|
|
|
// 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
|
|
|
|
|
|
|
|
#include <string>
|
|
|
|
#include "rocksdb/comparator.h"
|
|
|
|
#include "rocksdb/iterator.h"
|
|
|
|
#include "rocksdb/status.h"
|
|
|
|
|
|
|
|
namespace rocksdb {
|
|
|
|
|
|
|
|
class PinnedIteratorsManager;
|
|
|
|
|
|
|
|
class InternalIterator : public Cleanable {
|
|
|
|
public:
|
|
|
|
InternalIterator() {}
|
|
|
|
virtual ~InternalIterator() {}
|
|
|
|
|
|
|
|
// An iterator is either positioned at a key/value pair, or
|
|
|
|
// not valid. This method returns true iff the iterator is valid.
|
|
|
|
virtual bool Valid() const = 0;
|
|
|
|
|
|
|
|
// Position at the first key in the source. The iterator is Valid()
|
|
|
|
// after this call iff the source is not empty.
|
|
|
|
virtual void SeekToFirst() = 0;
|
|
|
|
|
|
|
|
// Position at the last key in the source. The iterator is
|
|
|
|
// Valid() after this call iff the source is not empty.
|
|
|
|
virtual void SeekToLast() = 0;
|
|
|
|
|
|
|
|
// Position at the first key in the source that at or past target
|
|
|
|
// The iterator is Valid() after this call iff the source contains
|
|
|
|
// an entry that comes at or past target.
|
|
|
|
virtual void Seek(const Slice& target) = 0;
|
|
|
|
|
|
|
|
// Position at the first key in the source that at or before target
|
|
|
|
// The iterator is Valid() after this call iff the source contains
|
|
|
|
// an entry that comes at or before target.
|
|
|
|
virtual void SeekForPrev(const Slice& target) = 0;
|
|
|
|
|
|
|
|
// Moves to the next entry in the source. After this call, Valid() is
|
|
|
|
// true iff the iterator was not positioned at the last entry in the source.
|
|
|
|
// REQUIRES: Valid()
|
|
|
|
virtual void Next() = 0;
|
|
|
|
|
|
|
|
// Moves to the previous entry in the source. After this call, Valid() is
|
|
|
|
// true iff the iterator was not positioned at the first entry in source.
|
|
|
|
// REQUIRES: Valid()
|
|
|
|
virtual void Prev() = 0;
|
|
|
|
|
|
|
|
// Return the key for the current entry. The underlying storage for
|
|
|
|
// the returned slice is valid only until the next modification of
|
|
|
|
// the iterator.
|
|
|
|
// REQUIRES: Valid()
|
|
|
|
virtual Slice key() const = 0;
|
|
|
|
|
|
|
|
// Return the value for the current entry. The underlying storage for
|
|
|
|
// the returned slice is valid only until the next modification of
|
|
|
|
// the iterator.
|
|
|
|
// REQUIRES: !AtEnd() && !AtStart()
|
|
|
|
virtual Slice value() const = 0;
|
|
|
|
|
|
|
|
// If an error has occurred, return it. Else return an ok status.
|
|
|
|
// If non-blocking IO is requested and this operation cannot be
|
|
|
|
// satisfied without doing some IO, then this returns Status::Incomplete().
|
|
|
|
virtual Status status() const = 0;
|
|
|
|
|
|
|
|
// Pass the PinnedIteratorsManager to the Iterator, most Iterators dont
|
|
|
|
// communicate with PinnedIteratorsManager so default implementation is no-op
|
|
|
|
// but for Iterators that need to communicate with PinnedIteratorsManager
|
|
|
|
// they will implement this function and use the passed pointer to communicate
|
|
|
|
// with PinnedIteratorsManager.
|
|
|
|
virtual void SetPinnedItersMgr(PinnedIteratorsManager* pinned_iters_mgr) {}
|
|
|
|
|
|
|
|
// If true, this means that the Slice returned by key() is valid as long as
|
|
|
|
// PinnedIteratorsManager::ReleasePinnedData is not called and the
|
|
|
|
// Iterator is not deleted.
|
|
|
|
//
|
|
|
|
// IsKeyPinned() is guaranteed to always return true if
|
|
|
|
// - Iterator is created with ReadOptions::pin_data = true
|
|
|
|
// - DB tables were created with BlockBasedTableOptions::use_delta_encoding
|
|
|
|
// set to false.
