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
314 lines
9.7 KiB
C++
314 lines
9.7 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).
|
|
#include "utilities/blob_db/blob_file.h"
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <algorithm>
|
|
#include <cinttypes>
|
|
#include <memory>
|
|
|
|
#include "db/column_family.h"
|
|
#include "db/db_impl/db_impl.h"
|
|
#include "db/dbformat.h"
|
|
#include "file/filename.h"
|
|
#include "file/readahead_raf.h"
|
|
#include "logging/logging.h"
|
|
#include "utilities/blob_db/blob_db_impl.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
namespace blob_db {
|
|
|
|
BlobFile::BlobFile(const BlobDBImpl* p, const std::string& bdir, uint64_t fn,
|
|
Logger* info_log)
|
|
: parent_(p), path_to_dir_(bdir), file_number_(fn), info_log_(info_log) {}
|
|
|
|
BlobFile::BlobFile(const BlobDBImpl* p, const std::string& bdir, uint64_t fn,
|
|
Logger* info_log, uint32_t column_family_id,
|
|
CompressionType compression, bool has_ttl,
|
|
const ExpirationRange& expiration_range)
|
|
: parent_(p),
|
|
path_to_dir_(bdir),
|
|
file_number_(fn),
|
|
info_log_(info_log),
|
|
column_family_id_(column_family_id),
|
|
compression_(compression),
|
|
has_ttl_(has_ttl),
|
|
expiration_range_(expiration_range),
|
|
header_(column_family_id, compression, has_ttl, expiration_range),
|
|
header_valid_(true) {}
|
|
|
|
BlobFile::~BlobFile() {
|
|
if (obsolete_) {
|
|
std::string pn(PathName());
|
|
Status s = Env::Default()->DeleteFile(PathName());
|
|
if (!s.ok()) {
|
|
// ROCKS_LOG_INFO(db_options_.info_log,
|
|
// "File could not be deleted %s", pn.c_str());
|
|
}
|
|
}
|
|
}
|
|
|
|
uint32_t BlobFile::GetColumnFamilyId() const { return column_family_id_; }
|
|
|
|
std::string BlobFile::PathName() const {
|
|
return BlobFileName(path_to_dir_, file_number_);
|
|
}
|
|
|
|
std::string BlobFile::DumpState() const {
|
|
char str[1000];
|
|
snprintf(
|
|
str, sizeof(str),
|
|
"path: %s fn: %" PRIu64 " blob_count: %" PRIu64 " file_size: %" PRIu64
|
|
" closed: %d obsolete: %d expiration_range: (%" PRIu64 ", %" PRIu64
|
|
"), writer: %d reader: %d",
|
|
path_to_dir_.c_str(), file_number_, blob_count_.load(), file_size_.load(),
|
|
closed_.load(), obsolete_.load(), expiration_range_.first,
|
|
expiration_range_.second, (!!log_writer_), (!!ra_file_reader_));
|
|
return str;
|
|
}
|
|
|
|
void BlobFile::MarkObsolete(SequenceNumber sequence) {
|
|
assert(Immutable());
|
|
obsolete_sequence_ = sequence;
|
|
obsolete_.store(true);
|
|
}
|
|
|
|
Status BlobFile::WriteFooterAndCloseLocked(const WriteOptions& write_options,
|
|
SequenceNumber sequence) {
|
|
BlobLogFooter footer;
|
|
footer.blob_count = blob_count_;
|
|
if (HasTTL()) {
|
|
footer.expiration_range = expiration_range_;
|
|
}
|
|
|
|
// this will close the file and reset the Writable File Pointer.
|
|
Status s = log_writer_->AppendFooter(write_options, footer,
|
|
/* checksum_method */ nullptr,
|
|
/* checksum_value */ nullptr);
|
|
if (s.ok()) {
|
|
closed_ = true;
|
|
immutable_sequence_ = sequence;
|
|
file_size_ += BlobLogFooter::kSize;
|
|
}
|
|
// delete the sequential writer
|
|
log_writer_.reset();
|
|
return s;
|
|
}
|
|
|
|
Status BlobFile::ReadFooter(BlobLogFooter* bf) {
|
|
if (file_size_ < (BlobLogHeader::kSize + BlobLogFooter::kSize)) {
|
|
return Status::IOError("File does not have footer", PathName());
|
|
}
|
|
|
|
uint64_t footer_offset = file_size_ - BlobLogFooter::kSize;
|
|
// assume that ra_file_reader_ is valid before we enter this
|
|
assert(ra_file_reader_);
|
|
|
|
Slice result;
|
|
std::string buf;
|
|
AlignedBuf aligned_buf;
|
|
Status s;
|
|
// TODO: rate limit reading footers from blob files.
