rocksdb/db/db_iter.h

441 lines
16 KiB
C
Raw Normal View History

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
#pragma once
#include <cstdint>
#include <string>
#include "db/db_impl/db_impl.h"
#include "db/range_del_aggregator.h"
#include "memory/arena.h"
#include "options/cf_options.h"
#include "rocksdb/db.h"
#include "rocksdb/iterator.h"
#include "rocksdb/wide_columns.h"
#include "table/iterator_wrapper.h"
#include "util/autovector.h"
namespace ROCKSDB_NAMESPACE {
class Version;
// This file declares the factory functions of DBIter, in its original form
// or a wrapped form with class ArenaWrappedDBIter, which is defined here.
// Class DBIter, which is declared and implemented inside db_iter.cc, is
// an iterator that converts internal keys (yielded by an InternalIterator)
// that were live at the specified sequence number into appropriate user
// keys.
// Each internal key consists of a user key, a sequence number, and a value
// type. DBIter deals with multiple key versions, tombstones, merge operands,
// etc, and exposes an Iterator.
// For example, DBIter may wrap following InternalIterator:
// user key: AAA value: v3 seqno: 100 type: Put
// user key: AAA value: v2 seqno: 97 type: Put
// user key: AAA value: v1 seqno: 95 type: Put
// user key: BBB value: v1 seqno: 90 type: Put
// user key: BBC value: N/A seqno: 98 type: Delete
// user key: BBC value: v1 seqno: 95 type: Put
// If the snapshot passed in is 102, then the DBIter is expected to
// expose the following iterator:
// key: AAA value: v3
// key: BBB value: v1
// If the snapshot passed in is 96, then it should expose:
// key: AAA value: v1
// key: BBB value: v1
// key: BBC value: v1
//
// 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 final : public Iterator {
public:
// The following is grossly complicated. TODO: clean it up
// Which direction is the iterator currently moving?
// (1) When moving forward:
// (1a) if current_entry_is_merged_ = false, the internal iterator is
// positioned at the exact entry that yields this->key(), this->value()
// (1b) if current_entry_is_merged_ = true, the internal iterator is
// positioned immediately after the last entry that contributed to the
// current this->value(). That entry may or may not have key equal to
// this->key().
// (2) When moving backwards, the internal iterator is positioned
// just before all entries whose user key == this->key().
Enable backward iterator for keys with user-defined timestamp (#8035) Summary: This PR does the following: - Enable backward iteration for keys with user-defined timestamp. Note that merge, single delete, range delete are not supported yet. - Introduces a new helper API `Comparator::EqualWithoutTimestamp()`. - Fix a typo in `SetTimestamp()`. - Add/update unit tests Run db_bench (built with DEBUG_LEVEL=0) to demonstrate that no overhead is introduced for CPU-intensive workloads with a lot of `Prev()`. Also provided results of iterating keys with timestamps. 1. Disable timestamp, run: ``` ./db_bench -db=/dev/shm/rocksdb -disable_wal=1 -benchmarks=fillseq,seekrandom[-W1-X6] -reverse_iterator=1 -seek_nexts=5 ``` Results: > Baseline > - seekrandom [AVG 6 runs] : 96115 ops/sec; 53.2 MB/sec > - seekrandom [MEDIAN 6 runs] : 98075 ops/sec; 54.2 MB/sec > > This PR > - seekrandom [AVG 6 runs] : 95521 ops/sec; 52.8 MB/sec > - seekrandom [MEDIAN 6 runs] : 96338 ops/sec; 53.3 MB/sec 2. Enable timestamp, run: ``` ./db_bench -user_timestamp_size=8 -db=/dev/shm/rocksdb -disable_wal=1 -benchmarks=fillseq,seekrandom[-W1-X6] -reverse_iterator=1 -seek_nexts=5 ``` Result: > Baseline: not supported > > This PR > - seekrandom [AVG 6 runs] : 90514 ops/sec; 50.1 MB/sec > - seekrandom [MEDIAN 6 runs] : 90834 ops/sec; 50.2 MB/sec Pull Request resolved: https://github.com/facebook/rocksdb/pull/8035 Reviewed By: ltamasi Differential Revision: D26926668 Pulled By: riversand963 fbshipit-source-id: 95330cc2242397c03e09d29e5417dfb0adc98ef5
2021-03-10 19:13:55 +00:00
enum Direction : uint8_t { 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;
skip_count_ = 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_);
RecordTick(global_statistics, NUMBER_ITER_SKIP, skip_count_);
PERF_COUNTER_ADD(iter_read_bytes, 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_;
// Map to Tickers::NUMBER_ITER_SKIP
uint64_t skip_count_;
};
DBIter(Env* _env, const ReadOptions& read_options,
const ImmutableOptions& ioptions,
const MutableCFOptions& mutable_cf_options, const Comparator* cmp,
InternalIterator* iter, const Version* version, SequenceNumber s,
bool arena_mode, uint64_t max_sequential_skip_in_iterations,
ReadCallback* read_callback, DBImpl* db_impl, ColumnFamilyData* cfd,
bool expose_blob_index);
// No copying allowed
DBIter(const DBIter&) = delete;
void operator=(const DBIter&) = delete;
~DBIter() override {
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
ThreadStatus::OperationType cur_op_type =
ThreadStatusUtil::GetThreadOperation();
ThreadStatusUtil::SetThreadOperation(
ThreadStatus::OperationType::OP_UNKNOWN);
// Release pinned data if any
if (pinned_iters_mgr_.PinningEnabled()) {
pinned_iters_mgr_.ReleasePinnedData();
}
RecordTick(statistics_, NO_ITERATOR_DELETED);
ResetInternalKeysSkippedCounter();
local_stats_.BumpGlobalStatistics(statistics_);
iter_.DeleteIter(arena_mode_);
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
ThreadStatusUtil::SetThreadOperation(cur_op_type);
}
void SetIter(InternalIterator* iter) {
assert(iter_.iter() == nullptr);
iter_.Set(iter);
iter_.iter()->SetPinnedItersMgr(&pinned_iters_mgr_);
}
bool Valid() const override {
#ifdef ROCKSDB_ASSERT_STATUS_CHECKED
if (valid_) {
status_.PermitUncheckedError();
}
#endif // ROCKSDB_ASSERT_STATUS_CHECKED
return valid_;
}
Slice key() const override {
assert(valid_);
if (timestamp_lb_) {
return saved_key_.GetInternalKey();
} else {
