mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-25 22:44:05 +00:00
06e593376c
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
246 lines
7.4 KiB
C++
246 lines
7.4 KiB
C++
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
#pragma once
|
|
|
|
#include <atomic>
|
|
#include <limits>
|
|
#include <memory>
|
|
#include <unordered_set>
|
|
|
|
#include "db/blob/blob_log_format.h"
|
|
#include "db/blob/blob_log_writer.h"
|
|
#include "file/random_access_file_reader.h"
|
|
#include "port/port.h"
|
|
#include "rocksdb/env.h"
|
|
#include "rocksdb/file_system.h"
|
|
#include "rocksdb/options.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
namespace blob_db {
|
|
|
|
class BlobDBImpl;
|
|
|
|
class BlobFile {
|
|
friend class BlobDBImpl;
|
|
friend struct BlobFileComparator;
|
|
friend struct BlobFileComparatorTTL;
|
|
friend class BlobIndexCompactionFilterBase;
|
|
friend class BlobIndexCompactionFilterGC;
|
|
|
|
private:
|
|
// access to parent
|
|
const BlobDBImpl* parent_{nullptr};
|
|
|
|
// path to blob directory
|
|
std::string path_to_dir_;
|
|
|
|
// the id of the file.
|
|
// the above 2 are created during file creation and never changed
|
|
// after that
|
|
uint64_t file_number_{0};
|
|
|
|
// The file numbers of the SST files whose oldest blob file reference
|
|
// points to this blob file.
|
|
std::unordered_set<uint64_t> linked_sst_files_;
|
|
|
|
// Info log.
|
|
Logger* info_log_{nullptr};
|
|
|
|
// Column family id.
|
|
uint32_t column_family_id_{std::numeric_limits<uint32_t>::max()};
|
|
|
|
// Compression type of blobs in the file
|
|
CompressionType compression_{kNoCompression};
|
|
|
|
// If true, the keys in this file all has TTL. Otherwise all keys don't
|
|
// have TTL.
|
|
bool has_ttl_{false};
|
|
|
|
// TTL range of blobs in the file.
|
|
ExpirationRange expiration_range_;
|
|
|
|
// number of blobs in the file
|
|
std::atomic<uint64_t> blob_count_{0};
|
|
|
|
// size of the file
|
|
std::atomic<uint64_t> file_size_{0};
|
|
|
|
BlobLogHeader header_;
|
|
|
|
// closed_ = true implies the file is no more mutable
|
|
// no more blobs will be appended and the footer has been written out
|
|
std::atomic<bool> closed_{false};
|
|
|
|
// The latest sequence number when the file was closed/made immutable.
|
|
SequenceNumber immutable_sequence_{0};
|
|
|
|
// Whether the file was marked obsolete (due to either TTL or GC).
|
|
// obsolete_ still needs to do iterator/snapshot checks
|
|
std::atomic<bool> obsolete_{false};
|
|
|
|
// The last sequence number by the time the file marked as obsolete.
|
|
// Data in this file is visible to a snapshot taken before the sequence.
|
|
SequenceNumber obsolete_sequence_{0};
|
|
|
|
// Sequential/Append writer for blobs
|
|
std::shared_ptr<BlobLogWriter> log_writer_;
|
|
|
|
// random access file reader for GET calls
|
|
std::shared_ptr<RandomAccessFileReader> ra_file_reader_;
|
|
|
|
// This Read-Write mutex is per file specific and protects
|
|
// all the datastructures
|
|
mutable port::RWMutex mutex_;
|
|
|
|
// time when the random access reader was last created.
|
|
std::atomic<std::int64_t> last_access_{-1};
|
|
|
|
bool header_valid_{false};
|
|
|
|
bool footer_valid_{false};
|
|
|
|
public:
|
|
BlobFile() = default;
|
|
|
|
BlobFile(const BlobDBImpl* parent, const std::string& bdir, uint64_t fnum,
|
|
Logger* info_log);
|
|
|
|
BlobFile(const BlobDBImpl* parent, const std::string& bdir, uint64_t fnum,
|
|
Logger* info_log, uint32_t column_family_id,
|
|
CompressionType compression, bool has_ttl,
|
|
const ExpirationRange& expiration_range);
|
|
|
|
~BlobFile();
|
|
|
|
uint32_t GetColumnFamilyId() const;
|
|
|
|
// Returns log file's absolute pathname.
|
|
std::string PathName() const;
|
|
|
|
// Primary identifier for blob file.
|
|
// once the file is created, this never changes
|
|
uint64_t BlobFileNumber() const { return file_number_; }
|
|
|
|
// Get the set of SST files whose oldest blob file reference points to
|
|
// this file.
