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/db/db_iter.cc

1227 lines
41 KiB

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same 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.
#include "db/db_iter.h"
#include <stdexcept>
[RocksDB] [MergeOperator] The new Merge Interface! Uses merge sequences. Summary: Here are the major changes to the Merge Interface. It has been expanded to handle cases where the MergeOperator is not associative. It does so by stacking up merge operations while scanning through the key history (i.e.: during Get() or Compaction), until a valid Put/Delete/end-of-history is encountered; it then applies all of the merge operations in the correct sequence starting with the base/sentinel value. I have also introduced an "AssociativeMerge" function which allows the user to take advantage of associative merge operations (such as in the case of counters). The implementation will always attempt to merge the operations/operands themselves together when they are encountered, and will resort to the "stacking" method if and only if the "associative-merge" fails. This implementation is conjectured to allow MergeOperator to handle the general case, while still providing the user with the ability to take advantage of certain efficiencies in their own merge-operator / data-structure. NOTE: This is a preliminary diff. This must still go through a lot of review, revision, and testing. Feedback welcome! Test Plan: -This is a preliminary diff. I have only just begun testing/debugging it. -I will be testing this with the existing MergeOperator use-cases and unit-tests (counters, string-append, and redis-lists) -I will be "desk-checking" and walking through the code with the help gdb. -I will find a way of stress-testing the new interface / implementation using db_bench, db_test, merge_test, and/or db_stress. -I will ensure that my tests cover all cases: Get-Memtable, Get-Immutable-Memtable, Get-from-Disk, Iterator-Range-Scan, Flush-Memtable-to-L0, Compaction-L0-L1, Compaction-Ln-L(n+1), Put/Delete found, Put/Delete not-found, end-of-history, end-of-file, etc. -A lot of feedback from the reviewers. Reviewers: haobo, dhruba, zshao, emayanke Reviewed By: haobo CC: leveldb Differential Revision: https://reviews.facebook.net/D11499
11 years ago
#include <deque>
#include <string>
#include <limits>
#include "db/dbformat.h"
Eliminate std::deque initialization while iterating over merge operands Summary: This patch is similar to D52563, When we iterate over a DB with merge operands we keep creating std::queue to store the operands, optimize this by reusing merge_operands_ data member Before the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.757 micros/op 266141 ops/sec; 29.4 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.413 micros/op 2423538 ops/sec; 268.1 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.451 micros/op 2219071 ops/sec; 245.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.420 micros/op 2382039 ops/sec; 263.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.408 micros/op 2452017 ops/sec; 271.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.947 micros/op 253376 ops/sec; 28.0 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.441 micros/op 2266473 ops/sec; 250.7 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.471 micros/op 2122033 ops/sec; 234.8 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.440 micros/op 2271407 ops/sec; 251.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.429 micros/op 2331471 ops/sec; 257.9 MB/s ``` with the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 4.080 micros/op 245092 ops/sec; 27.1 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.308 micros/op 3241843 ops/sec; 358.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.312 micros/op 3200408 ops/sec; 354.0 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.332 micros/op 3013962 ops/sec; 333.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.300 micros/op 3328017 ops/sec; 368.2 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.973 micros/op 251705 ops/sec; 27.8 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.320 micros/op 3123752 ops/sec; 345.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.335 micros/op 2986641 ops/sec; 330.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.339 micros/op 2950047 ops/sec; 326.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.319 micros/op 3131565 ops/sec; 346.4 MB/s ``` Test Plan: make check -j64 Reviewers: yhchiang, andrewkr, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56031
9 years ago
#include "db/merge_context.h"
#include "db/merge_helper.h"
#include "db/pinned_iterators_manager.h"
#include "monitoring/perf_context_imp.h"
#include "port/port.h"
#include "rocksdb/env.h"
#include "rocksdb/iterator.h"
#include "rocksdb/merge_operator.h"
#include "rocksdb/options.h"
#include "table/internal_iterator.h"
#include "util/arena.h"
#include "util/filename.h"
#include "util/logging.h"
#include "util/mutexlock.h"
#include "util/string_util.h"
namespace rocksdb {
#if 0
static void DumpInternalIter(Iterator* iter) {
for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
ParsedInternalKey k;
if (!ParseInternalKey(iter->key(), &k)) {
fprintf(stderr, "Corrupt '%s'\n", EscapeString(iter->key()).c_str());
} else {
fprintf(stderr, "@ '%s'\n", k.DebugString().c_str());
}
}
}
#endif
// Memtables and sstables that make the DB representation contain
// (userkey,seq,type) => uservalue entries. DBIter
// combines multiple entries for the same userkey found in the DB
// representation into a single entry while accounting for sequence
// numbers, deletion markers, overwrites, etc.
class DBIter: public Iterator {
public:
// The following is grossly complicated. TODO: clean it up
// Which direction is the iterator currently moving?
// (1) When moving forward, the internal iterator is positioned at
// the exact entry that yields this->key(), this->value()
// (2) When moving backwards, the internal iterator is positioned
// just before all entries whose user key == this->key().
enum Direction {
kForward,
kReverse
};
// LocalStatistics contain Statistics counters that will be aggregated per
// each iterator instance and then will be sent to the global statistics when
// the iterator is destroyed.
//
// The purpose of this approach is to avoid perf regression happening
// when multiple threads bump the atomic counters from a DBIter::Next().
struct LocalStatistics {
explicit LocalStatistics() { ResetCounters(); }
void ResetCounters() {
next_count_ = 0;
next_found_count_ = 0;
prev_count_ = 0;
prev_found_count_ = 0;
bytes_read_ = 0;
}
void BumpGlobalStatistics(Statistics* global_statistics) {
RecordTick(global_statistics, NUMBER_DB_NEXT, next_count_);
RecordTick(global_statistics, NUMBER_DB_NEXT_FOUND, next_found_count_);
RecordTick(global_statistics, NUMBER_DB_PREV, prev_count_);
RecordTick(global_statistics, NUMBER_DB_PREV_FOUND, prev_found_count_);
RecordTick(global_statistics, ITER_BYTES_READ, bytes_read_);
ResetCounters();
}
// Map to Tickers::NUMBER_DB_NEXT
uint64_t next_count_;
// Map to Tickers::NUMBER_DB_NEXT_FOUND
uint64_t next_found_count_;
// Map to Tickers::NUMBER_DB_PREV
uint64_t prev_count_;
// Map to Tickers::NUMBER_DB_PREV_FOUND
uint64_t prev_found_count_;
// Map to Tickers::ITER_BYTES_READ
uint64_t bytes_read_;
};
DBIter(Env* env, const ImmutableCFOptions& ioptions, const Comparator* cmp,
InternalIterator* iter, SequenceNumber s, bool arena_mode,
uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
const Slice* iterate_upper_bound = nullptr,
bool prefix_same_as_start = false, bool pin_data = false,
bool total_order_seek = false,
uint64_t max_skippable_internal_keys = 0)
: arena_mode_(arena_mode),
env_(env),
logger_(ioptions.info_log),
user_comparator_(cmp),
merge_operator_(ioptions.merge_operator),
iter_(iter),
sequence_(s),
direction_(kForward),
valid_(false),
current_entry_is_merged_(false),
statistics_(ioptions.statistics),
version_number_(version_number),
iterate_upper_bound_(iterate_upper_bound),
Introduce ReadOptions::pin_data (support zero copy for keys) Summary: This patch update the Iterator API to introduce new functions that allow users to keep the Slices returned by key() valid as long as the Iterator is not deleted ReadOptions::pin_data : If true keep loaded blocks in memory as long as the iterator is not deleted Iterator::IsKeyPinned() : If true, this mean that the Slice returned by key() is valid as long as the iterator is not deleted Also add a new option BlockBasedTableOptions::use_delta_encoding to allow users to disable delta_encoding if needed. Benchmark results (using https://phabricator.fb.com/P20083553) ``` // $ du -h /home/tec/local/normal.4K.Snappy/db10077 // 6.1G /home/tec/local/normal.4K.Snappy/db10077 // $ du -h /home/tec/local/zero.8K.LZ4/db10077 // 6.4G /home/tec/local/zero.8K.LZ4/db10077 // Benchmarks for shard db10077 // _build/opt/rocks/benchmark/rocks_copy_benchmark \ // --normal_db_path="/home/tec/local/normal.4K.Snappy/db10077" \ // --zero_db_path="/home/tec/local/zero.8K.LZ4/db10077" // First run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 1.73s 576.97m // BM_StringPiece 103.74% 1.67s 598.55m // ============================================================================ // Match rate : 1000000 / 1000000 // Second run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 611.99ms 1.63 // BM_StringPiece 203.76% 300.35ms 3.33 // ============================================================================ // Match rate : 1000000 / 1000000 ``` Test Plan: Unit tests Reviewers: sdong, igor, anthony, yhchiang, rven Reviewed By: rven Subscribers: dhruba, lovro, adsharma Differential Revision: https://reviews.facebook.net/D48999
9 years ago
prefix_same_as_start_(prefix_same_as_start),
pin_thru_lifetime_(pin_data),
total_order_seek_(total_order_seek),
range_del_agg_(ioptions.internal_comparator, s,
true /* collapse_deletions */) {
RecordTick(statistics_, NO_ITERATORS);
prefix_extractor_ = ioptions.prefix_extractor;
max_skip_ = max_sequential_skip_in_iterations;
max_skippable_internal_keys_ = max_skippable_internal_keys;
if (pin_thru_lifetime_) {
pinned_iters_mgr_.StartPinning();
}
if (iter_) {
iter_->SetPinnedItersMgr(&pinned_iters_mgr_);
}
}
virtual ~DBIter() {
Eliminate memcpy in Iterator::Prev() by pinning blocks for keys spanning multiple blocks Summary: This diff is stacked on top of this diff https://reviews.facebook.net/D56493 The current Iterator::Prev() implementation need to copy every value since the underlying Iterator may move after reading the value. This can be optimized by making sure that the block containing the value is pinned until the Iterator move. which will improve the throughput by up to 1.5X master ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.449 micros/op 2225887 ops/sec; 246.2 MB/s readreverse : 0.433 micros/op 2311508 ops/sec; 255.7 MB/s readreverse : 0.436 micros/op 2294335 ops/sec; 253.8 MB/s readreverse : 0.471 micros/op 2121295 ops/sec; 234.7 MB/s readreverse : 0.465 micros/op 2152227 ops/sec; 238.1 MB/s readreverse : 0.454 micros/op 2203011 ops/sec; 243.7 MB/s readreverse : 0.451 micros/op 2216095 ops/sec; 245.2 MB/s readreverse : 0.462 micros/op 2162447 ops/sec; 239.2 MB/s readreverse : 0.476 micros/op 2099151 ops/sec; 232.2 MB/s readreverse : 0.472 micros/op 2120710 ops/sec; 234.6 MB/s avg : 242.34 MB/s ==> 1000000_Keys_1KB.txt <== readreverse : 1.013 micros/op 986793 ops/sec; 978.7 MB/s readreverse : 0.942 micros/op 1061136 ops/sec; 1052.5 MB/s readreverse : 0.951 micros/op 1051901 ops/sec; 1043.3 MB/s readreverse : 0.932 micros/op 1072894 ops/sec; 1064.1 MB/s readreverse : 1.024 micros/op 976720 ops/sec; 968.7 MB/s readreverse : 0.935 micros/op 1069169 ops/sec; 1060.4 MB/s readreverse : 1.012 micros/op 988132 ops/sec; 980.1 MB/s readreverse : 0.962 micros/op 1039579 ops/sec; 1031.1 MB/s readreverse : 0.991 micros/op 1008924 ops/sec; 1000.7 MB/s readreverse : 1.004 micros/op 996144 ops/sec; 988.0 MB/s avg : 1016.76 MB/s ==> 1000000_Keys_10KB.txt <== readreverse : 4.167 micros/op 239952 ops/sec; 2346.9 MB/s readreverse : 4.070 micros/op 245713 ops/sec; 2403.3 MB/s readreverse : 4.572 micros/op 218733 ops/sec; 2139.4 MB/s readreverse : 4.497 micros/op 222388 ops/sec; 2175.2 MB/s readreverse : 4.203 micros/op 237920 ops/sec; 2327.1 MB/s readreverse : 4.206 micros/op 237756 ops/sec; 2325.5 MB/s readreverse : 4.181 micros/op 239149 ops/sec; 2339.1 MB/s readreverse : 4.157 micros/op 240552 ops/sec; 2352.8 MB/s readreverse : 4.187 micros/op 238848 ops/sec; 2336.1 MB/s readreverse : 4.106 micros/op 243575 ops/sec; 2382.4 MB/s avg : 2312.78 MB/s ==> 100000_Keys_100KB.txt <== readreverse : 41.281 micros/op 24224 ops/sec; 2366.0 MB/s readreverse : 39.722 micros/op 25175 ops/sec; 2458.9 MB/s readreverse : 40.319 micros/op 24802 ops/sec; 2422.5 MB/s readreverse : 39.762 micros/op 25149 ops/sec; 2456.4 MB/s readreverse : 40.916 micros/op 24440 ops/sec; 2387.1 MB/s readreverse : 41.188 micros/op 24278 ops/sec; 2371.4 MB/s readreverse : 40.061 micros/op 24962 ops/sec; 2438.1 MB/s readreverse : 40.221 micros/op 24862 ops/sec; 2428.4 MB/s readreverse : 40.084 micros/op 24947 ops/sec; 2436.7 MB/s readreverse : 40.655 micros/op 24597 ops/sec; 2402.4 MB/s avg : 2416.79 MB/s ==> 10000_Keys_1MB.txt <== readreverse : 298.038 micros/op 3355 ops/sec; 3355.3 MB/s readreverse : 335.001 micros/op 2985 ops/sec; 2985.1 MB/s readreverse : 286.956 micros/op 3484 ops/sec; 3484.9 MB/s readreverse : 329.954 micros/op 3030 ops/sec; 3030.8 MB/s readreverse : 306.428 micros/op 3263 ops/sec; 3263.5 MB/s readreverse : 330.749 micros/op 3023 ops/sec; 3023.5 MB/s readreverse : 328.903 micros/op 3040 ops/sec; 3040.5 MB/s readreverse : 324.853 micros/op 3078 ops/sec; 3078.4 MB/s readreverse : 320.488 micros/op 3120 ops/sec; 3120.3 MB/s readreverse : 320.536 micros/op 3119 ops/sec; 3119.8 MB/s avg : 3150.21 MB/s ``` After memcpy elimination ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.395 micros/op 2529890 ops/sec; 279.9 MB/s readreverse : 0.368 micros/op 2715922 ops/sec; 300.5 MB/s readreverse : 0.384 micros/op 2603929 ops/sec; 288.1 MB/s readreverse : 0.375 micros/op 2663286 ops/sec; 294.6 MB/s readreverse : 0.357 micros/op 2802180 ops/sec; 310.0 MB/s readreverse : 0.363 micros/op 2757684 ops/sec; 305.1 MB/s readreverse : 0.372 micros/op 2689603 ops/sec; 297.5 MB/s readreverse : 0.379 micros/op 2638599 ops/sec; 291.9 MB/s readreverse : 0.375 micros/op 2663803 ops/sec; 294.7 MB/s readreverse : 0.375 micros/op 2665579 ops/sec; 294.9 MB/s avg: 295.72 MB/s (1.22 X) ==> 1000000_Keys_1KB.txt <== readreverse : 0.879 micros/op 1138112 ops/sec; 1128.8 MB/s readreverse : 0.842 micros/op 1187998 ops/sec; 1178.3 MB/s readreverse : 0.837 micros/op 1194915 ops/sec; 1185.1 MB/s readreverse : 0.845 micros/op 1182983 ops/sec; 1173.3 MB/s readreverse : 0.877 micros/op 1140308 ops/sec; 1131.0 MB/s readreverse : 0.849 micros/op 1177581 ops/sec; 1168.0 MB/s readreverse : 0.915 micros/op 1093284 ops/sec; 1084.3 MB/s readreverse : 0.863 micros/op 1159418 ops/sec; 1149.9 MB/s readreverse : 0.895 micros/op 1117670 ops/sec; 1108.5 MB/s readreverse : 0.852 micros/op 1174116 ops/sec; 1164.5 MB/s avg: 1147.17 MB/s (1.12 X) ==> 1000000_Keys_10KB.txt <== readreverse : 3.870 micros/op 258386 ops/sec; 2527.2 MB/s readreverse : 3.568 micros/op 280296 ops/sec; 2741.5 MB/s readreverse : 4.005 micros/op 249694 ops/sec; 2442.2 MB/s readreverse : 3.550 micros/op 281719 ops/sec; 2755.5 MB/s readreverse : 3.562 micros/op 280758 ops/sec; 2746.1 MB/s readreverse : 3.507 micros/op 285125 ops/sec; 2788.8 MB/s readreverse : 3.463 micros/op 288739 ops/sec; 2824.1 MB/s readreverse : 3.428 micros/op 291734 ops/sec; 2853.4 MB/s readreverse : 3.553 micros/op 281491 ops/sec; 2753.2 MB/s readreverse : 3.535 micros/op 282885 ops/sec; 2766.9 MB/s avg : 2719.89 MB/s (1.17 X) ==> 100000_Keys_100KB.txt <== readreverse : 22.815 micros/op 43830 ops/sec; 4281.0 MB/s readreverse : 29.957 micros/op 33381 ops/sec; 3260.4 MB/s readreverse : 25.334 micros/op 39473 ops/sec; 3855.4 MB/s readreverse : 23.037 micros/op 43409 ops/sec; 4239.8 MB/s readreverse : 27.810 micros/op 35958 ops/sec; 3512.1 MB/s readreverse : 30.327 micros/op 32973 ops/sec; 3220.6 MB/s readreverse : 29.704 micros/op 33665 ops/sec; 3288.2 MB/s readreverse : 29.423 micros/op 33987 ops/sec; 3319.6 MB/s readreverse : 23.334 micros/op 42856 ops/sec; 4185.9 MB/s readreverse : 29.969 micros/op 33368 ops/sec; 3259.1 MB/s avg : 3642.21 MB/s (1.5 X) ==> 10000_Keys_1MB.txt <== readreverse : 244.748 micros/op 4085 ops/sec; 4085.9 MB/s readreverse : 230.208 micros/op 4343 ops/sec; 4344.0 MB/s readreverse : 235.655 micros/op 4243 ops/sec; 4243.6 MB/s readreverse : 235.730 micros/op 4242 ops/sec; 4242.2 MB/s readreverse : 237.346 micros/op 4213 ops/sec; 4213.3 MB/s readreverse : 227.306 micros/op 4399 ops/sec; 4399.4 MB/s readreverse : 194.957 micros/op 5129 ops/sec; 5129.4 MB/s readreverse : 238.359 micros/op 4195 ops/sec; 4195.4 MB/s readreverse : 221.588 micros/op 4512 ops/sec; 4513.0 MB/s readreverse : 235.911 micros/op 4238 ops/sec; 4239.0 MB/s avg : 4360.52 MB/s (1.38 X) ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: andrewkr, yhchiang, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56511