|
|
if (ra_file_reader_->use_direct_io()) {
|
|
s = ra_file_reader_->Read(IOOptions(), footer_offset, BlobLogFooter::kSize,
|
|
&result, nullptr, &aligned_buf);
|
|
} else {
|
|
buf.reserve(BlobLogFooter::kSize + 10);
|
|
s = ra_file_reader_->Read(IOOptions(), footer_offset, BlobLogFooter::kSize,
|
|
&result, &buf[0], nullptr);
|
|
}
|
|
if (!s.ok()) return s;
|
|
if (result.size() != BlobLogFooter::kSize) {
|
|
// should not happen
|
|
return Status::IOError("EOF reached before footer");
|
|
}
|
|
|
|
s = bf->DecodeFrom(result);
|
|
return s;
|
|
}
|
|
|
|
Status BlobFile::SetFromFooterLocked(const BlobLogFooter& footer) {
|
|
blob_count_ = footer.blob_count;
|
|
expiration_range_ = footer.expiration_range;
|
|
closed_ = true;
|
|
return Status::OK();
|
|
}
|
|
|
|
Status BlobFile::Fsync(const WriteOptions& write_options) {
|
|
Status s;
|
|
if (log_writer_.get()) {
|
|
s = log_writer_->Sync(write_options);
|
|
}
|
|
return s;
|
|
}
|
|
|
|
void BlobFile::CloseRandomAccessLocked() {
|
|
ra_file_reader_.reset();
|
|
last_access_ = -1;
|
|
}
|
|
|
|
Status BlobFile::GetReader(Env* env, const FileOptions& file_options,
|
|
std::shared_ptr<RandomAccessFileReader>* reader,
|
|
bool* fresh_open) {
|
|
assert(reader != nullptr);
|
|
assert(fresh_open != nullptr);
|
|
*fresh_open = false;
|
|
int64_t current_time = 0;
|
|
if (env->GetCurrentTime(¤t_time).ok()) {
|
|
last_access_.store(current_time);
|
|
}
|
|
Status s;
|
|
|
|
{
|
|
ReadLock lockbfile_r(&mutex_);
|
|
if (ra_file_reader_) {
|
|
*reader = ra_file_reader_;
|
|
return s;
|
|
}
|
|
}
|
|
|
|
WriteLock lockbfile_w(&mutex_);
|
|
// Double check.
|
|
if (ra_file_reader_) {
|
|
*reader = ra_file_reader_;
|
|
return s;
|
|
}
|
|
|
|
std::unique_ptr<FSRandomAccessFile> rfile;
|
|
s = env->GetFileSystem()->NewRandomAccessFile(PathName(), file_options,
|
|
&rfile, nullptr);
|
|
if (!s.ok()) {
|
|
ROCKS_LOG_ERROR(info_log_,
|
|
"Failed to open blob file for random-read: %s status: '%s'"
|
|
" exists: '%s'",
|
|
PathName().c_str(), s.ToString().c_str(),
|
|
env->FileExists(PathName()).ToString().c_str());
|
|
return s;
|
|
}
|
|
|
|
ra_file_reader_ =
|
|
std::make_shared<RandomAccessFileReader>(std::move(rfile), PathName());
|
|
*reader = ra_file_reader_;
|
|
*fresh_open = true;
|
|
return s;
|
|
}
|
|
|
|
Status BlobFile::ReadMetadata(const std::shared_ptr<FileSystem>& fs,
|
|
const FileOptions& file_options) {
|
|
assert(Immutable());
|
|
// Get file size.
|
|
uint64_t file_size = 0;
|
|
Status s =
|
|
fs->GetFileSize(PathName(), file_options.io_options, &file_size, nullptr);
|
|
if (s.ok()) {
|
|
file_size_ = file_size;
|
|
} else {
|
|
ROCKS_LOG_ERROR(info_log_,
|
|
"Failed to get size of blob file %" PRIu64 ", status: %s",
|
|
file_number_, s.ToString().c_str());
|
|
return s;
|
|
}
|
|
if (file_size < BlobLogHeader::kSize) {
|
|
ROCKS_LOG_ERROR(
|
|
info_log_, "Incomplete blob file blob file %" PRIu64 ", size: %" PRIu64,
|
|
file_number_, file_size);
|
|
return Status::Corruption("Incomplete blob file header.");
|
|
}
|
|
|
|
// Create file reader.
