You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/util/user_comparator_wrapper.h

85 lines
3.0 KiB

// 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 "monitoring/perf_context_imp.h"
#include "rocksdb/comparator.h"
namespace ROCKSDB_NAMESPACE {
// Wrapper of user comparator, with auto increment to
// perf_context.user_key_comparison_count.
class UserComparatorWrapper final : public Comparator {
public:
Separate internal and user key comparators in `BlockIter` (#6944) Summary: Replace `BlockIter::comparator_` and `IndexBlockIter::user_comparator_wrapper_` with a concrete `UserComparatorWrapper` and `InternalKeyComparator`. The motivation for this change was the inconvenience of not knowing the concrete type of `BlockIter::comparator_`, which prevented calling specialized internal key comparison functions to optimize comparison of keys with global seqno applied. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6944 Test Plan: benchmark setup -- single file DBs, in-memory, no compression. "normal_db" created by regular flush; "ingestion_db" created by ingesting a file. Both DBs have same contents. ``` $ TEST_TMPDIR=/dev/shm/normal_db/ ./db_bench -benchmarks=fillrandom,compact -write_buffer_size=10485760000 -disable_auto_compactions=true -compression_type=none -num=1000000 $ ./ldb write_extern_sst ./tmp.sst --db=/dev/shm/ingestion_db/dbbench/ --compression_type=no --hex --create_if_missing < <(./sst_dump --command=scan --output_hex --file=/dev/shm/normal_db/dbbench/000007.sst | awk 'began {print "0x" substr($1, 2, length($1) - 2), "==>", "0x" $5} ; /^Sst file format: block-based/ {began=1}') $ ./ldb ingest_extern_sst ./tmp.sst --db=/dev/shm/ingestion_db/dbbench/ ``` benchmark run command: ``` $ TEST_TMPDIR=/dev/shm/$DB/ ./db_bench -benchmarks=seekrandom -seek_nexts=$SEEK_NEXT -use_existing_db=true -cache_index_and_filter_blocks=false -num=1000000 -cache_size=0 -threads=1 -reads=200000000 -mmap_read=1 -verify_checksum=false ``` results: perf improved marginally for ingestion_db and did not change significantly for normal_db: SEEK_NEXT | DB | code | ops/sec | % change -- | -- | -- | -- | -- 0 | normal_db | master | 350880 |   0 | normal_db | PR6944 | 351040 | 0.0 0 | ingestion_db | master | 343255 |   0 | ingestion_db | PR6944 | 349424 | 1.8 10 | normal_db | master | 218711 |   10 | normal_db | PR6944 | 217892 | -0.4 10 | ingestion_db | master | 220334 |   10 | ingestion_db | PR6944 | 226437 | 2.8 Reviewed By: pdillinger Differential Revision: D21924676 Pulled By: ajkr fbshipit-source-id: ea4288a2eefa8112eb6c651a671c1de18c12e538
4 years ago
// `UserComparatorWrapper`s constructed with the default constructor are not
// usable and will segfault on any attempt to use them for comparisons.
UserComparatorWrapper() : user_comparator_(nullptr) {}
explicit UserComparatorWrapper(const Comparator* const user_cmp)
Iterator with timestamp (#6255) Summary: Preliminary support for iterator with user timestamp. Current implementation does not consider merge operator and reverse iterator. Auto compaction is also disabled in unit tests. Create an iterator with timestamp. ``` ... read_opts.timestamp = &ts; auto* iter = db->NewIterator(read_opts); // target is key without timestamp. for (iter->Seek(target); iter->Valid(); iter->Next()) {} for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {} delete iter; read_opts.timestamp = &ts1; // lower_bound and upper_bound are without timestamp. read_opts.iterate_lower_bound = &lower_bound; read_opts.iterate_upper_bound = &upper_bound; auto* iter1 = db->NewIterator(read_opts); // Do Seek or SeekToFirst() delete iter1; ``` Test plan (dev server) ``` $make check ``` Simple benchmarking (dev server) 1. The overhead introduced by this PR even when timestamp is disabled. key size: 16 bytes value size: 100 bytes Entries: 1000000 Data reside in main memory, and try to stress iterator. Repeated three times on master and this PR. - Seek without next ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 ``` master: 159047.0 ops/sec this PR: 158922.3 ops/sec (2% drop in throughput) - Seek and next 10 times ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 -seek_nexts=10 ``` master: 109539.3 ops/sec this PR: 107519.7 ops/sec (2% drop in throughput) Pull Request resolved: https://github.com/facebook/rocksdb/pull/6255 Differential Revision: D19438227 Pulled By: riversand963 fbshipit-source-id: b66b4979486f8474619f4aa6bdd88598870b0746
4 years ago
: Comparator(user_cmp->timestamp_size()), user_comparator_(user_cmp) {}
~UserComparatorWrapper() = default;
const Comparator* user_comparator() const { return user_comparator_; }
int Compare(const Slice& a, const Slice& b) const override {