9 years ago
// Release pinned data if any
if (pinned_iters_mgr_.PinningEnabled()) {
pinned_iters_mgr_.ReleasePinnedData();
}
RecordTick(statistics_, NO_ITERATORS, -1);
local_stats_.BumpGlobalStatistics(statistics_);
if (!arena_mode_) {
delete iter_;
} else {
iter_->~InternalIterator();
}
}
virtual void SetIter(InternalIterator* iter) {
assert(iter_ == nullptr);
iter_ = iter;
iter_->SetPinnedItersMgr(&pinned_iters_mgr_);
}
virtual RangeDelAggregator* GetRangeDelAggregator() {
return &range_del_agg_;
}
virtual bool Valid() const override { return valid_; }
virtual Slice key() const override {
assert(valid_);
return saved_key_.GetUserKey();
}
virtual Slice value() const override {
assert(valid_);
Eliminate memcpy in Iterator::Prev() by pinning blocks for keys spanning multiple blocks Summary: This diff is stacked on top of this diff https://reviews.facebook.net/D56493 The current Iterator::Prev() implementation need to copy every value since the underlying Iterator may move after reading the value. This can be optimized by making sure that the block containing the value is pinned until the Iterator move. which will improve the throughput by up to 1.5X master ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.449 micros/op 2225887 ops/sec; 246.2 MB/s readreverse : 0.433 micros/op 2311508 ops/sec; 255.7 MB/s readreverse : 0.436 micros/op 2294335 ops/sec; 253.8 MB/s readreverse : 0.471 micros/op 2121295 ops/sec; 234.7 MB/s readreverse : 0.465 micros/op 2152227 ops/sec; 238.1 MB/s readreverse : 0.454 micros/op 2203011 ops/sec; 243.7 MB/s readreverse : 0.451 micros/op 2216095 ops/sec; 245.2 MB/s readreverse : 0.462 micros/op 2162447 ops/sec; 239.2 MB/s readreverse : 0.476 micros/op 2099151 ops/sec; 232.2 MB/s readreverse : 0.472 micros/op 2120710 ops/sec; 234.6 MB/s avg : 242.34 MB/s ==> 1000000_Keys_1KB.txt <== readreverse : 1.013 micros/op 986793 ops/sec; 978.7 MB/s readreverse : 0.942 micros/op 1061136 ops/sec; 1052.5 MB/s readreverse : 0.951 micros/op 1051901 ops/sec; 1043.3 MB/s readreverse : 0.932 micros/op 1072894 ops/sec; 1064.1 MB/s readreverse : 1.024 micros/op 976720 ops/sec; 968.7 MB/s readreverse : 0.935 micros/op 1069169 ops/sec; 1060.4 MB/s readreverse : 1.012 micros/op 988132 ops/sec; 980.1 MB/s readreverse : 0.962 micros/op 1039579 ops/sec; 1031.1 MB/s readreverse : 0.991 micros/op 1008924 ops/sec; 1000.7 MB/s readreverse : 1.004 micros/op 996144 ops/sec; 988.0 MB/s avg : 1016.76 MB/s ==> 1000000_Keys_10KB.txt <== readreverse : 4.167 micros/op 239952 ops/sec; 2346.9 MB/s readreverse : 4.070 micros/op 245713 ops/sec; 2403.3 MB/s readreverse : 4.572 micros/op 218733 ops/sec; 2139.4 MB/s readreverse : 4.497 micros/op 222388 ops/sec; 2175.2 MB/s readreverse : 4.203 micros/op 237920 ops/sec; 2327.1 MB/s readreverse : 4.206 micros/op 237756 ops/sec; 2325.5 MB/s readreverse : 4.181 micros/op 239149 ops/sec; 2339.1 MB/s readreverse : 4.157 micros/op 240552 ops/sec; 2352.8 MB/s readreverse : 4.187 micros/op 238848 ops/sec; 2336.1 MB/s readreverse : 4.106 micros/op 243575 ops/sec; 2382.4 MB/s avg : 2312.78 MB/s ==> 100000_Keys_100KB.txt <== readreverse : 41.281 micros/op 24224 ops/sec; 2366.0 MB/s readreverse : 39.722 micros/op 25175 ops/sec; 2458.9 MB/s readreverse : 40.319 micros/op 24802 ops/sec; 2422.5 MB/s readreverse : 39.762 micros/op 25149 ops/sec; 2456.4 MB/s readreverse : 40.916 micros/op 24440 ops/sec; 2387.1 MB/s readreverse : 41.188 micros/op 24278 ops/sec; 2371.4 MB/s readreverse : 40.061 micros/op 24962 ops/sec; 2438.1 MB/s readreverse : 40.221 micros/op 24862 ops/sec; 2428.4 MB/s readreverse : 40.084 micros/op 24947 ops/sec; 2436.7 MB/s readreverse : 40.655 micros/op 24597 ops/sec; 2402.4 MB/s avg : 2416.79 MB/s ==> 10000_Keys_1MB.txt <== readreverse : 298.038 micros/op 3355 ops/sec; 3355.3 MB/s readreverse : 335.001 micros/op 2985 ops/sec; 2985.1 MB/s readreverse : 286.956 micros/op 3484 ops/sec; 3484.9 MB/s readreverse : 329.954 micros/op 3030 ops/sec; 3030.8 MB/s readreverse : 306.428 micros/op 3263 ops/sec; 3263.5 MB/s readreverse : 330.749 micros/op 3023 ops/sec; 3023.5 MB/s readreverse : 328.903 micros/op 3040 ops/sec; 3040.5 MB/s readreverse : 324.853 micros/op 3078 ops/sec; 3078.4 MB/s readreverse : 320.488 micros/op 3120 ops/sec; 3120.3 MB/s readreverse : 320.536 micros/op 3119 ops/sec; 3119.8 MB/s avg : 3150.21 MB/s ``` After memcpy elimination ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.395 micros/op 2529890 ops/sec; 279.9 MB/s readreverse : 0.368 micros/op 2715922 ops/sec; 300.5 MB/s readreverse : 0.384 micros/op 2603929 ops/sec; 288.1 MB/s readreverse : 0.375 micros/op 2663286 ops/sec; 294.6 MB/s readreverse : 0.357 micros/op 2802180 ops/sec; 310.0 MB/s readreverse : 0.363 micros/op 2757684 ops/sec; 305.1 MB/s readreverse : 0.372 micros/op 2689603 ops/sec; 297.5 MB/s readreverse : 0.379 micros/op 2638599 ops/sec; 291.9 MB/s readreverse : 0.375 micros/op 2663803 ops/sec; 294.7 MB/s readreverse : 0.375 micros/op 2665579 ops/sec; 294.9 MB/s avg: 295.72 MB/s (1.22 X) ==> 1000000_Keys_1KB.txt <== readreverse : 0.879 micros/op 1138112 ops/sec; 1128.8 MB/s readreverse : 0.842 micros/op 1187998 ops/sec; 1178.3 MB/s readreverse : 0.837 micros/op 1194915 ops/sec; 1185.1 MB/s readreverse : 0.845 micros/op 1182983 ops/sec; 1173.3 MB/s readreverse : 0.877 micros/op 1140308 ops/sec; 1131.0 MB/s readreverse : 0.849 micros/op 1177581 ops/sec; 1168.0 MB/s readreverse : 0.915 micros/op 1093284 ops/sec; 1084.3 MB/s readreverse : 0.863 micros/op 1159418 ops/sec; 1149.9 MB/s readreverse : 0.895 micros/op 1117670 ops/sec; 1108.5 MB/s readreverse : 0.852 micros/op 1174116 ops/sec; 1164.5 MB/s avg: 1147.17 MB/s (1.12 X) ==> 1000000_Keys_10KB.txt <== readreverse : 3.870 micros/op 258386 ops/sec; 2527.2 MB/s readreverse : 3.568 micros/op 280296 ops/sec; 2741.5 MB/s readreverse : 4.005 micros/op 249694 ops/sec; 2442.2 MB/s readreverse : 3.550 micros/op 281719 ops/sec; 2755.5 MB/s readreverse : 3.562 micros/op 280758 ops/sec; 2746.1 MB/s readreverse : 3.507 micros/op 285125 ops/sec; 2788.8 MB/s readreverse : 3.463 micros/op 288739 ops/sec; 2824.1 MB/s readreverse : 3.428 micros/op 291734 ops/sec; 2853.4 MB/s readreverse : 3.553 micros/op 281491 ops/sec; 2753.2 MB/s readreverse : 3.535 micros/op 282885 ops/sec; 2766.9 MB/s avg : 2719.89 MB/s (1.17 X) ==> 100000_Keys_100KB.txt <== readreverse : 22.815 micros/op 43830 ops/sec; 4281.0 MB/s readreverse : 29.957 micros/op 33381 ops/sec; 3260.4 MB/s readreverse : 25.334 micros/op 39473 ops/sec; 3855.4 MB/s readreverse : 23.037 micros/op 43409 ops/sec; 4239.8 MB/s readreverse : 27.810 micros/op 35958 ops/sec; 3512.1 MB/s readreverse : 30.327 micros/op 32973 ops/sec; 3220.6 MB/s readreverse : 29.704 micros/op 33665 ops/sec; 3288.2 MB/s readreverse : 29.423 micros/op 33987 ops/sec; 3319.6 MB/s readreverse : 23.334 micros/op 42856 ops/sec; 4185.9 MB/s readreverse : 29.969 micros/op 33368 ops/sec; 3259.1 MB/s avg : 3642.21 MB/s (1.5 X) ==> 10000_Keys_1MB.txt <== readreverse : 244.748 micros/op 4085 ops/sec; 4085.9 MB/s readreverse : 230.208 micros/op 4343 ops/sec; 4344.0 MB/s readreverse : 235.655 micros/op 4243 ops/sec; 4243.6 MB/s readreverse : 235.730 micros/op 4242 ops/sec; 4242.2 MB/s readreverse : 237.346 micros/op 4213 ops/sec; 4213.3 MB/s readreverse : 227.306 micros/op 4399 ops/sec; 4399.4 MB/s readreverse : 194.957 micros/op 5129 ops/sec; 5129.4 MB/s readreverse : 238.359 micros/op 4195 ops/sec; 4195.4 MB/s readreverse : 221.588 micros/op 4512 ops/sec; 4513.0 MB/s readreverse : 235.911 micros/op 4238 ops/sec; 4239.0 MB/s avg : 4360.52 MB/s (1.38 X) ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: andrewkr, yhchiang, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56511
9 years ago
if (current_entry_is_merged_) {
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 pinned_value_ is set then the result of merge operator is one of
// the merge operands and we should return it.
return pinned_value_.data() ? pinned_value_ : saved_value_;
Eliminate memcpy in Iterator::Prev() by pinning blocks for keys spanning multiple blocks Summary: This diff is stacked on top of this diff https://reviews.facebook.net/D56493 The current Iterator::Prev() implementation need to copy every value since the underlying Iterator may move after reading the value. This can be optimized by making sure that the block containing the value is pinned until the Iterator move. which will improve the throughput by up to 1.5X master ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.449 micros/op 2225887 ops/sec; 246.2 MB/s readreverse : 0.433 micros/op 2311508 ops/sec; 255.7 MB/s readreverse : 0.436 micros/op 2294335 ops/sec; 253.8 MB/s readreverse : 0.471 micros/op 2121295 ops/sec; 234.7 MB/s readreverse : 0.465 micros/op 2152227 ops/sec; 238.1 MB/s readreverse : 0.454 micros/op 2203011 ops/sec; 243.7 MB/s readreverse : 0.451 micros/op 2216095 ops/sec; 245.2 MB/s readreverse : 0.462 micros/op 2162447 ops/sec; 239.2 MB/s readreverse : 0.476 micros/op 2099151 ops/sec; 232.2 MB/s readreverse : 0.472 micros/op 2120710 ops/sec; 234.6 MB/s avg : 242.34 MB/s ==> 1000000_Keys_1KB.txt <== readreverse : 1.013 micros/op 986793 ops/sec; 978.7 MB/s readreverse : 0.942 micros/op 1061136 ops/sec; 1052.5 MB/s readreverse : 0.951 micros/op 1051901 ops/sec; 1043.3 MB/s readreverse : 0.932 micros/op 1072894 ops/sec; 1064.1 MB/s readreverse : 1.024 micros/op 976720 ops/sec; 968.7 MB/s readreverse : 0.935 micros/op 1069169 ops/sec; 1060.4 MB/s readreverse : 1.012 micros/op 988132 ops/sec; 980.1 MB/s readreverse : 0.962 micros/op 1039579 ops/sec; 1031.1 MB/s readreverse : 0.991 micros/op 1008924 ops/sec; 1000.7 MB/s readreverse : 1.004 micros/op 996144 ops/sec; 988.0 MB/s avg : 1016.76 MB/s ==> 1000000_Keys_10KB.txt <== readreverse : 4.167 micros/op 239952 ops/sec; 2346.9 MB/s readreverse : 4.070 micros/op 245713 ops/sec; 2403.3 MB/s readreverse : 4.572 micros/op 218733 ops/sec; 2139.4 MB/s readreverse : 4.497 micros/op 222388 ops/sec; 2175.2 MB/s readreverse : 4.203 micros/op 237920 ops/sec; 2327.1 MB/s readreverse : 4.206 micros/op 237756 ops/sec; 2325.5 MB/s readreverse : 4.181 micros/op 239149 ops/sec; 2339.1 MB/s readreverse : 4.157 micros/op 240552 ops/sec; 2352.8 MB/s readreverse : 4.187 micros/op 238848 ops/sec; 2336.1 MB/s readreverse : 4.106 micros/op 243575 ops/sec; 2382.4 MB/s avg : 2312.78 MB/s ==> 100000_Keys_100KB.txt <== readreverse : 41.281 micros/op 24224 ops/sec; 2366.0 MB/s readreverse : 39.722 micros/op 25175 ops/sec; 2458.9 MB/s readreverse : 40.319 micros/op 24802 ops/sec; 2422.5 MB/s readreverse : 39.762 micros/op 25149 ops/sec; 2456.4 MB/s readreverse : 40.916 micros/op 24440 ops/sec; 2387.1 MB/s readreverse : 41.188 micros/op 24278 ops/sec; 2371.4 MB/s readreverse : 40.061 micros/op 24962 ops/sec; 2438.1 MB/s readreverse : 40.221 micros/op 24862 ops/sec; 2428.4 MB/s readreverse : 40.084 micros/op 24947 ops/sec; 2436.7 MB/s readreverse : 40.655 micros/op 24597 ops/sec; 2402.4 MB/s avg : 2416.79 MB/s ==> 10000_Keys_1MB.txt <== readreverse : 298.038 micros/op 3355 ops/sec; 3355.3 MB/s readreverse : 335.001 micros/op 2985 ops/sec; 2985.1 MB/s readreverse : 286.956 micros/op 3484 ops/sec; 3484.9 MB/s readreverse : 329.954 micros/op 3030 ops/sec; 3030.8 MB/s readreverse : 306.428 micros/op 3263 ops/sec; 3263.5 MB/s readreverse : 330.749 micros/op 3023 ops/sec; 3023.5 MB/s readreverse : 328.903 micros/op 3040 ops/sec; 3040.5 MB/s readreverse : 324.853 micros/op 3078 ops/sec; 3078.4 MB/s readreverse : 320.488 micros/op 3120 ops/sec; 3120.3 MB/s readreverse : 320.536 micros/op 3119 ops/sec; 3119.8 MB/s avg : 3150.21 MB/s ``` After memcpy elimination ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.395 micros/op 2529890 ops/sec; 279.9 MB/s readreverse : 0.368 micros/op 2715922 ops/sec; 300.5 MB/s readreverse : 0.384 micros/op 2603929 ops/sec; 288.1 MB/s readreverse : 0.375 micros/op 2663286 ops/sec; 294.6 MB/s readreverse : 0.357 micros/op 2802180 ops/sec; 310.0 MB/s readreverse : 0.363 micros/op 2757684 ops/sec; 305.1 MB/s readreverse : 0.372 micros/op 2689603 ops/sec; 297.5 MB/s readreverse : 0.379 micros/op 2638599 ops/sec; 291.9 MB/s readreverse : 0.375 micros/op 2663803 ops/sec; 294.7 MB/s readreverse : 0.375 micros/op 2665579 ops/sec; 294.9 MB/s avg: 295.72 MB/s (1.22 X) ==> 1000000_Keys_1KB.txt <== readreverse : 0.879 micros/op 1138112 ops/sec; 1128.8 MB/s readreverse : 0.842 micros/op 1187998 ops/sec; 1178.3 MB/s readreverse : 0.837 micros/op 1194915 ops/sec; 1185.1 MB/s readreverse : 0.845 micros/op 1182983 ops/sec; 1173.3 MB/s readreverse : 0.877 micros/op 1140308 ops/sec; 1131.0 MB/s readreverse : 0.849 micros/op 1177581 ops/sec; 1168.0 MB/s readreverse : 0.915 micros/op 1093284 ops/sec; 1084.3 MB/s readreverse : 0.863 micros/op 1159418 ops/sec; 1149.9 MB/s readreverse : 0.895 micros/op 1117670 ops/sec; 1108.5 MB/s readreverse : 0.852 micros/op 1174116 ops/sec; 1164.5 MB/s avg: 1147.17 MB/s (1.12 X) ==> 1000000_Keys_10KB.txt <== readreverse : 3.870 micros/op 258386 ops/sec; 2527.2 MB/s readreverse : 3.568 micros/op 280296 ops/sec; 2741.5 MB/s readreverse : 4.005 micros/op 249694 ops/sec; 2442.2 MB/s readreverse : 3.550 micros/op 281719 ops/sec; 2755.5 MB/s readreverse : 3.562 micros/op 280758 ops/sec; 2746.1 MB/s readreverse : 3.507 micros/op 285125 ops/sec; 2788.8 MB/s readreverse : 3.463 micros/op 288739 ops/sec; 2824.1 MB/s readreverse : 3.428 micros/op 291734 ops/sec; 2853.4 MB/s readreverse : 3.553 micros/op 281491 ops/sec; 2753.2 MB/s readreverse : 3.535 micros/op 282885 ops/sec; 2766.9 MB/s avg : 2719.89 MB/s (1.17 X) ==> 100000_Keys_100KB.txt <== readreverse : 22.815 micros/op 43830 ops/sec; 4281.0 MB/s readreverse : 29.957 micros/op 33381 ops/sec; 3260.4 MB/s readreverse : 25.334 micros/op 39473 ops/sec; 3855.4 MB/s readreverse : 23.037 micros/op 43409 ops/sec; 4239.8 MB/s readreverse : 27.810 micros/op 35958 ops/sec; 3512.1 MB/s readreverse : 30.327 micros/op 32973 ops/sec; 3220.6 MB/s readreverse : 29.704 micros/op 33665 ops/sec; 3288.2 MB/s readreverse : 29.423 micros/op 33987 ops/sec; 3319.6 MB/s readreverse : 23.334 micros/op 42856 ops/sec; 4185.9 MB/s readreverse : 29.969 micros/op 33368 ops/sec; 3259.1 MB/s avg : 3642.21 MB/s (1.5 X) ==> 10000_Keys_1MB.txt <== readreverse : 244.748 micros/op 4085 ops/sec; 4085.9 MB/s readreverse : 230.208 micros/op 4343 ops/sec; 4344.0 MB/s readreverse : 235.655 micros/op 4243 ops/sec; 4243.6 MB/s readreverse : 235.730 micros/op 4242 ops/sec; 4242.2 MB/s readreverse : 237.346 micros/op 4213 ops/sec; 4213.3 MB/s readreverse : 227.306 micros/op 4399 ops/sec; 4399.4 MB/s readreverse : 194.957 micros/op 5129 ops/sec; 5129.4 MB/s readreverse : 238.359 micros/op 4195 ops/sec; 4195.4 MB/s readreverse : 221.588 micros/op 4512 ops/sec; 4513.0 MB/s readreverse : 235.911 micros/op 4238 ops/sec; 4239.0 MB/s avg : 4360.52 MB/s (1.38 X) ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: andrewkr, yhchiang, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56511
9 years ago
} else if (direction_ == kReverse) {
return pinned_value_;
} else {
return iter_->value();
}
}
virtual Status status() const override {
if (status_.ok()) {
return iter_->status();
} else {
return status_;
}
}
virtual Status GetProperty(std::string prop_name,
std::string* prop) override {
if (prop == nullptr) {
return Status::InvalidArgument("prop is nullptr");
}
if (prop_name == "rocksdb.iterator.super-version-number") {
// First try to pass the value returned from inner iterator.
