rocksdb/db/compaction_picker.h

305 lines
13 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).
//
// 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.
#pragma once
#include <memory>
#include <set>
#include <string>
#include <unordered_set>
#include <vector>
#include "db/compaction.h"
#include "db/version_set.h"
#include "options/cf_options.h"
#include "rocksdb/env.h"
#include "rocksdb/options.h"
#include "rocksdb/status.h"
namespace rocksdb {
class LogBuffer;
class Compaction;
class VersionStorageInfo;
struct CompactionInputFiles;
class CompactionPicker {
public:
CompactionPicker(const ImmutableCFOptions& ioptions,
const InternalKeyComparator* icmp);
virtual ~CompactionPicker();
// Pick level and inputs for a new compaction.
// Returns nullptr if there is no compaction to be done.
// Otherwise returns a pointer to a heap-allocated object that
// describes the compaction. Caller should delete the result.
virtual Compaction* PickCompaction(const std::string& cf_name,
const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* vstorage,
LogBuffer* log_buffer) = 0;
// Return a compaction object for compacting the range [begin,end] in
// the specified level. Returns nullptr if there is nothing in that
// level that overlaps the specified range. Caller should delete
// the result.
//
// The returned Compaction might not include the whole requested range.
// In that case, compaction_end will be set to the next key that needs
// compacting. In case the compaction will compact the whole range,
// compaction_end will be set to nullptr.
// Client is responsible for compaction_end storage -- when called,
// *compaction_end should point to valid InternalKey!
virtual Compaction* CompactRange(
const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* vstorage, int input_level, int output_level,
uint32_t output_path_id, const InternalKey* begin, const InternalKey* end,
InternalKey** compaction_end, bool* manual_conflict);
// The maximum allowed output level. Default value is NumberLevels() - 1.
virtual int MaxOutputLevel() const { return NumberLevels() - 1; }
virtual bool NeedsCompaction(const VersionStorageInfo* vstorage) const = 0;
// Sanitize the input set of compaction input files.
// When the input parameters do not describe a valid compaction, the
// function will try to fix the input_files by adding necessary
// files. If it's not possible to conver an invalid input_files
// into a valid one by adding more files, the function will return a
// non-ok status with specific reason.
#ifndef ROCKSDB_LITE
Status SanitizeCompactionInputFiles(std::unordered_set<uint64_t>* input_files,
const ColumnFamilyMetaData& cf_meta,
const int output_level) const;
#endif // ROCKSDB_LITE
// Free up the files that participated in a compaction
//
// Requirement: DB mutex held
void ReleaseCompactionFiles(Compaction* c, Status status);
// Returns true if any one of the specified files are being compacted
bool AreFilesInCompaction(const std::vector<FileMetaData*>& files);
// Takes a list of CompactionInputFiles and returns a (manual) Compaction
// object.
//
// Caller must provide a set of input files that has been passed through
// `SanitizeCompactionInputFiles` earlier. The lock should not be released
// between that call and this one.
Compaction* CompactFiles(const CompactionOptions& compact_options,
const std::vector<CompactionInputFiles>& input_files,
int output_level, VersionStorageInfo* vstorage,
const MutableCFOptions& mutable_cf_options,
uint32_t output_path_id);
// Converts a set of compaction input file numbers into
// a list of CompactionInputFiles.
