iter->value());
}
Status s = table_builder->Finish();
if (!s.ok()) {
fputs(s.ToString().c_str(), stderr);
exit(1);
}
uint64_t size = table_builder->FileSize();
env->DeleteFile(testFileName);
return size;
}
int SstFileReader::ShowAllCompressionSizes(size_t block_size) {
ReadOptions read_options;
Options opts;
const ImmutableCFOptions imoptions(opts);
rocksdb::InternalKeyComparator ikc(opts.comparator);
std::vector<std::unique_ptr<IntTblPropCollectorFactory> >
block_based_table_factories;
fprintf(stdout, "Block Size: %" ROCKSDB_PRIszt "\n", block_size);
std::pair<CompressionType, const char*> compressions[] = {
{CompressionType::kNoCompression, "kNoCompression"},
{CompressionType::kSnappyCompression, "kSnappyCompression"},
{CompressionType::kZlibCompression, "kZlibCompression"},
{CompressionType::kBZip2Compression, "kBZip2Compression"},
{CompressionType::kLZ4Compression, "kLZ4Compression"},
{CompressionType::kLZ4HCCompression, "kLZ4HCCompression"},
{CompressionType::kXpressCompression, "kXpressCompression"},
{CompressionType::kZSTD, "kZSTD"}};
for (auto& i : compressions) {
if (CompressionTypeSupported(i.first)) {
CompressionOptions compress_opt;
std::string column_family_name;
int unknown_level = -1;
TableBuilderOptions tb_opts(imoptions, ikc, &block_based_table_factories,
i.first, compress_opt,
nullptr /* compression_dict */,
false /* skip_filters */, column_family_name,
unknown_level);
uint64_t file_size = CalculateCompressedTableSize(tb_opts, block_size);
fprintf(stdout, "Compression: %s", i.second);
fprintf(stdout, " Size: %" PRIu64 "\n", file_size);
} else {
fprintf(stdout, "Unsupported compression type: %s.\n", i.second);
}
}
return 0;
}
Status SstFileReader::ReadTableProperties(uint64_t table_magic_number,
RandomAccessFileReader* file,
uint64_t file_size) {
TableProperties* table_properties = nullptr;
Status s = rocksdb::ReadTableProperties(file, file_size, table_magic_number,
ioptions_, &table_properties);
if (s.ok()) {
table_properties_.reset(table_properties);
} else {
fprintf(stdout, "Not able to read table properties\n");
}
return s;
}
Status SstFileReader::SetTableOptionsByMagicNumber(
uint64_t table_magic_number) {
assert(table_properties_);
if (table_magic_number == kBlockBasedTableMagicNumber ||
table_magic_number == kLegacyBlockBasedTableMagicNumber) {
options_.table_factory = std::make_shared<BlockBasedTableFactory>();
fprintf(stdout, "Sst file format: block-based\n");
auto& props = table_properties_->user_collected_properties;
auto pos = props.find(BlockBasedTablePropertyNames::kIndexType);
if (pos != props.end()) {
auto index_type_on_file = static_cast<BlockBasedTableOptions::IndexType>(
DecodeFixed32(pos->second.c_str()));
if (index_type_on_file ==
BlockBasedTableOptions::IndexType::kHashSearch) {
options_.prefix_extractor.reset(NewNoopTransform());
}
}
} else if (table_magic_number == kPlainTableMagicNumber ||
table_magic_number == kLegacyPlainTableMagicNumber) {
options_.allow_mmap_reads = true;
PlainTableOptions plain_table_options;
plain_table_options.user_key_len = kPlainTableVariableLength;
plain_table_options.bloom_bits_per_key = 0;
plain_table_options.hash_table_ratio = 0;
plain_table_options.index_sparseness = 1;
plain_table_options.huge_page_tlb_size = 0;
plain_table_options.encoding_type = kPlain;
plain_table_options.full_scan_mode = true;
options_.table_factory.reset(NewPlainTableFactory(plain_table_options));
fprintf(stdout, "Sst file format: plain table\n");
} else {
char error_msg_buffer[80];
snprintf(error_msg_buffer, sizeof(error_msg_buffer) - 1,
"Unsupported table magic number --- %lx",
(long)table_magic_number);
return Status::InvalidArgument(error_msg_buffer);
}
return Status::OK();
}
Status SstFileReader::SetOldTableOptions() {
assert(table_properties_ == nullptr);
options_.table_factory = std::make_shared<BlockBasedTableFactory>();
fprintf(stdout, "Sst file format: block-based(old version)\n");
return Status::OK();
}
Status SstFileReader::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) {
if (!table_reader_) {
return init_result_;
}
InternalIterator* iter =