if (!iter_->GetProperty(prop_name, prop).ok()) {
*prop = ToString(version_number_);
}
return Status::OK();
} else if (prop_name == "rocksdb.iterator.is-key-pinned") {
if (valid_) {
*prop = (pin_thru_lifetime_ && saved_key_.IsKeyPinned()) ? "1" : "0";
} else {
*prop = "Iterator is not valid.";
}
return Status::OK();
}
return Status::InvalidArgument("Undentified property.");
Introduce ReadOptions::pin_data (support zero copy for keys) Summary: This patch update the Iterator API to introduce new functions that allow users to keep the Slices returned by key() valid as long as the Iterator is not deleted ReadOptions::pin_data : If true keep loaded blocks in memory as long as the iterator is not deleted Iterator::IsKeyPinned() : If true, this mean that the Slice returned by key() is valid as long as the iterator is not deleted Also add a new option BlockBasedTableOptions::use_delta_encoding to allow users to disable delta_encoding if needed. Benchmark results (using https://phabricator.fb.com/P20083553) ``` // $ du -h /home/tec/local/normal.4K.Snappy/db10077 // 6.1G /home/tec/local/normal.4K.Snappy/db10077 // $ du -h /home/tec/local/zero.8K.LZ4/db10077 // 6.4G /home/tec/local/zero.8K.LZ4/db10077 // Benchmarks for shard db10077 // _build/opt/rocks/benchmark/rocks_copy_benchmark \ // --normal_db_path="/home/tec/local/normal.4K.Snappy/db10077" \ // --zero_db_path="/home/tec/local/zero.8K.LZ4/db10077" // First run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 1.73s 576.97m // BM_StringPiece 103.74% 1.67s 598.55m // ============================================================================ // Match rate : 1000000 / 1000000 // Second run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 611.99ms 1.63 // BM_StringPiece 203.76% 300.35ms 3.33 // ============================================================================ // Match rate : 1000000 / 1000000 ``` Test Plan: Unit tests Reviewers: sdong, igor, anthony, yhchiang, rven Reviewed By: rven Subscribers: dhruba, lovro, adsharma Differential Revision: https://reviews.facebook.net/D48999
9 years ago
}
virtual void Next() override;
virtual void Prev() override;
virtual void Seek(const Slice& target) override;
virtual void SeekForPrev(const Slice& target) override;
virtual void SeekToFirst() override;
virtual void SeekToLast() override;
private:
void ReverseToForward();
void ReverseToBackward();
void PrevInternal();
void FindParseableKey(ParsedInternalKey* ikey, Direction direction);
bool FindValueForCurrentKey();
bool FindValueForCurrentKeyUsingSeek();
void FindPrevUserKey();
void FindNextUserKey();
inline void FindNextUserEntry(bool skipping, bool prefix_check);
void FindNextUserEntryInternal(bool skipping, bool prefix_check);
bool ParseKey(ParsedInternalKey* key);
void MergeValuesNewToOld();
bool TooManyInternalKeysSkipped(bool increment = true);
Eliminate memcpy in Iterator::Prev() by pinning blocks for keys spanning multiple blocks Summary: This diff is stacked on top of this diff https://reviews.facebook.net/D56493 The current Iterator::Prev() implementation need to copy every value since the underlying Iterator may move after reading the value. This can be optimized by making sure that the block containing the value is pinned until the Iterator move. which will improve the throughput by up to 1.5X master ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.449 micros/op 2225887 ops/sec; 246.2 MB/s readreverse : 0.433 micros/op 2311508 ops/sec; 255.7 MB/s readreverse : 0.436 micros/op 2294335 ops/sec; 253.8 MB/s readreverse : 0.471 micros/op 2121295 ops/sec; 234.7 MB/s readreverse : 0.465 micros/op 2152227 ops/sec; 238.1 MB/s readreverse : 0.454 micros/op 2203011 ops/sec; 243.7 MB/s readreverse : 0.451 micros/op 2216095 ops/sec; 245.2 MB/s readreverse : 0.462 micros/op 2162447 ops/sec; 239.2 MB/s readreverse : 0.476 micros/op 2099151 ops/sec; 232.2 MB/s readreverse : 0.472 micros/op 2120710 ops/sec; 234.6 MB/s avg : 242.34 MB/s ==> 1000000_Keys_1KB.txt <== readreverse : 1.013 micros/op 986793 ops/sec; 978.7 MB/s readreverse : 0.942 micros/op 1061136 ops/sec; 1052.5 MB/s readreverse : 0.951 micros/op 1051901 ops/sec; 1043.3 MB/s readreverse : 0.932 micros/op 1072894 ops/sec; 1064.1 MB/s readreverse : 1.024 micros/op 976720 ops/sec; 968.7 MB/s readreverse : 0.935 micros/op 1069169 ops/sec; 1060.4 MB/s readreverse : 1.012 micros/op 988132 ops/sec; 980.1 MB/s readreverse : 0.962 micros/op 1039579 ops/sec; 1031.1 MB/s readreverse : 0.991 micros/op 1008924 ops/sec; 1000.7 MB/s readreverse : 1.004 micros/op 996144 ops/sec; 988.0 MB/s avg : 1016.76 MB/s ==> 1000000_Keys_10KB.txt <== readreverse : 4.167 micros/op 239952 ops/sec; 2346.9 MB/s readreverse : 4.070 micros/op 245713 ops/sec; 2403.3 MB/s readreverse : 4.572 micros/op 218733 ops/sec; 2139.4 MB/s readreverse : 4.497 micros/op 222388 ops/sec; 2175.2 MB/s readreverse : 4.203 micros/op 237920 ops/sec; 2327.1 MB/s readreverse : 4.206 micros/op 237756 ops/sec; 2325.5 MB/s readreverse : 4.181 micros/op 239149 ops/sec; 2339.1 MB/s readreverse : 4.157 micros/op 240552 ops/sec; 2352.8 MB/s readreverse : 4.187 micros/op 238848 ops/sec; 2336.1 MB/s readreverse : 4.106 micros/op 243575 ops/sec; 2382.4 MB/s avg : 2312.78 MB/s ==> 100000_Keys_100KB.txt <== readreverse : 41.281 micros/op 24224 ops/sec; 2366.0 MB/s readreverse : 39.722 micros/op 25175 ops/sec; 2458.9 MB/s readreverse : 40.319 micros/op 24802 ops/sec; 2422.5 MB/s readreverse : 39.762 micros/op 25149 ops/sec; 2456.4 MB/s readreverse : 40.916 micros/op 24440 ops/sec; 2387.1 MB/s readreverse : 41.188 micros/op 24278 ops/sec; 2371.4 MB/s readreverse : 40.061 micros/op 24962 ops/sec; 2438.1 MB/s readreverse : 40.221 micros/op 24862 ops/sec; 2428.4 MB/s readreverse : 40.084 micros/op 24947 ops/sec; 2436.7 MB/s readreverse : 40.655 micros/op 24597 ops/sec; 2402.4 MB/s avg : 2416.79 MB/s ==> 10000_Keys_1MB.txt <== readreverse : 298.038 micros/op 3355 ops/sec; 3355.3 MB/s readreverse : 335.001 micros/op 2985 ops/sec; 2985.1 MB/s readreverse : 286.956 micros/op 3484 ops/sec; 3484.9 MB/s readreverse : 329.954 micros/op 3030 ops/sec; 3030.8 MB/s readreverse : 306.428 micros/op 3263 ops/sec; 3263.5 MB/s readreverse : 330.749 micros/op 3023 ops/sec; 3023.5 MB/s readreverse : 328.903 micros/op 3040 ops/sec; 3040.5 MB/s readreverse : 324.853 micros/op 3078 ops/sec; 3078.4 MB/s readreverse : 320.488 micros/op 3120 ops/sec; 3120.3 MB/s readreverse : 320.536 micros/op 3119 ops/sec; 3119.8 MB/s avg : 3150.21 MB/s ``` After memcpy elimination ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.395 micros/op 2529890 ops/sec; 279.9 MB/s readreverse : 0.368 micros/op 2715922 ops/sec; 300.5 MB/s readreverse : 0.384 micros/op 2603929 ops/sec; 288.1 MB/s readreverse : 0.375 micros/op 2663286 ops/sec; 294.6 MB/s readreverse : 0.357 micros/op 2802180 ops/sec; 310.0 MB/s readreverse : 0.363 micros/op 2757684 ops/sec; 305.1 MB/s readreverse : 0.372 micros/op 2689603 ops/sec; 297.5 MB/s readreverse : 0.379 micros/op 2638599 ops/sec; 291.9 MB/s readreverse : 0.375 micros/op 2663803 ops/sec; 294.7 MB/s readreverse : 0.375 micros/op 2665579 ops/sec; 294.9 MB/s avg: 295.72 MB/s (1.22 X) ==> 1000000_Keys_1KB.txt <== readreverse : 0.879 micros/op 1138112 ops/sec; 1128.8 MB/s readreverse : 0.842 micros/op 1187998 ops/sec; 1178.3 MB/s readreverse : 0.837 micros/op 1194915 ops/sec; 1185.1 MB/s readreverse : 0.845 micros/op 1182983 ops/sec; 1173.3 MB/s readreverse : 0.877 micros/op 1140308 ops/sec; 1131.0 MB/s readreverse : 0.849 micros/op 1177581 ops/sec; 1168.0 MB/s readreverse : 0.915 micros/op 1093284 ops/sec; 1084.3 MB/s readreverse : 0.863 micros/op 1159418 ops/sec; 1149.9 MB/s readreverse : 0.895 micros/op 1117670 ops/sec; 1108.5 MB/s readreverse : 0.852 micros/op 1174116 ops/sec; 1164.5 MB/s avg: 1147.17 MB/s (1.12 X) ==> 1000000_Keys_10KB.txt <== readreverse : 3.870 micros/op 258386 ops/sec; 2527.2 MB/s readreverse : 3.568 micros/op 280296 ops/sec; 2741.5 MB/s readreverse : 4.005 micros/op 249694 ops/sec; 2442.2 MB/s readreverse : 3.550 micros/op 281719 ops/sec; 2755.5 MB/s readreverse : 3.562 micros/op 280758 ops/sec; 2746.1 MB/s readreverse : 3.507 micros/op 285125 ops/sec; 2788.8 MB/s readreverse : 3.463 micros/op 288739 ops/sec; 2824.1 MB/s readreverse : 3.428 micros/op 291734 ops/sec; 2853.4 MB/s readreverse : 3.553 micros/op 281491 ops/sec; 2753.2 MB/s readreverse : 3.535 micros/op 282885 ops/sec; 2766.9 MB/s avg : 2719.89 MB/s (1.17 X) ==> 100000_Keys_100KB.txt <== readreverse : 22.815 micros/op 43830 ops/sec; 4281.0 MB/s readreverse : 29.957 micros/op 33381 ops/sec; 3260.4 MB/s readreverse : 25.334 micros/op 39473 ops/sec; 3855.4 MB/s readreverse : 23.037 micros/op 43409 ops/sec; 4239.8 MB/s readreverse : 27.810 micros/op 35958 ops/sec; 3512.1 MB/s readreverse : 30.327 micros/op 32973 ops/sec; 3220.6 MB/s readreverse : 29.704 micros/op 33665 ops/sec; 3288.2 MB/s readreverse : 29.423 micros/op 33987 ops/sec; 3319.6 MB/s readreverse : 23.334 micros/op 42856 ops/sec; 4185.9 MB/s readreverse : 29.969 micros/op 33368 ops/sec; 3259.1 MB/s avg : 3642.21 MB/s (1.5 X) ==> 10000_Keys_1MB.txt <== readreverse : 244.748 micros/op 4085 ops/sec; 4085.9 MB/s readreverse : 230.208 micros/op 4343 ops/sec; 4344.0 MB/s readreverse : 235.655 micros/op 4243 ops/sec; 4243.6 MB/s readreverse : 235.730 micros/op 4242 ops/sec; 4242.2 MB/s readreverse : 237.346 micros/op 4213 ops/sec; 4213.3 MB/s readreverse : 227.306 micros/op 4399 ops/sec; 4399.4 MB/s readreverse : 194.957 micros/op 5129 ops/sec; 5129.4 MB/s readreverse : 238.359 micros/op 4195 ops/sec; 4195.4 MB/s readreverse : 221.588 micros/op 4512 ops/sec; 4513.0 MB/s readreverse : 235.911 micros/op 4238 ops/sec; 4239.0 MB/s avg : 4360.52 MB/s (1.38 X) ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: andrewkr, yhchiang, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56511
9 years ago
// Temporarily pin the blocks that we encounter until ReleaseTempPinnedData()
// is called
void TempPinData() {
if (!pin_thru_lifetime_) {
pinned_iters_mgr_.StartPinning();
}
}
// Release blocks pinned by TempPinData()
void ReleaseTempPinnedData() {
if (!pin_thru_lifetime_ && pinned_iters_mgr_.PinningEnabled()) {
pinned_iters_mgr_.ReleasePinnedData();
Eliminate memcpy in Iterator::Prev() by pinning blocks for keys spanning multiple blocks Summary: This diff is stacked on top of this diff https://reviews.facebook.net/D56493 The current Iterator::Prev() implementation need to copy every value since the underlying Iterator may move after reading the value. This can be optimized by making sure that the block containing the value is pinned until the Iterator move. which will improve the throughput by up to 1.5X master ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.449 micros/op 2225887 ops/sec; 246.2 MB/s readreverse : 0.433 micros/op 2311508 ops/sec; 255.7 MB/s readreverse : 0.436 micros/op 2294335 ops/sec; 253.8 MB/s readreverse : 0.471 micros/op 2121295 ops/sec; 234.7 MB/s readreverse : 0.465 micros/op 2152227 ops/sec; 238.1 MB/s readreverse : 0.454 micros/op 2203011 ops/sec; 243.7 MB/s readreverse : 0.451 micros/op 2216095 ops/sec; 245.2 MB/s readreverse : 0.462 micros/op 2162447 ops/sec; 239.2 MB/s readreverse : 0.476 micros/op 2099151 ops/sec; 232.2 MB/s readreverse : 0.472 micros/op 2120710 ops/sec; 234.6 MB/s avg : 242.34 MB/s ==> 1000000_Keys_1KB.txt <== readreverse : 1.013 micros/op 986793 ops/sec; 978.7 MB/s readreverse : 0.942 micros/op 1061136 ops/sec; 1052.5 MB/s readreverse : 0.951 micros/op 1051901 ops/sec; 1043.3 MB/s readreverse : 0.932 micros/op 1072894 ops/sec; 1064.1 MB/s readreverse : 1.024 micros/op 976720 ops/sec; 968.7 MB/s readreverse : 0.935 micros/op 1069169 ops/sec; 1060.4 MB/s readreverse : 1.012 micros/op 988132 ops/sec; 980.1 MB/s readreverse : 0.962 micros/op 1039579 ops/sec; 1031.1 MB/s readreverse : 0.991 micros/op 1008924 ops/sec; 1000.7 MB/s readreverse : 1.004 micros/op 996144 ops/sec; 988.0 MB/s avg : 1016.76 MB/s ==> 1000000_Keys_10KB.txt <== readreverse : 4.167 micros/op 239952 ops/sec; 2346.9 MB/s readreverse : 4.070 micros/op 245713 ops/sec; 2403.3 MB/s readreverse : 4.572 micros/op 218733 ops/sec; 2139.4 MB/s readreverse : 4.497 micros/op 222388 ops/sec; 2175.2 MB/s readreverse : 4.203 micros/op 237920 ops/sec; 2327.1 MB/s readreverse : 4.206 micros/op 237756 ops/sec; 2325.5 MB/s readreverse : 4.181 micros/op 239149 ops/sec; 2339.1 MB/s readreverse : 4.157 micros/op 240552 ops/sec; 2352.8 MB/s readreverse : 4.187 micros/op 238848 ops/sec; 2336.1 MB/s readreverse : 4.106 micros/op 243575 ops/sec; 2382.4 MB/s avg : 2312.78 MB/s ==> 100000_Keys_100KB.txt <== readreverse : 41.281 micros/op 24224 ops/sec; 2366.0 MB/s readreverse : 39.722 micros/op 25175 ops/sec; 2458.9 MB/s readreverse : 40.319 micros/op 24802 ops/sec; 2422.5 MB/s readreverse : 39.762 micros/op 25149 ops/sec; 2456.4 MB/s readreverse : 40.916 micros/op 24440 ops/sec; 2387.1 MB/s readreverse : 41.188 micros/op 24278 ops/sec; 2371.4 MB/s readreverse : 40.061 micros/op 24962 ops/sec; 2438.1 MB/s readreverse : 40.221 micros/op 24862 ops/sec; 2428.4 MB/s readreverse : 40.084 micros/op 24947 ops/sec; 2436.7 MB/s readreverse : 40.655 micros/op 24597 ops/sec; 2402.4 MB/s avg : 2416.79 MB/s ==> 10000_Keys_1MB.txt <== readreverse : 298.038 micros/op 3355 ops/sec; 3355.3 MB/s readreverse : 335.001 micros/op 2985 ops/sec; 2985.1 MB/s readreverse : 286.956 micros/op 3484 ops/sec; 3484.9 MB/s readreverse : 329.954 micros/op 3030 ops/sec; 3030.8 MB/s readreverse : 306.428 micros/op 3263 ops/sec; 3263.5 MB/s readreverse : 330.749 micros/op 3023 ops/sec; 3023.5 MB/s readreverse : 328.903 micros/op 3040 ops/sec; 3040.5 MB/s readreverse : 324.853 micros/op 3078 ops/sec; 3078.4 MB/s readreverse : 320.488 micros/op 3120 ops/sec; 3120.3 MB/s readreverse : 320.536 micros/op 3119 ops/sec; 3119.8 MB/s avg : 3150.21 MB/s ``` After memcpy elimination ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.395 micros/op 2529890 ops/sec; 279.9 MB/s readreverse : 0.368 micros/op 2715922 ops/sec; 300.5 MB/s readreverse : 0.384 micros/op 2603929 ops/sec; 288.1 MB/s readreverse : 0.375 micros/op 2663286 ops/sec; 294.6 MB/s readreverse : 0.357 micros/op 2802180 ops/sec; 310.0 MB/s readreverse : 0.363 micros/op 2757684 ops/sec; 305.1 MB/s readreverse : 0.372 micros/op 2689603 ops/sec; 297.5 MB/s readreverse : 0.379 micros/op 2638599 ops/sec; 291.9 MB/s readreverse : 0.375 micros/op 2663803 ops/sec; 294.7 MB/s readreverse : 0.375 micros/op 2665579 ops/sec; 294.9 MB/s avg: 295.72 MB/s (1.22 X) ==> 1000000_Keys_1KB.txt <== readreverse : 0.879 micros/op 1138112 ops/sec; 1128.8 MB/s readreverse : 0.842 micros/op 1187998 ops/sec; 1178.3 MB/s readreverse : 0.837 micros/op 1194915 ops/sec; 1185.1 MB/s readreverse : 0.845 micros/op 1182983 ops/sec; 1173.3 MB/s readreverse : 0.877 micros/op 1140308 ops/sec; 1131.0 MB/s readreverse : 0.849 micros/op 1177581 ops/sec; 1168.0 MB/s readreverse : 0.915 micros/op 1093284 ops/sec; 1084.3 MB/s readreverse : 0.863 micros/op 1159418 ops/sec; 1149.9 MB/s readreverse : 0.895 micros/op 1117670 ops/sec; 1108.5 MB/s readreverse : 0.852 micros/op 1174116 ops/sec; 1164.5 MB/s avg: 1147.17 MB/s (1.12 X) ==> 1000000_Keys_10KB.txt <== readreverse : 3.870 micros/op 258386 ops/sec; 2527.2 MB/s readreverse : 3.568 micros/op 280296 ops/sec; 2741.5 MB/s readreverse : 4.005 micros/op 249694 ops/sec; 2442.2 MB/s readreverse : 3.550 micros/op 281719 ops/sec; 2755.5 MB/s readreverse : 3.562 micros/op 280758 ops/sec; 2746.1 MB/s readreverse : 3.507 micros/op 285125 ops/sec; 2788.8 MB/s readreverse : 3.463 micros/op 288739 ops/sec; 2824.1 MB/s readreverse : 3.428 micros/op 291734 ops/sec; 2853.4 MB/s readreverse : 3.553 micros/op 281491 ops/sec; 2753.2 MB/s readreverse : 3.535 micros/op 282885 ops/sec; 2766.9 MB/s avg : 2719.89 MB/s (1.17 X) ==> 100000_Keys_100KB.txt <== readreverse : 22.815 micros/op 43830 ops/sec; 4281.0 MB/s readreverse : 29.957 micros/op 33381 ops/sec; 3260.4 MB/s readreverse : 25.334 micros/op 39473 ops/sec; 3855.4 MB/s readreverse : 23.037 micros/op 43409 ops/sec; 4239.8 MB/s readreverse : 27.810 micros/op 35958 ops/sec; 3512.1 MB/s readreverse : 30.327 micros/op 32973 ops/sec; 3220.6 MB/s readreverse : 29.704 micros/op 33665 ops/sec; 3288.2 MB/s readreverse : 29.423 micros/op 33987 ops/sec; 3319.6 MB/s readreverse : 23.334 micros/op 42856 ops/sec; 4185.9 MB/s readreverse : 29.969 micros/op 33368 ops/sec; 3259.1 MB/s avg : 3642.21 MB/s (1.5 X) ==> 10000_Keys_1MB.txt <== readreverse : 244.748 micros/op 4085 ops/sec; 4085.9 MB/s readreverse : 230.208 micros/op 4343 ops/sec; 4344.0 MB/s readreverse : 235.655 micros/op 4243 ops/sec; 4243.6 MB/s readreverse : 235.730 micros/op 4242 ops/sec; 4242.2 MB/s readreverse : 237.346 micros/op 4213 ops/sec; 4213.3 MB/s readreverse : 227.306 micros/op 4399 ops/sec; 4399.4 MB/s readreverse : 194.957 micros/op 5129 ops/sec; 5129.4 MB/s readreverse : 238.359 micros/op 4195 ops/sec; 4195.4 MB/s readreverse : 221.588 micros/op 4512 ops/sec; 4513.0 MB/s readreverse : 235.911 micros/op 4238 ops/sec; 4239.0 MB/s avg : 4360.52 MB/s (1.38 X) ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: andrewkr, yhchiang, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56511
9 years ago
}
}
inline void ClearSavedValue() {
if (saved_value_.capacity() > 1048576) {
std::string empty;
swap(empty, saved_value_);
} else {
saved_value_.clear();
}
}
inline void ResetInternalKeysSkippedCounter() {
num_internal_keys_skipped_ = 0;
}
const SliceTransform* prefix_extractor_;
bool arena_mode_;
Env* const env_;
Logger* logger_;
const Comparator* const user_comparator_;
const MergeOperator* const merge_operator_;
InternalIterator* iter_;
SequenceNumber const sequence_;
Status status_;
IterKey saved_key_;
std::string saved_value_;
Eliminate memcpy in Iterator::Prev() by pinning blocks for keys spanning multiple blocks Summary: This diff is stacked on top of this diff https://reviews.facebook.net/D56493 The current Iterator::Prev() implementation need to copy every value since the underlying Iterator may move after reading the value. This can be optimized by making sure that the block containing the value is pinned until the Iterator move. which will improve the throughput by up to 1.5X master ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.449 micros/op 2225887 ops/sec; 246.2 MB/s readreverse : 0.433 micros/op 2311508 ops/sec; 255.7 MB/s readreverse : 0.436 micros/op 2294335 ops/sec; 253.8 MB/s readreverse : 0.471 micros/op 2121295 ops/sec; 234.7 MB/s readreverse : 0.465 micros/op 2152227 ops/sec; 238.1 MB/s readreverse : 0.454 micros/op 2203011 ops/sec; 243.7 MB/s readreverse : 0.451 micros/op 2216095 ops/sec; 245.2 MB/s readreverse : 0.462 micros/op 2162447 ops/sec; 239.2 MB/s readreverse : 0.476 micros/op 2099151 ops/sec; 232.2 MB/s readreverse : 0.472 micros/op 2120710 ops/sec; 234.6 MB/s avg : 242.34 MB/s ==> 1000000_Keys_1KB.txt <== readreverse : 1.013 micros/op 986793 ops/sec; 978.7 MB/s readreverse : 0.942 micros/op 1061136 ops/sec; 1052.5 MB/s readreverse : 0.951 micros/op 1051901 ops/sec; 1043.3 MB/s readreverse : 0.932 micros/op 1072894 ops/sec; 1064.1 MB/s readreverse : 1.024 micros/op 976720 ops/sec; 968.7 MB/s readreverse : 0.935 micros/op 1069169 ops/sec; 1060.4 MB/s readreverse : 1.012 micros/op 988132 ops/sec; 980.1 MB/s readreverse : 0.962 micros/op 1039579 ops/sec; 1031.1 MB/s readreverse : 0.991 micros/op 1008924 ops/sec; 1000.7 MB/s readreverse : 1.004 micros/op 996144 ops/sec; 988.0 MB/s avg : 1016.76 MB/s ==> 1000000_Keys_10KB.txt <== readreverse : 4.167 micros/op 239952 ops/sec; 2346.9 MB/s readreverse : 4.070 micros/op 245713 ops/sec; 2403.3 MB/s readreverse : 4.572 micros/op 218733 ops/sec; 2139.4 MB/s readreverse : 4.497 micros/op 222388 ops/sec; 2175.2 MB/s readreverse : 4.203 micros/op 237920 ops/sec; 2327.1 MB/s readreverse : 4.206 micros/op 237756 ops/sec; 2325.5 MB/s readreverse : 4.181 micros/op 239149 ops/sec; 2339.1 MB/s readreverse : 4.157 micros/op 240552 ops/sec; 2352.8 MB/s readreverse : 4.187 micros/op 238848 ops/sec; 2336.1 MB/s readreverse : 4.106 micros/op 243575 ops/sec; 2382.4 MB/s avg : 2312.78 MB/s ==> 100000_Keys_100KB.txt <== readreverse : 41.281 micros/op 24224 ops/sec; 2366.0 MB/s readreverse : 39.722 micros/op 25175 ops/sec; 2458.9 MB/s readreverse : 40.319 micros/op 24802 ops/sec; 2422.5 MB/s readreverse : 39.762 micros/op 25149 ops/sec; 2456.4 MB/s readreverse : 40.916 micros/op 24440 ops/sec; 2387.1 MB/s readreverse : 41.188 micros/op 24278 ops/sec; 2371.4 MB/s readreverse : 40.061 micros/op 24962 ops/sec; 2438.1 MB/s readreverse : 40.221 micros/op 24862 ops/sec; 2428.4 MB/s readreverse : 40.084 micros/op 24947 ops/sec; 2436.7 MB/s readreverse : 40.655 micros/op 24597 ops/sec; 2402.4 MB/s avg : 2416.79 MB/s ==> 10000_Keys_1MB.txt <== readreverse : 298.038 micros/op 3355 ops/sec; 3355.3 MB/s readreverse : 335.001 micros/op 2985 ops/sec; 2985.1 MB/s readreverse : 286.956 micros/op 3484 ops/sec; 3484.9 MB/s readreverse : 329.954 micros/op 3030 ops/sec; 3030.8 MB/s readreverse : 306.428 micros/op 3263 ops/sec; 3263.5 MB/s readreverse : 330.749 micros/op 3023 ops/sec; 3023.5 MB/s readreverse : 328.903 micros/op 3040 ops/sec; 3040.5 MB/s readreverse : 324.853 micros/op 3078 ops/sec; 3078.4 MB/s readreverse : 320.488 micros/op 3120 ops/sec; 3120.3 MB/s readreverse : 320.536 micros/op 3119 ops/sec; 3119.8 MB/s avg : 3150.21 MB/s ``` After memcpy elimination ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.395 micros/op 2529890 ops/sec; 279.9 MB/s readreverse : 0.368 micros/op 2715922 ops/sec; 300.5 MB/s readreverse : 0.384 micros/op 2603929 ops/sec; 288.1 MB/s readreverse : 0.375 micros/op 2663286 ops/sec; 294.6 MB/s readreverse : 0.357 micros/op 2802180 ops/sec; 310.0 MB/s readreverse : 0.363 micros/op 2757684 ops/sec; 305.1 MB/s readreverse : 0.372 micros/op 2689603 ops/sec; 297.5 MB/s readreverse : 0.379 micros/op 2638599 ops/sec; 291.9 MB/s readreverse : 0.375 micros/op 2663803 ops/sec; 294.7 MB/s readreverse : 0.375 micros/op 2665579 ops/sec; 294.9 MB/s avg: 295.72 MB/s (1.22 X) ==> 1000000_Keys_1KB.txt <== readreverse : 0.879 micros/op 1138112 ops/sec; 1128.8 MB/s readreverse : 0.842 micros/op 1187998 ops/sec; 1178.3 MB/s readreverse : 0.837 micros/op 1194915 ops/sec; 1185.1 MB/s readreverse : 0.845 micros/op 1182983 ops/sec; 1173.3 MB/s readreverse : 0.877 micros/op 1140308 ops/sec; 1131.0 MB/s readreverse : 0.849 micros/op 1177581 ops/sec; 1168.0 MB/s readreverse : 0.915 micros/op 1093284 ops/sec; 1084.3 MB/s readreverse : 0.863 micros/op 1159418 ops/sec; 1149.9 MB/s readreverse : 0.895 micros/op 1117670 ops/sec; 1108.5 MB/s readreverse : 0.852 micros/op 1174116 ops/sec; 1164.5 MB/s avg: 1147.17 MB/s (1.12 X) ==> 1000000_Keys_10KB.txt <== readreverse : 3.870 micros/op 258386 ops/sec; 2527.2 MB/s readreverse : 3.568 micros/op 280296 ops/sec; 2741.5 MB/s readreverse : 4.005 micros/op 249694 ops/sec; 2442.2 MB/s readreverse : 3.550 micros/op 281719 ops/sec; 2755.5 MB/s readreverse : 3.562 micros/op 280758 ops/sec; 2746.1 MB/s readreverse : 3.507 micros/op 285125 ops/sec; 2788.8 MB/s readreverse : 3.463 micros/op 288739 ops/sec; 2824.1 MB/s readreverse : 3.428 micros/op 291734 ops/sec; 2853.4 MB/s readreverse : 3.553 micros/op 281491 ops/sec; 2753.2 MB/s readreverse : 3.535 micros/op 282885 ops/sec; 2766.9 MB/s avg : 2719.89 MB/s (1.17 X) ==> 100000_Keys_100KB.txt <== readreverse : 22.815 micros/op 43830 ops/sec; 4281.0 MB/s readreverse : 29.957 micros/op 33381 ops/sec; 3260.4 MB/s readreverse : 25.334 micros/op 39473 ops/sec; 3855.4 MB/s readreverse : 23.037 micros/op 43409 ops/sec; 4239.8 MB/s readreverse : 27.810 micros/op 35958 ops/sec; 3512.1 MB/s readreverse : 30.327 micros/op 32973 ops/sec; 3220.6 MB/s readreverse : 29.704 micros/op 33665 ops/sec; 3288.2 MB/s readreverse : 29.423 micros/op 33987 ops/sec; 3319.6 MB/s readreverse : 23.334 micros/op 42856 ops/sec; 4185.9 MB/s readreverse : 29.969 micros/op 33368 ops/sec; 3259.1 MB/s avg : 3642.21 MB/s (1.5 X) ==> 10000_Keys_1MB.txt <== readreverse : 244.748 micros/op 4085 ops/sec; 4085.9 MB/s readreverse : 230.208 micros/op 4343 ops/sec; 4344.0 MB/s readreverse : 235.655 micros/op 4243 ops/sec; 4243.6 MB/s readreverse : 235.730 micros/op 4242 ops/sec; 4242.2 MB/s readreverse : 237.346 micros/op 4213 ops/sec; 4213.3 MB/s readreverse : 227.306 micros/op 4399 ops/sec; 4399.4 MB/s readreverse : 194.957 micros/op 5129 ops/sec; 5129.4 MB/s readreverse : 238.359 micros/op 4195 ops/sec; 4195.4 MB/s readreverse : 221.588 micros/op 4512 ops/sec; 4513.0 MB/s readreverse : 235.911 micros/op 4238 ops/sec; 4239.0 MB/s avg : 4360.52 MB/s (1.38 X) ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: andrewkr, yhchiang, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56511
9 years ago
Slice pinned_value_;
Direction direction_;
bool valid_;
bool current_entry_is_merged_;
// for prefix seek mode to support prev()
Statistics* statistics_;
uint64_t max_skip_;
uint64_t max_skippable_internal_keys_;
uint64_t num_internal_keys_skipped_;
uint64_t version_number_;
const Slice* iterate_upper_bound_;
IterKey prefix_start_buf_;
Slice prefix_start_key_;
const bool prefix_same_as_start_;
// Means that we will pin all data blocks we read as long the Iterator
// is not deleted, will be true if ReadOptions::pin_data is true
const bool pin_thru_lifetime_;
const bool total_order_seek_;
// List of operands for merge operator.