Status GetCompactionInputsFromFileNumbers(
Make Compaction class easier to use Summary: The goal of this diff is to make Compaction class easier to use. This should also make new compaction algorithms easier to write (like CompactFiles from @yhchiang and dynamic leveled and multi-leveled universal from @sdong). Here are couple of things demonstrating that Compaction class is hard to use: 1. we have two constructors of Compaction class 2. there's this thing called grandparents_, but it appears to only be setup for leveled compaction and not compactfiles 3. it's easy to introduce a subtle and dangerous bug like this: D36225 4. SetupBottomMostLevel() is hard to understand and it shouldn't be. See this comment: https://github.com/facebook/rocksdb/blob/afbafeaeaebfd27a0f3e992fee8e0c57d07658fa/db/compaction.cc#L236-L241. It also made it harder for @yhchiang to write CompactFiles, as evidenced by this: https://github.com/facebook/rocksdb/blob/afbafeaeaebfd27a0f3e992fee8e0c57d07658fa/db/compaction_picker.cc#L204-L210 The problem is that we create Compaction object, which holds a lot of state, and then pass it around to some functions. After those functions are done mutating, then we call couple of functions on Compaction object, like SetupBottommostLevel() and MarkFilesBeingCompacted(). It is very hard to see what's happening with all that Compaction's state while it's travelling across different functions. If you're writing a new PickCompaction() function you need to try really hard to understand what are all the functions you need to run on Compaction object and what state you need to setup. My proposed solution is to make important parts of Compaction immutable after construction. PickCompaction() should calculate compaction inputs and then pass them onto Compaction object once they are finalized. That makes it easy to create a new compaction -- just provide all the parameters to the constructor and you're done. No need to call confusing functions after you created your object. This diff doesn't fully achieve that goal, but it comes pretty close. Here are some of the changes: * have one Compaction constructor instead of two. * inputs_ is constant after construction * MarkFilesBeingCompacted() is now private to Compaction class and automatically called on construction/destruction. * SetupBottommostLevel() is gone. Compaction figures it out on its own based on the input. * CompactionPicker's functions are not passing around Compaction object anymore. They are only passing around the state that they need. Test Plan: make check make asan_check make valgrind_check Reviewers: rven, anthony, sdong, yhchiang Reviewed By: yhchiang Subscribers: sdong, yhchiang, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D36687
2015-04-11 00:01:54 +02:00
std::vector<CompactionInputFiles>* input_files,
std::unordered_set<uint64_t>* input_set,
const VersionStorageInfo* vstorage,
const CompactionOptions& compact_options) const;
// Is there currently a compaction involving level 0 taking place
bool IsLevel0CompactionInProgress() const {
return !level0_compactions_in_progress_.empty();
}
// Return true if the passed key range overlap with a compaction output
// that is currently running.
bool RangeOverlapWithCompaction(const Slice& smallest_user_key,
const Slice& largest_user_key,
int level) const;
// Stores the minimal range that covers all entries in inputs in
// *smallest, *largest.
// REQUIRES: inputs is not empty
void GetRange(const CompactionInputFiles& inputs, InternalKey* smallest,
InternalKey* largest) const;
// Stores the minimal range that covers all entries in inputs1 and inputs2
// in *smallest, *largest.
// REQUIRES: inputs is not empty
void GetRange(const CompactionInputFiles& inputs1,
const CompactionInputFiles& inputs2, InternalKey* smallest,
InternalKey* largest) const;
// Stores the minimal range that covers all entries in inputs
// in *smallest, *largest.
// REQUIRES: inputs is not empty (at least on entry have one file)
void GetRange(const std::vector<CompactionInputFiles>& inputs,
InternalKey* smallest, InternalKey* largest) const;
int NumberLevels() const { return ioptions_.num_levels; }
// Add more files to the inputs on "level" to make sure that
// no newer version of a key is compacted to "level+1" while leaving an older
// version in a "level". Otherwise, any Get() will search "level" first,
// and will likely return an old/stale value for the key, since it always
// searches in increasing order of level to find the value. This could
// also scramble the order of merge operands. This function should be
// called any time a new Compaction is created, and its inputs_[0] are
// populated.
//
// Will return false if it is impossible to apply this compaction.
bool ExpandInputsToCleanCut(const std::string& cf_name,
Make Compaction class easier to use Summary: The goal of this diff is to make Compaction class easier to use. This should also make new compaction algorithms easier to write (like CompactFiles from @yhchiang and dynamic leveled and multi-leveled universal from @sdong). Here are couple of things demonstrating that Compaction class is hard to use: 1. we have two constructors of Compaction class 2. there's this thing called grandparents_, but it appears to only be setup for leveled compaction and not compactfiles 3. it's easy to introduce a subtle and dangerous bug like this: D36225 4. SetupBottomMostLevel() is hard to understand and it shouldn't be. See this comment: https://github.com/facebook/rocksdb/blob/afbafeaeaebfd27a0f3e992fee8e0c57d07658fa/db/compaction.cc#L236-L241. It also made it harder for @yhchiang to write CompactFiles, as evidenced by this: https://github.com/facebook/rocksdb/blob/afbafeaeaebfd27a0f3e992fee8e0c57d07658fa/db/compaction_picker.cc#L204-L210 The problem is that we create Compaction object, which holds a lot of state, and then pass it around to some functions. After those functions are done mutating, then we call couple of functions on Compaction object, like SetupBottommostLevel() and MarkFilesBeingCompacted(). It is very hard to see what's happening with all that Compaction's state while it's travelling across different functions. If you're writing a new PickCompaction() function you need to try really hard to understand what are all the functions you need to run on Compaction object and what state you need to setup. My proposed solution is to make important parts of Compaction immutable after construction. PickCompaction() should calculate compaction inputs and then pass them onto Compaction object once they are finalized. That makes it easy to create a new compaction -- just provide all the parameters to the constructor and you're done. No need to call confusing functions after you created your object. This diff doesn't fully achieve that goal, but it comes pretty close. Here are some of the changes: * have one Compaction constructor instead of two. * inputs_ is constant after construction * MarkFilesBeingCompacted() is now private to Compaction class and automatically called on construction/destruction. * SetupBottommostLevel() is gone. Compaction figures it out on its own based on the input. * CompactionPicker's functions are not passing around Compaction object anymore. They are only passing around the state that they need. Test Plan: make check make asan_check make valgrind_check Reviewers: rven, anthony, sdong, yhchiang Reviewed By: yhchiang Subscribers: sdong, yhchiang, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D36687
2015-04-11 00:01:54 +02:00
VersionStorageInfo* vstorage,
CompactionInputFiles* inputs);
// Returns true if any one of the parent files are being compacted
bool IsRangeInCompaction(VersionStorageInfo* vstorage,
const InternalKey* smallest,
const InternalKey* largest, int level, int* index);
// Returns true if the key range that `inputs` files cover overlap with the
// key range of a currently running compaction.
