rocksdb/db/blob/blob_log_writer.cc
mrambacher 3dff28cf9b Use SystemClock* instead of std::shared_ptr<SystemClock> in lower level routines (#8033)
Summary:
For performance purposes, the lower level routines were changed to use a SystemClock* instead of a std::shared_ptr<SystemClock>.  The shared ptr has some performance degradation on certain hardware classes.

For most of the system, there is no risk of the pointer being deleted/invalid because the shared_ptr will be stored elsewhere.  For example, the ImmutableDBOptions stores the Env which has a std::shared_ptr<SystemClock> in it.  The SystemClock* within the ImmutableDBOptions is essentially a "short cut" to gain access to this constant resource.

There were a few classes (PeriodicWorkScheduler?) where the "short cut" property did not hold.  In those cases, the shared pointer was preserved.

Using db_bench readrandom perf_level=3 on my EC2 box, this change performed as well or better than 6.17:

6.17: readrandom   :      28.046 micros/op 854902 ops/sec;   61.3 MB/s (355999 of 355999 found)
6.18: readrandom   :      32.615 micros/op 735306 ops/sec;   52.7 MB/s (290999 of 290999 found)
PR: readrandom   :      27.500 micros/op 871909 ops/sec;   62.5 MB/s (367999 of 367999 found)

(Note that the times for 6.18 are prior to revert of the SystemClock).

Pull Request resolved: https://github.com/facebook/rocksdb/pull/8033

Reviewed By: pdillinger

Differential Revision: D27014563

Pulled By: mrambacher

fbshipit-source-id: ad0459eba03182e454391b5926bf5cdd45657b67
2021-03-15 04:34:11 -07:00

173 lines
5.1 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.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() {
TEST_SYNC_POINT("BlobLogWriter::Sync");
StopWatch sync_sw(clock_, statistics_, BLOB_DB_BLOB_FILE_SYNC_MICROS);
Status s = dest_->Sync(use_fsync_);
RecordTick(statistics_, BLOB_DB_BLOB_FILE_SYNCED);
return s;
}
Status BlobLogWriter::WriteHeader(BlobLogHeader& header) {
assert(block_offset_ == 0);
assert(last_elem_type_ == kEtNone);
std::string str;
header.EncodeTo(&str);
Status s = dest_->Append(Slice(str));
if (s.ok()) {
block_offset_ += str.size();
if (do_flush_) {
s = dest_->Flush();
}
}
last_elem_type_ = kEtFileHdr;
RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_WRITTEN,
BlobLogHeader::kSize);
return s;
}
Status BlobLogWriter::AppendFooter(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 = dest_->Append(Slice(str));
if (s.ok()) {
block_offset_ += str.size();
s = Sync();
if (s.ok()) {
s = dest_->Close();
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;
RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_WRITTEN,
BlobLogFooter::kSize);
return s;
}
Status BlobLogWriter::AddRecord(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(buf, key, val, key_offset, blob_offset);
return s;
}
Status BlobLogWriter::AddRecord(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(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 std::string& headerbuf,
const Slice& key, const Slice& val,
uint64_t* key_offset,
uint64_t* blob_offset) {
StopWatch write_sw(clock_, statistics_, BLOB_DB_BLOB_FILE_WRITE_MICROS);
Status s = dest_->Append(Slice(headerbuf));
if (s.ok()) {
s = dest_->Append(key);
}
if (s.ok()) {
s = dest_->Append(val);
}
if (do_flush_ && s.ok()) {
s = dest_->Flush();
}
*key_offset = block_offset_ + BlobLogRecord::kHeaderSize;
*blob_offset = *key_offset + key.size();
block_offset_ = *blob_offset + val.size();
last_elem_type_ = kEtRecord;
RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_WRITTEN,
BlobLogRecord::kHeaderSize + key.size() + val.size());
return s;
}
} // namespace ROCKSDB_NAMESPACE