Eliminate std::deque initialization while iterating over merge operands Summary: This patch is similar to D52563, When we iterate over a DB with merge operands we keep creating std::queue to store the operands, optimize this by reusing merge_operands_ data member Before the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.757 micros/op 266141 ops/sec; 29.4 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.413 micros/op 2423538 ops/sec; 268.1 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.451 micros/op 2219071 ops/sec; 245.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.420 micros/op 2382039 ops/sec; 263.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.408 micros/op 2452017 ops/sec; 271.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.947 micros/op 253376 ops/sec; 28.0 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.441 micros/op 2266473 ops/sec; 250.7 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.471 micros/op 2122033 ops/sec; 234.8 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.440 micros/op 2271407 ops/sec; 251.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.429 micros/op 2331471 ops/sec; 257.9 MB/s ``` with the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 4.080 micros/op 245092 ops/sec; 27.1 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.308 micros/op 3241843 ops/sec; 358.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.312 micros/op 3200408 ops/sec; 354.0 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.332 micros/op 3013962 ops/sec; 333.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.300 micros/op 3328017 ops/sec; 368.2 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.973 micros/op 251705 ops/sec; 27.8 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.320 micros/op 3123752 ops/sec; 345.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.335 micros/op 2986641 ops/sec; 330.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.339 micros/op 2950047 ops/sec; 326.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.319 micros/op 3131565 ops/sec; 346.4 MB/s ``` Test Plan: make check -j64 Reviewers: yhchiang, andrewkr, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56031
9 years ago
MergeContext merge_context_;
RangeDelAggregator range_del_agg_;
LocalStatistics local_stats_;
PinnedIteratorsManager pinned_iters_mgr_;
// No copying allowed
DBIter(const DBIter&);
void operator=(const DBIter&);
};
inline bool DBIter::ParseKey(ParsedInternalKey* ikey) {
if (!ParseInternalKey(iter_->key(), ikey)) {
status_ = Status::Corruption("corrupted internal key in DBIter");
ROCKS_LOG_ERROR(logger_, "corrupted internal key in DBIter: %s",
iter_->key().ToString(true).c_str());
return false;
} else {
return true;
}
}
void DBIter::Next() {
assert(valid_);
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
// Release temporarily pinned blocks from last operation
ReleaseTempPinnedData();
ResetInternalKeysSkippedCounter();
if (direction_ == kReverse) {
ReverseToForward();
} else if (iter_->Valid() && !current_entry_is_merged_) {
// If the current value is not a merge, the iter position is the
// current key, which is already returned. We can safely issue a
// Next() without checking the current key.
// If the current key is a merge, very likely iter already points
// to the next internal position.
iter_->Next();
PERF_COUNTER_ADD(internal_key_skipped_count, 1);
}
if (statistics_ != nullptr) {
local_stats_.next_count_++;
}
// Now we point to the next internal position, for both of merge and
// not merge cases.
if (!iter_->Valid()) {
valid_ = false;
return;
}
FindNextUserEntry(true /* skipping the current user key */, prefix_same_as_start_);
if (statistics_ != nullptr && valid_) {
local_stats_.next_found_count_++;
local_stats_.bytes_read_ += (key().size() + value().size());
}
}
// PRE: saved_key_ has the current user key if skipping
// POST: saved_key_ should have the next user key if valid_,
// if the current entry is a result of merge
// current_entry_is_merged_ => true
// saved_value_ => the merged value
//
// NOTE: In between, saved_key_ can point to a user key that has
// a delete marker or a sequence number higher than sequence_
// saved_key_ MUST have a proper user_key before calling this function
//
// The prefix_check parameter controls whether we check the iterated
// keys against the prefix of the seeked key. Set to false when
// performing a seek without a key (e.g. SeekToFirst). Set to
// prefix_same_as_start_ for other iterations.
inline void DBIter::FindNextUserEntry(bool skipping, bool prefix_check) {
PERF_TIMER_GUARD(find_next_user_entry_time);
FindNextUserEntryInternal(skipping, prefix_check);
}
// Actual implementation of DBIter::FindNextUserEntry()
void DBIter::FindNextUserEntryInternal(bool skipping, bool prefix_check) {
// Loop until we hit an acceptable entry to yield
assert(iter_->Valid());
assert(direction_ == kForward);
current_entry_is_merged_ = false;
// How many times in a row we have skipped an entry with user key less than
// or equal to saved_key_. We could skip these entries either because
// sequence numbers were too high or because skipping = true.
// What saved_key_ contains throughout this method:
// - if skipping : saved_key_ contains the key that we need to skip,
// and we haven't seen any keys greater than that,
// - if num_skipped > 0 : saved_key_ contains the key that we have skipped
// num_skipped times, and we haven't seen any keys
// greater than that,
// - none of the above : saved_key_ can contain anything, it doesn't matter.
uint64_t num_skipped = 0;
do {
ParsedInternalKey ikey;
if (!ParseKey(&ikey)) {
// Skip corrupted keys.
iter_->Next();
continue;
}
if (iterate_upper_bound_ != nullptr &&
user_comparator_->Compare(ikey.user_key, *iterate_upper_bound_) >= 0) {
break;
}
if (prefix_extractor_ && prefix_check &&
prefix_extractor_->Transform(ikey.user_key)
.compare(prefix_start_key_) != 0) {
break;
}
if (TooManyInternalKeysSkipped()) {
return;
}
if (ikey.sequence <= sequence_) {
if (skipping &&
user_comparator_->Compare(ikey.user_key, saved_key_.GetUserKey()) <=
0) {
num_skipped++; // skip this entry
PERF_COUNTER_ADD(internal_key_skipped_count, 1);
} else {
num_skipped = 0;
switch (ikey.type) {
case kTypeDeletion:
case kTypeSingleDeletion:
// Arrange to skip all upcoming entries for this key since
// they are hidden by this deletion.
saved_key_.SetUserKey(
ikey.user_key,
!iter_->IsKeyPinned() || !pin_thru_lifetime_ /* copy */);
skipping = true;
PERF_COUNTER_ADD(internal_delete_skipped_count, 1);
break;
case kTypeValue:
saved_key_.SetUserKey(
ikey.user_key,
!iter_->IsKeyPinned() || !pin_thru_lifetime_ /* copy */);
if (range_del_agg_.ShouldDelete(
ikey, RangeDelAggregator::RangePositioningMode::
kForwardTraversal)) {
// Arrange to skip all upcoming entries for this key since
// they are hidden by this deletion.
skipping = true;
num_skipped = 0;
PERF_COUNTER_ADD(internal_delete_skipped_count, 1);
} else {
valid_ = true;
return;
}
break;
case kTypeMerge:
saved_key_.SetUserKey(
ikey.user_key,
!iter_->IsKeyPinned() || !pin_thru_lifetime_ /* copy */);
if (range_del_agg_.ShouldDelete(
ikey, RangeDelAggregator::RangePositioningMode::
kForwardTraversal)) {
// Arrange to skip all upcoming entries for this key since
// they are hidden by this deletion.
skipping = true;
num_skipped = 0;
PERF_COUNTER_ADD(internal_delete_skipped_count, 1);
} else {
// By now, we are sure the current ikey is going to yield a
// value
current_entry_is_merged_ = true;
valid_ = true;
MergeValuesNewToOld(); // Go to a different state machine
return;
}
break;
default:
assert(false);
break;
}
}
} else {
// This key was inserted after our snapshot was taken.
PERF_COUNTER_ADD(internal_recent_skipped_count, 1);
// Here saved_key_ may contain some old key, or the default empty key, or
// key assigned by some random other method. We don't care.
if (user_comparator_->Compare(ikey.user_key, saved_key_.GetUserKey()) <=
0) {
num_skipped++;
} else {
saved_key_.SetUserKey(
ikey.user_key,
!iter_->IsKeyPinned() || !pin_thru_lifetime_ /* copy */);
skipping = false;
num_skipped = 0;
}
}
// If we have sequentially iterated via numerous equal keys, then it's
// better to seek so that we can avoid too many key comparisons.
if (num_skipped > max_skip_) {
num_skipped = 0;
std::string last_key;
if (skipping) {
// We're looking for the next user-key but all we see are the same
// user-key with decreasing sequence numbers. Fast forward to
// sequence number 0 and type deletion (the smallest type).
AppendInternalKey(&last_key, ParsedInternalKey(saved_key_.GetUserKey(),
0, kTypeDeletion));
// Don't set skipping = false because we may still see more user-keys
// equal to saved_key_.
} else {
// We saw multiple entries with this user key and sequence numbers
// higher than sequence_. Fast forward to sequence_.
// Note that this only covers a case when a higher key was overwritten
// many times since our snapshot was taken, not the case when a lot of
// different keys were inserted after our snapshot was taken.
AppendInternalKey(&last_key,
ParsedInternalKey(saved_key_.GetUserKey(), sequence_,
kValueTypeForSeek));
}
iter_->Seek(last_key);
RecordTick(statistics_, NUMBER_OF_RESEEKS_IN_ITERATION);
} else {
iter_->Next();
}
} while (iter_->Valid());
valid_ = false;
}
// Merge values of the same user key starting from the current iter_ position
// Scan from the newer entries to older entries.
// PRE: iter_->key() points to the first merge type entry
// saved_key_ stores the user key
// POST: saved_value_ has the merged value for the user key
// iter_ points to the next entry (or invalid)
void DBIter::MergeValuesNewToOld() {
if (!merge_operator_) {
ROCKS_LOG_ERROR(logger_, "Options::merge_operator is null.");
status_ = Status::InvalidArgument("merge_operator_ must be set.");
valid_ = false;
return;
}
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
// Temporarily pin the blocks that hold merge operands
TempPinData();
Eliminate std::deque initialization while iterating over merge operands Summary: This patch is similar to D52563, When we iterate over a DB with merge operands we keep creating std::queue to store the operands, optimize this by reusing merge_operands_ data member Before the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.757 micros/op 266141 ops/sec; 29.4 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.413 micros/op 2423538 ops/sec; 268.1 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.451 micros/op 2219071 ops/sec; 245.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.420 micros/op 2382039 ops/sec; 263.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.408 micros/op 2452017 ops/sec; 271.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.947 micros/op 253376 ops/sec; 28.0 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.441 micros/op 2266473 ops/sec; 250.7 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.471 micros/op 2122033 ops/sec; 234.8 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.440 micros/op 2271407 ops/sec; 251.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.429 micros/op 2331471 ops/sec; 257.9 MB/s ``` with the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 4.080 micros/op 245092 ops/sec; 27.1 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.308 micros/op 3241843 ops/sec; 358.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.312 micros/op 3200408 ops/sec; 354.0 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.332 micros/op 3013962 ops/sec; 333.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.300 micros/op 3328017 ops/sec; 368.2 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.973 micros/op 251705 ops/sec; 27.8 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.320 micros/op 3123752 ops/sec; 345.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.335 micros/op 2986641 ops/sec; 330.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.339 micros/op 2950047 ops/sec; 326.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.319 micros/op 3131565 ops/sec; 346.4 MB/s ``` Test Plan: make check -j64 Reviewers: yhchiang, andrewkr, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56031
9 years ago
merge_context_.Clear();
[RocksDB] [MergeOperator] The new Merge Interface! Uses merge sequences. Summary: Here are the major changes to the Merge Interface. It has been expanded to handle cases where the MergeOperator is not associative. It does so by stacking up merge operations while scanning through the key history (i.e.: during Get() or Compaction), until a valid Put/Delete/end-of-history is encountered; it then applies all of the merge operations in the correct sequence starting with the base/sentinel value. I have also introduced an "AssociativeMerge" function which allows the user to take advantage of associative merge operations (such as in the case of counters). The implementation will always attempt to merge the operations/operands themselves together when they are encountered, and will resort to the "stacking" method if and only if the "associative-merge" fails. This implementation is conjectured to allow MergeOperator to handle the general case, while still providing the user with the ability to take advantage of certain efficiencies in their own merge-operator / data-structure. NOTE: This is a preliminary diff. This must still go through a lot of review, revision, and testing. Feedback welcome! Test Plan: -This is a preliminary diff. I have only just begun testing/debugging it. -I will be testing this with the existing MergeOperator use-cases and unit-tests (counters, string-append, and redis-lists) -I will be "desk-checking" and walking through the code with the help gdb. -I will find a way of stress-testing the new interface / implementation using db_bench, db_test, merge_test, and/or db_stress. -I will ensure that my tests cover all cases: Get-Memtable, Get-Immutable-Memtable, Get-from-Disk, Iterator-Range-Scan, Flush-Memtable-to-L0, Compaction-L0-L1, Compaction-Ln-L(n+1), Put/Delete found, Put/Delete not-found, end-of-history, end-of-file, etc. -A lot of feedback from the reviewers. Reviewers: haobo, dhruba, zshao, emayanke Reviewed By: haobo CC: leveldb Differential Revision: https://reviews.facebook.net/D11499
11 years ago
// Start the merge process by pushing the first operand
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
merge_context_.PushOperand(iter_->value(),
iter_->IsValuePinned() /* operand_pinned */);
ParsedInternalKey ikey;
Status s;
for (iter_->Next(); iter_->Valid(); iter_->Next()) {
if (!ParseKey(&ikey)) {
// skip corrupted key
continue;
}
if (!user_comparator_->Equal(ikey.user_key, saved_key_.GetUserKey())) {
// hit the next user key, stop right here
break;
} else if (kTypeDeletion == ikey.type || kTypeSingleDeletion == ikey.type ||
range_del_agg_.ShouldDelete(
ikey, RangeDelAggregator::RangePositioningMode::
kForwardTraversal)) {
// hit a delete with the same user key, stop right here
// iter_ is positioned after delete
iter_->Next();
break;
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
9 years ago
} else if (kTypeValue == ikey.type) {
[RocksDB] [MergeOperator] The new Merge Interface! Uses merge sequences. Summary: Here are the major changes to the Merge Interface. It has been expanded to handle cases where the MergeOperator is not associative. It does so by stacking up merge operations while scanning through the key history (i.e.: during Get() or Compaction), until a valid Put/Delete/end-of-history is encountered; it then applies all of the merge operations in the correct sequence starting with the base/sentinel value. I have also introduced an "AssociativeMerge" function which allows the user to take advantage of associative merge operations (such as in the case of counters). The implementation will always attempt to merge the operations/operands themselves together when they are encountered, and will resort to the "stacking" method if and only if the "associative-merge" fails. This implementation is conjectured to allow MergeOperator to handle the general case, while still providing the user with the ability to take advantage of certain efficiencies in their own merge-operator / data-structure. NOTE: This is a preliminary diff. This must still go through a lot of review, revision, and testing. Feedback welcome! Test Plan: -This is a preliminary diff. I have only just begun testing/debugging it. -I will be testing this with the existing MergeOperator use-cases and unit-tests (counters, string-append, and redis-lists) -I will be "desk-checking" and walking through the code with the help gdb. -I will find a way of stress-testing the new interface / implementation using db_bench, db_test, merge_test, and/or db_stress. -I will ensure that my tests cover all cases: Get-Memtable, Get-Immutable-Memtable, Get-from-Disk, Iterator-Range-Scan, Flush-Memtable-to-L0, Compaction-L0-L1, Compaction-Ln-L(n+1), Put/Delete found, Put/Delete not-found, end-of-history, end-of-file, etc. -A lot of feedback from the reviewers. Reviewers: haobo, dhruba, zshao, emayanke Reviewed By: haobo CC: leveldb Differential Revision: https://reviews.facebook.net/D11499
11 years ago
// hit a put, merge the put value with operands and store the
// final result in saved_value_. We are done!
