You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/util/file_checksum_helper.cc

171 lines
5.7 KiB

// 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).
//
// 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 "util/file_checksum_helper.h"
#include <unordered_set>
#include "db/log_reader.h"
#include "db/version_edit.h"
#include "db/version_edit_handler.h"
#include "file/sequence_file_reader.h"
#include "rocksdb/utilities/customizable_util.h"
namespace ROCKSDB_NAMESPACE {
void FileChecksumListImpl::reset() { checksum_map_.clear(); }
size_t FileChecksumListImpl::size() const { return checksum_map_.size(); }
Status FileChecksumListImpl::GetAllFileChecksums(
std::vector<uint64_t>* file_numbers, std::vector<std::string>* checksums,
std::vector<std::string>* checksum_func_names) {
if (file_numbers == nullptr || checksums == nullptr ||
checksum_func_names == nullptr) {
return Status::InvalidArgument("Pointer has not been initiated");
}
for (auto i : checksum_map_) {
file_numbers->push_back(i.first);
checksums->push_back(i.second.first);
checksum_func_names->push_back(i.second.second);
}
return Status::OK();
}
Status FileChecksumListImpl::SearchOneFileChecksum(
uint64_t file_number, std::string* checksum,
std::string* checksum_func_name) {
if (checksum == nullptr || checksum_func_name == nullptr) {
return Status::InvalidArgument("Pointer has not been initiated");
}
auto it = checksum_map_.find(file_number);
if (it == checksum_map_.end()) {
return Status::NotFound();
} else {
*checksum = it->second.first;
*checksum_func_name = it->second.second;
}
return Status::OK();
}
Status FileChecksumListImpl::InsertOneFileChecksum(
uint64_t file_number, const std::string& checksum,
const std::string& checksum_func_name) {
auto it = checksum_map_.find(file_number);
if (it == checksum_map_.end()) {
checksum_map_.insert(std::make_pair(
file_number, std::make_pair(checksum, checksum_func_name)));
} else {
it->second.first = checksum;
it->second.second = checksum_func_name;
}
return Status::OK();
}
Status FileChecksumListImpl::RemoveOneFileChecksum(uint64_t file_number) {
auto it = checksum_map_.find(file_number);
if (it == checksum_map_.end()) {
return Status::NotFound();
} else {
checksum_map_.erase(it);
}
return Status::OK();
}
FileChecksumList* NewFileChecksumList() {
FileChecksumListImpl* checksum_list = new FileChecksumListImpl();
return checksum_list;
}
std::shared_ptr<FileChecksumGenFactory> GetFileChecksumGenCrc32cFactory() {
static std::shared_ptr<FileChecksumGenFactory> default_crc32c_gen_factory(
new FileChecksumGenCrc32cFactory());
return default_crc32c_gen_factory;
}
Status GetFileChecksumsFromManifest(Env* src_env, const std::string& abs_path,
uint64_t manifest_file_size,
FileChecksumList* checksum_list) {
if (checksum_list == nullptr) {
return Status::InvalidArgument("checksum_list is nullptr");
}
assert(checksum_list);
Group rocksdb.sst.read.micros stat by IOActivity flush and compaction (#11288) Summary: **Context:** The existing stat rocksdb.sst.read.micros does not reflect each of compaction and flush cases but aggregate them, which is not so helpful for us to understand IO read behavior of each of them. **Summary** - Update `StopWatch` and `RandomAccessFileReader` to record `rocksdb.sst.read.micros` and `rocksdb.file.{flush/compaction}.read.micros` - Fixed the default histogram in `RandomAccessFileReader` - New field `ReadOptions/IOOptions::io_activity`; Pass `ReadOptions` through paths under db open, flush and compaction to where we can prepare `IOOptions` and pass it to `RandomAccessFileReader` - Use `thread_status_util` for assertion in `DbStressFSWrapper` for continuous testing on we are passing correct `io_activity` under db open, flush and compaction Pull Request resolved: https://github.com/facebook/rocksdb/pull/11288 Test Plan: - **Stress test** - **Db bench 1: rocksdb.sst.read.micros COUNT ≈ sum of rocksdb.file.read.flush.micros's and rocksdb.file.read.compaction.micros's.