rocksdb/db/table_cache.h

234 lines
11 KiB
C
Raw Permalink 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).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
//
// Thread-safe (provides internal synchronization)
#pragma once
#include <cstdint>
#include <string>
#include <vector>
#include "db/dbformat.h"
#include "db/range_del_aggregator.h"
#include "options/cf_options.h"
#include "port/port.h"
#include "rocksdb/cache.h"
#include "rocksdb/env.h"
#include "rocksdb/options.h"
#include "rocksdb/table.h"
#include "table/table_reader.h"
#include "trace_replay/block_cache_tracer.h"
namespace ROCKSDB_NAMESPACE {
class Env;
class Arena;
struct FileDescriptor;
class GetContext;
class HistogramImpl;
// Manages caching for TableReader objects for a column family. The actual
// cache is allocated separately and passed to the constructor. TableCache
// wraps around the underlying SST file readers by providing Get(),
// MultiGet() and NewIterator() methods that hide the instantiation,
// caching and access to the TableReader. The main purpose of this is
// performance - by caching the TableReader, it avoids unnecessary file opens
// and object allocation and instantiation. One exception is compaction, where
// a new TableReader may be instantiated - see NewIterator() comments
//
// Another service provided by TableCache is managing the row cache - if the
// DB is configured with a row cache, and the lookup key is present in the row
// cache, lookup is very fast. The row cache is obtained from
// ioptions.row_cache
class TableCache {
public:
TableCache(const ImmutableCFOptions& ioptions,
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 23:47:08 +01:00
const FileOptions& storage_options, Cache* cache,
BlockCacheTracer* const block_cache_tracer,
const std::shared_ptr<IOTracer>& io_tracer);
~TableCache();
// Return an iterator for the specified file number (the corresponding
// file length must be exactly "file_size" bytes). If "table_reader_ptr"
// is non-nullptr, also sets "*table_reader_ptr" to point to the Table object
// underlying the returned iterator, or nullptr if no Table object underlies
// the returned iterator. The returned "*table_reader_ptr" object is owned
// by the cache and should not be deleted, and is valid for as long as the
// returned iterator is live.
// @param options Must outlive the returned iterator.
// @param range_del_agg If non-nullptr, adds range deletions to the
// aggregator. If an error occurs, returns it in a NewErrorInternalIterator
// @param for_compaction If true, a new TableReader may be allocated (but
// not cached), depending on the CF options
// @param skip_filters Disables loading/accessing the filter block
// @param level The level this table is at, -1 for "not set / don't know"
InternalIterator* NewIterator(
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 23:47:08 +01:00
const ReadOptions& options, const FileOptions& toptions,
const InternalKeyComparator& internal_comparator,
const FileMetaData& file_meta, RangeDelAggregator* range_del_agg,
const SliceTransform* prefix_extractor, TableReader** table_reader_ptr,
HistogramImpl* file_read_hist, TableReaderCaller caller, Arena* arena,
bool skip_filters, int level, size_t max_file_size_for_l0_meta_pin,
const InternalKey* smallest_compaction_key,
Properly report IO errors when IndexType::kBinarySearchWithFirstKey is used (#6621) Summary: Context: Index type `kBinarySearchWithFirstKey` added the ability for sst file iterator to sometimes report a key from index without reading the corresponding data block. This is useful when sst blocks are cut at some meaningful boundaries (e.g. one block per key prefix), and many seeks land between blocks (e.g. for each prefix, the ranges of keys in different sst files are nearly disjoint, so a typical seek needs to read a data block from only one file even if all files have the prefix). But this added a new error condition, which rocksdb code was really not equipped to deal with: `InternalIterator::value()` may fail with an IO error or Status::Incomplete, but it's just a method returning a Slice, with no way to report error