table_reader_->NewIterator(ReadOptions(verify_checksum_, false));
uint64_t i = 0;
if (has_from) {
InternalKey ikey;
ikey.SetMaxPossibleForUserKey(from_key);
iter->Seek(ikey.Encode());
} else {
iter->SeekToFirst();
}
for (; iter->Valid(); iter->Next()) {
Slice key = iter->key();
Slice value = iter->value();
++i;
if (read_num > 0 && i > read_num)
break;
ParsedInternalKey ikey;
if (!ParseInternalKey(key, &ikey)) {
std::cerr << "Internal Key ["
<< key.ToString(true /* in hex*/)
<< "] parse error!\n";
continue;
}
// the key returned is not prefixed with out 'from' key
if (use_from_as_prefix && !ikey.user_key.starts_with(from_key)) {
break;
}
// If end marker was specified, we stop before it
if (has_to && BytewiseComparator()->Compare(ikey.user_key, to_key) >= 0) {
break;
}
if (print_kv) {
fprintf(stdout, "%s => %s\n",
ikey.DebugString(output_hex_).c_str(),
value.ToString(output_hex_).c_str());
}
}
read_num_ += i;
Status ret = iter->status();
delete iter;
return ret;
}
Status SstFileReader::ReadTableProperties(
std::shared_ptr<const TableProperties>* table_properties) {
if (!table_reader_) {
return init_result_;
}
*table_properties = table_reader_->GetTableProperties();
return init_result_;
}
namespace {
void print_help() {
fprintf(stderr,
Improve sst_dump help message Summary: Current Message ``` sst_dump [--command=check|scan|none|raw] [--verify_checksum] --file=data_dir_OR_sst_file [--output_hex] [--input_key_hex] [--from=<user_key>] [--to=<user_key>] [--read_num=NUM] [--show_properties] [--show_compression_sizes] [--show_compression_sizes [--set_block_size=<block_size>]] ``` New message ``` sst_dump --file=<data_dir_OR_sst_file> [--command=check|scan|raw] --file=<data_dir_OR_sst_file> Path to SST file or directory containing SST files --command=check|scan|raw check: Iterate over entries in files but dont print anything except if an error is encounterd (default command) scan: Iterate over entries in files and print them to screen raw: Dump all the table contents to <file_name>_dump.txt --output_hex Can be combined with scan command to print the keys and values in Hex --from=<user_key> Key to start reading from when executing check|scan --to=<user_key> Key to stop reading at when executing check|scan --read_num=<num> Maximum number of entries to read when executing check|scan --verify_checksum Verify file checksum when executing check|scan --input_key_hex Can be combined with --from and --to to indicate that these values are encoded in Hex --show_properties Print table properties after iterating over the file --show_compression_sizes Independent command that will recreate the SST file using 16K block size with different compressions and report the size of the file using such compression --set_block_size=<block_size> Can be combined with --show_compression_sizes to set the block size that will be used when trying different compression algorithms ``` Test Plan: none Reviewers: yhchiang, andrewkr, kradhakrishnan, yiwu, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56325
9 years ago
R"(sst_dump --file=<data_dir_OR_sst_file> [--command=check|scan|raw]
--file=<data_dir_OR_sst_file>
Path to SST file or directory containing SST files
--command=check|scan|raw|verify
Improve sst_dump help message Summary: Current Message ``` sst_dump [--command=check|scan|none|raw] [--verify_checksum] --file=data_dir_OR_sst_file [--output_hex] [--input_key_hex] [--from=<user_key>] [--to=<user_key>] [--read_num=NUM] [--show_properties] [--show_compression_sizes] [--show_compression_sizes [--set_block_size=<block_size>]] ``` New message ``` sst_dump --file=<data_dir_OR_sst_file> [--command=check|scan|raw] --file=<data_dir_OR_sst_file> Path to SST file or directory containing SST files --command=check|scan|raw check: Iterate over entries in files but dont print anything except if an error is encounterd (default command) scan: Iterate over entries in files and print them to screen raw: Dump all the table contents to <file_name>_dump.txt --output_hex Can be combined with scan command to print the keys and values in Hex --from=<user_key> Key to start reading from