rocksdb/table/sst_file_dumper.h

98 lines
3.6 KiB
C
Raw Normal View History

// 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 <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,
const EnvOptions& soptions = EnvOptions(),
bool silent = false);
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_; }
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,
Limit buffering for collecting samples for compression dictionary (#7970) Summary: For dictionary compression, we need to collect some representative samples of the data to be compressed, which we use to either generate or train (when `CompressionOptions::zstd_max_train_bytes > 0`) a dictionary. Previously, the strategy was to buffer all the data blocks during flush, and up to the target file size during compaction. That strategy allowed us to randomly pick samples from as wide a range as possible that'd be guaranteed to land in a single output file. However, some users try to make huge files in memory-constrained environments, where this strategy can cause OOM. This PR introduces an option, `CompressionOptions::max_dict_buffer_bytes`, that limits how much data blocks are buffered before we switch to unbuffered mode (which means creating the per-SST dictionary, writing out the buffered data, and compressing/writing new blocks as soon as they are built). It is not strict as we currently buffer more than just data blocks -- also keys are buffered. But it does make a step towards giving users predictable memory usage. Related changes include: - Changed sampling for dictionary compression to select unique data blocks when there is limited availability of data blocks - Made use of `BlockBuilder::SwapAndReset()` to save an allocation+memcpy when buffering data blocks for building a dictionary - Changed `ParseBoolean()` to accept an input containing characters after the boolean. This is necessary since, with this PR, a value for `CompressionOptions::enabled` is no longer necessarily the final component in the `CompressionOptions` string. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7970 Test Plan: - updated `CompressionOptions` unit tests to verify limit is respected (to the extent expected in the current implementation) in various scenarios of flush/compaction to bottommost/non-bottommost level - looked at jemalloc heap profiles right before and after switching to unbuffered mode during flush/compaction. Verified memory usage in buffering is proportional to the limit set. Reviewed By: pdillinger Differential Revision: D26467994 Pulled By: ajkr fbshipit-source-id: 3da4ef9fba59974e4ef40e40c01611002c861465
2021-02-19 23:06:59 +01:00
uint32_t max_dict_bytes, uint32_t zstd_max_train_bytes,
uint64_t max_dict_buffer_bytes);
Status ShowCompressionSize(size_t block_size, CompressionType compress_type,
const CompressionOptions& compress_opt);
private:
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
2015-02-26 01:34:26 +01:00
// 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();
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
2015-02-26 01:34:26 +01:00
// 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);
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
2015-02-26 01:34:26 +01:00
std::string file_name_;
uint64_t read_num_;
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_;
const ImmutableCFOptions ioptions_;
const MutableCFOptions moptions_;
ReadOptions read_options_;
InternalKeyComparator internal_comparator_;
std::unique_ptr<TableProperties> table_properties_;
};
} // namespace ROCKSDB_NAMESPACE
#endif // ROCKSDB_LITE