instead. Before this PR, this type of error wasn't handled at all (an empty slice was returned), and kBinarySearchWithFirstKey implementation was considered a prototype. Now that we (LogDevice) have experimented with kBinarySearchWithFirstKey for a while and confirmed that it's really useful, this PR is adding the missing error handling. It's a pretty inconvenient situation implementation-wise. The error needs to be reported from InternalIterator when trying to access value. But there are ~700 call sites of `InternalIterator::value()`, most of which either can't hit the error condition (because the iterator is reading from memtable or from index or something) or wouldn't benefit from the deferred loading of the value (e.g. compaction iterator that reads all values anyway). Adding error handling to all these call sites would needlessly bloat the code. So instead I made the deferred value loading optional: only the call sites that may use deferred loading have to call the new method `PrepareValue()` before calling `value()`. The feature is enabled with a new bool argument `allow_unprepared_value` to a bunch of methods that create iterators (it wouldn't make sense to put it in ReadOptions because it's completely internal to iterators, with virtually no user-visible effect). Lmk if you have better ideas. Note that the deferred value loading only happens for *internal* iterators. The user-visible iterator (DBIter) always prepares the value before returning from Seek/Next/etc. We could go further and add an API to defer that value loading too, but that's most likely not useful for LogDevice, so it doesn't seem worth the complexity for now. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6621 Test Plan: make -j5 check . Will also deploy to some logdevice test clusters and look at stats. Reviewed By: siying Differential Revision: D20786930 Pulled By: al13n321 fbshipit-source-id: 6da77d918bad3780522e918f17f4d5513d3e99ee
2020-04-16 02:37:23 +02:00
const InternalKey* largest_compaction_key, bool allow_unprepared_value);
// If a seek to internal key "k" in specified file finds an entry,
// call get_context->SaveValue() repeatedly until
// it returns false. As a side effect, it will insert the TableReader
// into the cache and potentially evict another entry
// @param get_context Context for get operation. The result of the lookup
// can be retrieved by calling get_context->State()
// @param file_read_hist If non-nullptr, the file reader statistics are
// recorded
// @param skip_filters Disables loading/accessing the filter block
// @param level The level this table is at, -1 for "not set / don't know"
Status Get(const ReadOptions& options,
const InternalKeyComparator& internal_comparator,
const FileMetaData& file_meta, const Slice& k,
GetContext* get_context,
const SliceTransform* prefix_extractor = nullptr,
HistogramImpl* file_read_hist = nullptr, bool skip_filters = false,
int level = -1, size_t max_file_size_for_l0_meta_pin = 0);
// Return the range delete tombstone iterator of the file specified by
// `file_meta`.
Status GetRangeTombstoneIterator(
const ReadOptions& options,
const InternalKeyComparator& internal_comparator,
const FileMetaData& file_meta,
std::unique_ptr<FragmentedRangeTombstoneIterator>* out_iter);
// If a seek to internal key "k" in specified file finds an entry,
// call get_context->SaveValue() repeatedly until
// it returns false. As a side effect, it will insert the TableReader
// into the cache and potentially evict another entry
// @param mget_range Pointer to the structure describing a batch of keys to
// be looked up in this table file. The result is stored
// in the embedded GetContext
// @param skip_filters Disables loading/accessing the filter block
// @param level The level this table is at, -1 for "not set / don't know"