when executing check|scan --to=<user_key> Key to stop reading at when executing check|scan --read_num=<num> Maximum number of entries to read when executing check|scan --verify_checksum Verify file checksum when executing check|scan --input_key_hex Can be combined with --from and --to to indicate that these values are encoded in Hex --show_properties Print table properties after iterating over the file --show_compression_sizes Independent command that will recreate the SST file using 16K block size with different compressions and report the size of the file using such compression --set_block_size=<block_size> Can be combined with --show_compression_sizes to set the block size that will be used when trying different compression algorithms ``` Test Plan: none Reviewers: yhchiang, andrewkr, kradhakrishnan, yiwu, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56325
9 years ago
check: Iterate over entries in files but dont print anything except if an error is encounterd (default command)
scan: Iterate over entries in files and print them to screen
raw: Dump all the table contents to <file_name>_dump.txt
verify: Iterate all the blocks in files verifying checksum to detect possible coruption but dont print anything except if a corruption is encountered
Improve sst_dump help message Summary: Current Message ``` sst_dump [--command=check|scan|none|raw] [--verify_checksum] --file=data_dir_OR_sst_file [--output_hex] [--input_key_hex] [--from=<user_key>] [--to=<user_key>] [--read_num=NUM] [--show_properties] [--show_compression_sizes] [--show_compression_sizes [--set_block_size=<block_size>]] ``` New message ``` sst_dump --file=<data_dir_OR_sst_file> [--command=check|scan|raw] --file=<data_dir_OR_sst_file> Path to SST file or directory containing SST files --command=check|scan|raw check: Iterate over entries in files but dont print anything except if an error is encounterd (default command) scan: Iterate over entries in files and print them to screen raw: Dump all the table contents to <file_name>_dump.txt --output_hex Can be combined with scan command to print the keys and values in Hex --from=<user_key> Key to start reading from when executing check|scan --to=<user_key> Key to stop reading at when executing check|scan --read_num=<num> Maximum number of entries to read when executing check|scan --verify_checksum Verify file checksum when executing check|scan --input_key_hex Can be combined with --from and --to to indicate that these values are encoded in Hex --show_properties Print table properties after iterating over the file --show_compression_sizes Independent command that will recreate the SST file using 16K block size with different compressions and report the size of the file using such compression --set_block_size=<block_size> Can be combined with --show_compression_sizes to set the block size that will be used when trying different compression algorithms ``` Test Plan: none Reviewers: yhchiang, andrewkr, kradhakrishnan, yiwu, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56325
9 years ago
--output_hex
Can be combined with scan command to print the keys and values in Hex
--from=<user_key>
Key to start reading from when executing check|scan
--to=<user_key>
Key to stop reading at when executing check|scan
--prefix=<user_key>
Returns all keys with this prefix when executing check|scan
Cannot be used in conjunction with --from
Improve sst_dump help message Summary: Current Message ``` sst_dump [--command=check|scan|none|raw] [--verify_checksum] --file=data_dir_OR_sst_file [--output_hex] [--input_key_hex] [--from=<user_key>] [--to=<user_key>] [--read_num=NUM] [--show_properties] [--show_compression_sizes] [--show_compression_sizes [--set_block_size=<block_size>]] ``` New message ``` sst_dump --file=<data_dir_OR_sst_file> [--command=check|scan|raw] --file=<data_dir_OR_sst_file> Path to SST file or directory containing SST files --command=check|scan|raw check: Iterate over entries in files but dont print anything except if an error is encounterd (default command) scan: Iterate over entries in files and print them to