bool FilesRangeOverlapWithCompaction(
const std::vector<CompactionInputFiles>& inputs, int level) const;
Make Compaction class easier to use Summary: The goal of this diff is to make Compaction class easier to use. This should also make new compaction algorithms easier to write (like CompactFiles from @yhchiang and dynamic leveled and multi-leveled universal from @sdong). Here are couple of things demonstrating that Compaction class is hard to use: 1. we have two constructors of Compaction class 2. there's this thing called grandparents_, but it appears to only be setup for leveled compaction and not compactfiles 3. it's easy to introduce a subtle and dangerous bug like this: D36225 4. SetupBottomMostLevel() is hard to understand and it shouldn't be. See this comment: https://github.com/facebook/rocksdb/blob/afbafeaeaebfd27a0f3e992fee8e0c57d07658fa/db/compaction.cc#L236-L241. It also made it harder for @yhchiang to write CompactFiles, as evidenced by this: https://github.com/facebook/rocksdb/blob/afbafeaeaebfd27a0f3e992fee8e0c57d07658fa/db/compaction_picker.cc#L204-L210 The problem is that we create Compaction object, which holds a lot of state, and then pass it around to some functions. After those functions are done mutating, then we call couple of functions on Compaction object, like SetupBottommostLevel() and MarkFilesBeingCompacted(). It is very hard to see what's happening with all that Compaction's state while it's travelling across different functions. If you're writing a new PickCompaction() function you need to try really hard to understand what are all the functions you need to run on Compaction object and what state you need to setup. My proposed solution is to make important parts of Compaction immutable after construction. PickCompaction() should calculate compaction inputs and then pass them onto Compaction object once they are finalized. That makes it easy to create a new compaction -- just provide all the parameters to the constructor and you're done. No need to call confusing functions after you created your object. This diff doesn't fully achieve that goal, but it comes pretty close. Here are some of the changes: * have one Compaction constructor instead of two. * inputs_ is constant after construction * MarkFilesBeingCompacted() is now private to Compaction class and automatically called on construction/destruction. * SetupBottommostLevel() is gone. Compaction figures it out on its own based on the input. * CompactionPicker's functions are not passing around Compaction object anymore. They are only passing around the state that they need. Test Plan: make check make asan_check make valgrind_check Reviewers: rven, anthony, sdong, yhchiang Reviewed By: yhchiang Subscribers: sdong, yhchiang, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D36687
2015-04-11 00:01:54 +02:00
bool SetupOtherInputs(const std::string& cf_name,
const MutableCFOptions& mutable_cf_options,
Make Compaction class easier to use Summary: The goal of this diff is to make Compaction class easier to use. This should also make new compaction algorithms easier to write (like CompactFiles from @yhchiang and dynamic leveled and multi-leveled universal from @sdong). Here are couple of things demonstrating that Compaction class is hard to use: 1. we have two constructors of Compaction class 2. there's this thing called grandparents_, but it appears to only be setup for leveled compaction and not compactfiles 3. it's easy to introduce a subtle and dangerous bug like this: D36225 4. SetupBottomMostLevel() is hard to understand and it shouldn't be. See this comment: https://github.com/facebook/rocksdb/blob/afbafeaeaebfd27a0f3e992fee8e0c57d07658fa/db/compaction.cc#L236-L241. It also made it harder for @yhchiang to write CompactFiles, as evidenced by this: https://github.com/facebook/rocksdb/blob/afbafeaeaebfd27a0f3e992fee8e0c57d07658fa/db/compaction_picker.cc#L204-L210 The problem is that we create Compaction object, which holds a lot of state, and then pass it around to some functions. After those functions are done mutating, then we call couple of functions on Compaction