Introduce a new MultiGet batching implementation (#5011) Summary: This PR introduces a new MultiGet() API, with the underlying implementation grouping keys based on SST file and batching lookups in a file. The reason for the new API is twofold - the definition allows callers to allocate storage for status and values on stack instead of std::vector, as well as return values as PinnableSlices in order to avoid copying, and it keeps the original MultiGet() implementation intact while we experiment with batching. Batching is useful when there is some spatial locality to the keys being queries, as well as larger batch sizes. The main benefits are due to - 1. Fewer function calls, especially to BlockBasedTableReader::MultiGet() and FullFilterBlockReader::KeysMayMatch() 2. Bloom filter cachelines can be prefetched, hiding the cache miss latency The next step is to optimize the binary searches in the level_storage_info, index blocks and data blocks, since we could reduce the number of key comparisons if the keys are relatively close to each other. The batching optimizations also need to be extended to other formats, such as PlainTable and filter formats. This also needs to be added to db_stress. Benchmark results from db_bench for various batch size/locality of reference combinations are given below. Locality was simulated by offsetting the keys in a batch by a stride length. Each SST file is about 8.6MB uncompressed and key/value size is 16/100 uncompressed. To focus on the cpu benefit of batching, the runs were single threaded and bound to the same cpu to eliminate interference from other system events. The results show a 10-25% improvement in micros/op from smaller to larger batch sizes (4 - 32). Batch Sizes 1 | 2 | 4 | 8 | 16 | 32 Random pattern (Stride length 0) 4.158 | 4.109 | 4.026 | 4.05 | 4.1 | 4.074 - Get 4.438 | 4.302 | 4.165 | 4.122 | 4.096 | 4.075 - MultiGet (no batching) 4.461 | 4.256 | 4.277 | 4.11 | 4.182 | 4.14 - MultiGet (w/ batching) Good locality (Stride length 16) 4.048 | 3.659 | 3.248 | 2.99 | 2.84 | 2.753 4.429 | 3.728 | 3.406 | 3.053 | 2.911 | 2.781 4.452 | 3.45 | 2.833 | 2.451 | 2.233 | 2.135 Good locality (Stride length 256) 4.066 | 3.786 | 3.581 | 3.447 | 3.415 | 3.232 4.406 | 4.005 | 3.644 | 3.49 | 3.381 | 3.268 4.393 | 3.649 | 3.186 | 2.882 | 2.676 | 2.62 Medium locality (Stride length 4096) 4.012 | 3.922 | 3.768 | 3.61 | 3.582 | 3.555 4.364 | 4.057 | 3.791 | 3.65 | 3.57 | 3.465 4.479 | 3.758 | 3.316 | 3.077 | 2.959 | 2.891 dbbench command used (on a DB with 4 levels, 12 million keys)- TEST_TMPDIR=/dev/shm numactl -C 10 ./db_bench.tmp -use_existing_db=true -benchmarks="readseq,multireadrandom" -write_buffer_size=4194304 -target_file_size_base=4194304 -max_bytes_for_level_base=16777216 -num=12000000 -reads=12000000 -duration=90 -threads=1 -compression_type=none -cache_size=4194304000 -batch_size=32 -disable_auto_compactions=true -bloom_bits=10 -cache_index_and_filter_blocks=true -pin_l0_filter_and_index_blocks_in_cache=true -multiread_batched=true -multiread_stride=4 Pull Request resolved: https://github.com/facebook/rocksdb/pull/5011 Differential Revision: D14348703 Pulled By: anand1976 fbshipit-source-id: 774406dab3776d979c809522a67bedac6c17f84b
2019-04-11 23:24:09 +02:00
Status MultiGet(const ReadOptions& options,
const InternalKeyComparator& internal_comparator,
const FileMetaData& file_meta,
const MultiGetContext::Range* mget_range,
const SliceTransform* prefix_extractor = nullptr,
HistogramImpl* file_read_hist = nullptr,
bool skip_filters = false, int level = -1);
// Evict any entry for the specified file number
static void Evict(Cache* cache, uint64_t file_number);
// Clean table handle and erase it from the table cache
// Used in DB close, or the file is not live anymore.
void EraseHandle(const FileDescriptor& fd, Cache::Handle* handle);
// Find table reader
// @param skip_filters Disables loading/accessing the filter block
// @param level == -1 means not specified
Status FindTable(const ReadOptions& ro, const FileOptions& toptions,
const InternalKeyComparator& internal_comparator,
const FileDescriptor& file_fd, Cache::Handle**,
const SliceTransform* prefix_extractor = nullptr,
const bool no_io = false, bool record_read_stats = true,
HistogramImpl* file_read_hist = nullptr,
bool skip_filters = false, int level = -1,
bool prefetch_index_and_filter_in_cache = true,
size_t max_file_size_for_l0_meta_pin = 0);
// Get TableReader from a cache handle.