// ignore corruption if there is any.
const Slice val = iter_->value();
s = MergeHelper::TimedFullMerge(
merge_operator_, ikey.user_key, &val, merge_context_.GetOperands(),
&saved_value_, logger_, statistics_, env_, &pinned_value_);
if (!s.ok()) {
status_ = s;
}
// iter_ is positioned after put
iter_->Next();
return;
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
9 years ago
} else if (kTypeMerge == ikey.type) {
[RocksDB] [MergeOperator] The new Merge Interface! Uses merge sequences. Summary: Here are the major changes to the Merge Interface. It has been expanded to handle cases where the MergeOperator is not associative. It does so by stacking up merge operations while scanning through the key history (i.e.: during Get() or Compaction), until a valid Put/Delete/end-of-history is encountered; it then applies all of the merge operations in the correct sequence starting with the base/sentinel value. I have also introduced an "AssociativeMerge" function which allows the user to take advantage of associative merge operations (such as in the case of counters). The implementation will always attempt to merge the operations/operands themselves together when they are encountered, and will resort to the "stacking" method if and only if the "associative-merge" fails. This implementation is conjectured to allow MergeOperator to handle the general case, while still providing the user with the ability to take advantage of certain efficiencies in their own merge-operator / data-structure. NOTE: This is a preliminary diff. This must still go through a lot of review, revision, and testing. Feedback welcome! Test Plan: -This is a preliminary diff. I have only just begun testing/debugging it. -I will be testing this with the existing MergeOperator use-cases and unit-tests (counters, string-append, and redis-lists) -I will be "desk-checking" and walking through the code with the help gdb. -I will find a way of stress-testing the new interface / implementation using db_bench, db_test, merge_test, and/or db_stress. -I will ensure that my tests cover all cases: Get-Memtable, Get-Immutable-Memtable, Get-from-Disk, Iterator-Range-Scan, Flush-Memtable-to-L0, Compaction-L0-L1, Compaction-Ln-L(n+1), Put/Delete found, Put/Delete not-found, end-of-history, end-of-file, etc. -A lot of feedback from the reviewers. Reviewers: haobo, dhruba, zshao, emayanke Reviewed By: haobo CC: leveldb Differential Revision: https://reviews.facebook.net/D11499
11 years ago
// hit a merge, add the value as an operand and run associative merge.
// when complete, add result to operands and continue.
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
merge_context_.PushOperand(iter_->value(),
iter_->IsValuePinned() /* operand_pinned */);
PERF_COUNTER_ADD(internal_merge_count, 1);
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
9 years ago
} else {
assert(false);
}
}
// we either exhausted all internal keys under this user key, or hit
// a deletion marker.
// feed null as the existing value to the merge operator, such that
// client can differentiate this scenario and do things accordingly.
s = MergeHelper::TimedFullMerge(merge_operator_, saved_key_.GetUserKey(),
nullptr, merge_context_.GetOperands(),
&saved_value_, logger_, statistics_, env_,
&pinned_value_);
if (!s.ok()) {
status_ = s;
}
}
void DBIter::Prev() {
assert(valid_);
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
ReleaseTempPinnedData();
ResetInternalKeysSkippedCounter();
if (direction_ == kForward) {
ReverseToBackward();
}
PrevInternal();
if (statistics_ != nullptr) {
local_stats_.prev_count_++;
if (valid_) {
local_stats_.prev_found_count_++;
local_stats_.bytes_read_ += (key().size() + value().size());
}
}
}
void DBIter::ReverseToForward() {
if (prefix_extractor_ != nullptr && !total_order_seek_) {
IterKey last_key;
last_key.SetInternalKey(ParsedInternalKey(
saved_key_.GetUserKey(), kMaxSequenceNumber, kValueTypeForSeek));
iter_->Seek(last_key.GetInternalKey());
}
FindNextUserKey();
direction_ = kForward;
if (!iter_->Valid()) {
iter_->SeekToFirst();
range_del_agg_.InvalidateTombstoneMapPositions();
}
}
void DBIter::ReverseToBackward() {
if (prefix_extractor_ != nullptr && !total_order_seek_) {
IterKey last_key;
last_key.SetInternalKey(ParsedInternalKey(saved_key_.GetUserKey(), 0,
kValueTypeForSeekForPrev));
iter_->SeekForPrev(last_key.GetInternalKey());
}
if (current_entry_is_merged_) {
// Not placed in the same key. Need to call Prev() until finding the
// previous key.
if (!iter_->Valid()) {
iter_->SeekToLast();
range_del_agg_.InvalidateTombstoneMapPositions();
}
ParsedInternalKey ikey;
FindParseableKey(&ikey, kReverse);
while (iter_->Valid() &&
user_comparator_->Compare(ikey.user_key, saved_key_.GetUserKey()) >
0) {
if (ikey.sequence > sequence_) {
PERF_COUNTER_ADD(internal_recent_skipped_count, 1);
} else {
PERF_COUNTER_ADD(internal_key_skipped_count, 1);
}
iter_->Prev();
FindParseableKey(&ikey, kReverse);
}
}
#ifndef NDEBUG
if (iter_->Valid()) {
ParsedInternalKey ikey;
assert(ParseKey(&ikey));
assert(user_comparator_->Compare(ikey.user_key, saved_key_.GetUserKey()) <=
0);
}
#endif
FindPrevUserKey();
direction_ = kReverse;
}
void DBIter::PrevInternal() {
if (!iter_->Valid()) {
valid_ = false;
return;
}
ParsedInternalKey ikey;
while (iter_->Valid()) {
saved_key_.SetUserKey(
ExtractUserKey(iter_->key()),
!iter_->IsKeyPinned() || !pin_thru_lifetime_ /* copy */);
if (FindValueForCurrentKey()) {
valid_ = true;
if (!iter_->Valid()) {
return;
}
FindParseableKey(&ikey, kReverse);
if (user_comparator_->Equal(ikey.user_key, saved_key_.GetUserKey())) {
FindPrevUserKey();
}
if (valid_ && prefix_extractor_ && prefix_same_as_start_ &&
prefix_extractor_->Transform(saved_key_.GetUserKey())
.compare(prefix_start_key_) != 0) {
valid_ = false;
}
return;
}
if (TooManyInternalKeysSkipped(false)) {
return;
}
if (!iter_->Valid()) {
break;
}
FindParseableKey(&ikey, kReverse);
if (user_comparator_->Equal(ikey.user_key, saved_key_.GetUserKey())) {
FindPrevUserKey();
}
}
// We haven't found any key - iterator is not valid
// Or the prefix is different than start prefix
assert(!iter_->Valid());
valid_ = false;
}
// This function checks, if the entry with biggest sequence_number <= sequence_
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
9 years ago
// is non kTypeDeletion or kTypeSingleDeletion. If it's not, we save value in
// saved_value_
bool DBIter::FindValueForCurrentKey() {
assert(iter_->Valid());
Eliminate std::deque initialization while iterating over merge operands Summary: This patch is similar to D52563, When we iterate over a DB with merge operands we keep creating std::queue to store the operands, optimize this by reusing merge_operands_ data member Before the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.757 micros/op 266141 ops/sec; 29.4 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.413 micros/op 2423538 ops/sec; 268.1 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.451 micros/op 2219071 ops/sec; 245.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.420 micros/op 2382039 ops/sec; 263.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.408 micros/op 2452017 ops/sec; 271.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.947 micros/op 253376 ops/sec; 28.0 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.441 micros/op 2266473 ops/sec; 250.7 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.471 micros/op 2122033 ops/sec; 234.8 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.440 micros/op 2271407 ops/sec; 251.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.429 micros/op 2331471 ops/sec; 257.9 MB/s ``` with the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 4.080 micros/op 245092 ops/sec; 27.1 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.308 micros/op 3241843 ops/sec; 358.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.312 micros/op 3200408 ops/sec; 354.0 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.332 micros/op 3013962 ops/sec; 333.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.300 micros/op 3328017 ops/sec; 368.2 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.973 micros/op 251705 ops/sec; 27.8 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.320 micros/op 3123752 ops/sec; 345.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.335 micros/op 2986641 ops/sec; 330.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.339 micros/op 2950047 ops/sec; 326.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.319 micros/op 3131565 ops/sec; 346.4 MB/s ``` Test Plan: make check -j64 Reviewers: yhchiang, andrewkr, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56031
9 years ago
merge_context_.Clear();
Eliminate memcpy in Iterator::Prev() by pinning blocks for keys spanning multiple blocks Summary: This diff is stacked on top of this diff https://reviews.facebook.net/D56493 The current Iterator::Prev() implementation need to copy every value since the underlying Iterator may move after reading the value. This can be optimized by making sure that the block containing the value is pinned until the Iterator move. which will improve the throughput by up to 1.5X master ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.449 micros/op 2225887 ops/sec; 246.2 MB/s readreverse : 0.433 micros/op 2311508 ops/sec; 255.7 MB/s readreverse : 0.436 micros/op 2294335 ops/sec; 253.8 MB/s readreverse : 0.471 micros/op 2121295 ops/sec; 234.7 MB/s readreverse : 0.465 micros/op 2152227 ops/sec; 238.1 MB/s readreverse : 0.454 micros/op 2203011 ops/sec; 243.7 MB/s readreverse : 0.451 micros/op 2216095 ops/sec; 245.2 MB/s readreverse : 0.462 micros/op 2162447 ops/sec; 239.2 MB/s readreverse : 0.476 micros/op 2099151 ops/sec; 232.2 MB/s readreverse : 0.472 micros/op 2120710 ops/sec; 234.6 MB/s avg : 242.34 MB/s ==> 1000000_Keys_1KB.txt <== readreverse : 1.013 micros/op 986793 ops/sec; 978.7 MB/s readreverse : 0.942 micros/op 1061136 ops/sec; 1052.5 MB/s readreverse : 0.951 micros/op 1051901 ops/sec; 1043.3 MB/s readreverse : 0.932 micros/op 1072894 ops/sec; 1064.1 MB/s readreverse : 1.024 micros/op 976720 ops/sec; 968.7 MB/s readreverse : 0.935 micros/op 1069169 ops/sec; 1060.4 MB/s readreverse : 1.012 micros/op 988132 ops/sec; 980.1 MB/s readreverse : 0.962 micros/op 1039579 ops/sec; 1031.1 MB/s readreverse : 0.991 micros/op 1008924 ops/sec; 1000.7 MB/s readreverse : 1.004 micros/op 996144 ops/sec; 988.0 MB/s avg : 1016.76 MB/s ==> 1000000_Keys_10KB.txt <== readreverse : 4.167 micros/op 239952 ops/sec; 2346.9 MB/s readreverse : 4.070 micros/op 245713 ops/sec; 2403.3 MB/s readreverse : 4.572 micros/op 218733 ops/sec; 2139.4 MB/s readreverse : 4.497 micros/op 222388 ops/sec; 2175.2 MB/s readreverse : 4.203 micros/op 237920 ops/sec; 2327.1 MB/s readreverse : 4.206 micros/op 237756 ops/sec; 2325.5 MB/s readreverse : 4.181 micros/op 239149 ops/sec; 2339.1 MB/s readreverse : 4.157 micros/op 240552 ops/sec; 2352.8 MB/s readreverse : 4.187 micros/op 238848 ops/sec; 2336.1 MB/s readreverse : 4.106 micros/op 243575 ops/sec; 2382.4 MB/s avg : 2312.78 MB/s ==> 100000_Keys_100KB.txt <== readreverse : 41.281 micros/op 24224 ops/sec; 2366.0 MB/s readreverse : 39.722 micros/op 25175 ops/sec; 2458.9 MB/s readreverse : 40.319 micros/op 24802 ops/sec; 2422.5 MB/s readreverse : 39.762 micros/op 25149 ops/sec; 2456.4 MB/s readreverse : 40.916 micros/op 24440 ops/sec; 2387.1 MB/s readreverse : 41.188 micros/op 24278 ops/sec; 2371.4 MB/s readreverse : 40.061 micros/op 24962 ops/sec; 2438.1 MB/s readreverse : 40.221 micros/op 24862 ops/sec; 2428.4 MB/s readreverse : 40.084 micros/op 24947 ops/sec; 2436.7 MB/s readreverse : 40.655 micros/op 24597 ops/sec; 2402.4 MB/s avg : 2416.79 MB/s ==> 10000_Keys_1MB.txt <== readreverse : 298.038 micros/op 3355 ops/sec; 3355.3 MB/s readreverse : 335.001 micros/op 2985 ops/sec; 2985.1 MB/s readreverse : 286.956 micros/op 3484 ops/sec; 3484.9 MB/s readreverse : 329.954 micros/op 3030 ops/sec; 3030.8 MB/s readreverse : 306.428 micros/op 3263 ops/sec; 3263.5 MB/s readreverse : 330.749 micros/op 3023 ops/sec; 3023.5 MB/s readreverse : 328.903 micros/op 3040 ops/sec; 3040.5 MB/s readreverse : 324.853 micros/op 3078 ops/sec; 3078.4 MB/s readreverse : 320.488 micros/op 3120 ops/sec; 3120.3 MB/s readreverse : 320.536 micros/op 3119 ops/sec; 3119.8 MB/s avg : 3150.21 MB/s ``` After memcpy elimination ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.395 micros/op 2529890 ops/sec; 279.9 MB/s readreverse : 0.368 micros/op 2715922 ops/sec; 300.5 MB/s readreverse : 0.384 micros/op 2603929 ops/sec; 288.1 MB/s readreverse : 0.375 micros/op 2663286 ops/sec; 294.6 MB/s readreverse : 0.357 micros/op 2802180 ops/sec; 310.0 MB/s readreverse : 0.363 micros/op 2757684 ops/sec; 305.1 MB/s readreverse : 0.372 micros/op 2689603 ops/sec; 297.5 MB/s readreverse : 0.379 micros/op 2638599 ops/sec; 291.9 MB/s readreverse : 0.375 micros/op 2663803 ops/sec; 294.7 MB/s readreverse : 0.375 micros/op 2665579 ops/sec; 294.9 MB/s avg: 295.72 MB/s (1.22 X) ==> 1000000_Keys_1KB.txt <== readreverse : 0.879 micros/op 1138112 ops/sec; 1128.8 MB/s readreverse : 0.842 micros/op 1187998 ops/sec; 1178.3 MB/s readreverse : 0.837 micros/op 1194915 ops/sec; 1185.1 MB/s readreverse : 0.845 micros/op 1182983 ops/sec; 1173.3 MB/s readreverse : 0.877 micros/op 1140308 ops/sec; 1131.0 MB/s readreverse : 0.849 micros/op 1177581 ops/sec; 1168.0 MB/s readreverse : 0.915 micros/op 1093284 ops/sec; 1084.3 MB/s readreverse : 0.863 micros/op 1159418 ops/sec; 1149.9 MB/s readreverse : 0.895 micros/op 1117670 ops/sec; 1108.5 MB/s readreverse : 0.852 micros/op 1174116 ops/sec; 1164.5 MB/s avg: 1147.17 MB/s (1.12 X) ==> 1000000_Keys_10KB.txt <== readreverse : 3.870 micros/op 258386 ops/sec; 2527.2 MB/s readreverse : 3.568 micros/op 280296 ops/sec; 2741.5 MB/s readreverse : 4.005 micros/op 249694 ops/sec; 2442.2 MB/s readreverse : 3.550 micros/op 281719 ops/sec; 2755.5 MB/s readreverse : 3.562 micros/op 280758 ops/sec; 2746.1 MB/s readreverse : 3.507 micros/op 285125 ops/sec; 2788.8 MB/s readreverse : 3.463 micros/op 288739 ops/sec; 2824.1 MB/s readreverse : 3.428 micros/op 291734 ops/sec; 2853.4 MB/s readreverse : 3.553 micros/op 281491 ops/sec; 2753.2 MB/s readreverse : 3.535 micros/op 282885 ops/sec; 2766.9 MB/s avg : 2719.89 MB/s (1.17 X) ==> 100000_Keys_100KB.txt <== readreverse : 22.815 micros/op 43830 ops/sec; 4281.0 MB/s readreverse : 29.957 micros/op 33381 ops/sec; 3260.4 MB/s readreverse : 25.334 micros/op 39473 ops/sec; 3855.4 MB/s readreverse : 23.037 micros/op 43409 ops/sec; 4239.8 MB/s readreverse : 27.810 micros/op 35958 ops/sec; 3512.1 MB/s readreverse : 30.327 micros/op 32973 ops/sec; 3220.6 MB/s readreverse : 29.704 micros/op 33665 ops/sec; 3288.2 MB/s readreverse : 29.423 micros/op 33987 ops/sec; 3319.6 MB/s readreverse : 23.334 micros/op 42856 ops/sec; 4185.9 MB/s readreverse : 29.969 micros/op 33368 ops/sec; 3259.1 MB/s avg : 3642.21 MB/s (1.5 X) ==> 10000_Keys_1MB.txt <== readreverse : 244.748 micros/op 4085 ops/sec; 4085.9 MB/s readreverse : 230.208 micros/op 4343 ops/sec; 4344.0 MB/s readreverse : 235.655 micros/op 4243 ops/sec; 4243.6 MB/s readreverse : 235.730 micros/op 4242 ops/sec; 4242.2 MB/s readreverse : 237.346 micros/op 4213 ops/sec; 4213.3 MB/s readreverse : 227.306 micros/op 4399 ops/sec; 4399.4 MB/s readreverse : 194.957 micros/op 5129 ops/sec; 5129.4 MB/s readreverse : 238.359 micros/op 4195 ops/sec; 4195.4 MB/s readreverse : 221.588 micros/op 4512 ops/sec; 4513.0 MB/s readreverse : 235.911 micros/op 4238 ops/sec; 4239.0 MB/s avg : 4360.52 MB/s (1.38 X) ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: andrewkr, yhchiang, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56511
9 years ago
current_entry_is_merged_ = false;
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
9 years ago
// last entry before merge (could be kTypeDeletion, kTypeSingleDeletion or
// kTypeValue)
ValueType last_not_merge_type = kTypeDeletion;
ValueType last_key_entry_type = kTypeDeletion;
ParsedInternalKey ikey;
FindParseableKey(&ikey, kReverse);
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
// Temporarily pin blocks that hold (merge operands / the value)
ReleaseTempPinnedData();
TempPinData();
size_t num_skipped = 0;
while (iter_->Valid() && ikey.sequence <= sequence_ &&
user_comparator_->Equal(ikey.user_key, saved_key_.GetUserKey())) {
if (TooManyInternalKeysSkipped()) {
return false;
}
// We iterate too much: let's use Seek() to avoid too much key comparisons
if (num_skipped >= max_skip_) {
return FindValueForCurrentKeyUsingSeek();
}
last_key_entry_type = ikey.type;
switch (last_key_entry_type) {
case kTypeValue:
if (range_del_agg_.ShouldDelete(
ikey,
RangeDelAggregator::RangePositioningMode::kBackwardTraversal)) {
last_key_entry_type = kTypeRangeDeletion;
PERF_COUNTER_ADD(internal_delete_skipped_count, 1);
} else {
assert(iter_->IsValuePinned());
pinned_value_ = iter_->value();
}