Iterator with timestamp (#6255) Summary: Preliminary support for iterator with user timestamp. Current implementation does not consider merge operator and reverse iterator. Auto compaction is also disabled in unit tests. Create an iterator with timestamp. ``` ... read_opts.timestamp = &ts; auto* iter = db->NewIterator(read_opts); // target is key without timestamp. for (iter->Seek(target); iter->Valid(); iter->Next()) {} for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {} delete iter; read_opts.timestamp = &ts1; // lower_bound and upper_bound are without timestamp. read_opts.iterate_lower_bound = &lower_bound; read_opts.iterate_upper_bound = &upper_bound; auto* iter1 = db->NewIterator(read_opts); // Do Seek or SeekToFirst() delete iter1; ``` Test plan (dev server) ``` $make check ``` Simple benchmarking (dev server) 1. The overhead introduced by this PR even when timestamp is disabled. key size: 16 bytes value size: 100 bytes Entries: 1000000 Data reside in main memory, and try to stress iterator. Repeated three times on master and this PR. - Seek without next ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 ``` master: 159047.0 ops/sec this PR: 158922.3 ops/sec (2% drop in throughput) - Seek and next 10 times ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 -seek_nexts=10 ``` master: 109539.3 ops/sec this PR: 107519.7 ops/sec (2% drop in throughput) Pull Request resolved: https://github.com/facebook/rocksdb/pull/6255 Differential Revision: D19438227 Pulled By: riversand963 fbshipit-source-id: b66b4979486f8474619f4aa6bdd88598870b0746
2020-03-07 00:21:03 +00:00
const Slice ukey_and_ts = saved_key_.GetUserKey();
return Slice(ukey_and_ts.data(), ukey_and_ts.size() - timestamp_size_);
}
}
Slice value() const override {
assert(valid_);
return value_;
}
const WideColumns& columns() const override {
assert(valid_);
return wide_columns_;
}
Status status() const override {
if (status_.ok()) {
return iter_.status();
} else {
assert(!valid_);
return status_;
}
}
Iterator with timestamp (#6255) Summary: Preliminary support for iterator with user timestamp. Current implementation does not consider merge operator and reverse iterator. Auto compaction is also disabled in unit tests. Create an iterator with timestamp. ``` ... read_opts.timestamp = &ts; auto* iter = db->NewIterator(read_opts); // target is key without timestamp. for (iter->Seek(target); iter->Valid(); iter->Next()) {} for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {} delete iter; read_opts.timestamp = &ts1; // lower_bound and upper_bound are without timestamp. read_opts.iterate_lower_bound = &lower_bound; read_opts.iterate_upper_bound = &upper_bound; auto* iter1 = db->NewIterator(read_opts); // Do Seek or SeekToFirst() delete iter1; ``` Test plan (dev server) ``` $make check ``` Simple benchmarking (dev server) 1. The overhead introduced by this PR even when timestamp is disabled. key size: 16 bytes value size: 100 bytes Entries: 1000000 Data reside in main memory, and try to stress iterator. Repeated three times on master and this PR. - Seek without next ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 ``` master: 159047.0 ops/sec this PR: 158922.3 ops/sec (2% drop in throughput) - Seek and next 10 times ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 -seek_nexts=10 ``` master: 109539.3 ops/sec this PR: 107519.7 ops/sec (2% drop in throughput) Pull Request resolved: https://github.com/facebook/rocksdb/pull/6255 Differential Revision: D19438227 Pulled By: riversand963 fbshipit-source-id: b66b4979486f8474619f4aa6bdd88598870b0746
2020-03-07 00:21:03 +00:00
Slice timestamp() const override {
assert(valid_);
assert(timestamp_size_ > 0);
Enable backward iterator for keys with user-defined timestamp (#8035) Summary: This PR does the following: - Enable backward iteration for keys with user-defined timestamp. Note that merge, single delete, range delete are not supported yet. - Introduces a new helper API `Comparator::EqualWithoutTimestamp()`. - Fix a typo in `SetTimestamp()`. - Add/update unit tests Run db_bench (built with DEBUG_LEVEL=0) to demonstrate that no overhead is introduced for CPU-intensive workloads with a lot of `Prev()`. Also provided results of iterating keys with timestamps. 1. Disable timestamp, run: ``` ./db_bench -db=/dev/shm/rocksdb -disable_wal=1 -benchmarks=fillseq,seekrandom[-W1-X6] -reverse_iterator=1 -seek_nexts=5 ``` Results: > Baseline > - seekrandom [AVG 6 runs] : 96115 ops/sec; 53.2 MB/sec > - seekrandom [MEDIAN 6 runs] : 98075 ops/sec; 54.2 MB/sec > > This PR > - seekrandom [AVG 6 runs] : 95521 ops/sec; 52.8 MB/sec > - seekrandom [MEDIAN 6 runs] : 96338 ops/sec; 53.3 MB/sec 2. Enable timestamp, run: ``` ./db_bench -user_timestamp_size=8 -db=/dev/shm/rocksdb -disable_wal=1 -benchmarks=fillseq,seekrandom[-W1-X6] -reverse_iterator=1 -seek_nexts=5 ``` Result: > Baseline: not supported > > This PR > - seekrandom [AVG 6 runs] : 90514 ops/sec; 50.1 MB/sec > - seekrandom [MEDIAN 6 runs] : 90834 ops/sec; 50.2 MB/sec Pull Request resolved: https://github.com/facebook/rocksdb/pull/8035 Reviewed By: ltamasi Differential Revision: D26926668 Pulled By: riversand963 fbshipit-source-id: 95330cc2242397c03e09d29e5417dfb0adc98ef5
2021-03-10 19:13:55 +00:00
if (direction_ == kReverse) {
return saved_timestamp_;
}