** (without blob) - May not be exactly the same due to `HistogramStat::Add` only guarantees atomic not accuracy across threads. ``` ./db_bench -db=/dev/shm/testdb/ -statistics=true -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -target_file_size_base=655 -disable_auto_compactions=false -compression_type=none -bloom_bits=3 (-use_plain_table=1 -prefix_size=10) ``` ``` // BlockBasedTable rocksdb.sst.read.micros P50 : 2.009374 P95 : 4.968548 P99 : 8.110362 P100 : 43.000000 COUNT : 40456 SUM : 114805 rocksdb.file.read.flush.micros P50 : 1.871841 P95 : 3.872407 P99 : 5.540541 P100 : 43.000000 COUNT : 2250 SUM : 6116 rocksdb.file.read.compaction.micros P50 : 2.023109 P95 : 5.029149 P99 : 8.196910 P100 : 26.000000 COUNT : 38206 SUM : 108689 // PlainTable Does not apply ``` - **Db bench 2: performance** **Read** SETUP: db with 900 files ``` ./db_bench -db=/dev/shm/testdb/ -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=true -target_file_size_base=655 -compression_type=none ```run till convergence ``` ./db_bench -seed=1678564177044286 -use_existing_db=true -db=/dev/shm/testdb -benchmarks=readrandom[-X60] -statistics=true -num=1000000 -disable_auto_compactions=true -compression_type=none -bloom_bits=3 ``` Pre-change `readrandom [AVG 60 runs] : 21568 (± 248) ops/sec` Post-change (no regression, -0.3%) `readrandom [AVG 60 runs] : 21486 (± 236) ops/sec` **Compaction/Flush**run till convergence ``` ./db_bench -db=/dev/shm/testdb2/ -seed=1678564177044286 -benchmarks="fillseq[-X60]" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=false -target_file_size_base=655 -compression_type=none rocksdb.sst.read.micros COUNT : 33820 rocksdb.sst.read.flush.micros COUNT : 1800 rocksdb.sst.read.compaction.micros COUNT : 32020 ``` Pre-change `fillseq [AVG 46 runs] : 1391 (± 214) ops/sec; 0.7 (± 0.1) MB/sec` Post-change (no regression, ~-0.4%) `fillseq [AVG 46 runs] : 1385 (± 216) ops/sec; 0.7 (± 0.1) MB/sec` Reviewed By: ajkr Differential Revision: D44007011 Pulled By: hx235 fbshipit-source-id: a54c89e4846dfc9a135389edf3f3eedfea257132
2 years ago
// TODO: plumb Env::IOActivity
const ReadOptions read_options;
checksum_list->reset();
Status s;
std::unique_ptr<SequentialFileReader> file_reader;
{
std::unique_ptr<FSSequentialFile> file;
const std::shared_ptr<FileSystem>& fs = src_env->GetFileSystem();
s = fs->NewSequentialFile(abs_path,
fs->OptimizeForManifestRead(FileOptions()), &file,
nullptr /* dbg */);
if (!s.ok()) {
return s;
}
file_reader.reset(new SequentialFileReader(std::move(file), abs_path));
}
struct LogReporter : public log::Reader::Reporter {
Status* status_ptr;
virtual void Corruption(size_t /*bytes*/, const Status& st) override {
if (status_ptr->ok()) {
*status_ptr = st;
}
}
} reporter;
reporter.status_ptr = &s;
log::Reader reader(nullptr, std::move(file_reader), &reporter,
true /* checksum */, 0 /* log_number */);
Group rocksdb.sst.read.micros stat by IOActivity flush and compaction (#11288) Summary: **Context:** The existing stat rocksdb.sst.read.micros does not reflect each of compaction and flush cases but aggregate them, which is not so helpful for us to understand IO read behavior of each of them. **Summary** - Update `StopWatch` and `RandomAccessFileReader` to record `rocksdb.sst.read.micros` and `rocksdb.file.