|
|
|
|
virtual bool IsKeyPinned() const { return false; }
|
|
|
|
|
Introduce FullMergeV2 (eliminate memcpy from merge operators)
Summary:
This diff update the code to pin the merge operator operands while the merge operation is done, so that we can eliminate the memcpy cost, to do that we need a new public API for FullMerge that replace the std::deque<std::string> with std::vector<Slice>
This diff is stacked on top of D56493 and D56511
In this diff we
- Update FullMergeV2 arguments to be encapsulated in MergeOperationInput and MergeOperationOutput which will make it easier to add new arguments in the future
- Replace std::deque<std::string> with std::vector<Slice> to pass operands
- Replace MergeContext std::deque with std::vector (based on a simple benchmark I ran https://gist.github.com/IslamAbdelRahman/78fc86c9ab9f52b1df791e58943fb187)
- Allow FullMergeV2 output to be an existing operand
```
[Everything in Memtable | 10K operands | 10 KB each | 1 operand per key]
DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --merge_keys=10000 --num=10000 --disable_auto_compactions --value_size=10240 --write_buffer_size=1000000000
[FullMergeV2]
readseq : 0.607 micros/op 1648235 ops/sec; 16121.2 MB/s
readseq : 0.478 micros/op 2091546 ops/sec; 20457.2 MB/s
readseq : 0.252 micros/op 3972081 ops/sec; 38850.5 MB/s
readseq : 0.237 micros/op 4218328 ops/sec; 41259.0 MB/s
readseq : 0.247 micros/op 4043927 ops/sec; 39553.2 MB/s
[master]
readseq : 3.935 micros/op 254140 ops/sec; 2485.7 MB/s
readseq : 3.722 micros/op 268657 ops/sec; 2627.7 MB/s
readseq : 3.149 micros/op 317605 ops/sec; 3106.5 MB/s
readseq : 3.125 micros/op 320024 ops/sec; 3130.1 MB/s
readseq : 4.075 micros/op 245374 ops/sec; 2400.0 MB/s
```
```
[Everything in Memtable | 10K operands | 10 KB each | 10 operand per key]
DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --merge_keys=1000 --num=10000 --disable_auto_compactions --value_size=10240 --write_buffer_size=1000000000
[FullMergeV2]
readseq : 3.472 micros/op 288018 ops/sec; 2817.1 MB/s
readseq : 2.304 micros/op 434027 ops/sec; 4245.2 MB/s
readseq : 1.163 micros/op 859845 ops/sec; 8410.0 MB/s
readseq : 1.192 micros/op 838926 ops/sec; 8205.4 MB/s
readseq : 1.250 micros/op 800000 ops/sec; 7824.7 MB/s
[master]
readseq : 24.025 micros/op 41623 ops/sec; 407.1 MB/s
readseq : 18.489 micros/op 54086 ops/sec; 529.0 MB/s
readseq : 18.693 micros/op 53495 ops/sec; 523.2 MB/s
readseq : 23.621 micros/op 42335 ops/sec; 414.1 MB/s
readseq : 18.775 micros/op 53262 ops/sec; 521.0 MB/s
```
```
[Everything in Block cache | 10K operands | 10 KB each | 1 operand per key]
[FullMergeV2]
$ DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --num=100000 --db="/dev/shm/merge-random-10K-10KB" --cache_size=1000000000 --use_existing_db --disable_auto_compactions
readseq : 14.741 micros/op 67837 ops/sec; 663.5 MB/s
readseq : 1.029 micros/op 971446 ops/sec; 9501.6 MB/s
readseq : 0.974 micros/op 1026229 ops/sec; 10037.4 MB/s
readseq : 0.965 micros/op 1036080 ops/sec; 10133.8 MB/s
readseq : 0.943 micros/op 1060657 ops/sec; 10374.2 MB/s
[master]
readseq : 16.735 micros/op 59755 ops/sec; 584.5 MB/s
readseq : 3.029 micros/op 330151 ops/sec; 3229.2 MB/s
readseq : 3.136 micros/op 318883 ops/sec; 3119.0 MB/s
readseq : 3.065 micros/op 326245 ops/sec; 3191.0 MB/s