screen raw: Dump all the table contents to <file_name>_dump.txt --output_hex Can be combined with scan command to print the keys and values in Hex --from=<user_key> Key to start reading from when executing check|scan --to=<user_key> Key to stop reading at when executing check|scan --read_num=<num> Maximum number of entries to read when executing check|scan --verify_checksum Verify file checksum when executing check|scan --input_key_hex Can be combined with --from and --to to indicate that these values are encoded in Hex --show_properties Print table properties after iterating over the file --show_compression_sizes Independent command that will recreate the SST file using 16K block size with different compressions and report the size of the file using such compression --set_block_size=<block_size> Can be combined with --show_compression_sizes to set the block size that will be used when trying different compression algorithms ``` Test Plan: none Reviewers: yhchiang, andrewkr, kradhakrishnan, yiwu, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56325
9 years ago
--read_num=<num>
Maximum number of entries to read when executing check|scan
--verify_checksum
Verify file checksum when executing check|scan
--input_key_hex
Can be combined with --from and --to to indicate that these values are encoded in Hex
--show_properties
Print table properties after iterating over the file
--show_compression_sizes
Independent command that will recreate the SST file using 16K block size with different
compressions and report the size of the file using such compression
--set_block_size=<block_size>
Can be combined with --show_compression_sizes to set the block size that will be used
when trying different compression algorithms
--parse_internal_key=<0xKEY>
Convenience option to parse an internal key on the command line. Dumps the
internal key in hex format {'key' @ SN: type}
Improve sst_dump help message Summary: Current Message ``` sst_dump [--command=check|scan|none|raw] [--verify_checksum] --file=data_dir_OR_sst_file [--output_hex] [--input_key_hex] [--from=<user_key>] [--to=<user_key>] [--read_num=NUM] [--show_properties] [--show_compression_sizes] [--show_compression_sizes [--set_block_size=<block_size>]] ``` New message ``` sst_dump --file=<data_dir_OR_sst_file> [--command=check|scan|raw] --file=<data_dir_OR_sst_file> Path to SST file or directory containing SST files --command=check|scan|raw check: Iterate over entries in files but dont print anything except if an error is encounterd (default command) scan: Iterate over entries in files and print them to screen raw: Dump all the table contents to <file_name>_dump.txt --output_hex Can be combined with scan command to print the keys and values in Hex --from=<user_key> Key to start reading from when executing check|scan --to=<user_key> Key to stop reading at when executing check|scan --read_num=<num> Maximum number of entries to read when executing check|scan --verify_checksum Verify file checksum when executing check|scan --input_key_hex Can be combined with --from and --to to indicate that these values are encoded in Hex --show_properties Print table properties after iterating over the file --show_compression_sizes Independent command that will recreate the SST file using 16K block size with different compressions and report the size of the file using such compression --set_block_size=<block_size> Can be combined with --show_compression_sizes to set the block size that will be used when trying different compression algorithms ``` Test Plan: none Reviewers: yhchiang, andrewkr, kradhakrishnan, yiwu, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56325
9 years ago
)");
}
} // namespace
int SSTDumpTool::Run(int argc, char** argv) {
const char* dir_or_file = nullptr;
uint64_t read_num = -1;
std::string command;
char junk;
uint64_t n;
bool verify_checksum = false;
bool output_hex = false;
bool input_key_hex = false;
bool has_from = false;
bool has_to = false;
bool use_from_as_prefix = false;
bool show_properties = false;
bool show_compression_sizes = false;
bool show_summary = false;