Iterator with timestamp (#6255) Summary: Preliminary support for iterator with user timestamp. Current implementation does not consider merge operator and reverse iterator. Auto compaction is also disabled in unit tests. Create an iterator with timestamp. ``` ... read_opts.timestamp = &ts; auto* iter = db->NewIterator(read_opts); // target is key without timestamp. for (iter->Seek(target); iter->Valid(); iter->Next()) {} for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {} delete iter; read_opts.timestamp = &ts1; // lower_bound and upper_bound are without timestamp. read_opts.iterate_lower_bound = &lower_bound; read_opts.iterate_upper_bound = &upper_bound; auto* iter1 = db->NewIterator(read_opts); // Do Seek or SeekToFirst() delete iter1; ``` Test plan (dev server) ``` $make check ``` Simple benchmarking (dev server) 1. The overhead introduced by this PR even when timestamp is disabled. key size: 16 bytes value size: 100 bytes Entries: 1000000 Data reside in main memory, and try to stress iterator. Repeated three times on master and this PR. - Seek without next ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 ``` master: 159047.0 ops/sec this PR: 158922.3 ops/sec (2% drop in throughput) - Seek and next 10 times ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 -seek_nexts=10 ``` master: 109539.3 ops/sec this PR: 107519.7 ops/sec (2% drop in throughput) Pull Request resolved: https://github.com/facebook/rocksdb/pull/6255 Differential Revision: D19438227 Pulled By: riversand963 fbshipit-source-id: b66b4979486f8474619f4aa6bdd88598870b0746
2020-03-07 00:21:03 +00:00
const Slice ukey_and_ts = saved_key_.GetUserKey();
assert(timestamp_size_ < ukey_and_ts.size());
return ExtractTimestampFromUserKey(ukey_and_ts, timestamp_size_);
}
bool IsBlob() const {
assert(valid_);
return is_blob_;
}
Status GetProperty(std::string prop_name, std::string* prop) override;
void Next() final override;
void Prev() final override;
Iterator with timestamp (#6255) Summary: Preliminary support for iterator with user timestamp. Current implementation does not consider merge operator and reverse iterator. Auto compaction is also disabled in unit tests. Create an iterator with timestamp. ``` ... read_opts.timestamp = &ts; auto* iter = db->NewIterator(read_opts); // target is key without timestamp. for (iter->Seek(target); iter->Valid(); iter->Next()) {} for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {} delete iter; read_opts.timestamp = &ts1; // lower_bound and upper_bound are without timestamp. read_opts.iterate_lower_bound = &lower_bound; read_opts.iterate_upper_bound = &upper_bound; auto* iter1 = db->NewIterator(read_opts); // Do Seek or SeekToFirst() delete iter1; ``` Test plan (dev server) ``` $make check ``` Simple benchmarking (dev server) 1. The overhead introduced by this PR even when timestamp is disabled. key size: 16 bytes value size: 100 bytes Entries: 1000000 Data reside in main memory, and try to stress iterator. Repeated three times on master and this PR. - Seek without next ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 ``` master: 159047.0 ops/sec this PR: 158922.3 ops/sec (2% drop in throughput) - Seek and next 10 times ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 -seek_nexts=10 ``` master: 109539.3 ops/sec this PR: 107519.7 ops/sec (2% drop in throughput) Pull Request resolved: https://github.com/facebook/rocksdb/pull/6255 Differential Revision: D19438227 Pulled By: riversand963 fbshipit-source-id: b66b4979486f8474619f4aa6bdd88598870b0746
2020-03-07 00:21:03 +00:00
// 'target' does not contain timestamp, even if user timestamp feature is
// enabled.
void Seek(const Slice& target) final override;
void SeekForPrev(const Slice& target) final override;
void SeekToFirst() final override;
void SeekToLast() final override;
Env* env() const { return env_; }
void set_sequence(uint64_t s) {
sequence_ = s;
if (read_callback_) {
read_callback_->Refresh(s);
}
Add new Iterator API Refresh(const snapshot*) (#10594) Summary: This PR resolves https://github.com/facebook/rocksdb/issues/10487 & https://github.com/facebook/rocksdb/issues/10536, user code needs to call Refresh() periodically. The main code change is to support range deletions. A range tombstone iterator uses a sequence number as upper bound to decide which range tombstones are effective. During Iterator refresh, this sequence number upper bound needs to be updated for all range tombstone iterators under DBIter and LevelIterator. LevelIterator may create new table iterators and range tombstone iterator during scanning, so it needs to be aware of iterator refresh. The code path that propagates this change is `db_iter_->set_sequence(read_seq) -> MergingIterator::SetRangeDelReadSeqno() -> TruncatedRangeDelIterator::SetRangeDelReadSeqno() and LevelIterator::SetRangeDelReadSeqno()`. This change also fixes an issue where range tombstone iterators created by LevelIterator may access ReadOptions::snapshot, even though we do not explicitly require users to keep a snapshot alive after creating an Iterator. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10594 Test Plan: * New unit tests. * Add Iterator::Refresh(snapshot) to stress test. Note that this change only adds tests for refreshing to the same snapshot since this is the main target use case. TODO in a following PR: * Stress test Iterator::Refresh() to different snapshots or no snapshot. Reviewed By: ajkr Differential Revision: D48456896 Pulled By: cbi42 fbshipit-source-id: 2e642c04e91235cc9542ef4cd37b3c20823bd779
2023-09-15 17:44:43 +00:00
iter_.SetRangeDelReadSeqno(s);
}
void set_valid(bool v) { valid_ = v; }
private:
// For all methods in this block:
// PRE: iter_->Valid() && status_.ok()
// Return false if there was an error, and status() is non-ok, valid_ = false;
// in this case callers would usually stop what they were doing and return.
bool ReverseToForward();
bool ReverseToBackward();
// Set saved_key_ to the seek key to target, with proper sequence number set.
// It might get adjusted if the seek key is smaller than iterator lower bound.
// target does not have timestamp.
void SetSavedKeyToSeekTarget(const Slice& target);
// Set saved_key_ to the seek key to target, with proper sequence number set.
// It might get adjusted if the seek key is larger than iterator upper bound.
// target does not have timestamp.
void SetSavedKeyToSeekForPrevTarget(const Slice& target);
bool FindValueForCurrentKey();
bool FindValueForCurrentKeyUsingSeek();
bool FindUserKeyBeforeSavedKey();
// If `skipping_saved_key` is true, the function will keep iterating until it
// finds a user key that is larger than `saved_key_`.