readseq : 3.014 micros/op 331813 ops/sec; 3245.4 MB/s
```
```
[Everything in Block cache | 10K operands | 10 KB each | 10 operand per key]
DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --num=100000 --db="/dev/shm/merge-random-10-operands-10K-10KB" --cache_size=1000000000 --use_existing_db --disable_auto_compactions
[FullMergeV2]
readseq : 24.325 micros/op 41109 ops/sec; 402.1 MB/s
readseq : 1.470 micros/op 680272 ops/sec; 6653.7 MB/s
readseq : 1.231 micros/op 812347 ops/sec; 7945.5 MB/s
readseq : 1.091 micros/op 916590 ops/sec; 8965.1 MB/s
readseq : 1.109 micros/op 901713 ops/sec; 8819.6 MB/s
[master]
readseq : 27.257 micros/op 36687 ops/sec; 358.8 MB/s
readseq : 4.443 micros/op 225073 ops/sec; 2201.4 MB/s
readseq : 5.830 micros/op 171526 ops/sec; 1677.7 MB/s
readseq : 4.173 micros/op 239635 ops/sec; 2343.8 MB/s
readseq : 4.150 micros/op 240963 ops/sec; 2356.8 MB/s
```
Test Plan: COMPILE_WITH_ASAN=1 make check -j64
Reviewers: yhchiang, andrewkr, sdong
Reviewed By: sdong
Subscribers: lovro, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D57075
8 years ago
|
|
|
// If true, this means that the Slice returned by value() is valid as long as
|
|
|
|
// PinnedIteratorsManager::ReleasePinnedData is not called and the
|
Introduce FullMergeV2 (eliminate memcpy from merge operators)
Summary:
This diff update the code to pin the merge operator operands while the merge operation is done, so that we can eliminate the memcpy cost, to do that we need a new public API for FullMerge that replace the std::deque<std::string> with std::vector<Slice>
This diff is stacked on top of D56493 and D56511
In this diff we
- Update FullMergeV2 arguments to be encapsulated in MergeOperationInput and MergeOperationOutput which will make it easier to add new arguments in the future
- Replace std::deque<std::string> with std::vector<Slice> to pass operands
- Replace MergeContext std::deque with std::vector (based on a simple benchmark I ran https://gist.github.com/IslamAbdelRahman/78fc86c9ab9f52b1df791e58943fb187)
- Allow FullMergeV2 output to be an existing operand
```
[Everything in Memtable | 10K operands | 10 KB each | 1 operand per key]
DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --merge_keys=10000 --num=10000 --disable_auto_compactions --value_size=10240 --write_buffer_size=1000000000
[FullMergeV2]
readseq : 0.607 micros/op 1648235 ops/sec; 16121.2 MB/s
readseq : 0.478 micros/op 2091546 ops/sec; 20457.2 MB/s
readseq : 0.252 micros/op 3972081 ops/sec; 38850.5 MB/s
readseq : 0.237 micros/op 4218328 ops/sec; 41259.0 MB/s
readseq : 0.247 micros/op 4043927 ops/sec; 39553.2 MB/s
[master]
readseq : 3.935 micros/op 254140 ops/sec; 2485.7 MB/s
readseq : 3.722 micros/op 268657 ops/sec; 2627.7 MB/s
readseq : 3.149 micros/op 317605 ops/sec; 3106.5 MB/s
readseq : 3.125 micros/op 320024 ops/sec; 3130.1 MB/s
readseq : 4.075 micros/op 245374 ops/sec; 2400.0 MB/s
```
```
[Everything in Memtable | 10K operands | 10 KB each | 10 operand per key]
DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --merge_keys=1000 --num=10000 --disable_auto_compactions --value_size=10240 --write_buffer_size=1000000000
[FullMergeV2]
readseq : 3.472 micros/op 288018 ops/sec; 2817.1 MB/s
readseq : 2.304 micros/op 434027 ops/sec; 4245.2 MB/s