|
|
const std::unordered_set<uint64_t>& GetLinkedSstFiles() const {
|
|
return linked_sst_files_;
|
|
}
|
|
|
|
// Link an SST file whose oldest blob file reference points to this file.
|
|
void LinkSstFile(uint64_t sst_file_number) {
|
|
assert(linked_sst_files_.find(sst_file_number) == linked_sst_files_.end());
|
|
linked_sst_files_.insert(sst_file_number);
|
|
}
|
|
|
|
// Unlink an SST file whose oldest blob file reference points to this file.
|
|
void UnlinkSstFile(uint64_t sst_file_number) {
|
|
auto it = linked_sst_files_.find(sst_file_number);
|
|
assert(it != linked_sst_files_.end());
|
|
linked_sst_files_.erase(it);
|
|
}
|
|
|
|
// the following functions are atomic, and don't need
|
|
// read lock
|
|
uint64_t BlobCount() const {
|
|
return blob_count_.load(std::memory_order_acquire);
|
|
}
|
|
|
|
std::string DumpState() const;
|
|
|
|
// if the file is not taking any more appends.
|
|
bool Immutable() const { return closed_.load(); }
|
|
|
|
// Mark the file as immutable.
|
|
// REQUIRES: write lock held, or access from single thread (on DB open).
|
|
void MarkImmutable(SequenceNumber sequence) {
|
|
closed_ = true;
|
|
immutable_sequence_ = sequence;
|
|
}
|
|
|
|
SequenceNumber GetImmutableSequence() const {
|
|
assert(Immutable());
|
|
return immutable_sequence_;
|
|
}
|
|
|
|
// Whether the file was marked obsolete (due to either TTL or GC).
|
|
bool Obsolete() const {
|
|
assert(Immutable() || !obsolete_.load());
|
|
return obsolete_.load();
|
|
}
|
|
|
|
// Mark file as obsolete (due to either TTL or GC). The file is not visible to
|
|
// snapshots with sequence greater or equal to the given sequence.
|
|
void MarkObsolete(SequenceNumber sequence);
|
|
|
|
SequenceNumber GetObsoleteSequence() const {
|
|
assert(Obsolete());
|
|
return obsolete_sequence_;
|
|
}
|
|
|
|
Status Fsync(const WriteOptions& write_options);
|
|
|
|
uint64_t GetFileSize() const {
|
|
return file_size_.load(std::memory_order_acquire);
|
|
}
|
|
|
|
// All Get functions which are not atomic, will need ReadLock on the mutex
|
|
|
|
const ExpirationRange& GetExpirationRange() const {
|
|
return expiration_range_;
|
|
}
|
|
|
|
void ExtendExpirationRange(uint64_t expiration) {
|
|
expiration_range_.first = std::min(expiration_range_.first, expiration);
|
|
expiration_range_.second = std::max(expiration_range_.second, expiration);
|
|
}
|
|
|
|
bool HasTTL() const { return has_ttl_; }
|
|
|
|
void SetHasTTL(bool has_ttl) { has_ttl_ = has_ttl; }
|
|
|
|
CompressionType GetCompressionType() const { return compression_; }
|
|
|
|
std::shared_ptr<BlobLogWriter> GetWriter() const { return log_writer_; }
|
|
|
|
// Read blob file header and footer. Return corruption if file header is
|
|
// malform or incomplete. If footer is malform or incomplete, set
|
|
// footer_valid_ to false and return Status::OK.
|
|
Status ReadMetadata(const std::shared_ptr<FileSystem>& fs,
|
|
const FileOptions& file_options);
|
|
|
|
Status GetReader(Env* env, const FileOptions& file_options,
|
|
std::shared_ptr<RandomAccessFileReader>* reader,
|
|
bool* fresh_open);
|
|
|
|
private:
|
|
Status ReadFooter(BlobLogFooter* footer);
|
|
|
|
Status WriteFooterAndCloseLocked(const WriteOptions& write_options,
|
|
SequenceNumber sequence);
|
|
|
|
void CloseRandomAccessLocked();
|
|
|
|
// this is used, when you are reading only the footer of a
|
|
// previously closed file
|
|
Status SetFromFooterLocked(const BlobLogFooter& footer);
|
|
|
|
void set_expiration_range(const ExpirationRange& expiration_range) {
|
|
expiration_range_ = expiration_range;
|
|
}
|
|
|
|
// The following functions are atomic, and don't need locks
|
|
void SetFileSize(uint64_t fs) { file_size_ = fs; }
|
|
|
|
void SetBlobCount(uint64_t bc) { blob_count_ = bc; }
|
|
|
|
void BlobRecordAdded(uint64_t record_size) {
|
|
++blob_count_;
|
|
file_size_ += record_size;
|
|
}
|
|
};
|
|
} // namespace blob_db
|
|
} // namespace ROCKSDB_NAMESPACE
|