// If `prefix` is not null, the iterator needs to stop when all keys for the
// prefix are exhausted and the iterator is set to invalid.
bool FindNextUserEntry(bool skipping_saved_key, const Slice* prefix);
// Internal implementation of FindNextUserEntry().
bool FindNextUserEntryInternal(bool skipping_saved_key, const Slice* prefix);
bool ParseKey(ParsedInternalKey* key);
bool MergeValuesNewToOld();
// If prefix is not null, we need to set the iterator to invalid if no more
// entry can be found within the prefix.
void PrevInternal(const Slice* prefix);
bool TooManyInternalKeysSkipped(bool increment = true);
make iterator return versions between timestamp bounds (#6544) Summary: (Based on Yanqin's idea) Add a new field in readoptions as lower timestamp bound for iterator. When the parameter is not supplied (nullptr), the iterator returns the latest visible version of a record. When it is supplied, the existing timestamp field is the upper bound. Together the two serves as a bounded time window. The iterator returns all versions of a record falling in the window. SeekRandom perf test (10 minutes) on the same development machine ram drive with the same DB data shows no regression (within marge of error). The test is adapted from https://github.com/facebook/rocksdb/wiki/RocksDB-In-Memory-Workload-Performance-Benchmarks. base line (commit e860f8840): seekrandom : 7.836 micros/op 4082449 ops/sec; (0 of 73481999 found) This PR: seekrandom : 7.764 micros/op 4120935 ops/sec; (0 of 71303999 found) db_bench --db=r:\rocksdb.github --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --cache_size=2147483648 --cache_numshardbits=6 --compression_type=none --compression_ratio=1 --min_level_to_compress=-1 --disable_seek_compaction=1 --hard_rate_limit=2 --write_buffer_size=134217728 --max_write_buffer_number=2 --level0_file_num_compaction_trigger=8 --target_file_size_base=134217728 --max_bytes_for_level_base=1073741824 --disable_wal=0 --wal_dir=r:\rocksdb.github\WAL_LOG --sync=0 --verify_checksum=1 --statistics=0 --stats_per_interval=0 --stats_interval=1048576 --histogram=0 --use_plain_table=1 --open_files=-1 --memtablerep=prefix_hash --bloom_bits=10 --bloom_locality=1 --duration=600 --benchmarks=seekrandom --use_existing_db=1 --num=25000000 --threads=32 --allow_concurrent_memtable_write=0 Pull Request resolved: https://github.com/facebook/rocksdb/pull/6544 Reviewed By: ltamasi Differential Revision: D20844069 Pulled By: riversand963 fbshipit-source-id: d97f2bf38a323c8c6a68db213b2d3c694b1c1f74
2020-04-10 16:49:38 +00:00
bool IsVisible(SequenceNumber sequence, const Slice& ts,
bool* more_recent = nullptr);
// 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();
}
}
inline void ClearSavedValue() {
if (saved_value_.capacity() > 1048576) {
std::string empty;
swap(empty, saved_value_);
} else {
saved_value_.clear();
}
}
inline void ResetInternalKeysSkippedCounter() {
local_stats_.skip_count_ += num_internal_keys_skipped_;
if (valid_) {
local_stats_.skip_count_--;
}
num_internal_keys_skipped_ = 0;
}
bool expect_total_order_inner_iter() {
assert(expect_total_order_inner_iter_ || prefix_extractor_ != nullptr);
return expect_total_order_inner_iter_;
}
make iterator return versions between timestamp bounds (#6544) Summary: (Based on Yanqin's idea) Add a new field in readoptions as lower timestamp bound for iterator. When the parameter is not supplied (nullptr), the iterator returns the latest visible version of a record. When it is supplied, the existing timestamp field is the upper bound. Together the two serves as a bounded time window. The iterator returns all versions of a record falling in the window. SeekRandom perf test (10 minutes) on the same development machine ram drive with the same DB data shows no regression (within marge of error). The test is adapted from https://github.com/facebook/rocksdb/wiki/RocksDB-In-Memory-Workload-Performance-Benchmarks. base line (commit e860f8840): seekrandom : 7.836 micros/op 4082449 ops/sec; (0 of 73481999 found) This PR: seekrandom : 7.764 micros/op 4120935 ops/sec; (0 of 71303999 found) db_bench --db=r:\rocksdb.github --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --cache_size=2147483648 --cache_numshardbits=6 --compression_type=none --compression_ratio=1 --min_level_to_compress=-1 --disable_seek_compaction=1 --hard_rate_limit=2 --write_buffer_size=134217728 --max_write_buffer_number=2 --level0_file_num_compaction_trigger=8 --target_file_size_base=134217728 --max_bytes_for_level_base=1073741824 --disable_wal=0 --wal_dir=r:\rocksdb.github\WAL_LOG --sync=0 --verify_checksum=1 --statistics=0 --stats_per_interval=0 --stats_interval=1048576 --histogram=0 --use_plain_table=1 --open_files=-1 --memtablerep=prefix_hash --bloom_bits=10 --bloom_locality=1 --duration=600 --benchmarks=seekrandom --use_existing_db=1 --num=25000000 --threads=32 --allow_concurrent_memtable_write=0 Pull Request resolved: https://github.com/facebook/rocksdb/pull/6544 Reviewed By: ltamasi Differential Revision: D20844069 Pulled By: riversand963 fbshipit-source-id: d97f2bf38a323c8c6a68db213b2d3c694b1c1f74
2020-04-10 16:49:38 +00:00
// If lower bound of timestamp is given by ReadOptions.iter_start_ts, we need
// to return versions of the same key. We cannot just skip if the key value
// is the same but timestamps are different but fall in timestamp range.
inline int CompareKeyForSkip(const Slice& a, const Slice& b) {
return timestamp_lb_ != nullptr
? user_comparator_.Compare(a, b)
: user_comparator_.CompareWithoutTimestamp(a, b);
}
// Retrieves the blob value for the specified user key using the given blob
// index when using the integrated BlobDB implementation.