readseq : 1.163 micros/op 859845 ops/sec; 8410.0 MB/s
readseq : 1.192 micros/op 838926 ops/sec; 8205.4 MB/s
readseq : 1.250 micros/op 800000 ops/sec; 7824.7 MB/s
[master]
readseq : 24.025 micros/op 41623 ops/sec; 407.1 MB/s
readseq : 18.489 micros/op 54086 ops/sec; 529.0 MB/s
readseq : 18.693 micros/op 53495 ops/sec; 523.2 MB/s
readseq : 23.621 micros/op 42335 ops/sec; 414.1 MB/s
readseq : 18.775 micros/op 53262 ops/sec; 521.0 MB/s
```
```
[Everything in Block cache | 10K operands | 10 KB each | 1 operand per key]
[FullMergeV2]
$ DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --num=100000 --db="/dev/shm/merge-random-10K-10KB" --cache_size=1000000000 --use_existing_db --disable_auto_compactions
readseq : 14.741 micros/op 67837 ops/sec; 663.5 MB/s
readseq : 1.029 micros/op 971446 ops/sec; 9501.6 MB/s
readseq : 0.974 micros/op 1026229 ops/sec; 10037.4 MB/s
readseq : 0.965 micros/op 1036080 ops/sec; 10133.8 MB/s
readseq : 0.943 micros/op 1060657 ops/sec; 10374.2 MB/s
[master]
readseq : 16.735 micros/op 59755 ops/sec; 584.5 MB/s
readseq : 3.029 micros/op 330151 ops/sec; 3229.2 MB/s
readseq : 3.136 micros/op 318883 ops/sec; 3119.0 MB/s
readseq : 3.065 micros/op 326245 ops/sec; 3191.0 MB/s
readseq : 3.014 micros/op 331813 ops/sec; 3245.4 MB/s
```
```
[Everything in Block cache | 10K operands | 10 KB each | 10 operand per key]
DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --num=100000 --db="/dev/shm/merge-random-10-operands-10K-10KB" --cache_size=1000000000 --use_existing_db --disable_auto_compactions
[FullMergeV2]
readseq : 24.325 micros/op 41109 ops/sec; 402.1 MB/s
readseq : 1.470 micros/op 680272 ops/sec; 6653.7 MB/s
readseq : 1.231 micros/op 812347 ops/sec; 7945.5 MB/s
readseq : 1.091 micros/op 916590 ops/sec; 8965.1 MB/s
readseq : 1.109 micros/op 901713 ops/sec; 8819.6 MB/s
[master]
readseq : 27.257 micros/op 36687 ops/sec; 358.8 MB/s
readseq : 4.443 micros/op 225073 ops/sec; 2201.4 MB/s
readseq : 5.830 micros/op 171526 ops/sec; 1677.7 MB/s
readseq : 4.173 micros/op 239635 ops/sec; 2343.8 MB/s
readseq : 4.150 micros/op 240963 ops/sec; 2356.8 MB/s
```
Test Plan: COMPILE_WITH_ASAN=1 make check -j64
Reviewers: yhchiang, andrewkr, sdong
Reviewed By: sdong
Subscribers: lovro, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D57075
8 years ago
|
|
|
// Iterator is not deleted.
|
|
|
|
virtual bool IsValuePinned() const { return false; }
|
|
|
|
|
|
|
|
virtual Status GetProperty(std::string prop_name, std::string* prop) {
|
|
|
|
return Status::NotSupported("");
|
|
|
|
}
|
|
|
|
|
|
|
|
protected:
|
|
|
|
void SeekForPrevImpl(const Slice& target, const Comparator* cmp) {
|
|
|
|
Seek(target);
|
|
|
|
if (!Valid()) {
|
|
|
|
SeekToLast();
|
|
|
|
}
|
|
|
|
while (Valid() && cmp->Compare(target, key()) < 0) {
|
|
|
|
Prev();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
// No copying allowed
|
|
|
|
InternalIterator(const InternalIterator&) = delete;
|
|
|
|
InternalIterator& operator=(const InternalIterator&) = delete;
|
|
|
|
};
|
|
|
|
|
|
|
|
// Return an empty iterator (yields nothing).
|
|
|
|
extern InternalIterator* NewEmptyInternalIterator();
|
|
|
|
|
|
|
|
// Return an empty iterator with the specified status.
|
|
|
|
extern InternalIterator* NewErrorInternalIterator(const Status& status);
|
|
|
|
|
|
|
|
} // namespace rocksdb
|