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
279 lines
9.4 KiB
C++
279 lines
9.4 KiB
C++
// Copyright (c) 2019-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/file_system.h"
|
|
|
|
#include "env/composite_env_wrapper.h"
|
|
#include "env/env_chroot.h"
|
|
#include "env/env_encryption_ctr.h"
|
|
#include "env/fs_readonly.h"
|
|
#include "env/mock_env.h"
|
|
#include "logging/env_logger.h"
|
|
#include "options/db_options.h"
|
|
#include "rocksdb/convenience.h"
|
|
#include "rocksdb/utilities/customizable_util.h"
|
|
#include "rocksdb/utilities/object_registry.h"
|
|
#include "rocksdb/utilities/options_type.h"
|
|
#include "util/string_util.h"
|
|
#include "utilities/counted_fs.h"
|
|
#include "utilities/env_timed.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
FileSystem::FileSystem() = default;
|
|
|
|
FileSystem::~FileSystem() = default;
|
|
|
|
static int RegisterBuiltinFileSystems(ObjectLibrary& library,
|
|
const std::string& /*arg*/) {
|
|
library.AddFactory<FileSystem>(
|
|
TimedFileSystem::kClassName(),
|
|
[](const std::string& /*uri*/, std::unique_ptr<FileSystem>* guard,
|
|
std::string* /* errmsg */) {
|
|
guard->reset(new TimedFileSystem(nullptr));
|
|
return guard->get();
|
|
});
|
|
library.AddFactory<FileSystem>(
|
|
ReadOnlyFileSystem::kClassName(),
|
|
[](const std::string& /*uri*/, std::unique_ptr<FileSystem>* guard,
|
|
std::string* /* errmsg */) {
|
|
guard->reset(new ReadOnlyFileSystem(nullptr));
|
|
return guard->get();
|
|
});
|
|
library.AddFactory<FileSystem>(
|
|
EncryptedFileSystem::kClassName(),
|
|
[](const std::string& /*uri*/, std::unique_ptr<FileSystem>* guard,
|
|
std::string* errmsg) {
|
|
Status s = NewEncryptedFileSystemImpl(nullptr, nullptr, guard);
|
|
if (!s.ok()) {
|
|
*errmsg = s.ToString();
|
|
}
|
|
return guard->get();
|
|
});
|
|
library.AddFactory<FileSystem>(
|
|
CountedFileSystem::kClassName(),
|
|
[](const std::string& /*uri*/, std::unique_ptr<FileSystem>* guard,
|
|
std::string* /*errmsg*/) {
|
|
guard->reset(new CountedFileSystem(FileSystem::Default()));
|
|
return guard->get();
|
|
});
|
|
library.AddFactory<FileSystem>(
|
|
MockFileSystem::kClassName(),
|
|
[](const std::string& /*uri*/, std::unique_ptr<FileSystem>* guard,
|
|
std::string* /*errmsg*/) {
|
|
guard->reset(new MockFileSystem(SystemClock::Default()));
|
|
return guard->get();
|
|
});
|
|
#ifndef OS_WIN
|
|
library.AddFactory<FileSystem>(
|
|
ChrootFileSystem::kClassName(),
|
|
[](const std::string& /*uri*/, std::unique_ptr<FileSystem>* guard,
|
|
std::string* /* errmsg */) {
|
|
guard->reset(new ChrootFileSystem(nullptr, ""));
|
|
return guard->get();
|
|
});
|
|
#endif // OS_WIN
|
|
size_t num_types;
|
|
return static_cast<int>(library.GetFactoryCount(&num_types));
|
|
}
|
|
|
|
Status FileSystem::CreateFromString(const ConfigOptions& config_options,
|
|
const std::string& value,
|
|
std::shared_ptr<FileSystem>* result) {
|
|
auto default_fs = FileSystem::Default();
|
|
if (default_fs->IsInstanceOf(value)) {
|
|
*result = default_fs;
|
|
return Status::OK();
|
|
} else {
|
|
static std::once_flag once;
|
|
std::call_once(once, [&]() {
|
|
RegisterBuiltinFileSystems(*(ObjectLibrary::Default().get()), "");
|
|
});
|
|
return LoadSharedObject<FileSystem>(config_options, value, result);
|
|
}
|
|
}
|
|
|
|
IOStatus FileSystem::ReuseWritableFile(const std::string& fname,
|
|
const std::string& old_fname,
|
|
const FileOptions& opts,
|
|
std::unique_ptr<FSWritableFile>* result,
|
|
IODebugContext* dbg) {
|
|
IOStatus s = RenameFile(old_fname, fname, opts.io_options, dbg);
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
return NewWritableFile(fname, opts, result, dbg);
|
|
}
|
|
|
|
IOStatus FileSystem::NewLogger(const std::string& fname,
|
|
const IOOptions& io_opts,
|
|
std::shared_ptr<Logger>* result,
|
|
IODebugContext* dbg) {
|
|
FileOptions options;
|
|
options.io_options = io_opts;
|
|
// TODO: Tune the buffer size.
