mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-29 18:33:58 +00:00
f26cb0f093
Summary: Based on my recent findings (posted in our internal group), if we use fallocate without KEEP_SIZE flag, we get superior performance of fdatasync() in append-only workloads. This diff provides an option for user to not use KEEP_SIZE flag, thus optimizing his sync performance by up to 2x-3x. At one point we also just called posix_fallocate instead of fallocate, which isn't very fast: http://code.woboq.org/userspace/glibc/sysdeps/posix/posix_fallocate.c.html (tl;dr it manually writes out zero bytes to allocate storage). This diff also fixes that, by first calling fallocate and then posix_fallocate if fallocate is not supported. Test Plan: make check Reviewers: dhruba, sdong, haobo, ljin Reviewed By: dhruba CC: leveldb Differential Revision: https://reviews.facebook.net/D16761
263 lines
6 KiB
C++
263 lines
6 KiB
C++
// Copyright (c) 2013, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under the BSD-style license found in the
|
|
// LICENSE file in the root directory of this source tree. An additional grant
|
|
// of patent rights can be found in the PATENTS file in the same directory.
|
|
//
|
|
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
|
|
// Use of this source code is governed by a BSD-style license that can be
|
|
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
|
|
|
#include "rocksdb/env.h"
|
|
|
|
#include <sys/time.h>
|
|
#include "rocksdb/options.h"
|
|
#include "util/arena.h"
|
|
#include "util/autovector.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
Env::~Env() {
|
|
}
|
|
|
|
SequentialFile::~SequentialFile() {
|
|
}
|
|
|
|
RandomAccessFile::~RandomAccessFile() {
|
|
}
|
|
|
|
WritableFile::~WritableFile() {
|
|
}
|
|
|
|
Logger::~Logger() {
|
|
}
|
|
|
|
FileLock::~FileLock() {
|
|
}
|
|
|
|
void LogFlush(Logger *info_log) {
|
|
if (info_log) {
|
|
info_log->Flush();
|
|
}
|
|
}
|
|
|
|
void Log(Logger* info_log, const char* format, ...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(InfoLogLevel::INFO, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
|
|
void Log(const InfoLogLevel log_level, Logger* info_log, const char* format,
|
|
...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(log_level, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
|
|
void Debug(Logger* info_log, const char* format, ...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(InfoLogLevel::DEBUG, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
|
|
void Info(Logger* info_log, const char* format, ...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(InfoLogLevel::INFO, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
|
|
void Warn(Logger* info_log, const char* format, ...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(InfoLogLevel::WARN, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
void Error(Logger* info_log, const char* format, ...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(InfoLogLevel::ERROR, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
void Fatal(Logger* info_log, const char* format, ...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(InfoLogLevel::FATAL, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
|
|
void LogFlush(const shared_ptr<Logger>& info_log) {
|
|
if (info_log) {
|
|
info_log->Flush();
|
|
}
|
|
}
|
|
|
|
void Log(const InfoLogLevel log_level, const shared_ptr<Logger>& info_log,
|
|
const char* format, ...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(log_level, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
|
|
void Debug(const shared_ptr<Logger>& info_log, const char* format, ...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(InfoLogLevel::DEBUG, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
|
|
void Info(const shared_ptr<Logger>& info_log, const char* format, ...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(InfoLogLevel::INFO, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
|
|
void Warn(const shared_ptr<Logger>& info_log, const char* format, ...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(InfoLogLevel::WARN, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
|
|
void Error(const shared_ptr<Logger>& info_log, const char* format, ...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(InfoLogLevel::ERROR, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
|
|
void Fatal(const shared_ptr<Logger>& info_log, const char* format, ...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(InfoLogLevel::FATAL, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
|
|
void Log(const shared_ptr<Logger>& info_log, const char* format, ...) {
|
|
if (info_log) {
|
|
va_list ap;
|
|
va_start(ap, format);
|
|
info_log->Logv(InfoLogLevel::INFO, format, ap);
|
|
va_end(ap);
|
|
}
|
|
}
|
|
|
|
static Status DoWriteStringToFile(Env* env, const Slice& data,
|
|
const std::string& fname,
|
|
bool should_sync) {
|
|
unique_ptr<WritableFile> file;
|
|
EnvOptions soptions;
|
|
Status s = env->NewWritableFile(fname, &file, soptions);
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
s = file->Append(data);
|
|
if (s.ok() && should_sync) {
|
|
s = file->Sync();
|
|
}
|
|
if (!s.ok()) {
|
|
env->DeleteFile(fname);
|
|
}
|
|
return s;
|
|
}
|
|
|
|
Status WriteStringToFile(Env* env, const Slice& data,
|
|
const std::string& fname) {
|
|
return DoWriteStringToFile(env, data, fname, false);
|
|
}
|
|
|
|
Status WriteStringToFileSync(Env* env, const Slice& data,
|
|
const std::string& fname) {
|
|
return DoWriteStringToFile(env, data, fname, true);
|
|
}
|
|
|
|
Status ReadFileToString(Env* env, const std::string& fname, std::string* data) {
|
|
EnvOptions soptions;
|
|
data->clear();
|
|
unique_ptr<SequentialFile> file;
|
|
Status s = env->NewSequentialFile(fname, &file, soptions);
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
static const int kBufferSize = 8192;
|
|
char* space = new char[kBufferSize];
|
|
while (true) {
|
|
Slice fragment;
|
|
s = file->Read(kBufferSize, &fragment, space);
|
|
if (!s.ok()) {
|
|
break;
|
|
}
|
|
data->append(fragment.data(), fragment.size());
|
|
if (fragment.empty()) {
|
|
break;
|
|
}
|
|
}
|
|
delete[] space;
|
|
return s;
|
|
}
|
|
|
|
EnvWrapper::~EnvWrapper() {
|
|
}
|
|
|
|
namespace { // anonymous namespace
|
|
|
|
void AssignEnvOptions(EnvOptions* env_options, const Options& options) {
|
|
env_options->use_os_buffer = options.allow_os_buffer;
|
|
env_options->use_mmap_reads = options.allow_mmap_reads;
|
|
env_options->use_mmap_writes = options.allow_mmap_writes;
|
|
env_options->set_fd_cloexec = options.is_fd_close_on_exec;
|
|
env_options->bytes_per_sync = options.bytes_per_sync;
|
|
}
|
|
|
|
}
|
|
|
|
EnvOptions Env::OptimizeForLogWrite(const EnvOptions& env_options) const {
|
|
return env_options;
|
|
}
|
|
|
|
EnvOptions Env::OptimizeForManifestWrite(const EnvOptions& env_options) const {
|
|
return env_options;
|
|
}
|
|
|
|
EnvOptions::EnvOptions(const Options& options) {
|
|
AssignEnvOptions(this, options);
|
|
}
|
|
|
|
EnvOptions::EnvOptions() {
|
|
Options options;
|
|
AssignEnvOptions(this, options);
|
|
}
|
|
|
|
|
|
} // namespace rocksdb
|