|
|
|
// 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
4 years ago
|
|
|
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:
|
|
|
|
// 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 ImmutableCFOptions& ioptions,
|
|
|
|
const EnvOptions& soptions,
|
|
|
|
const InternalKeyComparator& internal_comparator,
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
10 years ago
|
|
|
uint64_t file_size,
|
|
|
|
std::unique_ptr<TableReader>* table_reader);
|
|
|
|
|
|
|
|
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_;
|
Adding pin_l0_filter_and_index_blocks_in_cache feature and related fixes.
Summary:
When a block based table file is opened, if prefetch_index_and_filter is true, it will prefetch the index and filter blocks, putting them into the block cache.
What this feature adds: when a L0 block based table file is opened, if pin_l0_filter_and_index_blocks_in_cache is true in the options (and prefetch_index_and_filter is true), then the filter and index blocks aren't released back to the block cache at the end of BlockBasedTableReader::Open(). Instead the table reader takes ownership of them, hence pinning them, ie. the LRU cache will never push them out. Meanwhile in the table reader, further accesses will not hit the block cache, thus avoiding lock contention.
Test Plan:
'export TEST_TMPDIR=/dev/shm/ && DISABLE_JEMALLOC=1 OPT=-g make all valgrind_check -j32' is OK.
I didn't run the Java tests, I don't have Java set up on my devserver.
Reviewers: sdong
Reviewed By: sdong
Subscribers: andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D56133
9 years ago
|
|
|
|
|
|
|
Status init_result_;
|
|
|
|
std::unique_ptr<TableReader> table_reader_;
|
|
|
|
std::unique_ptr<RandomAccessFileReader> file_;
|
Adding pin_l0_filter_and_index_blocks_in_cache feature and related fixes.
Summary:
When a block based table file is opened, if prefetch_index_and_filter is true, it will prefetch the index and filter blocks, putting them into the block cache.
What this feature adds: when a L0 block based table file is opened, if pin_l0_filter_and_index_blocks_in_cache is true in the options (and prefetch_index_and_filter is true), then the filter and index blocks aren't released back to the block cache at the end of BlockBasedTableReader::Open(). Instead the table reader takes ownership of them, hence pinning them, ie. the LRU cache will never push them out. Meanwhile in the table reader, further accesses will not hit the block cache, thus avoiding lock contention.
Test Plan:
'export TEST_TMPDIR=/dev/shm/ && DISABLE_JEMALLOC=1 OPT=-g make all valgrind_check -j32' is OK.
I didn't run the Java tests, I don't have Java set up on my devserver.
Reviewers: sdong
Reviewed By: sdong
Subscribers: andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D56133
9 years ago
|
|
|
|
|
|
|
const ImmutableCFOptions ioptions_;
|
|
|
|
const MutableCFOptions moptions_;
|
|
|
|
ReadOptions read_options_;
|
|
|
|
InternalKeyComparator internal_comparator_;
|
|
|
|
std::unique_ptr<TableProperties> table_properties_;
|
|
|
|
};
|
|
|
|
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|
|
|
|
|
|
|
|
#endif // ROCKSDB_LITE
|