mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 07:30:54 +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
148 lines
4.6 KiB
C++
148 lines
4.6 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 "rocksdb/experimental.h"
|
|
|
|
#include "db/db_impl/db_impl.h"
|
|
#include "db/version_util.h"
|
|
#include "logging/logging.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
namespace experimental {
|
|
|
|
|
|
Status SuggestCompactRange(DB* db, ColumnFamilyHandle* column_family,
|
|
const Slice* begin, const Slice* end) {
|
|
if (db == nullptr) {
|
|
return Status::InvalidArgument("DB is empty");
|
|
}
|
|
|
|
return db->SuggestCompactRange(column_family, begin, end);
|
|
}
|
|
|
|
Status PromoteL0(DB* db, ColumnFamilyHandle* column_family, int target_level) {
|
|
if (db == nullptr) {
|
|
return Status::InvalidArgument("Didn't recognize DB object");
|
|
}
|
|
return db->PromoteL0(column_family, target_level);
|
|
}
|
|
|
|
|
|
Status SuggestCompactRange(DB* db, const Slice* begin, const Slice* end) {
|
|
return SuggestCompactRange(db, db->DefaultColumnFamily(), begin, end);
|
|
}
|
|
|
|
Status UpdateManifestForFilesState(
|
|
const DBOptions& db_opts, const std::string& db_name,
|
|
const std::vector<ColumnFamilyDescriptor>& column_families,
|
|
const UpdateManifestForFilesStateOptions& opts) {
|
|
// TODO: plumb Env::IOActivity, Env::IOPriority
|
|
const ReadOptions read_options;
|
|
const WriteOptions write_options;
|
|
OfflineManifestWriter w(db_opts, db_name);
|
|
Status s = w.Recover(column_families);
|
|
|
|
size_t files_updated = 0;
|
|
size_t cfs_updated = 0;
|
|
auto fs = db_opts.env->GetFileSystem();
|
|
|
|
for (auto cfd : *w.Versions().GetColumnFamilySet()) {
|
|
if (!s.ok()) {
|
|
break;
|
|
}
|
|
assert(cfd);
|
|
|
|
if (cfd->IsDropped() || !cfd->initialized()) {
|
|
continue;
|
|
}
|
|
|
|
const auto* current = cfd->current();
|
|
assert(current);
|
|
|
|
const auto* vstorage = current->storage_info();
|
|
assert(vstorage);
|
|
|
|
VersionEdit edit;
|
|
edit.SetColumnFamily(cfd->GetID());
|
|
|
|
/* SST files */
|
|
for (int level = 0; level < cfd->NumberLevels(); level++) {
|
|
if (!s.ok()) {
|
|
break;
|
|
}
|
|
const auto& level_files = vstorage->LevelFiles(level);
|
|
|
|
for (const auto& lf : level_files) {
|
|
assert(lf);
|
|
|
|
uint64_t number = lf->fd.GetNumber();
|
|
std::string fname =
|
|
TableFileName(w.IOptions().db_paths, number, lf->fd.GetPathId());
|
|
|
|
std::unique_ptr<FSSequentialFile> f;
|
|
FileOptions fopts;
|
|
// Use kUnknown to signal the FileSystem to search all tiers for the
|
|
// file.
|
|
fopts.temperature = Temperature::kUnknown;
|
|
|
|
IOStatus file_ios =
|
|
fs->NewSequentialFile(fname, fopts, &f, /*dbg*/ nullptr);
|
|
if (file_ios.ok()) {
|
|
if (opts.update_temperatures) {
|
|
Temperature temp = f->GetTemperature();
|
|
if (temp != Temperature::kUnknown && temp != lf->temperature) {
|
|
// Current state inconsistent with manifest
|
|
++files_updated;
|
|
edit.DeleteFile(level, number);
|
|
edit.AddFile(
|
|
level, number, lf->fd.GetPathId(), lf->fd.GetFileSize(),
|
|
lf->smallest, lf->largest, lf->fd.smallest_seqno,
|
|
lf->fd.largest_seqno, lf->marked_for_compaction, temp,
|
|
lf->oldest_blob_file_number, lf->oldest_ancester_time,
|
|
lf->file_creation_time, lf->epoch_number, lf->file_checksum,
|
|
lf->file_checksum_func_name, lf->unique_id,
|
|
lf->compensated_range_deletion_size, lf->tail_size,
|
|
lf->user_defined_timestamps_persisted);
|
|
}
|
|
}
|
|
} else {
|
|
s = file_ios;
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
if (s.ok() && edit.NumEntries() > 0) {
|
|
std::unique_ptr<FSDirectory> db_dir;
|
|
s = fs->NewDirectory(db_name, IOOptions(), &db_dir, nullptr);
|
|
if (s.ok()) {
|
|
s = w.LogAndApply(read_options, write_options, cfd, &edit,
|
|
db_dir.get());
|
|
}
|
|
if (s.ok()) {
|
|
++cfs_updated;
|
|
}
|
|
}
|
|
}
|
|
|
|
if (cfs_updated > 0) {
|
|
ROCKS_LOG_INFO(db_opts.info_log,
|
|
"UpdateManifestForFilesState: updated %zu files in %zu CFs",
|
|
files_updated, cfs_updated);
|
|
} else if (s.ok()) {
|
|
ROCKS_LOG_INFO(db_opts.info_log,
|
|
"UpdateManifestForFilesState: no updates needed");
|
|
}
|
|
if (!s.ok()) {
|
|
ROCKS_LOG_ERROR(db_opts.info_log, "UpdateManifestForFilesState failed: %s",
|
|
s.ToString().c_str());
|
|
}
|
|
|
|
return s;
|
|
}
|
|
|
|
} // namespace experimental
|
|
} // namespace ROCKSDB_NAMESPACE
|