bool SetBlobValueIfNeeded(const Slice& user_key, const Slice& blob_index);
void ResetBlobValue() {
is_blob_ = false;
blob_value_.Reset();
}
void SetValueAndColumnsFromPlain(const Slice& slice) {
assert(value_.empty());
assert(wide_columns_.empty());
value_ = slice;
wide_columns_.emplace_back(kDefaultWideColumnName, slice);
}
bool SetValueAndColumnsFromEntity(Slice slice);
Integrate FullMergeV3 into the query and compaction paths (#11858) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/11858 The patch builds on https://github.com/facebook/rocksdb/pull/11807 and integrates the `FullMergeV3` API into the read and compaction code paths by updating and extending the logic in `MergeHelper`. In particular, when it comes to merge inputs, the existing `TimedFullMergeWithEntity` is folded into `TimedFullMerge`, since wide-column base values are now handled the same way as plain base values (or no base values for that matter), e.g. they are passed directly to the `MergeOperator`. On the other hand, there is some new differentiation on the output side. Namely, there are now two sets of `TimedFullMerge` variants: one set for contexts where the complete merge result and its value type are needed (used by iterators and compactions), and another set where the merge result is needed in a form determined by the client (used by the point lookup APIs, where e.g. for `Get` we have to extract the value of the default column of any wide-column results). Implementation-wise, the two sets of overloads use different visitors to process the `std::variant` produced by `FullMergeV3`. This has the benefit of eliminating some repeated code e.g. in the point lookup paths, since `TimedFullMerge` now populates the application's result object (`PinnableSlice`/`string` or `PinnableWideColumns`) directly. Moreover, within each set of variants, there is a separate overload for the no base value/plain base value/wide-column base value cases, which eliminates some repeated branching w/r/t to the type of the base value if any. Reviewed By: jaykorean Differential Revision: D49352562 fbshipit-source-id: c2fb9853dba3fbbc6918665bde4195c4ea150a0c
2023-09-20 00:27:04 +00:00
bool SetValueAndColumnsFromMergeResult(const Status& merge_status,
ValueType result_type);
void ResetValueAndColumns() {
value_.clear();
wide_columns_.clear();
}
Integrate FullMergeV3 into the query and compaction paths (#11858) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/11858 The patch builds on https://github.com/facebook/rocksdb/pull/11807 and integrates the `FullMergeV3` API into the read and compaction code paths by updating and extending the logic in `MergeHelper`. In particular, when it comes to merge inputs, the existing `TimedFullMergeWithEntity` is folded into `TimedFullMerge`, since wide-column base values are now handled the same way as plain base values (or no base values for that matter), e.g. they are passed directly to the `MergeOperator`. On the other hand, there is some new differentiation on the output side. Namely, there are now two sets of `TimedFullMerge` variants: one set for contexts where the complete merge result and its value type are needed (used by iterators and compactions), and another set where the merge result is needed in a form determined by the client (used by the point lookup APIs, where e.g. for `Get` we have to extract the value of the default column of any wide-column results). Implementation-wise, the two sets of overloads use different visitors to process the `std::variant` produced by `FullMergeV3`. This has the benefit of eliminating some repeated code e.g. in the point lookup paths, since `TimedFullMerge` now populates the application's result object (`PinnableSlice`/`string` or `PinnableWideColumns`) directly. Moreover, within each set of variants, there is a separate overload for the no base value/plain base value/wide-column base value cases, which eliminates some repeated branching w/r/t to the type of the base value if any. Reviewed By: jaykorean Differential Revision: D49352562 fbshipit-source-id: c2fb9853dba3fbbc6918665bde4195c4ea150a0c
2023-09-20 00:27:04 +00:00
// The following methods perform the actual merge operation for the
// no base value/plain base value/wide-column base value cases.
// If user-defined timestamp is enabled, `user_key` includes timestamp.
Integrate FullMergeV3 into the query and compaction paths (#11858) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/11858 The patch builds on https://github.com/facebook/rocksdb/pull/11807 and integrates the `FullMergeV3` API into the read and compaction code paths by updating and extending the logic in `MergeHelper`. In particular, when it comes to merge inputs, the existing `TimedFullMergeWithEntity` is folded into `TimedFullMerge`, since wide-column base values are now handled the same way as plain base values (or no base values for that matter), e.g. they are passed directly to the `MergeOperator`. On the other hand, there is some new differentiation on the output side. Namely, there are now two sets of `TimedFullMerge` variants: one set for contexts where the complete merge result and its value type are needed (used by iterators and compactions), and another set where the merge result is needed in a form determined by the client (used by the point lookup APIs, where e.g. for `Get` we have to extract the value of the default column of any wide-column results). Implementation-wise, the two sets of overloads use different visitors to process the `std::variant` produced by `FullMergeV3`. This has the benefit of eliminating some repeated code e.g. in the point lookup paths, since `TimedFullMerge` now populates the application's result object (`PinnableSlice`/`string` or `PinnableWideColumns`) directly. Moreover, within each set of variants, there is a separate overload for the no base value/plain base value/wide-column base value cases, which eliminates some repeated branching w/r/t to the type of the base value if any. Reviewed By: jaykorean Differential Revision: D49352562 fbshipit-source-id: c2fb9853dba3fbbc6918665bde4195c4ea150a0c
2023-09-20 00:27:04 +00:00
bool MergeWithNoBaseValue(const Slice& user_key);
bool MergeWithPlainBaseValue(const Slice& value, const Slice& user_key);
bool MergeWithWideColumnBaseValue(const Slice& entity, const Slice& user_key);