Eliminate std::deque initialization while iterating over merge operands Summary: This patch is similar to D52563, When we iterate over a DB with merge operands we keep creating std::queue to store the operands, optimize this by reusing merge_operands_ data member Before the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.757 micros/op 266141 ops/sec; 29.4 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.413 micros/op 2423538 ops/sec; 268.1 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.451 micros/op 2219071 ops/sec; 245.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.420 micros/op 2382039 ops/sec; 263.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.408 micros/op 2452017 ops/sec; 271.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.947 micros/op 253376 ops/sec; 28.0 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.441 micros/op 2266473 ops/sec; 250.7 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.471 micros/op 2122033 ops/sec; 234.8 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.440 micros/op 2271407 ops/sec; 251.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.429 micros/op 2331471 ops/sec; 257.9 MB/s ``` with the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 4.080 micros/op 245092 ops/sec; 27.1 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.308 micros/op 3241843 ops/sec; 358.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.312 micros/op 3200408 ops/sec; 354.0 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.332 micros/op 3013962 ops/sec; 333.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.300 micros/op 3328017 ops/sec; 368.2 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.973 micros/op 251705 ops/sec; 27.8 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.320 micros/op 3123752 ops/sec; 345.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.335 micros/op 2986641 ops/sec; 330.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.339 micros/op 2950047 ops/sec; 326.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.319 micros/op 3131565 ops/sec; 346.4 MB/s ``` Test Plan: make check -j64 Reviewers: yhchiang, andrewkr, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56031
9 years ago
merge_context_.Clear();
last_not_merge_type = last_key_entry_type;
break;
case kTypeDeletion:
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
9 years ago
case kTypeSingleDeletion:
Eliminate std::deque initialization while iterating over merge operands Summary: This patch is similar to D52563, When we iterate over a DB with merge operands we keep creating std::queue to store the operands, optimize this by reusing merge_operands_ data member Before the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.757 micros/op 266141 ops/sec; 29.4 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.413 micros/op 2423538 ops/sec; 268.1 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.451 micros/op 2219071 ops/sec; 245.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.420 micros/op 2382039 ops/sec; 263.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.408 micros/op 2452017 ops/sec; 271.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.947 micros/op 253376 ops/sec; 28.0 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.441 micros/op 2266473 ops/sec; 250.7 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.471 micros/op 2122033 ops/sec; 234.8 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.440 micros/op 2271407 ops/sec; 251.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.429 micros/op 2331471 ops/sec; 257.9 MB/s ``` with the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 4.080 micros/op 245092 ops/sec; 27.1 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.308 micros/op 3241843 ops/sec; 358.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.312 micros/op 3200408 ops/sec; 354.0 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.332 micros/op 3013962 ops/sec; 333.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.300 micros/op 3328017 ops/sec; 368.2 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.973 micros/op 251705 ops/sec; 27.8 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.320 micros/op 3123752 ops/sec; 345.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.335 micros/op 2986641 ops/sec; 330.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.339 micros/op 2950047 ops/sec; 326.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.319 micros/op 3131565 ops/sec; 346.4 MB/s ``` Test Plan: make check -j64 Reviewers: yhchiang, andrewkr, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56031
9 years ago
merge_context_.Clear();
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
9 years ago
last_not_merge_type = last_key_entry_type;
PERF_COUNTER_ADD(internal_delete_skipped_count, 1);
break;
case kTypeMerge:
if (range_del_agg_.ShouldDelete(
ikey,
RangeDelAggregator::RangePositioningMode::kBackwardTraversal)) {
merge_context_.Clear();
last_key_entry_type = kTypeRangeDeletion;
last_not_merge_type = last_key_entry_type;
PERF_COUNTER_ADD(internal_delete_skipped_count, 1);
} else {
assert(merge_operator_ != nullptr);
merge_context_.PushOperandBack(
iter_->value(), iter_->IsValuePinned() /* operand_pinned */);
PERF_COUNTER_ADD(internal_merge_count, 1);
}
break;
default:
assert(false);
}
PERF_COUNTER_ADD(internal_key_skipped_count, 1);
assert(user_comparator_->Equal(ikey.user_key, saved_key_.GetUserKey()));
iter_->Prev();
++num_skipped;
FindParseableKey(&ikey, kReverse);
}
Status s;
switch (last_key_entry_type) {
case kTypeDeletion:
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
9 years ago
case kTypeSingleDeletion:
case kTypeRangeDeletion:
valid_ = false;
return false;
case kTypeMerge:
Eliminate memcpy in Iterator::Prev() by pinning blocks for keys spanning multiple blocks Summary: This diff is stacked on top of this diff https://reviews.facebook.net/D56493 The current Iterator::Prev() implementation need to copy every value since the underlying Iterator may move after reading the value. This can be optimized by making sure that the block containing the value is pinned until the Iterator move. which will improve the throughput by up to 1.5X master ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.449 micros/op 2225887 ops/sec; 246.2 MB/s readreverse : 0.433 micros/op 2311508 ops/sec; 255.7 MB/s readreverse : 0.436 micros/op 2294335 ops/sec; 253.8 MB/s readreverse : 0.471 micros/op 2121295 ops/sec; 234.7 MB/s readreverse : 0.465 micros/op 2152227 ops/sec; 238.1 MB/s readreverse : 0.454 micros/op 2203011 ops/sec; 243.7 MB/s readreverse : 0.451 micros/op 2216095 ops/sec; 245.2 MB/s readreverse : 0.462 micros/op 2162447 ops/sec; 239.2 MB/s readreverse : 0.476 micros/op 2099151 ops/sec; 232.2 MB/s readreverse : 0.472 micros/op 2120710 ops/sec; 234.6 MB/s avg : 242.34 MB/s ==> 1000000_Keys_1KB.txt <== readreverse : 1.013 micros/op 986793 ops/sec; 978.7 MB/s readreverse : 0.942 micros/op 1061136 ops/sec; 1052.5 MB/s readreverse : 0.951 micros/op 1051901 ops/sec; 1043.3 MB/s readreverse : 0.932 micros/op 1072894 ops/sec; 1064.1 MB/s readreverse : 1.024 micros/op 976720 ops/sec; 968.7 MB/s readreverse : 0.935 micros/op 1069169 ops/sec; 1060.4 MB/s readreverse : 1.012 micros/op 988132 ops/sec; 980.1 MB/s readreverse : 0.962 micros/op 1039579 ops/sec; 1031.1 MB/s readreverse : 0.991 micros/op 1008924 ops/sec; 1000.7 MB/s readreverse : 1.004 micros/op 996144 ops/sec; 988.0 MB/s avg : 1016.76 MB/s ==> 1000000_Keys_10KB.txt <== readreverse : 4.167 micros/op 239952 ops/sec; 2346.9 MB/s readreverse : 4.070 micros/op 245713 ops/sec; 2403.3 MB/s readreverse : 4.572 micros/op 218733 ops/sec; 2139.4 MB/s readreverse : 4.497 micros/op 222388 ops/sec; 2175.2 MB/s readreverse : 4.203 micros/op 237920 ops/sec; 2327.1 MB/s readreverse : 4.206 micros/op 237756 ops/sec; 2325.5 MB/s readreverse : 4.181 micros/op 239149 ops/sec; 2339.1 MB/s readreverse : 4.157 micros/op 240552 ops/sec; 2352.8 MB/s readreverse : 4.187 micros/op 238848 ops/sec; 2336.1 MB/s readreverse : 4.106 micros/op 243575 ops/sec; 2382.4 MB/s avg : 2312.78 MB/s ==> 100000_Keys_100KB.txt <== readreverse : 41.281 micros/op 24224 ops/sec; 2366.0 MB/s readreverse : 39.722 micros/op 25175 ops/sec; 2458.9 MB/s readreverse : 40.319 micros/op 24802 ops/sec; 2422.5 MB/s readreverse : 39.762 micros/op 25149 ops/sec; 2456.4 MB/s readreverse : 40.916 micros/op 24440 ops/sec; 2387.1 MB/s readreverse : 41.188 micros/op 24278 ops/sec; 2371.4 MB/s readreverse : 40.061 micros/op 24962 ops/sec; 2438.1 MB/s readreverse : 40.221 micros/op 24862 ops/sec; 2428.4 MB/s readreverse : 40.084 micros/op 24947 ops/sec; 2436.7 MB/s readreverse : 40.655 micros/op 24597 ops/sec; 2402.4 MB/s avg : 2416.79 MB/s ==> 10000_Keys_1MB.txt <== readreverse : 298.038 micros/op 3355 ops/sec; 3355.3 MB/s readreverse : 335.001 micros/op 2985 ops/sec; 2985.1 MB/s readreverse : 286.956 micros/op 3484 ops/sec; 3484.9 MB/s readreverse : 329.954 micros/op 3030 ops/sec; 3030.8 MB/s readreverse : 306.428 micros/op 3263 ops/sec; 3263.5 MB/s readreverse : 330.749 micros/op 3023 ops/sec; 3023.5 MB/s readreverse : 328.903 micros/op 3040 ops/sec; 3040.5 MB/s readreverse : 324.853 micros/op 3078 ops/sec; 3078.4 MB/s readreverse : 320.488 micros/op 3120 ops/sec; 3120.3 MB/s readreverse : 320.536 micros/op 3119 ops/sec; 3119.8 MB/s avg : 3150.21 MB/s ``` After memcpy elimination ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.395 micros/op 2529890 ops/sec; 279.9 MB/s readreverse : 0.368 micros/op 2715922 ops/sec; 300.5 MB/s readreverse : 0.384 micros/op 2603929 ops/sec; 288.1 MB/s readreverse : 0.375 micros/op 2663286 ops/sec; 294.6 MB/s readreverse : 0.357 micros/op 2802180 ops/sec; 310.0 MB/s readreverse : 0.363 micros/op 2757684 ops/sec; 305.1 MB/s readreverse : 0.372 micros/op 2689603 ops/sec; 297.5 MB/s readreverse : 0.379 micros/op 2638599 ops/sec; 291.9 MB/s readreverse : 0.375 micros/op 2663803 ops/sec; 294.7 MB/s readreverse : 0.375 micros/op 2665579 ops/sec; 294.9 MB/s avg: 295.72 MB/s (1.22 X) ==> 1000000_Keys_1KB.txt <== readreverse : 0.879 micros/op 1138112 ops/sec; 1128.8 MB/s readreverse : 0.842 micros/op 1187998 ops/sec; 1178.3 MB/s readreverse : 0.837 micros/op 1194915 ops/sec; 1185.1 MB/s readreverse : 0.845 micros/op 1182983 ops/sec; 1173.3 MB/s readreverse : 0.877 micros/op 1140308 ops/sec; 1131.0 MB/s readreverse : 0.849 micros/op 1177581 ops/sec; 1168.0 MB/s readreverse : 0.915 micros/op 1093284 ops/sec; 1084.3 MB/s readreverse : 0.863 micros/op 1159418 ops/sec; 1149.9 MB/s readreverse : 0.895 micros/op 1117670 ops/sec; 1108.5 MB/s readreverse : 0.852 micros/op 1174116 ops/sec; 1164.5 MB/s avg: 1147.17 MB/s (1.12 X) ==> 1000000_Keys_10KB.txt <== readreverse : 3.870 micros/op 258386 ops/sec; 2527.2 MB/s readreverse : 3.568 micros/op 280296 ops/sec; 2741.5 MB/s readreverse : 4.005 micros/op 249694 ops/sec; 2442.2 MB/s readreverse : 3.550 micros/op 281719 ops/sec; 2755.5 MB/s readreverse : 3.562 micros/op 280758 ops/sec; 2746.1 MB/s readreverse : 3.507 micros/op 285125 ops/sec; 2788.8 MB/s readreverse : 3.463 micros/op 288739 ops/sec; 2824.1 MB/s readreverse : 3.428 micros/op 291734 ops/sec; 2853.4 MB/s readreverse : 3.553 micros/op 281491 ops/sec; 2753.2 MB/s readreverse : 3.535 micros/op 282885 ops/sec; 2766.9 MB/s avg : 2719.89 MB/s (1.17 X) ==> 100000_Keys_100KB.txt <== readreverse : 22.815 micros/op 43830 ops/sec; 4281.0 MB/s readreverse : 29.957 micros/op 33381 ops/sec; 3260.4 MB/s readreverse : 25.334 micros/op 39473 ops/sec; 3855.4 MB/s readreverse : 23.037 micros/op 43409 ops/sec; 4239.8 MB/s readreverse : 27.810 micros/op 35958 ops/sec; 3512.1 MB/s readreverse : 30.327 micros/op 32973 ops/sec; 3220.6 MB/s readreverse : 29.704 micros/op 33665 ops/sec; 3288.2 MB/s readreverse : 29.423 micros/op 33987 ops/sec; 3319.6 MB/s readreverse : 23.334 micros/op 42856 ops/sec; 4185.9 MB/s readreverse : 29.969 micros/op 33368 ops/sec; 3259.1 MB/s avg : 3642.21 MB/s (1.5 X) ==> 10000_Keys_1MB.txt <== readreverse : 244.748 micros/op 4085 ops/sec; 4085.9 MB/s readreverse : 230.208 micros/op 4343 ops/sec; 4344.0 MB/s readreverse : 235.655 micros/op 4243 ops/sec; 4243.6 MB/s readreverse : 235.730 micros/op 4242 ops/sec; 4242.2 MB/s readreverse : 237.346 micros/op 4213 ops/sec; 4213.3 MB/s readreverse : 227.306 micros/op 4399 ops/sec; 4399.4 MB/s readreverse : 194.957 micros/op 5129 ops/sec; 5129.4 MB/s readreverse : 238.359 micros/op 4195 ops/sec; 4195.4 MB/s readreverse : 221.588 micros/op 4512 ops/sec; 4513.0 MB/s readreverse : 235.911 micros/op 4238 ops/sec; 4239.0 MB/s avg : 4360.52 MB/s (1.38 X) ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: andrewkr, yhchiang, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56511
9 years ago
current_entry_is_merged_ = true;
if (last_not_merge_type == kTypeDeletion ||
last_not_merge_type == kTypeSingleDeletion ||
last_not_merge_type == kTypeRangeDeletion) {
s = MergeHelper::TimedFullMerge(
merge_operator_, saved_key_.GetUserKey(), nullptr,
merge_context_.GetOperands(), &saved_value_, logger_, statistics_,
env_, &pinned_value_);
} else {
assert(last_not_merge_type == kTypeValue);
s = MergeHelper::TimedFullMerge(
merge_operator_, saved_key_.GetUserKey(), &pinned_value_,
merge_context_.GetOperands(), &saved_value_, logger_, statistics_,
env_, &pinned_value_);
}
break;
case kTypeValue:
// do nothing - we've already has value in saved_value_
break;
default:
assert(false);
break;
}
valid_ = true;
if (!s.ok()) {
status_ = s;
}
return true;
}
// This function is used in FindValueForCurrentKey.
// We use Seek() function instead of Prev() to find necessary value
bool DBIter::FindValueForCurrentKeyUsingSeek() {
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
// FindValueForCurrentKey will enable pinning before calling
// FindValueForCurrentKeyUsingSeek()
assert(pinned_iters_mgr_.PinningEnabled());
std::string last_key;
AppendInternalKey(&last_key, ParsedInternalKey(saved_key_.GetUserKey(),
sequence_, kValueTypeForSeek));
iter_->Seek(last_key);
RecordTick(statistics_, NUMBER_OF_RESEEKS_IN_ITERATION);
// assume there is at least one parseable key for this user key
ParsedInternalKey ikey;
FindParseableKey(&ikey, kForward);
if (ikey.type == kTypeDeletion || ikey.type == kTypeSingleDeletion ||
range_del_agg_.ShouldDelete(
ikey, RangeDelAggregator::RangePositioningMode::kBackwardTraversal)) {
valid_ = false;
return false;
}
if (ikey.type == kTypeValue) {
assert(iter_->IsValuePinned());
pinned_value_ = iter_->value();
valid_ = true;
return true;
}
// kTypeMerge. We need to collect all kTypeMerge values and save them
// in operands
Eliminate memcpy in Iterator::Prev() by pinning blocks for keys spanning multiple blocks Summary: This diff is stacked on top of this diff https://reviews.facebook.net/D56493 The current Iterator::Prev() implementation need to copy every value since the underlying Iterator may move after reading the value. This can be optimized by making sure that the block containing the value is pinned until the Iterator move. which will improve the throughput by up to 1.5X master ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.449 micros/op 2225887 ops/sec; 246.2 MB/s readreverse : 0.433 micros/op 2311508 ops/sec; 255.7 MB/s readreverse : 0.436 micros/op 2294335 ops/sec; 253.8 MB/s readreverse : 0.471 micros/op 2121295 ops/sec; 234.7 MB/s readreverse : 0.465 micros/op 2152227 ops/sec; 238.1 MB/s readreverse : 0.454 micros/op 2203011 ops/sec; 243.7 MB/s readreverse : 0.451 micros/op 2216095 ops/sec; 245.2 MB/s readreverse : 0.462 micros/op 2162447 ops/sec; 239.2 MB/s readreverse : 0.476 micros/op 2099151 ops/sec; 232.2 MB/s readreverse : 0.472 micros/op 2120710 ops/sec; 234.6 MB/s avg : 242.34 MB/s ==> 1000000_Keys_1KB.txt <== readreverse : 1.013 micros/op 986793 ops/sec; 978.7 MB/s readreverse : 0.942 micros/op 1061136 ops/sec; 1052.5 MB/s readreverse : 0.951 micros/op 1051901 ops/sec; 1043.3 MB/s readreverse : 0.932 micros/op 1072894 ops/sec; 1064.1 MB/s readreverse : 1.024 micros/op 976720 ops/sec; 968.7 MB/s readreverse : 0.935 micros/op 1069169 ops/sec; 1060.4 MB/s readreverse : 1.012 micros/op 988132 ops/sec; 980.1 MB/s readreverse : 0.962 micros/op 1039579 ops/sec; 1031.1 MB/s readreverse : 0.991 micros/op 1008924 ops/sec; 1000.7 MB/s readreverse : 1.004 micros/op 996144 ops/sec; 988.0 MB/s avg : 1016.76 MB/s ==> 1000000_Keys_10KB.txt <== readreverse : 4.167 micros/op 239952 ops/sec; 2346.9 MB/s readreverse : 4.070 micros/op 245713 ops/sec; 2403.3 MB/s readreverse : 4.572 micros/op 218733 ops/sec; 2139.4 MB/s readreverse : 4.497 micros/op 222388 ops/sec; 2175.2 MB/s readreverse : 4.203 micros/op 237920 ops/sec; 2327.1 MB/s readreverse : 4.206 micros/op 237756 ops/sec; 2325.5 MB/s readreverse : 4.181 micros/op 239149 ops/sec; 2339.1 MB/s readreverse : 4.157 micros/op 240552 ops/sec; 2352.8 MB/s readreverse : 4.187 micros/op 238848 ops/sec; 2336.1 MB/s readreverse : 4.106 micros/op 243575 ops/sec; 2382.4 MB/s avg : 2312.78 MB/s ==> 100000_Keys_100KB.txt <== readreverse : 41.281 micros/op 24224 ops/sec; 2366.0 MB/s readreverse : 39.722 micros/op 25175 ops/sec; 2458.9 MB/s readreverse : 40.319 micros/op 24802 ops/sec; 2422.5 MB/s readreverse : 39.762 micros/op 25149 ops/sec; 2456.4 MB/s readreverse : 40.916 micros/op 24440 ops/sec; 2387.1 MB/s readreverse : 41.188 micros/op 24278 ops/sec; 2371.4 MB/s readreverse : 40.061 micros/op 24962 ops/sec; 2438.1 MB/s readreverse : 40.221 micros/op 24862 ops/sec; 2428.4 MB/s readreverse : 40.084 micros/op 24947 ops/sec; 2436.7 MB/s readreverse : 40.655 micros/op 24597 ops/sec; 2402.4 MB/s avg : 2416.79 MB/s ==> 10000_Keys_1MB.txt <== readreverse : 298.038 micros/op 3355 ops/sec; 3355.3 MB/s readreverse : 335.001 micros/op 2985 ops/sec; 2985.1 MB/s readreverse : 286.956 micros/op 3484 ops/sec; 3484.9 MB/s readreverse : 329.954 micros/op 3030 ops/sec; 3030.8 MB/s readreverse : 306.428 micros/op 3263 ops/sec; 3263.5 MB/s readreverse : 330.749 micros/op 3023 ops/sec; 3023.5 MB/s readreverse : 328.903 micros/op 3040 ops/sec; 3040.5 MB/s readreverse : 324.853 micros/op 3078 ops/sec; 3078.4 MB/s readreverse : 320.488 micros/op 3120 ops/sec; 3120.3 MB/s readreverse : 320.536 micros/op 3119 ops/sec; 3119.8 MB/s avg : 3150.21 MB/s ``` After memcpy elimination ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.395 micros/op 2529890 ops/sec; 279.9 MB/s readreverse : 0.368 micros/op 2715922 ops/sec; 300.5 MB/s readreverse : 0.384 micros/op 2603929 ops/sec; 288.1 MB/s readreverse : 0.375 micros/op 2663286 ops/sec; 294.6 MB/s readreverse : 0.357 micros/op 2802180 ops/sec; 310.0 MB/s readreverse : 0.363 micros/op 2757684 ops/sec; 305.1 MB/s readreverse : 0.372 micros/op 2689603 ops/sec; 297.5 MB/s readreverse : 0.379 micros/op 2638599 ops/sec; 291.9 MB/s readreverse : 0.375 micros/op 2663803 