TableReader* GetTableReaderFromHandle(Cache::Handle* handle);
// Get the table properties of a given table.
// @no_io: indicates if we should load table to the cache if it is not present
// in table cache yet.
// @returns: `properties` will be reset on success. Please note that we will
// return Status::Incomplete() if table is not present in cache and
// we set `no_io` to be true.
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 23:47:08 +01:00
Status GetTableProperties(const FileOptions& toptions,
const InternalKeyComparator& internal_comparator,
const FileDescriptor& file_meta,
std::shared_ptr<const TableProperties>* properties,
const SliceTransform* prefix_extractor = nullptr,
bool no_io = false);
// Return total memory usage of the table reader of the file.
// 0 if table reader of the file is not loaded.
size_t GetMemoryUsageByTableReader(
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 23:47:08 +01:00
const FileOptions& toptions,
const InternalKeyComparator& internal_comparator,
const FileDescriptor& fd,
const SliceTransform* prefix_extractor = nullptr);
// Returns approximated offset of a key in a file represented by fd.
uint64_t ApproximateOffsetOf(
const Slice& key, const FileDescriptor& fd, TableReaderCaller caller,
const InternalKeyComparator& internal_comparator,
const SliceTransform* prefix_extractor = nullptr);
// Returns approximated data size between start and end keys in a file
// represented by fd (the start key must not be greater than the end key).
uint64_t ApproximateSize(const Slice& start, const Slice& end,
const FileDescriptor& fd, TableReaderCaller caller,
const InternalKeyComparator& internal_comparator,
const SliceTransform* prefix_extractor = nullptr);
// Release the handle from a cache
void ReleaseHandle(Cache::Handle* handle);
Cache* get_cache() const { return cache_; }
// Capacity of the backing Cache that indicates infinite TableCache capacity.
// For example when max_open_files is -1 we set the backing Cache to this.
static const int kInfiniteCapacity = 0x400000;
// The tables opened with this TableCache will be immortal, i.e., their
// lifetime is as long as that of the DB.
void SetTablesAreImmortal() {
if (cache_->GetCapacity() >= kInfiniteCapacity) {
immortal_tables_ = true;
}
}
private:
// Build a table reader
Status GetTableReader(const ReadOptions& ro, const FileOptions& file_options,
const InternalKeyComparator& internal_comparator,
const FileDescriptor& fd, bool sequential_mode,
bool record_read_stats, HistogramImpl* file_read_hist,
std::unique_ptr<TableReader>* table_reader,
const SliceTransform* prefix_extractor = nullptr,
bool skip_filters = false, int level = -1,
bool prefetch_index_and_filter_in_cache = true,
size_t max_file_size_for_l0_meta_pin = 0);
// Create a key prefix for looking up the row cache. The prefix is of the
// format row_cache_id + fd_number + seq_no. Later, the user key can be
// appended to form the full key
void CreateRowCacheKeyPrefix(const ReadOptions& options,
const FileDescriptor& fd,
const Slice& internal_key,
GetContext* get_context, IterKey& row_cache_key);
// Helper function to lookup the row cache for a key. It appends the
// user key to row_cache_key at offset prefix_size
bool GetFromRowCache(const Slice& user_key, IterKey& row_cache_key,
size_t prefix_size, GetContext* get_context);
const ImmutableCFOptions& ioptions_;
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 23:47:08 +01:00
const FileOptions& file_options_;
Cache* const cache_;
std::string row_cache_id_;
bool immortal_tables_;
BlockCacheTracer* const block_cache_tracer_;
Striped<port::Mutex, Slice> loader_mutex_;
std::shared_ptr<IOTracer> io_tracer_;
};
} // namespace ROCKSDB_NAMESPACE