Fix bug in auto_readahead_size that returned wrong key (#12229) Summary: IndexType::kBinarySearchWithFirstKey + BlockCacheLookupForReadAheadSize enabled => FindNextUserEntryInternal assertion fails or iterator lands at a wrong key because BlockCacheLookupForReadAheadSize moves the index_iter_ and in internal_wrapper.h, result_.key didn't update and pointed to wrong key. Also ikey_ was also pointing to iter_.key() instead of copying the key. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12229 Test Plan: ``` rm -rf /dev/shm/rocksdb_test/rocksdb_crashtest_blackbox_alt3 /dev/shm/rocksdb_test/rocksdb_crashtest_expected_alt3 mkdir /dev/shm/rocksdb_test/rocksdb_crashtest_blackbox_alt3 /dev/shm/rocksdb_test/rocksdb_crashtest_expected_alt3 ./db_stress -threads=1 --acquire_snapshot_one_in=0 --adaptive_readahead=0 --allow_concurrent_memtable_write=0 --allow_data_in_errors=True --allow_setting_blob_options_dynamically=0 --async_io=0 --auto_readahead_size=1 --avoid_flush_during_recovery=0 --avoid_unnecessary_blocking_io=1 --backup_max_size=0 --backup_one_in=0 --batch_protection_bytes_per_key=0 --blob_cache_size=0 --blob_compaction_readahead_size=0 --blob_compression_type=lz4 --blob_file_size=0 --blob_file_starting_level=0 --blob_garbage_collection_age_cutoff=0 --blob_garbage_collection_force_threshold=0 --block_protection_bytes_per_key=0 --block_size=2048 --bloom_before_level=2147483646 --bloom_bits=15 --bottommost_compression_type=snappy --bottommost_file_compaction_delay=0 --bytes_per_sync=0 --cache_index_and_filter_blocks=0 --cache_size=8388608 --cache_type=lru_cache --charge_compression_dictionary_building_buffer=0 --charge_file_metadata=0 --charge_filter_construction=0 --charge_table_reader=0 --checkpoint_one_in=0 --checksum_type=kCRC32c --clear_column_family_one_in=0 --column_families=1 --compact_files_one_in=0 --compact_range_one_in=0 --compaction_pri=1 --compaction_readahead_size=0 --compaction_ttl=0 --compressed_secondary_cache_size=0 --compression_checksum=0 --compression_max_dict_buffer_bytes=511 --compression_max_dict_bytes=16384 --compression_parallel_threads=1 --compression_type=none --compression_use_zstd_dict_trainer=1 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --data_block_index_type=1 --db=/dev/shm/rocksdb_test/rocksdb_crashtest_blackbox_alt3 --db_write_buffer_size=0 --delpercent=0 --delrangepercent=0 --destroy_db_initially=0 --detect_filter_construct_corruption=0 --disable_wal=0 --enable_blob_files=0 --enable_blob_garbage_collection=0 --enable_compaction_filter=0 --enable_pipelined_write=0 --enable_thread_tracking=1 --expected_values_dir=/dev/shm/rocksdb_test/rocksdb_crashtest_expected_alt3 --fail_if_options_file_error=1 --fifo_allow_compaction=0 --file_checksum_impl=crc32c --flush_one_in=1000000 --format_version=3 --get_current_wal_file_one_in=0 --get_live_files_one_in=0 --get_property_one_in=0 --get_sorted_wal_files_one_in=0 --index_block_restart_interval=13 --index_type=3 --ingest_external_file_one_in=10 --initial_auto_readahead_size=0 --iterpercent=55 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=0 --lock_wal_one_in=0 --long_running_snapshots=0 --manual_wal_flush_one_in=0 --mark_for_compaction_one_file_in=0 --max_auto_readahead_size=0 --max_background_compactions=1 --max_bytes_for_level_base=67108864 --max_key=100000 --max_key_len=3 --max_manifest_file_size=1073741824 --max_write_batch_group_size_bytes=16 --max_write_buffer_number=10 --max_write_buffer_size_to_maintain=4194304 --memtable_max_range_deletions=1000 --memtable_prefix_bloom_size_ratio=0.5 --memtable_protection_bytes_per_key=0 --memtable_whole_key_filtering=0 --memtablerep=skip_list --min_blob_size=8 --min_write_buffer_number_to_merge=2 --mmap_read=0 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=2 --open_files=-1 --open_metadata_write_fault_one_in=0 --open_read_fault_one_in=0 --open_write_fault_one_in=0 --ops_per_thread=10000000 --optimize_filters_for_memory=0 --paranoid_file_checks=0 --partition_filters=0 --partition_pinning=0 --pause_background_one_in=0 --periodic_compaction_seconds=0 --prefix_size=1 --prefixpercent=0 --prepopulate_block_cache=0 --preserve_internal_time_seconds=0 --progress_reports=0 --read_fault_one_in=0 --readahead_size=1 --readpercent=45 --recycle_log_file_num=1 --reopen=0 --secondary_cache_fault_one_in=0 --secondary_cache_uri= --set_options_one_in=0 --snapshot_hold_ops=0 --sst_file_manager_bytes_per_sec=0 --sst_file_manager_bytes_per_truncate=0 --stats_dump_period_sec=600 --subcompactions=1 --sync=0 --sync_fault_injection=0 --target_file_size_base=16777216 --target_file_size_multiplier=1 --test_batches_snapshots=0 --top_level_index_pinning=0 --unpartitioned_pinning=0 --use_blob_cache=0 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=0 --use_get_entity=0 --use_merge=0 --use_multi_get_entity=0 --use_multiget=0 --use_put_entity_one_in=0 --use_shared_block_and_blob_cache=0 --use_write_buffer_manager=0 --user_timestamp_size=0 --value_size_mult=32 --verification_only=0 --verify_checksum=0 --verify_checksum_one_in=0 --verify_db_one_in=0 --verify_file_checksums_one_in=0 --verify_iterator_with_expected_state_one_in=1 --verify_sst_unique_id_in_manifest=0 --wal_bytes_per_sync=0 --wal_compression=none --write_buffer_size=33554432 --write_dbid_to_manifest=0 --write_fault_one_in=0 --writepercent=0 > repro.out Verification failed. Expected state has key 0000000000000077000000000000004178, iterator is at key 0000000000000077000000000000008A78 Column family: default, op_logs: S 0000000000000077000000000000003D7878787878 NNNN No writes or ops? Verification failed :( ``` Reviewed By: ajkr Differential Revision: D52710655 Pulled By: akankshamahajan15 fbshipit-source-id: 9d2e684e190fb0832bdce3337bce1c6548cd054d
2024-01-16 19:30:36 +00:00
bool PrepareValue() {
if (!iter_.PrepareValue()) {
assert(!iter_.status().ok());
valid_ = false;
return false;
}
// ikey_ could change as BlockBasedTableIterator does Block cache
// lookup and index_iter_ could point to different block resulting
// in ikey_ pointing to wrong key. So ikey_ needs to be updated in
// case of Seek/Next calls to point to right key again.
if (!ParseKey(&ikey_)) {
return false;
}
return true;
}
const SliceTransform* prefix_extractor_;
Env* const env_;
SystemClock* clock_;
Logger* logger_;
UserComparatorWrapper user_comparator_;
const MergeOperator* const merge_operator_;
IteratorWrapper iter_;
const Version* version_;
ReadCallback* read_callback_;
// Max visible sequence number. It is normally the snapshot seq unless we have
// uncommitted data in db as in WriteUnCommitted.
SequenceNumber sequence_;
IterKey saved_key_;
// Reusable internal key data structure. This is only used inside one function
// and should not be used across functions. Reusing this object can reduce
// overhead of calling construction of the function if creating it each time.
ParsedInternalKey ikey_;
std::string saved_value_;
Slice pinned_value_;
// for prefix seek mode to support prev()
PinnableSlice blob_value_;
// Value of the default column
Slice value_;
// All columns (i.e. name-value pairs)
WideColumns wide_columns_;
Statistics* statistics_;
uint64_t max_skip_;
uint64_t max_skippable_internal_keys_;
uint64_t num_internal_keys_skipped_;
const Slice* iterate_lower_bound_;
const Slice* iterate_upper_bound_;
// The prefix of the seek key. It is only used when prefix_same_as_start_
// is true and prefix extractor is not null. In Next() or Prev(), current keys
// will be checked against this prefix, so that the iterator can be
// invalidated if the keys in this prefix has been exhausted. Set it using
// SetUserKey() and use it using GetUserKey().
