mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-27 20:43:57 +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
208 lines
6.2 KiB
C++
208 lines
6.2 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 "db/blob/blob_log_writer.h"
|
|
|
|
#include <cstdint>
|
|
#include <string>
|
|
|
|
#include "db/blob/blob_log_format.h"
|
|
#include "file/writable_file_writer.h"
|
|
#include "monitoring/statistics_impl.h"
|
|
#include "rocksdb/system_clock.h"
|
|
#include "test_util/sync_point.h"
|
|
#include "util/coding.h"
|
|
#include "util/stop_watch.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
BlobLogWriter::BlobLogWriter(std::unique_ptr<WritableFileWriter>&& dest,
|
|
SystemClock* clock, Statistics* statistics,
|
|
uint64_t log_number, bool use_fs, bool do_flush,
|
|
uint64_t boffset)
|
|
: dest_(std::move(dest)),
|
|
clock_(clock),
|
|
statistics_(statistics),
|
|
log_number_(log_number),
|
|
block_offset_(boffset),
|
|
use_fsync_(use_fs),
|
|
do_flush_(do_flush),
|
|
last_elem_type_(kEtNone) {}
|
|
|
|
BlobLogWriter::~BlobLogWriter() = default;
|
|
|
|
Status BlobLogWriter::Sync(const WriteOptions& write_options) {
|
|
TEST_SYNC_POINT("BlobLogWriter::Sync");
|
|
|
|
StopWatch sync_sw(clock_, statistics_, BLOB_DB_BLOB_FILE_SYNC_MICROS);
|
|
IOOptions opts;
|
|
Status s = WritableFileWriter::PrepareIOOptions(write_options, opts);
|
|
if (s.ok()) {
|
|
s = dest_->Sync(opts, use_fsync_);
|
|
}
|
|
if (s.ok()) {
|
|
RecordTick(statistics_, BLOB_DB_BLOB_FILE_SYNCED);
|
|
}
|
|
return s;
|
|
}
|
|
|
|
Status BlobLogWriter::WriteHeader(const WriteOptions& write_options,
|
|
BlobLogHeader& header) {
|
|
assert(block_offset_ == 0);
|
|
assert(last_elem_type_ == kEtNone);
|
|
std::string str;
|
|
header.EncodeTo(&str);
|
|
|
|
IOOptions opts;
|
|
Status s = WritableFileWriter::PrepareIOOptions(write_options, opts);
|
|
if (s.ok()) {
|
|
s = dest_->Append(opts, Slice(str));
|
|
}
|
|
if (s.ok()) {
|
|
block_offset_ += str.size();
|
|
if (do_flush_) {
|
|
s = dest_->Flush(opts);
|
|
}
|
|
}
|
|
last_elem_type_ = kEtFileHdr;
|
|
if (s.ok()) {
|
|
RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_WRITTEN,
|
|
BlobLogHeader::kSize);
|
|
}
|
|
return s;
|
|
}
|
|
|
|
Status BlobLogWriter::AppendFooter(const WriteOptions& write_options,
|
|
BlobLogFooter& footer,
|
|
std::string* checksum_method,
|
|
std::string* checksum_value) {
|
|
assert(block_offset_ != 0);
|
|
assert(last_elem_type_ == kEtFileHdr || last_elem_type_ == kEtRecord);
|
|
|
|
std::string str;
|
|
footer.EncodeTo(&str);
|
|
|
|
Status s;
|
|
if (dest_->seen_error()) {
|
|
s.PermitUncheckedError();
|
|
return Status::IOError("Seen Error. Skip closing.");
|
|
} else {
|
|
IOOptions opts;
|
|
s = WritableFileWriter::PrepareIOOptions(write_options, opts);
|
|
if (s.ok()) {
|
|
s = dest_->Append(opts, Slice(str));
|
|
}
|
|
if (s.ok()) {
|
|
block_offset_ += str.size();
|
|
s = Sync(write_options);
|
|
|
|
if (s.ok()) {
|
|
s = dest_->Close(opts);
|