object, like SetupBottommostLevel() and MarkFilesBeingCompacted(). It is very hard to see what's happening with all that Compaction's state while it's travelling across different functions. If you're writing a new PickCompaction() function you need to try really hard to understand what are all the functions you need to run on Compaction object and what state you need to setup. My proposed solution is to make important parts of Compaction immutable after construction. PickCompaction() should calculate compaction inputs and then pass them onto Compaction object once they are finalized. That makes it easy to create a new compaction -- just provide all the parameters to the constructor and you're done. No need to call confusing functions after you created your object. This diff doesn't fully achieve that goal, but it comes pretty close. Here are some of the changes: * have one Compaction constructor instead of two. * inputs_ is constant after construction * MarkFilesBeingCompacted() is now private to Compaction class and automatically called on construction/destruction. * SetupBottommostLevel() is gone. Compaction figures it out on its own based on the input. * CompactionPicker's functions are not passing around Compaction object anymore. They are only passing around the state that they need. Test Plan: make check make asan_check make valgrind_check Reviewers: rven, anthony, sdong, yhchiang Reviewed By: yhchiang Subscribers: sdong, yhchiang, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D36687
2015-04-11 00:01:54 +02:00
VersionStorageInfo* vstorage,
CompactionInputFiles* inputs,
CompactionInputFiles* output_level_inputs,
int* parent_index, int base_index);
void GetGrandparents(VersionStorageInfo* vstorage,
const CompactionInputFiles& inputs,
const CompactionInputFiles& output_level_inputs,
std::vector<FileMetaData*>* grandparents);
// Register this compaction in the set of running compactions
void RegisterCompaction(Compaction* c);
// Remove this compaction from the set of running compactions
void UnregisterCompaction(Compaction* c);
std::set<Compaction*>* level0_compactions_in_progress() {
return &level0_compactions_in_progress_;
}
std::unordered_set<Compaction*>* compactions_in_progress() {
return &compactions_in_progress_;
}
protected:
const ImmutableCFOptions& ioptions_;
// A helper function to SanitizeCompactionInputFiles() that
// sanitizes "input_files" by adding necessary files.
#ifndef ROCKSDB_LITE
virtual Status SanitizeCompactionInputFilesForAllLevels(
std::unordered_set<uint64_t>* input_files,
const ColumnFamilyMetaData& cf_meta, const int output_level) const;
#endif // ROCKSDB_LITE
// Keeps track of all compactions that are running on Level0.
// Protected by DB mutex
std::set<Compaction*> level0_compactions_in_progress_;
// Keeps track of all compactions that are running.
// Protected by DB mutex
std::unordered_set<Compaction*> compactions_in_progress_;
const InternalKeyComparator* const icmp_;
};
class LevelCompactionPicker : public CompactionPicker {
public:
LevelCompactionPicker(const ImmutableCFOptions& ioptions,
const InternalKeyComparator* icmp)
: CompactionPicker(ioptions, icmp) {}
virtual Compaction* PickCompaction(const std::string& cf_name,
const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* vstorage,
LogBuffer* log_buffer) override;
virtual bool NeedsCompaction(
const VersionStorageInfo* vstorage) const override;
};
#ifndef ROCKSDB_LITE
class FIFOCompactionPicker : public CompactionPicker {
public:
FIFOCompactionPicker(const ImmutableCFOptions& ioptions,
const InternalKeyComparator* icmp)
: CompactionPicker(ioptions, icmp) {}
virtual Compaction* PickCompaction(const std::string& cf_name,
const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* version,
LogBuffer* log_buffer) override;
virtual Compaction* CompactRange(
const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* vstorage, int input_level, int output_level,
uint32_t output_path_id, const InternalKey* begin, const InternalKey* end,
InternalKey** compaction_end, bool* manual_conflict) override;
// The maximum allowed output level. Always returns 0.