IterKey prefix_;
Status status_;
Direction direction_;
bool valid_;
bool current_entry_is_merged_;
// True if we know that the current entry's seqnum is 0.
// This information is used as that the next entry will be for another
// user key.
bool is_key_seqnum_zero_;
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_;
// Expect the inner iterator to maintain a total order.
// prefix_extractor_ must be non-NULL if the value is false.
const bool expect_total_order_inner_iter_;
ReadTier read_tier_;
bool fill_cache_;
bool verify_checksums_;
// Whether the iterator is allowed to expose blob references. Set to true when
// the stacked BlobDB implementation is used, false otherwise.
bool expose_blob_index_;
bool is_blob_;
bool arena_mode_;
Group rocksdb.sst.read.micros stat by different user read IOActivity + misc (#11444) Summary: **Context/Summary:** - Similar to https://github.com/facebook/rocksdb/pull/11288 but for user read such as `Get(), MultiGet(), DBIterator::XXX(), Verify(File)Checksum()`. - For this, I refactored some user-facing `MultiGet` calls in `TransactionBase` and various types of `DB` so that it does not call a user-facing `Get()` but `GetImpl()` for passing the `ReadOptions::io_activity` check (see PR conversation) - New user read stats breakdown are guarded by `kExceptDetailedTimers` since measurement shows they have 4-5% regression to the upstream/main. - Misc - More refactoring: with https://github.com/facebook/rocksdb/pull/11288, we complete passing `ReadOptions/IOOptions` to FS level. So we can now replace the previously [added](https://github.com/facebook/rocksdb/pull/9424) `rate_limiter_priority` parameter in `RandomAccessFileReader`'s `Read/MultiRead/Prefetch()` with `IOOptions::rate_limiter_priority` - Also, `ReadAsync()` call time is measured in `SST_READ_MICRO` now Pull Request resolved: https://github.com/facebook/rocksdb/pull/11444 Test Plan: - CI fake db crash/stress test - Microbenchmarking **Build** `make clean && ROCKSDB_NO_FBCODE=1 DEBUG_LEVEL=0 make -jN db_basic_bench` - google benchmark version: https://github.com/google/benchmark/commit/604f6fd3f4b34a84ec4eb4db81d842fa4db829cd - db_basic_bench_base: upstream - db_basic_bench_pr: db_basic_bench_base + this PR - asyncread_db_basic_bench_base: upstream + [db basic bench patch for IteratorNext](https://github.com/facebook/rocksdb/compare/main...hx235:rocksdb:micro_bench_async_read) - asyncread_db_basic_bench_pr: asyncread_db_basic_bench_base + this PR **Test** Get ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{null_stat|base|pr} --benchmark_filter=DBGet/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1/negative_query:0/enable_filter:0/mmap:1/threads:1 --benchmark_repetitions=1000 ``` Result ``` Coming soon ``` AsyncRead ``` TEST_TMPDIR=/dev/shm ./asyncread_db_basic_bench_{base|pr} --benchmark_filter=IteratorNext/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1/async_io:1/include_detailed_timers:0 --benchmark_repetitions=1000 > syncread_db_basic_bench_{base|pr}.out ``` Result ``` Base: 1956,1956,1968,1977,1979,1986,1988,1988,1988,1990,1991,1991,1993,1993,1993,1993,1994,1996,1997,1997,1997,1998,1999,2001,2001,2002,2004,2007,2007,2008, PR (2.3% regression, due to measuring `SST_READ_MICRO` that wasn't measured before): 1993,2014,2016,2022,2024,2027,2027,2028,2028,2030,2031,2031,2032,2032,2038,2039,2042,2044,2044,2047,2047,2047,2048,2049,2050,2052,2052,2052,2053,2053, ``` Reviewed By: ajkr Differential Revision: D45918925 Pulled By: hx235 fbshipit-source-id: 58a54560d9ebeb3a59b6d807639692614dad058a
2023-08-09 00:26:50 +00:00
const Env::IOActivity io_activity_;
// List of operands for merge operator.
MergeContext merge_context_;
LocalStatistics local_stats_;
PinnedIteratorsManager pinned_iters_mgr_;
DBImpl* db_impl_;
ColumnFamilyData* cfd_;
Iterator with timestamp (#6255) Summary: Preliminary support for iterator with user timestamp. Current implementation does not consider merge operator and reverse iterator. Auto compaction is also disabled in unit tests. Create an iterator with timestamp. ``` ... read_opts.timestamp = &ts; auto* iter = db->NewIterator(read_opts); // target is key without timestamp. for (iter->Seek(target); iter->Valid(); iter->Next()) {} for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {} delete iter; read_opts.timestamp = &ts1; // lower_bound and upper_bound are without timestamp. read_opts.iterate_lower_bound = &lower_bound; read_opts.iterate_upper_bound = &upper_bound; auto* iter1 = db->NewIterator(read_opts); // Do Seek or SeekToFirst() delete iter1; ``` Test plan (dev server) ``` $make check ``` Simple benchmarking (dev server) 1. The overhead introduced by this PR even when timestamp is disabled. key size: 16 bytes value size: 100 bytes Entries: 1000000 Data reside in main memory, and try to stress iterator. Repeated three times on master and this PR. - Seek without next ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 ``` master: 159047.0 ops/sec this PR: 158922.3 ops/sec (2% drop in throughput) - Seek and next 10 times ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 -seek_nexts=10 ``` master: 109539.3 ops/sec this PR: 107519.7 ops/sec (2% drop in throughput) Pull Request resolved: https://github.com/facebook/rocksdb/pull/6255 Differential Revision: D19438227 Pulled By: riversand963 fbshipit-source-id: b66b4979486f8474619f4aa6bdd88598870b0746
2020-03-07 00:21:03 +00:00
const Slice* const timestamp_ub_;