|
|
|
if (s.ok()) {
|
|
assert(!!checksum_method == !!checksum_value);
|
|
|
|
if (checksum_method) {
|
|
assert(checksum_method->empty());
|
|
|
|
std::string method = dest_->GetFileChecksumFuncName();
|
|
if (method != kUnknownFileChecksumFuncName) {
|
|
*checksum_method = std::move(method);
|
|
}
|
|
}
|
|
if (checksum_value) {
|
|
assert(checksum_value->empty());
|
|
|
|
std::string value = dest_->GetFileChecksum();
|
|
if (value != kUnknownFileChecksum) {
|
|
*checksum_value = std::move(value);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
dest_.reset();
|
|
}
|
|
|
|
last_elem_type_ = kEtFileFooter;
|
|
if (s.ok()) {
|
|
RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_WRITTEN,
|
|
BlobLogFooter::kSize);
|
|
}
|
|
return s;
|
|
}
|
|
|
|
Status BlobLogWriter::AddRecord(const WriteOptions& write_options,
|
|
const Slice& key, const Slice& val,
|
|
uint64_t expiration, uint64_t* key_offset,
|
|
uint64_t* blob_offset) {
|
|
assert(block_offset_ != 0);
|
|
assert(last_elem_type_ == kEtFileHdr || last_elem_type_ == kEtRecord);
|
|
|
|
std::string buf;
|
|
ConstructBlobHeader(&buf, key, val, expiration);
|
|
|
|
Status s =
|
|
EmitPhysicalRecord(write_options, buf, key, val, key_offset, blob_offset);
|
|
return s;
|
|
}
|
|
|
|
Status BlobLogWriter::AddRecord(const WriteOptions& write_options,
|
|
const Slice& key, const Slice& val,
|
|
uint64_t* key_offset, uint64_t* blob_offset) {
|
|
assert(block_offset_ != 0);
|
|
assert(last_elem_type_ == kEtFileHdr || last_elem_type_ == kEtRecord);
|
|
|
|
std::string buf;
|
|
ConstructBlobHeader(&buf, key, val, 0);
|
|
|
|
Status s =
|
|
EmitPhysicalRecord(write_options, buf, key, val, key_offset, blob_offset);
|
|
return s;
|
|
}
|
|
|
|
void BlobLogWriter::ConstructBlobHeader(std::string* buf, const Slice& key,
|
|
const Slice& val, uint64_t expiration) {
|
|
BlobLogRecord record;
|
|
record.key = key;
|
|
record.value = val;
|
|
record.expiration = expiration;
|
|
record.EncodeHeaderTo(buf);
|
|
}
|
|
|
|
Status BlobLogWriter::EmitPhysicalRecord(const WriteOptions& write_options,
|
|
const std::string& headerbuf,
|
|
const Slice& key, const Slice& val,
|
|
uint64_t* key_offset,
|
|
uint64_t* blob_offset) {
|
|
IOOptions opts;
|
|
Status s = WritableFileWriter::PrepareIOOptions(write_options, opts);
|
|
if (s.ok()) {
|
|
s = dest_->Append(opts, Slice(headerbuf));
|
|
}
|
|
if (s.ok()) {
|
|
s = dest_->Append(opts, key);
|
|
}
|
|
if (s.ok()) {
|
|
s = dest_->Append(opts, val);
|
|
}
|
|
if (do_flush_ && s.ok()) {
|
|
s = dest_->Flush(opts);
|
|
}
|
|
|
|
*key_offset = block_offset_ + BlobLogRecord::kHeaderSize;
|
|
*blob_offset = *key_offset + key.size();
|
|
block_offset_ = *blob_offset + val.size();
|
|
last_elem_type_ = kEtRecord;
|
|
if (s.ok()) {
|
|
RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_WRITTEN,
|
|
BlobLogRecord::kHeaderSize + key.size() + val.size());
|
|
}
|
|
return s;
|
|
}
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|