|
|
options.writable_file_max_buffer_size = 1024 * 1024;
|
|
std::unique_ptr<FSWritableFile> writable_file;
|
|
const IOStatus status = NewWritableFile(fname, options, &writable_file, dbg);
|
|
if (!status.ok()) {
|
|
return status;
|
|
}
|
|
|
|
*result = std::make_shared<EnvLogger>(std::move(writable_file), fname,
|
|
options, Env::Default());
|
|
return IOStatus::OK();
|
|
}
|
|
|
|
FileOptions FileSystem::OptimizeForLogRead(
|
|
const FileOptions& file_options) const {
|
|
FileOptions optimized_file_options(file_options);
|
|
optimized_file_options.use_direct_reads = false;
|
|
return optimized_file_options;
|
|
}
|
|
|
|
FileOptions FileSystem::OptimizeForManifestRead(
|
|
const FileOptions& file_options) const {
|
|
FileOptions optimized_file_options(file_options);
|
|
optimized_file_options.use_direct_reads = false;
|
|
return optimized_file_options;
|
|
}
|
|
|
|
FileOptions FileSystem::OptimizeForLogWrite(const FileOptions& file_options,
|
|
const DBOptions& db_options) const {
|
|
FileOptions optimized_file_options(file_options);
|
|
optimized_file_options.bytes_per_sync = db_options.wal_bytes_per_sync;
|
|
optimized_file_options.writable_file_max_buffer_size =
|
|
db_options.writable_file_max_buffer_size;
|
|
return optimized_file_options;
|
|
}
|
|
|
|
FileOptions FileSystem::OptimizeForManifestWrite(
|
|
const FileOptions& file_options) const {
|
|
return file_options;
|
|
}
|
|
|
|
FileOptions FileSystem::OptimizeForCompactionTableWrite(
|
|
const FileOptions& file_options,
|
|
const ImmutableDBOptions& db_options) const {
|
|
FileOptions optimized_file_options(file_options);
|
|
optimized_file_options.use_direct_writes =
|
|
db_options.use_direct_io_for_flush_and_compaction;
|
|
return optimized_file_options;
|
|
}
|
|
|
|
FileOptions FileSystem::OptimizeForCompactionTableRead(
|
|
const FileOptions& file_options,
|
|
const ImmutableDBOptions& db_options) const {
|
|
FileOptions optimized_file_options(file_options);
|
|
optimized_file_options.use_direct_reads = db_options.use_direct_reads;
|
|
return optimized_file_options;
|
|
}
|
|
|
|
FileOptions FileSystem::OptimizeForBlobFileRead(
|
|
const FileOptions& file_options,
|
|
const ImmutableDBOptions& db_options) const {
|
|
FileOptions optimized_file_options(file_options);
|
|
optimized_file_options.use_direct_reads = db_options.use_direct_reads;
|
|
return optimized_file_options;
|
|
}
|
|
|
|
IOStatus WriteStringToFile(FileSystem* fs, const Slice& data,
|
|
const std::string& fname, bool should_sync,
|
|
const IOOptions& io_options) {
|
|
std::unique_ptr<FSWritableFile> file;
|
|
EnvOptions soptions;
|
|
IOStatus s = fs->NewWritableFile(fname, soptions, &file, nullptr);
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