PERF_COUNTER_ADD(user_key_comparison_count, 1);
return user_comparator_->Compare(a, b);
}
bool Equal(const Slice& a, const Slice& b) const override {
PERF_COUNTER_ADD(user_key_comparison_count, 1);
return user_comparator_->Equal(a, b);
}
const char* Name() const override { return user_comparator_->Name(); }
void FindShortestSeparator(std::string* start,
const Slice& limit) const override {
return user_comparator_->FindShortestSeparator(start, limit);
}
void FindShortSuccessor(std::string* key) const override {
return user_comparator_->FindShortSuccessor(key);
}
const Comparator* GetRootComparator() const override {
return user_comparator_->GetRootComparator();
}
bool IsSameLengthImmediateSuccessor(const Slice& s,
const Slice& t) const override {
return user_comparator_->IsSameLengthImmediateSuccessor(s, t);
}
bool CanKeysWithDifferentByteContentsBeEqual() const override {
return user_comparator_->CanKeysWithDifferentByteContentsBeEqual();
}
Iterator with timestamp (#6255) Summary: Preliminary support for iterator with user timestamp. Current implementation does not consider merge operator and reverse iterator. Auto compaction is also disabled in unit tests. Create an iterator with timestamp. ``` ... read_opts.timestamp = &ts; auto* iter = db->NewIterator(read_opts); // target is key without timestamp. for (iter->Seek(target); iter->Valid(); iter->Next()) {} for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {} delete iter; read_opts.timestamp = &ts1; // lower_bound and upper_bound are without timestamp. read_opts.iterate_lower_bound = &lower_bound; read_opts.iterate_upper_bound = &upper_bound; auto* iter1 = db->NewIterator(read_opts); // Do Seek or SeekToFirst() delete iter1; ``` Test plan (dev server) ``` $make check ``` Simple benchmarking (dev server) 1. The overhead introduced by this PR even when timestamp is disabled. key size: 16 bytes value size: 100 bytes Entries: 1000000 Data reside in main memory, and try to stress iterator. Repeated three times on master and this PR. - Seek without next ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 ``` master: 159047.0 ops/sec this PR: 158922.3 ops/sec (2% drop in throughput) - Seek and next 10 times ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 -seek_nexts=10 ``` master: 109539.3 ops/sec this PR: 107519.7 ops/sec (2% drop in throughput) Pull Request resolved: https://github.com/facebook/rocksdb/pull/6255 Differential Revision: D19438227 Pulled By: riversand963 fbshipit-source-id: b66b4979486f8474619f4aa6bdd88598870b0746
4 years ago
int CompareTimestamp(const Slice& ts1, const Slice& ts2) const override {
return user_comparator_->CompareTimestamp(ts1, ts2);
}
using Comparator::CompareWithoutTimestamp;
int CompareWithoutTimestamp(const Slice& a, bool a_has_ts, const Slice& b,
bool b_has_ts) const override {
PERF_COUNTER_ADD(user_key_comparison_count, 1);
return user_comparator_->CompareWithoutTimestamp(a, a_has_ts, b, b_has_ts);
}
Enable backward iterator for keys with user-defined timestamp (#8035) Summary: This PR does the following: - Enable backward iteration for keys with user-defined timestamp. Note that merge, single delete, range delete are not supported yet. - Introduces a new helper API `Comparator::EqualWithoutTimestamp()`. - Fix a typo in `SetTimestamp()`. - Add/update unit tests Run db_bench (built with DEBUG_LEVEL=0) to demonstrate that no overhead is introduced for CPU-intensive workloads with a lot of `Prev()`. Also provided results of iterating keys with timestamps. 1. Disable timestamp, run: ``` ./db_bench -db=/dev/shm/rocksdb -disable_wal=1 -benchmarks=fillseq,seekrandom[-W1-X6] -reverse_iterator=1 -seek_nexts=5 ``` Results: > Baseline > - seekrandom [AVG 6 runs] : 96115 ops/sec; 53.2 MB/sec > - seekrandom [MEDIAN 6 runs] : 98075 ops/sec; 54.2 MB/sec > > This PR > - seekrandom [AVG 6 runs] : 95521 ops/sec; 52.8 MB/sec > - seekrandom [MEDIAN 6 runs] : 96338 ops/sec; 53.3 MB/sec 2. Enable timestamp, run: ``` ./db_bench -user_timestamp_size=8 -db=/dev/shm/rocksdb -disable_wal=1 -benchmarks=fillseq,seekrandom[-W1-X6] -reverse_iterator=1 -seek_nexts=5 ``` Result: > Baseline: not supported > > This PR > - seekrandom [AVG 6 runs] : 90514 ops/sec; 50.1 MB/sec > - seekrandom [MEDIAN 6 runs] : 90834 ops/sec; 50.2 MB/sec Pull Request resolved: https://github.com/facebook/rocksdb/pull/8035 Reviewed By: ltamasi Differential Revision: D26926668 Pulled By: riversand963 fbshipit-source-id: 95330cc2242397c03e09d29e5417dfb0adc98ef5
3 years ago
bool EqualWithoutTimestamp(const Slice& a, const Slice& b) const override {
return user_comparator_->EqualWithoutTimestamp(a, b);
}
private:
const Comparator* user_comparator_;
};
} // namespace ROCKSDB_NAMESPACE