bool set_block_size = false;
std::string from_key;
std::string to_key;
std::string block_size_str;
size_t block_size;
uint64_t total_num_files = 0;
uint64_t total_num_data_blocks = 0;
uint64_t total_data_block_size = 0;
uint64_t total_index_block_size = 0;
uint64_t total_filter_block_size = 0;
for (int i = 1; i < argc; i++) {
if (strncmp(argv[i], "--file=", 7) == 0) {
dir_or_file = argv[i] + 7;
} else if (strcmp(argv[i], "--output_hex") == 0) {
output_hex = true;
} else if (strcmp(argv[i], "--input_key_hex") == 0) {
input_key_hex = true;
} else if (sscanf(argv[i],
"--read_num=%lu%c",
(unsigned long*)&n, &junk) == 1) {
read_num = n;
} else if (strcmp(argv[i], "--verify_checksum") == 0) {
verify_checksum = true;
} else if (strncmp(argv[i], "--command=", 10) == 0) {
command = argv[i] + 10;
} else if (strncmp(argv[i], "--from=", 7) == 0) {
from_key = argv[i] + 7;
has_from = true;
} else if (strncmp(argv[i], "--to=", 5) == 0) {
to_key = argv[i] + 5;
has_to = true;
} else if (strncmp(argv[i], "--prefix=", 9) == 0) {
from_key = argv[i] + 9;
use_from_as_prefix = true;
} else if (strcmp(argv[i], "--show_properties") == 0) {
show_properties = true;
} else if (strcmp(argv[i], "--show_compression_sizes") == 0) {
show_compression_sizes = true;
} else if (strcmp(argv[i], "--show_summary") == 0) {
show_summary = true;
} else if (strncmp(argv[i], "--set_block_size=", 17) == 0) {
set_block_size = true;
block_size_str = argv[i] + 17;
std::istringstream iss(block_size_str);
if (iss.fail()) {
fprintf(stderr, "block size must be numeric");
exit(1);
}
iss >> block_size;
} else if (strncmp(argv[i], "--parse_internal_key=", 21) == 0) {
std::string in_key(argv[i] + 21);
try {
in_key = rocksdb::LDBCommand::HexToString(in_key);
} catch (...) {
std::cerr << "ERROR: Invalid key input '"
<< in_key
<< "' Use 0x{hex representation of internal rocksdb key}" << std::endl;
return -1;
}
Slice sl_key = rocksdb::Slice(in_key);
ParsedInternalKey ikey;
int retc = 0;
if (!ParseInternalKey(sl_key, &ikey)) {
std::cerr << "Internal Key [" << sl_key.ToString(true /* in hex*/)
<< "] parse error!\n";
retc = -1;
}
fprintf(stdout, "key=%s\n", ikey.DebugString(true).c_str());
return retc;
} else {
fprintf(stderr, "Unrecognized argument '%s'\n\n", argv[i]);
print_help();
exit(1);
}
}
if (use_from_as_prefix && has_from) {
fprintf(stderr, "Cannot specify --prefix and --from\n\n");
exit(1);
}
if (input_key_hex) {
if (has_from || use_from_as_prefix) {
from_key = rocksdb::LDBCommand::HexToString(from_key);
}
if (has_to) {
to_key = rocksdb::LDBCommand::HexToString(to_key);
}
}
if (dir_or_file == nullptr) {
fprintf(stderr, "file or directory must be specified.\n\n");
print_help();
exit(1);
}
std::vector<std::string> filenames;
rocksdb::Env* env = rocksdb::Env::Default();
rocksdb::Status st = env->GetChildren(dir_or_file, &filenames);
bool dir = true;
if (!st.ok()) {
filenames.clear();
filenames.push_back(dir_or_file);
dir = false;
}
fprintf(stdout, "from [%s] to [%s]\n",
rocksdb::Slice(from_key).ToString(true).c_str(),
rocksdb::Slice(to_key).ToString(true).c_str());
uint64_t total_read = 0;
for (size_t i = 0; i < filenames.size(); i++) {
std::string filename = filenames.at(i);
if (filename.length() <= 4 ||
filename.rfind(".sst") != filename.length() - 4) {
// ignore
continue;
}
if (dir) {
filename = std::string(dir_or_file) + "/" + filename;
}
rocksdb::SstFileReader reader(filename, verify_checksum,
output_hex);
if (!reader.getStatus().ok()) {
fprintf(stderr, "%s: %s\n", filename.c_str(),
reader.getStatus().ToString().c_str());
continue;
}
if (show_compression_sizes) {
if (set_block_size) {
reader.ShowAllCompressionSizes(block_size);
} else {
reader.ShowAllCompressionSizes(16384);
}
return 0;
}
if (command == "raw") {
std::string out_filename = filename.substr(0, filename.length() - 4);
out_filename.append("_dump.txt");
st = reader.DumpTable(out_filename);
if (!st.ok()) {
fprintf(stderr, "%s: %s\n", filename.c_str(), st.ToString().c_str());
exit(1);
} else {
fprintf(stdout, "raw dump written to file %s\n", &out_filename[0]);
}
continue;
}
// scan all files in give file path.