ops/sec; 294.7 MB/s readreverse : 0.375 micros/op 2665579 ops/sec; 294.9 MB/s avg: 295.72 MB/s (1.22 X) ==> 1000000_Keys_1KB.txt <== readreverse : 0.879 micros/op 1138112 ops/sec; 1128.8 MB/s readreverse : 0.842 micros/op 1187998 ops/sec; 1178.3 MB/s readreverse : 0.837 micros/op 1194915 ops/sec; 1185.1 MB/s readreverse : 0.845 micros/op 1182983 ops/sec; 1173.3 MB/s readreverse : 0.877 micros/op 1140308 ops/sec; 1131.0 MB/s readreverse : 0.849 micros/op 1177581 ops/sec; 1168.0 MB/s readreverse : 0.915 micros/op 1093284 ops/sec; 1084.3 MB/s readreverse : 0.863 micros/op 1159418 ops/sec; 1149.9 MB/s readreverse : 0.895 micros/op 1117670 ops/sec; 1108.5 MB/s readreverse : 0.852 micros/op 1174116 ops/sec; 1164.5 MB/s avg: 1147.17 MB/s (1.12 X) ==> 1000000_Keys_10KB.txt <== readreverse : 3.870 micros/op 258386 ops/sec; 2527.2 MB/s readreverse : 3.568 micros/op 280296 ops/sec; 2741.5 MB/s readreverse : 4.005 micros/op 249694 ops/sec; 2442.2 MB/s readreverse : 3.550 micros/op 281719 ops/sec; 2755.5 MB/s readreverse : 3.562 micros/op 280758 ops/sec; 2746.1 MB/s readreverse : 3.507 micros/op 285125 ops/sec; 2788.8 MB/s readreverse : 3.463 micros/op 288739 ops/sec; 2824.1 MB/s readreverse : 3.428 micros/op 291734 ops/sec; 2853.4 MB/s readreverse : 3.553 micros/op 281491 ops/sec; 2753.2 MB/s readreverse : 3.535 micros/op 282885 ops/sec; 2766.9 MB/s avg : 2719.89 MB/s (1.17 X) ==> 100000_Keys_100KB.txt <== readreverse : 22.815 micros/op 43830 ops/sec; 4281.0 MB/s readreverse : 29.957 micros/op 33381 ops/sec; 3260.4 MB/s readreverse : 25.334 micros/op 39473 ops/sec; 3855.4 MB/s readreverse : 23.037 micros/op 43409 ops/sec; 4239.8 MB/s readreverse : 27.810 micros/op 35958 ops/sec; 3512.1 MB/s readreverse : 30.327 micros/op 32973 ops/sec; 3220.6 MB/s readreverse : 29.704 micros/op 33665 ops/sec; 3288.2 MB/s readreverse : 29.423 micros/op 33987 ops/sec; 3319.6 MB/s readreverse : 23.334 micros/op 42856 ops/sec; 4185.9 MB/s readreverse : 29.969 micros/op 33368 ops/sec; 3259.1 MB/s avg : 3642.21 MB/s (1.5 X) ==> 10000_Keys_1MB.txt <== readreverse : 244.748 micros/op 4085 ops/sec; 4085.9 MB/s readreverse : 230.208 micros/op 4343 ops/sec; 4344.0 MB/s readreverse : 235.655 micros/op 4243 ops/sec; 4243.6 MB/s readreverse : 235.730 micros/op 4242 ops/sec; 4242.2 MB/s readreverse : 237.346 micros/op 4213 ops/sec; 4213.3 MB/s readreverse : 227.306 micros/op 4399 ops/sec; 4399.4 MB/s readreverse : 194.957 micros/op 5129 ops/sec; 5129.4 MB/s readreverse : 238.359 micros/op 4195 ops/sec; 4195.4 MB/s readreverse : 221.588 micros/op 4512 ops/sec; 4513.0 MB/s readreverse : 235.911 micros/op 4238 ops/sec; 4239.0 MB/s avg : 4360.52 MB/s (1.38 X) ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: andrewkr, yhchiang, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56511
9 years ago
current_entry_is_merged_ = true;
Eliminate std::deque initialization while iterating over merge operands Summary: This patch is similar to D52563, When we iterate over a DB with merge operands we keep creating std::queue to store the operands, optimize this by reusing merge_operands_ data member Before the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.757 micros/op 266141 ops/sec; 29.4 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.413 micros/op 2423538 ops/sec; 268.1 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.451 micros/op 2219071 ops/sec; 245.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.420 micros/op 2382039 ops/sec; 263.5 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.408 micros/op 2452017 ops/sec; 271.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.947 micros/op 253376 ops/sec; 28.0 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.441 micros/op 2266473 ops/sec; 250.7 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.471 micros/op 2122033 ops/sec; 234.8 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.440 micros/op 2271407 ops/sec; 251.3 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.429 micros/op 2331471 ops/sec; 257.9 MB/s ``` with the patch ``` ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq" --db="/dev/shm/bench_merge_memcpy_on_the_fly/" --merge_operator="put" --merge_keys=10000 --num=10000 DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 4.080 micros/op 245092 ops/sec; 27.1 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.308 micros/op 3241843 ops/sec; 358.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.312 micros/op 3200408 ops/sec; 354.0 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.332 micros/op 3013962 ops/sec; 333.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.300 micros/op 3328017 ops/sec; 368.2 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] mergerandom : 3.973 micros/op 251705 ops/sec; 27.8 MB/s ( updates:10000) DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.320 micros/op 3123752 ops/sec; 345.6 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.335 micros/op 2986641 ops/sec; 330.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.339 micros/op 2950047 ops/sec; 326.4 MB/s DB path: [/dev/shm/bench_merge_memcpy_on_the_fly/] readseq : 0.319 micros/op 3131565 ops/sec; 346.4 MB/s ``` Test Plan: make check -j64 Reviewers: yhchiang, andrewkr, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56031
9 years ago
merge_context_.Clear();
while (
iter_->Valid() &&
user_comparator_->Equal(ikey.user_key, saved_key_.GetUserKey()) &&
ikey.type == kTypeMerge &&
!range_del_agg_.ShouldDelete(
ikey, RangeDelAggregator::RangePositioningMode::kBackwardTraversal)) {
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
merge_context_.PushOperand(iter_->value(),
iter_->IsValuePinned() /* operand_pinned */);
PERF_COUNTER_ADD(internal_merge_count, 1);
iter_->Next();
FindParseableKey(&ikey, kForward);
}
Status s;
if (!iter_->Valid() ||
!user_comparator_->Equal(ikey.user_key, saved_key_.GetUserKey()) ||
ikey.type == kTypeDeletion || ikey.type == kTypeSingleDeletion ||
range_del_agg_.ShouldDelete(
ikey, RangeDelAggregator::RangePositioningMode::kBackwardTraversal)) {
s = MergeHelper::TimedFullMerge(merge_operator_, saved_key_.GetUserKey(),
nullptr, merge_context_.GetOperands(),
&saved_value_, logger_, statistics_, env_,
&pinned_value_);
// Make iter_ valid and point to saved_key_
if (!iter_->Valid() ||
!user_comparator_->Equal(ikey.user_key, saved_key_.GetUserKey())) {
iter_->Seek(last_key);
RecordTick(statistics_, NUMBER_OF_RESEEKS_IN_ITERATION);
}
valid_ = true;
if (!s.ok()) {
status_ = s;
}
return true;
}
const Slice& val = iter_->value();
s = MergeHelper::TimedFullMerge(merge_operator_, saved_key_.GetUserKey(),
&val, merge_context_.GetOperands(),
&saved_value_, logger_, statistics_, env_,
&pinned_value_);
valid_ = true;
if (!s.ok()) {
status_ = s;
}
return true;
}
// Used in Next to change directions
// Go to next user key
// Don't use Seek(),
// because next user key will be very close
void DBIter::FindNextUserKey() {
if (!iter_->Valid()) {
return;
}
ParsedInternalKey ikey;
FindParseableKey(&ikey, kForward);
while (iter_->Valid() &&
!user_comparator_->Equal(ikey.user_key, saved_key_.GetUserKey())) {
iter_->Next();
FindParseableKey(&ikey, kForward);
}
}
// Go to previous user_key
void DBIter::FindPrevUserKey() {
if (!iter_->Valid()) {
return;
}
size_t num_skipped = 0;
ParsedInternalKey ikey;
FindParseableKey(&ikey, kReverse);
int cmp;
while (iter_->Valid() &&
((cmp = user_comparator_->Compare(ikey.user_key,
saved_key_.GetUserKey())) == 0 ||
(cmp > 0 && ikey.sequence > sequence_))) {
if (TooManyInternalKeysSkipped()) {
return;
}
if (cmp == 0) {
if (num_skipped >= max_skip_) {
num_skipped = 0;
IterKey last_key;
last_key.SetInternalKey(ParsedInternalKey(
saved_key_.GetUserKey(), kMaxSequenceNumber, kValueTypeForSeek));
iter_->Seek(last_key.GetInternalKey());
RecordTick(statistics_, NUMBER_OF_RESEEKS_IN_ITERATION);
} else {
++num_skipped;
}
}
if (ikey.sequence > sequence_) {
PERF_COUNTER_ADD(internal_recent_skipped_count, 1);
} else {
PERF_COUNTER_ADD(internal_key_skipped_count, 1);
}
iter_->Prev();
FindParseableKey(&ikey, kReverse);
}
}
bool DBIter::TooManyInternalKeysSkipped(bool increment) {
if ((max_skippable_internal_keys_ > 0) &&
(num_internal_keys_skipped_ > max_skippable_internal_keys_)) {
valid_ = false;
status_ = Status::Incomplete("Too many internal keys skipped.");
return true;
} else if (increment) {
num_internal_keys_skipped_++;
}
return false;
}
// Skip all unparseable keys
void DBIter::FindParseableKey(ParsedInternalKey* ikey, Direction direction) {
while (iter_->Valid() && !ParseKey(ikey)) {
if (direction == kReverse) {
iter_->Prev();
} else {
iter_->Next();
}
}
}
void DBIter::Seek(const Slice& target) {
StopWatch sw(env_, statistics_, DB_SEEK);
Eliminate memcpy in Iterator::Prev() by pinning blocks for keys spanning multiple blocks Summary: This diff is stacked on top of this diff https://reviews.facebook.net/D56493 The current Iterator::Prev() implementation need to copy every value since the underlying Iterator may move after reading the value. This can be optimized by making sure that the block containing the value is pinned until the Iterator move. which will improve the throughput by up to 1.5X master ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.449 micros/op 2225887 ops/sec; 246.2 MB/s readreverse : 0.433 micros/op 2311508 ops/sec; 255.7 MB/s readreverse : 0.436 micros/op 2294335 ops/sec; 253.8 MB/s readreverse : 0.471 micros/op 2121295 ops/sec; 234.7 MB/s readreverse : 0.465 micros/op 2152227 ops/sec; 238.1 MB/s readreverse : 0.454 micros/op 2203011 ops/sec; 243.7 MB/s readreverse : 0.451 micros/op 2216095 ops/sec; 245.2 MB/s readreverse : 0.462 micros/op 2162447 ops/sec; 239.2 MB/s readreverse : 0.476 micros/op 2099151 ops/sec; 232.2 MB/s readreverse : 0.472 micros/op 2120710 ops/sec; 234.6 MB/s avg : 242.34 MB/s ==> 1000000_Keys_1KB.txt <== readreverse : 1.013 micros/op 986793 ops/sec; 978.7 MB/s readreverse : 0.942 micros/op 1061136 ops/sec; 1052.5 MB/s readreverse : 0.951 micros/op 1051901 ops/sec; 1043.3 MB/s readreverse : 0.932 micros/op 1072894 ops/sec; 1064.1 MB/s readreverse : 1.024 micros/op 976720 ops/sec; 968.7 MB/s readreverse : 0.935 micros/op 1069169 ops/sec; 1060.4 MB/s readreverse : 1.012 micros/op 988132 ops/sec; 980.1 MB/s readreverse : 0.962 micros/op 1039579 ops/sec; 1031.1 MB/s readreverse : 0.991 micros/op 1008924 ops/sec; 1000.7 MB/s readreverse : 1.004 micros/op 996144 ops/sec; 988.0 MB/s avg : 1016.76 MB/s ==> 1000000_Keys_10KB.txt <== readreverse : 4.167 micros/op 239952 ops/sec; 2346.9 MB/s readreverse : 4.070 micros/op 245713 ops/sec; 2403.3 MB/s readreverse : 4.572 micros/op 218733 ops/sec; 2139.4 MB/s readreverse : 4.497 micros/op 222388 ops/sec; 2175.2 MB/s readreverse : 4.203 micros/op 237920 ops/sec; 2327.1 MB/s readreverse : 4.206 micros/op 237756 ops/sec; 2325.5 MB/s readreverse : 4.181 micros/op 239149 ops/sec; 2339.1 MB/s readreverse : 4.157 micros/op 240552 ops/sec; 2352.8 MB/s readreverse : 4.187 micros/op 238848 ops/sec; 2336.1 MB/s readreverse : 4.106 micros/op 243575 ops/sec; 2382.4 MB/s avg : 2312.78 MB/s ==> 100000_Keys_100KB.txt <== readreverse : 41.281 micros/op 24224 ops/sec; 2366.0 MB/s readreverse : 39.722 micros/op 25175 ops/sec; 2458.9 MB/s readreverse : 40.319 micros/op 24802 ops/sec; 2422.5 MB/s readreverse : 39.762 micros/op 25149 ops/sec; 2456.4 MB/s readreverse : 40.916 micros/op 24440 ops/sec; 2387.1 MB/s readreverse : 41.188 micros/op 24278 ops/sec; 2371.4 MB/s readreverse : 40.061 micros/op 24962 ops/sec; 2438.1 MB/s readreverse : 40.221 micros/op 24862 ops/sec; 2428.4 MB/s readreverse : 40.084 micros/op 24947 ops/sec; 2436.7 MB/s readreverse : 40.655 micros/op 24597 ops/sec; 2402.4 MB/s avg : 2416.79 MB/s ==> 10000_Keys_1MB.txt <== readreverse : 298.038 micros/op 3355 ops/sec; 3355.3 MB/s readreverse : 335.001 micros/op 2985 ops/sec; 2985.1 MB/s readreverse : 286.956 micros/op 3484 ops/sec; 3484.9 MB/s readreverse : 329.954 micros/op 3030 ops/sec; 3030.8 MB/s readreverse : 306.428 micros/op 3263 ops/sec; 3263.5 MB/s readreverse : 330.749 micros/op 3023 ops/sec; 3023.5 MB/s readreverse : 328.903 micros/op 3040 ops/sec; 3040.5 MB/s readreverse : 324.853 micros/op 3078 ops/sec; 3078.4 MB/s readreverse : 320.488 micros/op 3120 ops/sec; 3120.3 MB/s readreverse : 320.536 micros/op 3119 ops/sec; 3119.8 MB/s avg : 3150.21 MB/s ``` After memcpy elimination ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.395 micros/op 2529890 ops/sec; 279.9 MB/s readreverse : 0.368 micros/op 2715922 ops/sec; 300.5 MB/s readreverse : 0.384 micros/op 2603929 ops/sec; 288.1 MB/s readreverse : 0.375 micros/op 2663286 ops/sec; 294.6 MB/s readreverse : 0.357 micros/op 2802180 ops/sec; 310.0 MB/s readreverse : 0.363 micros/op 2757684 ops/sec; 305.1 MB/s readreverse : 0.372 micros/op 2689603 ops/sec; 297.5 MB/s readreverse : 0.379 micros/op 2638599 ops/sec; 291.9 MB/s readreverse : 0.375 micros/op 2663803 ops/sec; 294.7 MB/s readreverse : 0.375 micros/op 2665579 ops/sec; 294.9 MB/s avg: 295.72 MB/s (1.22 X) ==> 1000000_Keys_1KB.txt <== readreverse : 0.879 micros/op 1138112 ops/sec; 1128.8 MB/s readreverse : 0.842 micros/op 1187998 ops/sec; 1178.3 MB/s readreverse : 0.837 micros/op 1194915 ops/sec; 1185.1 MB/s readreverse : 0.845 micros/op 1182983 ops/sec; 1173.3 MB/s readreverse : 0.877 micros/op 1140308 ops/sec; 1131.0 MB/s readreverse : 0.849 micros/op 1177581 ops/sec; 1168.0 MB/s readreverse : 0.915 micros/op 1093284 ops/sec; 1084.3 MB/s readreverse : 0.863 micros/op 1159418 ops/sec; 1149.9 MB/s readreverse : 0.895 micros/op 1117670 ops/sec; 1108.5 MB/s readreverse : 0.852 micros/op 1174116 ops/sec; 1164.5 MB/s avg: 1147.17 MB/s (1.12 X) ==> 1000000_Keys_10KB.txt <== readreverse : 3.870 micros/op 258386 ops/sec; 2527.2 MB/s readreverse : 3.568 micros/op 280296 ops/sec; 2741.5 MB/s readreverse : 4.005 micros/op 249694 ops/sec; 2442.2 MB/s readreverse : 3.550 micros/op 281719 ops/sec; 2755.5 MB/s readreverse : 3.562 micros/op 280758 ops/sec; 2746.1 MB/s readreverse : 3.507 micros/op 285125 ops/sec; 2788.8 MB/s readreverse : 3.463 micros/op 288739 ops/sec; 2824.1 MB/s readreverse : 3.428 micros/op 291734 ops/sec; 2853.4 MB/s readreverse : 3.553 micros/op 281491 ops/sec; 2753.2 MB/s readreverse : 3.535 micros/op 282885 ops/sec; 2766.9 MB/s avg : 2719.89 MB/s (1.17 X) ==> 100000_Keys_100KB.txt <== readreverse : 22.815 micros/op 43830 ops/sec; 4281.0 MB/s readreverse : 29.957 micros/op 33381 ops/sec; 3260.4 MB/s readreverse : 25.334 micros/op 39473 ops/sec; 3855.4 MB/s readreverse : 23.037 micros/op 43409 ops/sec; 4239.8 MB/s readreverse : 27.810 micros/op 35958 ops/sec; 3512.1 MB/s readreverse : 30.327 micros/op 32973 ops/sec; 3220.6 MB/s readreverse : 29.704 micros/op 33665 ops/sec; 3288.2 MB/s readreverse : 29.423 micros/op 33987 ops/sec; 3319.6 MB/s readreverse : 23.334 micros/op 42856 ops/sec; 4185.9 MB/s readreverse : 29.969 micros/op 33368 ops/sec; 3259.1 MB/s avg : 3642.21 MB/s (1.5 X) ==> 10000_Keys_1MB.txt <== readreverse : 244.748 micros/op 4085 ops/sec; 4085.9 MB/s readreverse : 230.208 micros/op 4343 ops/sec; 4344.0 MB/s readreverse : 235.655 micros/op 4243 ops/sec; 4243.6 MB/s readreverse : 235.730 micros/op 4242 ops/sec; 4242.2 MB/s readreverse : 237.346 micros/op 4213 ops/sec; 4213.3 MB/s readreverse : 227.306 micros/op 4399 ops/sec; 4399.4 MB/s readreverse : 194.957 micros/op 5129 ops/sec; 5129.4 MB/s readreverse : 238.359 micros/op 4195 ops/sec; 4195.4 MB/s readreverse : 221.588 micros/op 4512 ops/sec; 4513.0 MB/s readreverse : 235.911 micros/op 4238 ops/sec; 4239.0 MB/s avg : 4360.52 MB/s (1.38 X) ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: andrewkr, yhchiang, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56511
9 years ago
ReleaseTempPinnedData();
ResetInternalKeysSkippedCounter();
saved_key_.Clear();
saved_key_.SetInternalKey(target, sequence_);
{
PERF_TIMER_GUARD(seek_internal_seek_time);
iter_->Seek(saved_key_.GetInternalKey());
range_del_agg_.InvalidateTombstoneMapPositions();
}
RecordTick(statistics_, NUMBER_DB_SEEK);
if (iter_->Valid()) {
if (prefix_extractor_ && prefix_same_as_start_) {
prefix_start_key_ = prefix_extractor_->Transform(target);
}
direction_ = kForward;
ClearSavedValue();
FindNextUserEntry(false /* not skipping */, prefix_same_as_start_);
if (!valid_) {
prefix_start_key_.clear();
}
if (statistics_ != nullptr) {
if (valid_) {
RecordTick(statistics_, NUMBER_DB_SEEK_FOUND);
RecordTick(statistics_, ITER_BYTES_READ, key().size() + value().size());
}
}
} else {
valid_ = false;
}
if (valid_ && prefix_extractor_ && prefix_same_as_start_) {
prefix_start_buf_.SetUserKey(prefix_start_key_);
prefix_start_key_ = prefix_start_buf_.GetUserKey();
}
}
void DBIter::SeekForPrev(const Slice& target) {
StopWatch sw(env_, statistics_, DB_SEEK);
ReleaseTempPinnedData();
ResetInternalKeysSkippedCounter();
saved_key_.Clear();
// now saved_key is used to store internal key.
saved_key_.SetInternalKey(target, 0 /* sequence_number */,
kValueTypeForSeekForPrev);
{
PERF_TIMER_GUARD(seek_internal_seek_time);
iter_->SeekForPrev(saved_key_.GetInternalKey());
range_del_agg_.InvalidateTombstoneMapPositions();
}
RecordTick(statistics_, NUMBER_DB_SEEK);
if (iter_->Valid()) {
if (prefix_extractor_ && prefix_same_as_start_) {
prefix_start_key_ = prefix_extractor_->Transform(target);
}
direction_ = kReverse;
ClearSavedValue();
PrevInternal();
if (!valid_) {
prefix_start_key_.clear();
}
if (statistics_ != nullptr) {
if (valid_) {
RecordTick(statistics_, NUMBER_DB_SEEK_FOUND);
RecordTick(statistics_, ITER_BYTES_READ, key().size() + value().size());
}
}
} else {
valid_ = false;
}
if (valid_ && prefix_extractor_ && prefix_same_as_start_) {
prefix_start_buf_.SetUserKey(prefix_start_key_);
prefix_start_key_ = prefix_start_buf_.GetUserKey();
}
}
void DBIter::SeekToFirst() {
// Don't use iter_::Seek() if we set a prefix extractor
// because prefix seek will be used.