{flush/compaction}.read.micros` - Fixed the default histogram in `RandomAccessFileReader` - New field `ReadOptions/IOOptions::io_activity`; Pass `ReadOptions` through paths under db open, flush and compaction to where we can prepare `IOOptions` and pass it to `RandomAccessFileReader` - Use `thread_status_util` for assertion in `DbStressFSWrapper` for continuous testing on we are passing correct `io_activity` under db open, flush and compaction Pull Request resolved: https://github.com/facebook/rocksdb/pull/11288 Test Plan: - **Stress test** - **Db bench 1: rocksdb.sst.read.micros COUNT ≈ sum of rocksdb.file.read.flush.micros's and rocksdb.file.read.compaction.micros's.** (without blob) - May not be exactly the same due to `HistogramStat::Add` only guarantees atomic not accuracy across threads. ``` ./db_bench -db=/dev/shm/testdb/ -statistics=true -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -target_file_size_base=655 -disable_auto_compactions=false -compression_type=none -bloom_bits=3 (-use_plain_table=1 -prefix_size=10) ``` ``` // BlockBasedTable rocksdb.sst.read.micros P50 : 2.009374 P95 : 4.968548 P99 : 8.110362 P100 : 43.000000 COUNT : 40456 SUM : 114805 rocksdb.file.read.flush.micros P50 : 1.871841 P95 : 3.872407 P99 : 5.540541 P100 : 43.000000 COUNT : 2250 SUM : 6116 rocksdb.file.read.compaction.micros P50 : 2.023109 P95 : 5.029149 P99 : 8.196910 P100 : 26.000000 COUNT : 38206 SUM : 108689 // PlainTable Does not apply ``` - **Db bench 2: performance** **Read** SETUP: db with 900 files ``` ./db_bench -db=/dev/shm/testdb/ -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=true -target_file_size_base=655 -compression_type=none ```run till convergence ``` ./db_bench -seed=1678564177044286 -use_existing_db=true -db=/dev/shm/testdb -benchmarks=readrandom[-X60] -statistics=true -num=1000000 -disable_auto_compactions=true -compression_type=none -bloom_bits=3 ``` Pre-change `readrandom [AVG 60 runs] : 21568 (± 248) ops/sec` Post-change (no regression, -0.3%) `readrandom [AVG 60 runs] : 21486 (± 236) ops/sec` **Compaction/Flush**run till convergence ``` ./db_bench -db=/dev/shm/testdb2/ -seed=1678564177044286 -benchmarks="fillseq[-X60]" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=false -target_file_size_base=655 -compression_type=none rocksdb.sst.read.micros COUNT : 33820 rocksdb.sst.read.flush.micros COUNT : 1800 rocksdb.sst.read.compaction.micros COUNT : 32020 ``` Pre-change `fillseq [AVG 46 runs] : 1391 (± 214) ops/sec; 0.7 (± 0.1) MB/sec` Post-change (no regression, ~-0.4%) `fillseq [AVG 46 runs] : 1385 (± 216) ops/sec; 0.7 (± 0.1) MB/sec` Reviewed By: ajkr Differential Revision: D44007011 Pulled By: hx235 fbshipit-source-id: a54c89e4846dfc9a135389edf3f3eedfea257132
2 years ago
FileChecksumRetriever retriever(read_options, manifest_file_size,
*checksum_list);
retriever.Iterate(reader, &s);
assert(!retriever.status().ok() ||
manifest_file_size == std::numeric_limits<uint64_t>::max() ||
reader.LastRecordEnd() == manifest_file_size);
return retriever.status();
}
namespace {
static int RegisterFileChecksumGenFactories(ObjectLibrary& library,
const std::string& /*arg*/) {
library.AddFactory<FileChecksumGenFactory>(
FileChecksumGenCrc32cFactory::kClassName(),
[](const std::string& /*uri*/,
std::unique_ptr<FileChecksumGenFactory>* guard,
std::string* /* errmsg */) {
guard->reset(new FileChecksumGenCrc32cFactory());
return guard->get();
});
return 1;
}
} // namespace
Status FileChecksumGenFactory::CreateFromString(
const ConfigOptions& options, const std::string& value,
std::shared_ptr<FileChecksumGenFactory>* result) {
static std::once_flag once;
std::call_once(once, [&]() {
RegisterFileChecksumGenFactories(*(ObjectLibrary::Default().get()), "");
});
if (value == FileChecksumGenCrc32cFactory::kClassName()) {
*result = GetFileChecksumGenCrc32cFactory();
return Status::OK();
} else {
Status s = LoadSharedObject<FileChecksumGenFactory>(options, value, result);
return s;
}
}
} // namespace ROCKSDB_NAMESPACE