if (command == "" || command == "scan" || command == "check") {
st = reader.ReadSequential(
command == "scan", read_num > 0 ? (read_num - total_read) : read_num,
has_from || use_from_as_prefix, from_key, has_to, to_key,
use_from_as_prefix);
if (!st.ok()) {
fprintf(stderr, "%s: %s\n", filename.c_str(),
st.ToString().c_str());
}
total_read += reader.GetReadNumber();
if (read_num > 0 && total_read > read_num) {
break;
}
}
if (command == "verify") {
st = reader.VerifyChecksum();
if (!st.ok()) {
fprintf(stderr, "%s is corrupted: %s\n", filename.c_str(),
st.ToString().c_str());
} else {
fprintf(stdout, "The file is ok\n");
}
continue;
}
if (show_properties || show_summary) {
const rocksdb::TableProperties* table_properties;
std::shared_ptr<const rocksdb::TableProperties>
table_properties_from_reader;
st = reader.ReadTableProperties(&table_properties_from_reader);
if (!st.ok()) {
fprintf(stderr, "%s: %s\n", filename.c_str(), st.ToString().c_str());
fprintf(stderr, "Try to use initial table properties\n");
table_properties = reader.GetInitTableProperties();
} else {
table_properties = table_properties_from_reader.get();
}
if (table_properties != nullptr) {
if (show_properties) {
fprintf(stdout,
"Table Properties:\n"
"------------------------------\n"
" %s",
table_properties->ToString("\n ", ": ").c_str());
fprintf(stdout, "# deleted keys: %" PRIu64 "\n",
rocksdb::GetDeletedKeys(
table_properties->user_collected_properties));
bool property_present;
uint64_t merge_operands = rocksdb::GetMergeOperands(
table_properties->user_collected_properties, &property_present);
if (property_present) {
fprintf(stdout, " # merge operands: %" PRIu64 "\n",
merge_operands);
} else {
fprintf(stdout, " # merge operands: UNKNOWN\n");
}
}
total_num_files += 1;
total_num_data_blocks += table_properties->num_data_blocks;
total_data_block_size += table_properties->data_size;
total_index_block_size += table_properties->index_size;
total_filter_block_size += table_properties->filter_size;
}
if (show_properties) {
fprintf(stdout,
"Raw user collected properties\n"
"------------------------------\n");
for (const auto& kv : table_properties->user_collected_properties) {
std::string prop_name = kv.first;
std::string prop_val = Slice(kv.second).ToString(true);
fprintf(stdout, " # %s: 0x%s\n", prop_name.c_str(),
prop_val.c_str());
}
}
}
}
if (show_summary) {
fprintf(stdout, "total number of files: %" PRIu64 "\n", total_num_files);
fprintf(stdout, "total number of data blocks: %" PRIu64 "\n",
total_num_data_blocks);
fprintf(stdout, "total data block size: %" PRIu64 "\n",
total_data_block_size);
fprintf(stdout, "total index block size: %" PRIu64 "\n",
total_index_block_size);
fprintf(stdout, "total filter block size: %" PRIu64 "\n",
total_filter_block_size);
}
return 0;
}
} // namespace rocksdb
#endif // ROCKSDB_LITE