|
|
std::unique_ptr<RandomAccessFileReader> file_reader;
|
|
s = RandomAccessFileReader::Create(fs, PathName(), file_options, &file_reader,
|
|
nullptr);
|
|
if (!s.ok()) {
|
|
ROCKS_LOG_ERROR(info_log_,
|
|
"Failed to open blob file %" PRIu64 ", status: %s",
|
|
file_number_, s.ToString().c_str());
|
|
return s;
|
|
}
|
|
|
|
// Read file header.
|
|
std::string header_buf;
|
|
AlignedBuf aligned_buf;
|
|
Slice header_slice;
|
|
// TODO: rate limit reading headers from blob files.
|
|
if (file_reader->use_direct_io()) {
|
|
s = file_reader->Read(IOOptions(), 0, BlobLogHeader::kSize, &header_slice,
|
|
nullptr, &aligned_buf);
|
|
} else {
|
|
header_buf.reserve(BlobLogHeader::kSize);
|
|
s = file_reader->Read(IOOptions(), 0, BlobLogHeader::kSize, &header_slice,
|
|
&header_buf[0], nullptr);
|
|
}
|
|
if (!s.ok()) {
|
|
ROCKS_LOG_ERROR(
|
|
info_log_, "Failed to read header of blob file %" PRIu64 ", status: %s",
|
|
file_number_, s.ToString().c_str());
|
|
return s;
|
|
}
|
|
BlobLogHeader header;
|
|
s = header.DecodeFrom(header_slice);
|
|
if (!s.ok()) {
|
|
ROCKS_LOG_ERROR(info_log_,
|
|
"Failed to decode header of blob file %" PRIu64
|
|
", status: %s",
|
|
file_number_, s.ToString().c_str());
|
|
return s;
|
|
}
|
|
column_family_id_ = header.column_family_id;
|
|
compression_ = header.compression;
|
|
has_ttl_ = header.has_ttl;
|
|
if (has_ttl_) {
|
|
expiration_range_ = header.expiration_range;
|
|
}
|
|
header_valid_ = true;
|
|
|
|
// Read file footer.
|
|
if (file_size_ < BlobLogHeader::kSize + BlobLogFooter::kSize) {
|
|
// OK not to have footer.
|
|
assert(!footer_valid_);
|
|
return Status::OK();
|
|
}
|
|
std::string footer_buf;
|
|
Slice footer_slice;
|
|
// TODO: rate limit reading footers from blob files.
|
|
if (file_reader->use_direct_io()) {
|
|
s = file_reader->Read(IOOptions(), file_size - BlobLogFooter::kSize,
|
|
BlobLogFooter::kSize, &footer_slice, nullptr,
|
|
&aligned_buf);
|
|
} else {
|
|
footer_buf.reserve(BlobLogFooter::kSize);
|
|
s = file_reader->Read(IOOptions(), file_size - BlobLogFooter::kSize,
|
|
BlobLogFooter::kSize, &footer_slice, &footer_buf[0],
|
|
nullptr);
|
|
}
|
|
if (!s.ok()) {
|
|
ROCKS_LOG_ERROR(
|
|
info_log_, "Failed to read footer of blob file %" PRIu64 ", status: %s",
|
|
file_number_, s.ToString().c_str());
|
|
return s;
|
|
}
|
|
BlobLogFooter footer;
|
|
s = footer.DecodeFrom(footer_slice);
|
|
if (!s.ok()) {
|
|
// OK not to have footer.
|
|
assert(!footer_valid_);
|
|
return Status::OK();
|
|
}
|
|
blob_count_ = footer.blob_count;
|
|
if (has_ttl_) {
|
|
assert(header.expiration_range.first <= footer.expiration_range.first);
|
|
assert(header.expiration_range.second >= footer.expiration_range.second);
|
|
expiration_range_ = footer.expiration_range;
|
|
}
|
|
footer_valid_ = true;
|
|
return Status::OK();
|
|
}
|
|
|
|
} // namespace blob_db
|
|
} // namespace ROCKSDB_NAMESPACE
|