if (prefix_extractor_ != nullptr) {
max_skip_ = std::numeric_limits<uint64_t>::max();
}
direction_ = kForward;
Eliminate memcpy in Iterator::Prev() by pinning blocks for keys spanning multiple blocks Summary: This diff is stacked on top of this diff https://reviews.facebook.net/D56493 The current Iterator::Prev() implementation need to copy every value since the underlying Iterator may move after reading the value. This can be optimized by making sure that the block containing the value is pinned until the Iterator move. which will improve the throughput by up to 1.5X master ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.449 micros/op 2225887 ops/sec; 246.2 MB/s readreverse : 0.433 micros/op 2311508 ops/sec; 255.7 MB/s readreverse : 0.436 micros/op 2294335 ops/sec; 253.8 MB/s readreverse : 0.471 micros/op 2121295 ops/sec; 234.7 MB/s readreverse : 0.465 micros/op 2152227 ops/sec; 238.1 MB/s readreverse : 0.454 micros/op 2203011 ops/sec; 243.7 MB/s readreverse : 0.451 micros/op 2216095 ops/sec; 245.2 MB/s readreverse : 0.462 micros/op 2162447 ops/sec; 239.2 MB/s readreverse : 0.476 micros/op 2099151 ops/sec; 232.2 MB/s readreverse : 0.472 micros/op 2120710 ops/sec; 234.6 MB/s avg : 242.34 MB/s ==> 1000000_Keys_1KB.txt <== readreverse : 1.013 micros/op 986793 ops/sec; 978.7 MB/s readreverse : 0.942 micros/op 1061136 ops/sec; 1052.5 MB/s readreverse : 0.951 micros/op 1051901 ops/sec; 1043.3 MB/s readreverse : 0.932 micros/op 1072894 ops/sec; 1064.1 MB/s readreverse : 1.024 micros/op 976720 ops/sec; 968.7 MB/s readreverse : 0.935 micros/op 1069169 ops/sec; 1060.4 MB/s readreverse : 1.012 micros/op 988132 ops/sec; 980.1 MB/s readreverse : 0.962 micros/op 1039579 ops/sec; 1031.1 MB/s readreverse : 0.991 micros/op 1008924 ops/sec; 1000.7 MB/s readreverse : 1.004 micros/op 996144 ops/sec; 988.0 MB/s avg : 1016.76 MB/s ==> 1000000_Keys_10KB.txt <== readreverse : 4.167 micros/op 239952 ops/sec; 2346.9 MB/s readreverse : 4.070 micros/op 245713 ops/sec; 2403.3 MB/s readreverse : 4.572 micros/op 218733 ops/sec; 2139.4 MB/s readreverse : 4.497 micros/op 222388 ops/sec; 2175.2 MB/s readreverse : 4.203 micros/op 237920 ops/sec; 2327.1 MB/s readreverse : 4.206 micros/op 237756 ops/sec; 2325.5 MB/s readreverse : 4.181 micros/op 239149 ops/sec; 2339.1 MB/s readreverse : 4.157 micros/op 240552 ops/sec; 2352.8 MB/s readreverse : 4.187 micros/op 238848 ops/sec; 2336.1 MB/s readreverse : 4.106 micros/op 243575 ops/sec; 2382.4 MB/s avg : 2312.78 MB/s ==> 100000_Keys_100KB.txt <== readreverse : 41.281 micros/op 24224 ops/sec; 2366.0 MB/s readreverse : 39.722 micros/op 25175 ops/sec; 2458.9 MB/s readreverse : 40.319 micros/op 24802 ops/sec; 2422.5 MB/s readreverse : 39.762 micros/op 25149 ops/sec; 2456.4 MB/s readreverse : 40.916 micros/op 24440 ops/sec; 2387.1 MB/s readreverse : 41.188 micros/op 24278 ops/sec; 2371.4 MB/s readreverse : 40.061 micros/op 24962 ops/sec; 2438.1 MB/s readreverse : 40.221 micros/op 24862 ops/sec; 2428.4 MB/s readreverse : 40.084 micros/op 24947 ops/sec; 2436.7 MB/s readreverse : 40.655 micros/op 24597 ops/sec; 2402.4 MB/s avg : 2416.79 MB/s ==> 10000_Keys_1MB.txt <== readreverse : 298.038 micros/op 3355 ops/sec; 3355.3 MB/s readreverse : 335.001 micros/op 2985 ops/sec; 2985.1 MB/s readreverse : 286.956 micros/op 3484 ops/sec; 3484.9 MB/s readreverse : 329.954 micros/op 3030 ops/sec; 3030.8 MB/s readreverse : 306.428 micros/op 3263 ops/sec; 3263.5 MB/s readreverse : 330.749 micros/op 3023 ops/sec; 3023.5 MB/s readreverse : 328.903 micros/op 3040 ops/sec; 3040.5 MB/s readreverse : 324.853 micros/op 3078 ops/sec; 3078.4 MB/s readreverse : 320.488 micros/op 3120 ops/sec; 3120.3 MB/s readreverse : 320.536 micros/op 3119 ops/sec; 3119.8 MB/s avg : 3150.21 MB/s ``` After memcpy elimination ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.395 micros/op 2529890 ops/sec; 279.9 MB/s readreverse : 0.368 micros/op 2715922 ops/sec; 300.5 MB/s readreverse : 0.384 micros/op 2603929 ops/sec; 288.1 MB/s readreverse : 0.375 micros/op 2663286 ops/sec; 294.6 MB/s readreverse : 0.357 micros/op 2802180 ops/sec; 310.0 MB/s readreverse : 0.363 micros/op 2757684 ops/sec; 305.1 MB/s readreverse : 0.372 micros/op 2689603 ops/sec; 297.5 MB/s readreverse : 0.379 micros/op 2638599 ops/sec; 291.9 MB/s readreverse : 0.375 micros/op 2663803 ops/sec; 294.7 MB/s readreverse : 0.375 micros/op 2665579 ops/sec; 294.9 MB/s avg: 295.72 MB/s (1.22 X) ==> 1000000_Keys_1KB.txt <== readreverse : 0.879 micros/op 1138112 ops/sec; 1128.8 MB/s readreverse : 0.842 micros/op 1187998 ops/sec; 1178.3 MB/s readreverse : 0.837 micros/op 1194915 ops/sec; 1185.1 MB/s readreverse : 0.845 micros/op 1182983 ops/sec; 1173.3 MB/s readreverse : 0.877 micros/op 1140308 ops/sec; 1131.0 MB/s readreverse : 0.849 micros/op 1177581 ops/sec; 1168.0 MB/s readreverse : 0.915 micros/op 1093284 ops/sec; 1084.3 MB/s readreverse : 0.863 micros/op 1159418 ops/sec; 1149.9 MB/s readreverse : 0.895 micros/op 1117670 ops/sec; 1108.5 MB/s readreverse : 0.852 micros/op 1174116 ops/sec; 1164.5 MB/s avg: 1147.17 MB/s (1.12 X) ==> 1000000_Keys_10KB.txt <== readreverse : 3.870 micros/op 258386 ops/sec; 2527.2 MB/s readreverse : 3.568 micros/op 280296 ops/sec; 2741.5 MB/s readreverse : 4.005 micros/op 249694 ops/sec; 2442.2 MB/s readreverse : 3.550 micros/op 281719 ops/sec; 2755.5 MB/s readreverse : 3.562 micros/op 280758 ops/sec; 2746.1 MB/s readreverse : 3.507 micros/op 285125 ops/sec; 2788.8 MB/s readreverse : 3.463 micros/op 288739 ops/sec; 2824.1 MB/s readreverse : 3.428 micros/op 291734 ops/sec; 2853.4 MB/s readreverse : 3.553 micros/op 281491 ops/sec; 2753.2 MB/s readreverse : 3.535 micros/op 282885 ops/sec; 2766.9 MB/s avg : 2719.89 MB/s (1.17 X) ==> 100000_Keys_100KB.txt <== readreverse : 22.815 micros/op 43830 ops/sec; 4281.0 MB/s readreverse : 29.957 micros/op 33381 ops/sec; 3260.4 MB/s readreverse : 25.334 micros/op 39473 ops/sec; 3855.4 MB/s readreverse : 23.037 micros/op 43409 ops/sec; 4239.8 MB/s readreverse : 27.810 micros/op 35958 ops/sec; 3512.1 MB/s readreverse : 30.327 micros/op 32973 ops/sec; 3220.6 MB/s readreverse : 29.704 micros/op 33665 ops/sec; 3288.2 MB/s readreverse : 29.423 micros/op 33987 ops/sec; 3319.6 MB/s readreverse : 23.334 micros/op 42856 ops/sec; 4185.9 MB/s readreverse : 29.969 micros/op 33368 ops/sec; 3259.1 MB/s avg : 3642.21 MB/s (1.5 X) ==> 10000_Keys_1MB.txt <== readreverse : 244.748 micros/op 4085 ops/sec; 4085.9 MB/s readreverse : 230.208 micros/op 4343 ops/sec; 4344.0 MB/s readreverse : 235.655 micros/op 4243 ops/sec; 4243.6 MB/s readreverse : 235.730 micros/op 4242 ops/sec; 4242.2 MB/s readreverse : 237.346 micros/op 4213 ops/sec; 4213.3 MB/s readreverse : 227.306 micros/op 4399 ops/sec; 4399.4 MB/s readreverse : 194.957 micros/op 5129 ops/sec; 5129.4 MB/s readreverse : 238.359 micros/op 4195 ops/sec; 4195.4 MB/s readreverse : 221.588 micros/op 4512 ops/sec; 4513.0 MB/s readreverse : 235.911 micros/op 4238 ops/sec; 4239.0 MB/s avg : 4360.52 MB/s (1.38 X) ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: andrewkr, yhchiang, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56511
9 years ago
ReleaseTempPinnedData();
ResetInternalKeysSkippedCounter();
ClearSavedValue();
{
PERF_TIMER_GUARD(seek_internal_seek_time);
iter_->SeekToFirst();
range_del_agg_.InvalidateTombstoneMapPositions();
}
RecordTick(statistics_, NUMBER_DB_SEEK);
if (iter_->Valid()) {
saved_key_.SetUserKey(
ExtractUserKey(iter_->key()),
!iter_->IsKeyPinned() || !pin_thru_lifetime_ /* copy */);
FindNextUserEntry(false /* not skipping */, false /* no prefix check */);
if (statistics_ != nullptr) {
if (valid_) {
RecordTick(statistics_, NUMBER_DB_SEEK_FOUND);
RecordTick(statistics_, ITER_BYTES_READ, key().size() + value().size());
}
}
} else {
valid_ = false;
}
if (valid_ && prefix_extractor_ && prefix_same_as_start_) {
prefix_start_buf_.SetUserKey(
prefix_extractor_->Transform(saved_key_.GetUserKey()));
prefix_start_key_ = prefix_start_buf_.GetUserKey();
}
}
void DBIter::SeekToLast() {
// Don't use iter_::Seek() if we set a prefix extractor
// because prefix seek will be used.
if (prefix_extractor_ != nullptr) {
max_skip_ = std::numeric_limits<uint64_t>::max();
}
direction_ = kReverse;
Eliminate memcpy in Iterator::Prev() by pinning blocks for keys spanning multiple blocks Summary: This diff is stacked on top of this diff https://reviews.facebook.net/D56493 The current Iterator::Prev() implementation need to copy every value since the underlying Iterator may move after reading the value. This can be optimized by making sure that the block containing the value is pinned until the Iterator move. which will improve the throughput by up to 1.5X master ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.449 micros/op 2225887 ops/sec; 246.2 MB/s readreverse : 0.433 micros/op 2311508 ops/sec; 255.7 MB/s readreverse : 0.436 micros/op 2294335 ops/sec; 253.8 MB/s readreverse : 0.471 micros/op 2121295 ops/sec; 234.7 MB/s readreverse : 0.465 micros/op 2152227 ops/sec; 238.1 MB/s readreverse : 0.454 micros/op 2203011 ops/sec; 243.7 MB/s readreverse : 0.451 micros/op 2216095 ops/sec; 245.2 MB/s readreverse : 0.462 micros/op 2162447 ops/sec; 239.2 MB/s readreverse : 0.476 micros/op 2099151 ops/sec; 232.2 MB/s readreverse : 0.472 micros/op 2120710 ops/sec; 234.6 MB/s avg : 242.34 MB/s ==> 1000000_Keys_1KB.txt <== readreverse : 1.013 micros/op 986793 ops/sec; 978.7 MB/s readreverse : 0.942 micros/op 1061136 ops/sec; 1052.5 MB/s readreverse : 0.951 micros/op 1051901 ops/sec; 1043.3 MB/s readreverse : 0.932 micros/op 1072894 ops/sec; 1064.1 MB/s readreverse : 1.024 micros/op 976720 ops/sec; 968.7 MB/s readreverse : 0.935 micros/op 1069169 ops/sec; 1060.4 MB/s readreverse : 1.012 micros/op 988132 ops/sec; 980.1 MB/s readreverse : 0.962 micros/op 1039579 ops/sec; 1031.1 MB/s readreverse : 0.991 micros/op 1008924 ops/sec; 1000.7 MB/s readreverse : 1.004 micros/op 996144 ops/sec; 988.0 MB/s avg : 1016.76 MB/s ==> 1000000_Keys_10KB.txt <== readreverse : 4.167 micros/op 239952 ops/sec; 2346.9 MB/s readreverse : 4.070 micros/op 245713 ops/sec; 2403.3 MB/s readreverse : 4.572 micros/op 218733 ops/sec; 2139.4 MB/s readreverse : 4.497 micros/op 222388 ops/sec; 2175.2 MB/s readreverse : 4.203 micros/op 237920 ops/sec; 2327.1 MB/s readreverse : 4.206 micros/op 237756 ops/sec; 2325.5 MB/s readreverse : 4.181 micros/op 239149 ops/sec; 2339.1 MB/s readreverse : 4.157 micros/op 240552 ops/sec; 2352.8 MB/s readreverse : 4.187 micros/op 238848 ops/sec; 2336.1 MB/s readreverse : 4.106 micros/op 243575 ops/sec; 2382.4 MB/s avg : 2312.78 MB/s ==> 100000_Keys_100KB.txt <== readreverse : 41.281 micros/op 24224 ops/sec; 2366.0 MB/s readreverse : 39.722 micros/op 25175 ops/sec; 2458.9 MB/s readreverse : 40.319 micros/op 24802 ops/sec; 2422.5 MB/s readreverse : 39.762 micros/op 25149 ops/sec; 2456.4 MB/s readreverse : 40.916 micros/op 24440 ops/sec; 2387.1 MB/s readreverse : 41.188 micros/op 24278 ops/sec; 2371.4 MB/s readreverse : 40.061 micros/op 24962 ops/sec; 2438.1 MB/s readreverse : 40.221 micros/op 24862 ops/sec; 2428.4 MB/s readreverse : 40.084 micros/op 24947 ops/sec; 2436.7 MB/s readreverse : 40.655 micros/op 24597 ops/sec; 2402.4 MB/s avg : 2416.79 MB/s ==> 10000_Keys_1MB.txt <== readreverse : 298.038 micros/op 3355 ops/sec; 3355.3 MB/s readreverse : 335.001 micros/op 2985 ops/sec; 2985.1 MB/s readreverse : 286.956 micros/op 3484 ops/sec; 3484.9 MB/s readreverse : 329.954 micros/op 3030 ops/sec; 3030.8 MB/s readreverse : 306.428 micros/op 3263 ops/sec; 3263.5 MB/s readreverse : 330.749 micros/op 3023 ops/sec; 3023.5 MB/s readreverse : 328.903 micros/op 3040 ops/sec; 3040.5 MB/s readreverse : 324.853 micros/op 3078 ops/sec; 3078.4 MB/s readreverse : 320.488 micros/op 3120 ops/sec; 3120.3 MB/s readreverse : 320.536 micros/op 3119 ops/sec; 3119.8 MB/s avg : 3150.21 MB/s ``` After memcpy elimination ``` ==> 1000000_Keys_100Byte.txt <== readreverse : 0.395 micros/op 2529890 ops/sec; 279.9 MB/s readreverse : 0.368 micros/op 2715922 ops/sec; 300.5 MB/s readreverse : 0.384 micros/op 2603929 ops/sec; 288.1 MB/s readreverse : 0.375 micros/op 2663286 ops/sec; 294.6 MB/s readreverse : 0.357 micros/op 2802180 ops/sec; 310.0 MB/s readreverse : 0.363 micros/op 2757684 ops/sec; 305.1 MB/s readreverse : 0.372 micros/op 2689603 ops/sec; 297.5 MB/s readreverse : 0.379 micros/op 2638599 ops/sec; 291.9 MB/s readreverse : 0.375 micros/op 2663803 ops/sec; 294.7 MB/s readreverse : 0.375 micros/op 2665579 ops/sec; 294.9 MB/s avg: 295.72 MB/s (1.22 X) ==> 1000000_Keys_1KB.txt <== readreverse : 0.879 micros/op 1138112 ops/sec; 1128.8 MB/s readreverse : 0.842 micros/op 1187998 ops/sec; 1178.3 MB/s readreverse : 0.837 micros/op 1194915 ops/sec; 1185.1 MB/s readreverse : 0.845 micros/op 1182983 ops/sec; 1173.3 MB/s readreverse : 0.877 micros/op 1140308 ops/sec; 1131.0 MB/s readreverse : 0.849 micros/op 1177581 ops/sec; 1168.0 MB/s readreverse : 0.915 micros/op 1093284 ops/sec; 1084.3 MB/s readreverse : 0.863 micros/op 1159418 ops/sec; 1149.9 MB/s readreverse : 0.895 micros/op 1117670 ops/sec; 1108.5 MB/s readreverse : 0.852 micros/op 1174116 ops/sec; 1164.5 MB/s avg: 1147.17 MB/s (1.12 X) ==> 1000000_Keys_10KB.txt <== readreverse : 3.870 micros/op 258386 ops/sec; 2527.2 MB/s readreverse : 3.568 micros/op 280296 ops/sec; 2741.5 MB/s readreverse : 4.005 micros/op 249694 ops/sec; 2442.2 MB/s readreverse : 3.550 micros/op 281719 ops/sec; 2755.5 MB/s readreverse : 3.562 micros/op 280758 ops/sec; 2746.1 MB/s readreverse : 3.507 micros/op 285125 ops/sec; 2788.8 MB/s readreverse : 3.463 micros/op 288739 ops/sec; 2824.1 MB/s readreverse : 3.428 micros/op 291734 ops/sec; 2853.4 MB/s readreverse : 3.553 micros/op 281491 ops/sec; 2753.2 MB/s readreverse : 3.535 micros/op 282885 ops/sec; 2766.9 MB/s avg : 2719.89 MB/s (1.17 X) ==> 100000_Keys_100KB.txt <== readreverse : 22.815 micros/op 43830 ops/sec; 4281.0 MB/s readreverse : 29.957 micros/op 33381 ops/sec; 3260.4 MB/s readreverse : 25.334 micros/op 39473 ops/sec; 3855.4 MB/s readreverse : 23.037 micros/op 43409 ops/sec; 4239.8 MB/s readreverse : 27.810 micros/op 35958 ops/sec; 3512.1 MB/s readreverse : 30.327 micros/op 32973 ops/sec; 3220.6 MB/s readreverse : 29.704 micros/op 33665 ops/sec; 3288.2 MB/s readreverse : 29.423 micros/op 33987 ops/sec; 3319.6 MB/s readreverse : 23.334 micros/op 42856 ops/sec; 4185.9 MB/s readreverse : 29.969 micros/op 33368 ops/sec; 3259.1 MB/s avg : 3642.21 MB/s (1.5 X) ==> 10000_Keys_1MB.txt <== readreverse : 244.748 micros/op 4085 ops/sec; 4085.9 MB/s readreverse : 230.208 micros/op 4343 ops/sec; 4344.0 MB/s readreverse : 235.655 micros/op 4243 ops/sec; 4243.6 MB/s readreverse : 235.730 micros/op 4242 ops/sec; 4242.2 MB/s readreverse : 237.346 micros/op 4213 ops/sec; 4213.3 MB/s readreverse : 227.306 micros/op 4399 ops/sec; 4399.4 MB/s readreverse : 194.957 micros/op 5129 ops/sec; 5129.4 MB/s readreverse : 238.359 micros/op 4195 ops/sec; 4195.4 MB/s readreverse : 221.588 micros/op 4512 ops/sec; 4513.0 MB/s readreverse : 235.911 micros/op 4238 ops/sec; 4239.0 MB/s avg : 4360.52 MB/s (1.38 X) ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: andrewkr, yhchiang, sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56511
9 years ago
ReleaseTempPinnedData();
ResetInternalKeysSkippedCounter();
ClearSavedValue();
{
PERF_TIMER_GUARD(seek_internal_seek_time);
iter_->SeekToLast();
range_del_agg_.InvalidateTombstoneMapPositions();
}
// When the iterate_upper_bound is set to a value,
// it will seek to the last key before the
// ReadOptions.iterate_upper_bound
if (iter_->Valid() && iterate_upper_bound_ != nullptr) {
SeekForPrev(*iterate_upper_bound_);
range_del_agg_.InvalidateTombstoneMapPositions();
if (!Valid()) {
return;
} else if (user_comparator_->Equal(*iterate_upper_bound_, key())) {
Prev();
}
} else {
PrevInternal();
}
if (statistics_ != nullptr) {
RecordTick(statistics_, NUMBER_DB_SEEK);
if (valid_) {
RecordTick(statistics_, NUMBER_DB_SEEK_FOUND);
RecordTick(statistics_, ITER_BYTES_READ, key().size() + value().size());
}
}
if (valid_ && prefix_extractor_ && prefix_same_as_start_) {
prefix_start_buf_.SetUserKey(
prefix_extractor_->Transform(saved_key_.GetUserKey()));
prefix_start_key_ = prefix_start_buf_.GetUserKey();
}
}
Iterator* NewDBIterator(
Env* env, const ImmutableCFOptions& ioptions,
const Comparator* user_key_comparator, InternalIterator* internal_iter,
const SequenceNumber& sequence, uint64_t max_sequential_skip_in_iterations,
uint64_t version_number, const Slice* iterate_upper_bound,
bool prefix_same_as_start, bool pin_data, bool total_order_seek,
uint64_t max_skippable_internal_keys) {
DBIter* db_iter =
new DBIter(env, ioptions, user_key_comparator, internal_iter, sequence,
false, max_sequential_skip_in_iterations, version_number,
iterate_upper_bound, prefix_same_as_start, pin_data,
total_order_seek, max_skippable_internal_keys);
Introduce ReadOptions::pin_data (support zero copy for keys) Summary: This patch update the Iterator API to introduce new functions that allow users to keep the Slices returned by key() valid as long as the Iterator is not deleted ReadOptions::pin_data : If true keep loaded blocks in memory as long as the iterator is not deleted Iterator::IsKeyPinned() : If true, this mean that the Slice returned by key() is valid as long as the iterator is not deleted Also add a new option BlockBasedTableOptions::use_delta_encoding to allow users to disable delta_encoding if needed. Benchmark results (using https://phabricator.fb.com/P20083553) ``` // $ du -h /home/tec/local/normal.4K.Snappy/db10077 // 6.1G /home/tec/local/normal.4K.Snappy/db10077 // $ du -h /home/tec/local/zero.8K.LZ4/db10077 // 6.4G /home/tec/local/zero.8K.LZ4/db10077 // Benchmarks for shard db10077 // _build/opt/rocks/benchmark/rocks_copy_benchmark \ // --normal_db_path="/home/tec/local/normal.4K.Snappy/db10077" \ // --zero_db_path="/home/tec/local/zero.8K.LZ4/db10077" // First run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 1.73s 576.97m // BM_StringPiece 103.74% 1.67s 598.55m // ============================================================================ // Match rate : 1000000 / 1000000 // Second run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 611.99ms 1.63 // BM_StringPiece 203.76% 300.35ms 3.33 // ============================================================================ // Match rate : 1000000 / 1000000 ``` Test Plan: Unit tests Reviewers: sdong, igor, anthony, yhchiang, rven Reviewed By: rven Subscribers: dhruba, lovro, adsharma Differential Revision: https://reviews.facebook.net/D48999
9 years ago
return db_iter;
}
ArenaWrappedDBIter::~ArenaWrappedDBIter() { db_iter_->~DBIter(); }
void ArenaWrappedDBIter::SetDBIter(DBIter* iter) { db_iter_ = iter; }
RangeDelAggregator* ArenaWrappedDBIter::GetRangeDelAggregator() {
return db_iter_->GetRangeDelAggregator();
}
void ArenaWrappedDBIter::SetIterUnderDBIter(InternalIterator* iter) {
static_cast<DBIter*>(db_iter_)->SetIter(iter);
}
inline bool ArenaWrappedDBIter::Valid() const { return db_iter_->Valid(); }
inline void ArenaWrappedDBIter::SeekToFirst() { db_iter_->SeekToFirst(); }
inline void ArenaWrappedDBIter::SeekToLast() { db_iter_->SeekToLast(); }
inline void ArenaWrappedDBIter::Seek(const Slice& target) {
db_iter_->Seek(target);
}
inline void ArenaWrappedDBIter::SeekForPrev(const Slice& target) {
db_iter_->SeekForPrev(target);
}
inline void ArenaWrappedDBIter::Next() { db_iter_->Next(); }
inline void ArenaWrappedDBIter::Prev() { db_iter_->Prev(); }
inline Slice ArenaWrappedDBIter::key() const { return db_iter_->key(); }
inline Slice ArenaWrappedDBIter::value() const { return db_iter_->value(); }
inline Status ArenaWrappedDBIter::status() const { return db_iter_->status(); }
inline Status ArenaWrappedDBIter::GetProperty(std::string prop_name,
std::string* prop) {
return db_iter_->GetProperty(prop_name, prop);
}
void ArenaWrappedDBIter::RegisterCleanup(CleanupFunction function, void* arg1,
void* arg2) {
db_iter_->RegisterCleanup(function, arg1, arg2);
}
ArenaWrappedDBIter* NewArenaWrappedDbIterator(
Env* env, const ImmutableCFOptions& ioptions,
const Comparator* user_key_comparator, const SequenceNumber& sequence,
uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
const Slice* iterate_upper_bound, bool prefix_same_as_start, bool pin_data,
bool total_order_seek, uint64_t max_skippable_internal_keys) {
ArenaWrappedDBIter* iter = new ArenaWrappedDBIter();
Arena* arena = iter->GetArena();
auto mem = arena->AllocateAligned(sizeof(DBIter));
DBIter* db_iter =
new (mem) DBIter(env, ioptions, user_key_comparator, nullptr, sequence,
true, max_sequential_skip_in_iterations, version_number,
iterate_upper_bound, prefix_same_as_start, pin_data,
total_order_seek, max_skippable_internal_keys);
iter->SetDBIter(db_iter);
return iter;
}
} // namespace rocksdb