make iterator return versions between timestamp bounds (#6544) Summary: (Based on Yanqin's idea) Add a new field in readoptions as lower timestamp bound for iterator. When the parameter is not supplied (nullptr), the iterator returns the latest visible version of a record. When it is supplied, the existing timestamp field is the upper bound. Together the two serves as a bounded time window. The iterator returns all versions of a record falling in the window. SeekRandom perf test (10 minutes) on the same development machine ram drive with the same DB data shows no regression (within marge of error). The test is adapted from https://github.com/facebook/rocksdb/wiki/RocksDB-In-Memory-Workload-Performance-Benchmarks. base line (commit e860f8840): seekrandom : 7.836 micros/op 4082449 ops/sec; (0 of 73481999 found) This PR: seekrandom : 7.764 micros/op 4120935 ops/sec; (0 of 71303999 found) db_bench --db=r:\rocksdb.github --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --cache_size=2147483648 --cache_numshardbits=6 --compression_type=none --compression_ratio=1 --min_level_to_compress=-1 --disable_seek_compaction=1 --hard_rate_limit=2 --write_buffer_size=134217728 --max_write_buffer_number=2 --level0_file_num_compaction_trigger=8 --target_file_size_base=134217728 --max_bytes_for_level_base=1073741824 --disable_wal=0 --wal_dir=r:\rocksdb.github\WAL_LOG --sync=0 --verify_checksum=1 --statistics=0 --stats_per_interval=0 --stats_interval=1048576 --histogram=0 --use_plain_table=1 --open_files=-1 --memtablerep=prefix_hash --bloom_bits=10 --bloom_locality=1 --duration=600 --benchmarks=seekrandom --use_existing_db=1 --num=25000000 --threads=32 --allow_concurrent_memtable_write=0 Pull Request resolved: https://github.com/facebook/rocksdb/pull/6544 Reviewed By: ltamasi Differential Revision: D20844069 Pulled By: riversand963 fbshipit-source-id: d97f2bf38a323c8c6a68db213b2d3c694b1c1f74
2020-04-10 16:49:38 +00:00
const Slice* const timestamp_lb_;
Iterator with timestamp (#6255) Summary: Preliminary support for iterator with user timestamp. Current implementation does not consider merge operator and reverse iterator. Auto compaction is also disabled in unit tests. Create an iterator with timestamp. ``` ... read_opts.timestamp = &ts; auto* iter = db->NewIterator(read_opts); // target is key without timestamp. for (iter->Seek(target); iter->Valid(); iter->Next()) {} for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {} delete iter; read_opts.timestamp = &ts1; // lower_bound and upper_bound are without timestamp. read_opts.iterate_lower_bound = &lower_bound; read_opts.iterate_upper_bound = &upper_bound; auto* iter1 = db->NewIterator(read_opts); // Do Seek or SeekToFirst() delete iter1; ``` Test plan (dev server) ``` $make check ``` Simple benchmarking (dev server) 1. The overhead introduced by this PR even when timestamp is disabled. key size: 16 bytes value size: 100 bytes Entries: 1000000 Data reside in main memory, and try to stress iterator. Repeated three times on master and this PR. - Seek without next ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 ``` master: 159047.0 ops/sec this PR: 158922.3 ops/sec (2% drop in throughput) - Seek and next 10 times ``` ./db_bench -db=/dev/shm/rocksdbtest-1000 -benchmarks=fillseq,seekrandom -enable_pipelined_write=false -disable_wal=true -format_version=3 -seek_nexts=10 ``` master: 109539.3 ops/sec this PR: 107519.7 ops/sec (2% drop in throughput) Pull Request resolved: https://github.com/facebook/rocksdb/pull/6255 Differential Revision: D19438227 Pulled By: riversand963 fbshipit-source-id: b66b4979486f8474619f4aa6bdd88598870b0746
2020-03-07 00:21:03 +00:00
const size_t timestamp_size_;
Enable backward iterator for keys with user-defined timestamp (#8035) Summary: This PR does the following: - Enable backward iteration for keys with user-defined timestamp. Note that merge, single delete, range delete are not supported yet. - Introduces a new helper API `Comparator::EqualWithoutTimestamp()`. - Fix a typo in `SetTimestamp()`. - Add/update unit tests Run db_bench (built with DEBUG_LEVEL=0) to demonstrate that no overhead is introduced for CPU-intensive workloads with a lot of `Prev()`. Also provided results of iterating keys with timestamps. 1. Disable timestamp, run: ``` ./db_bench -db=/dev/shm/rocksdb -disable_wal=1 -benchmarks=fillseq,seekrandom[-W1-X6] -reverse_iterator=1 -seek_nexts=5 ``` Results: > Baseline > - seekrandom [AVG 6 runs] : 96115 ops/sec; 53.2 MB/sec > - seekrandom [MEDIAN 6 runs] : 98075 ops/sec; 54.2 MB/sec > > This PR > - seekrandom [AVG 6 runs] : 95521 ops/sec; 52.8 MB/sec > - seekrandom [MEDIAN 6 runs] : 96338 ops/sec; 53.3 MB/sec 2. Enable timestamp, run: ``` ./db_bench -user_timestamp_size=8 -db=/dev/shm/rocksdb -disable_wal=1 -benchmarks=fillseq,seekrandom[-W1-X6] -reverse_iterator=1 -seek_nexts=5 ``` Result: > Baseline: not supported > > This PR > - seekrandom [AVG 6 runs] : 90514 ops/sec; 50.1 MB/sec > - seekrandom [MEDIAN 6 runs] : 90834 ops/sec; 50.2 MB/sec Pull Request resolved: https://github.com/facebook/rocksdb/pull/8035 Reviewed By: ltamasi Differential Revision: D26926668 Pulled By: riversand963 fbshipit-source-id: 95330cc2242397c03e09d29e5417dfb0adc98ef5
2021-03-10 19:13:55 +00:00
std::string saved_timestamp_;
};
// Return a new iterator that converts internal keys (yielded by
// "*internal_iter") that were live at the specified `sequence` number
// into appropriate user keys.
extern Iterator* NewDBIterator(
Env* env, const ReadOptions& read_options, const ImmutableOptions& ioptions,
const MutableCFOptions& mutable_cf_options,
const Comparator* user_key_comparator, InternalIterator* internal_iter,
const Version* version, const SequenceNumber& sequence,
uint64_t max_sequential_skip_in_iterations, ReadCallback* read_callback,
DBImpl* db_impl = nullptr, ColumnFamilyData* cfd = nullptr,
bool expose_blob_index = false);
} // namespace ROCKSDB_NAMESPACE