s = file->Append(data, io_options, nullptr);
|
|
if (s.ok() && should_sync) {
|
|
s = file->Sync(io_options, nullptr);
|
|
}
|
|
if (!s.ok()) {
|
|
fs->DeleteFile(fname, io_options, nullptr);
|
|
}
|
|
return s;
|
|
}
|
|
|
|
IOStatus ReadFileToString(FileSystem* fs, const std::string& fname,
|
|
std::string* data) {
|
|
FileOptions soptions;
|
|
data->clear();
|
|
std::unique_ptr<FSSequentialFile> file;
|
|
IOStatus s = status_to_io_status(
|
|
fs->NewSequentialFile(fname, soptions, &file, nullptr));
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
static const int kBufferSize = 8192;
|
|
char* space = new char[kBufferSize];
|
|
while (true) {
|
|
Slice fragment;
|
|
s = file->Read(kBufferSize, IOOptions(), &fragment, space, nullptr);
|
|
if (!s.ok()) {
|
|
break;
|
|
}
|
|
data->append(fragment.data(), fragment.size());
|
|
if (fragment.empty()) {
|
|
break;
|
|
}
|
|
}
|
|
delete[] space;
|
|
return s;
|
|
}
|
|
|
|
namespace {
|
|
static std::unordered_map<std::string, OptionTypeInfo> fs_wrapper_type_info = {
|
|
{"target",
|
|
OptionTypeInfo::AsCustomSharedPtr<FileSystem>(
|
|
0, OptionVerificationType::kByName, OptionTypeFlags::kDontSerialize)},
|
|
};
|
|
} // namespace
|
|
FileSystemWrapper::FileSystemWrapper(const std::shared_ptr<FileSystem>& t)
|
|
: target_(t) {
|
|
RegisterOptions("", &target_, &fs_wrapper_type_info);
|
|
}
|
|
|
|
Status FileSystemWrapper::PrepareOptions(const ConfigOptions& options) {
|
|
if (target_ == nullptr) {
|
|
target_ = FileSystem::Default();
|
|
}
|
|
return FileSystem::PrepareOptions(options);
|
|
}
|
|
|
|
std::string FileSystemWrapper::SerializeOptions(
|
|
const ConfigOptions& config_options, const std::string& header) const {
|
|
auto parent = FileSystem::SerializeOptions(config_options, "");
|
|
if (config_options.IsShallow() || target_ == nullptr ||
|
|
target_->IsInstanceOf(FileSystem::kDefaultName())) {
|
|
return parent;
|
|
} else {
|
|
std::string result = header;
|
|
if (!StartsWith(parent, OptionTypeInfo::kIdPropName())) {
|
|
result.append(OptionTypeInfo::kIdPropName()).append("=");
|
|
}
|
|
result.append(parent);
|
|
if (!EndsWith(result, config_options.delimiter)) {
|
|
result.append(config_options.delimiter);
|
|
}
|
|
result.append("target=").append(target_->ToString(config_options));
|
|
return result;
|
|
}
|
|
}
|
|
|
|
DirFsyncOptions::DirFsyncOptions() { reason = kDefault; }
|
|
|
|
DirFsyncOptions::DirFsyncOptions(std::string file_renamed_new_name) {
|
|
reason = kFileRenamed;
|
|
renamed_new_name = file_renamed_new_name;
|
|
}
|
|
|
|
DirFsyncOptions::DirFsyncOptions(FsyncReason fsync_reason) {
|
|
assert(fsync_reason != kFileRenamed);
|
|
reason = fsync_reason;
|
|
}
|
|
} // namespace ROCKSDB_NAMESPACE
|