virtual int MaxOutputLevel() const override { return 0; }
virtual bool NeedsCompaction(
const VersionStorageInfo* vstorage) const override;
FIFO Compaction with TTL Summary: Introducing FIFO compactions with TTL. FIFO compaction is based on size only which makes it tricky to enable in production as use cases can have organic growth. A user requested an option to drop files based on the time of their creation instead of the total size. To address that request: - Added a new TTL option to FIFO compaction options. - Updated FIFO compaction score to take TTL into consideration. - Added a new table property, creation_time, to keep track of when the SST file is created. - Creation_time is set as below: - On Flush: Set to the time of flush. - On Compaction: Set to the max creation_time of all the files involved in the compaction. - On Repair and Recovery: Set to the time of repair/recovery. - Old files created prior to this code change will have a creation_time of 0. - FIFO compaction with TTL is enabled when ttl > 0. All files older than ttl will be deleted during compaction. i.e. `if (file.creation_time < (current_time - ttl)) then delete(file)`. This will enable cases where you might want to delete all files older than, say, 1 day. - FIFO compaction will fall back to the prior way of deleting files based on size if: - the creation_time of all files involved in compaction is 0. - the total size (of all SST files combined) does not drop below `compaction_options_fifo.max_table_files_size` even if the files older than ttl are deleted. This feature is not supported if max_open_files != -1 or with table formats other than Block-based. **Test Plan:** Added tests. **Benchmark results:** Base: FIFO with max size: 100MB :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 readwhilewriting : 1.924 micros/op 519858 ops/sec; 13.6 MB/s (1176277 of 5000000 found) ``` With TTL (a low one for testing) :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 --fifo_compaction_ttl=20 readwhilewriting : 1.902 micros/op 525817 ops/sec; 13.7 MB/s (1185057 of 5000000 found) ``` Example Log lines: ``` 2017/06/26-15:17:24.609249 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609177) [db/compaction_picker.cc:1471] [default] FIFO compaction: picking file 40 with creation time 1498515423 for deletion 2017/06/26-15:17:24.609255 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609234) [db/db_impl_compaction_flush.cc:1541] [default] Deleted 1 files ... 2017/06/26-15:17:25.553185 7fd5a61a5800 [DEBUG] [db/db_impl_files.cc:309] [JOB 0] Delete /dev/shm/dbbench/000040.sst type=2 #40 -- OK 2017/06/26-15:17:25.553205 7fd5a61a5800 EVENT_LOG_v1 {"time_micros": 1498515445553199, "job": 0, "event": "table_file_deletion", "file_number": 40} ``` SST Files remaining in the dbbench dir, after db_bench execution completed: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ ls -l /dev/shm//dbbench/*.sst -rw-r--r--. 1 svemuri users 30749887 Jun 26 15:17 /dev/shm//dbbench/000042.sst -rw-r--r--. 1 svemuri users 30768779 Jun 26 15:17 /dev/shm//dbbench/000044.sst -rw-r--r--. 1 svemuri users 30757481 Jun 26 15:17 /dev/shm//dbbench/000046.sst ``` Closes https://github.com/facebook/rocksdb/pull/2480 Differential Revision: D5305116 Pulled By: sagar0 fbshipit-source-id: 3e5cfcf5dd07ed2211b5b37492eb235b45139174
2017-06-28 02:02:20 +02:00
private:
Compaction* PickTTLCompaction(const std::string& cf_name,
const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* version,
LogBuffer* log_buffer);
Compaction* PickSizeCompaction(const std::string& cf_name,
const MutableCFOptions& mutable_cf_options,
VersionStorageInfo* version,
LogBuffer* log_buffer);
};
class NullCompactionPicker : public CompactionPicker {
public:
NullCompactionPicker(const ImmutableCFOptions& ioptions,
const InternalKeyComparator* icmp)
: CompactionPicker(ioptions, icmp) {}
virtual ~NullCompactionPicker() {}
// Always return "nullptr"
Compaction* PickCompaction(const std::string& /*cf_name*/,
const MutableCFOptions& /*mutable_cf_options*/,
VersionStorageInfo* /*vstorage*/,
LogBuffer* /*log_buffer*/) override {
return nullptr;
}
// Always return "nullptr"
Compaction* CompactRange(const std::string& /*cf_name*/,
const MutableCFOptions& /*mutable_cf_options*/,
VersionStorageInfo* /*vstorage*/,
int /*input_level*/, int /*output_level*/,
uint32_t /*output_path_id*/,
const InternalKey* /*begin*/,
const InternalKey* /*end*/,
InternalKey** /*compaction_end*/,
bool* /*manual_conflict*/) override {
return nullptr;
}
// Always returns false.
virtual bool NeedsCompaction(
const VersionStorageInfo* /*vstorage*/) const override {
return false;
}
};
#endif // !ROCKSDB_LITE
CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
const VersionStorageInfo* vstorage,
const MutableCFOptions& mutable_cf_options,
int level, int base_level,
const bool enable_compression = true);
} // namespace rocksdb