rocksdb/tools/db_bench_tool_test.cc
Hui Xiao 06e593376c Group SST write in flush, compaction and db open with new stats (#11910)
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
2023-12-29 15:29:23 -08:00

343 lines
11 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).
//
// 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/db_bench_tool.h"
#include "db/db_impl/db_impl.h"
#include "options/options_parser.h"
#include "rocksdb/utilities/options_util.h"
#include "test_util/testharness.h"
#include "test_util/testutil.h"
#include "util/random.h"
#ifdef GFLAGS
#include "util/gflags_compat.h"
namespace ROCKSDB_NAMESPACE {
namespace {
static const int kMaxArgCount = 100;
static const size_t kArgBufferSize = 100000;
} // namespace
class DBBenchTest : public testing::Test {
public:
DBBenchTest() : rnd_(0xFB) {
test_path_ = test::PerThreadDBPath("db_bench_test");
Env::Default()->CreateDir(test_path_);
db_path_ = test_path_ + "/db";
wal_path_ = test_path_ + "/wal";
}
~DBBenchTest() {
// DestroyDB(db_path_, Options());
}
void ResetArgs() {
argc_ = 0;
cursor_ = 0;
memset(arg_buffer_, 0, kArgBufferSize);
}
void AppendArgs(const std::vector<std::string>& args) {
for (const auto& arg : args) {
ASSERT_LE(cursor_ + arg.size() + 1, kArgBufferSize);
ASSERT_LE(argc_ + 1, kMaxArgCount);
snprintf(arg_buffer_ + cursor_, arg.size() + 1, "%s", arg.c_str());
argv_[argc_++] = arg_buffer_ + cursor_;
cursor_ += arg.size() + 1;
}
}
// Gets the default options for this test/db_bench.
// Note that db_bench may change some of the default option values and that
// the database might as well. The options changed by db_bench are
// specified here; the ones by the DB are set via SanitizeOptions
Options GetDefaultOptions(CompactionStyle style = kCompactionStyleLevel,
int levels = 7) const {
Options opt;
opt.create_if_missing = true;
opt.max_open_files = 256;
opt.max_background_compactions = 10;
opt.dump_malloc_stats = true; // db_bench uses a different default
opt.compaction_style = style;
opt.num_levels = levels;
opt.compression = kNoCompression;
opt.arena_block_size = 8388608;
return SanitizeOptions(db_path_, opt);
}
void RunDbBench(const std::string& options_file_name) {
AppendArgs({"./db_bench", "--benchmarks=fillseq", "--use_existing_db=0",
"--num=1000", "--compression_type=none",
std::string(std::string("--db=") + db_path_).c_str(),
std::string(std::string("--wal_dir=") + wal_path_).c_str(),
std::string(std::string("--options_file=") + options_file_name)
.c_str()});
ASSERT_EQ(0, db_bench_tool(argc(), argv()));
}
void VerifyOptions(const Options& opt) {
DBOptions loaded_db_opts;
ConfigOptions config_opts;
config_opts.ignore_unknown_options = false;
config_opts.input_strings_escaped = true;
config_opts.env = Env::Default();
std::vector<ColumnFamilyDescriptor> cf_descs;
ASSERT_OK(
LoadLatestOptions(config_opts, db_path_, &loaded_db_opts, &cf_descs));
ConfigOptions exact;
exact.input_strings_escaped = false;
exact.sanity_level = ConfigOptions::kSanityLevelExactMatch;
ASSERT_OK(RocksDBOptionsParser::VerifyDBOptions(exact, DBOptions(opt),
loaded_db_opts));
ASSERT_OK(RocksDBOptionsParser::VerifyCFOptions(
exact, ColumnFamilyOptions(opt), cf_descs[0].options));
// check with the default rocksdb options and expect failure
ASSERT_NOK(RocksDBOptionsParser::VerifyDBOptions(exact, DBOptions(),
loaded_db_opts));
ASSERT_NOK(RocksDBOptionsParser::VerifyCFOptions(
exact, ColumnFamilyOptions(), cf_descs[0].options));
}
char** argv() { return argv_; }
int argc() { return argc_; }
std::string db_path_;
std::string test_path_;
std::string wal_path_;
char arg_buffer_[kArgBufferSize];
char* argv_[kMaxArgCount];
int argc_ = 0;
int cursor_ = 0;
Random rnd_;
};
namespace {} // namespace
TEST_F(DBBenchTest, OptionsFile) {
const std::string kOptionsFileName = test_path_ + "/OPTIONS_test";
Options opt = GetDefaultOptions();
ASSERT_OK(PersistRocksDBOptions(WriteOptions(), DBOptions(opt), {"default"},
{ColumnFamilyOptions(opt)}, kOptionsFileName,
opt.env->GetFileSystem().get()));
// override the following options as db_bench will not take these
// options from the options file
opt.wal_dir = wal_path_;
RunDbBench(kOptionsFileName);
opt.delayed_write_rate = 16 * 1024 * 1024; // Set by SanitizeOptions
VerifyOptions(opt);
}
TEST_F(DBBenchTest, OptionsFileUniversal) {
const std::string kOptionsFileName = test_path_ + "/OPTIONS_test";
Options opt = GetDefaultOptions(kCompactionStyleUniversal, 1);
ASSERT_OK(PersistRocksDBOptions(WriteOptions(), DBOptions(opt), {"default"},
{ColumnFamilyOptions(opt)}, kOptionsFileName,
opt.env->GetFileSystem().get()));
// override the following options as db_bench will not take these
// options from the options file
opt.wal_dir = wal_path_;
RunDbBench(kOptionsFileName);
VerifyOptions(opt);
}
TEST_F(DBBenchTest, OptionsFileMultiLevelUniversal) {
const std::string kOptionsFileName = test_path_ + "/OPTIONS_test";
Options opt = GetDefaultOptions(kCompactionStyleUniversal, 12);
ASSERT_OK(PersistRocksDBOptions(WriteOptions(), DBOptions(opt), {"default"},
{ColumnFamilyOptions(opt)}, kOptionsFileName,
opt.env->GetFileSystem().get()));
// override the following options as db_bench will not take these
// options from the options file
opt.wal_dir = wal_path_;
RunDbBench(kOptionsFileName);
VerifyOptions(opt);
}
const std::string options_file_content = R"OPTIONS_FILE(
[Version]
rocksdb_version=4.3.1
options_file_version=1.1
[DBOptions]
wal_bytes_per_sync=1048576
delete_obsolete_files_period_micros=0
WAL_ttl_seconds=0
WAL_size_limit_MB=0
db_write_buffer_size=0
max_subcompactions=1
table_cache_numshardbits=4
max_open_files=-1
max_file_opening_threads=10
max_background_compactions=5
use_fsync=false
use_adaptive_mutex=false
max_total_wal_size=18446744073709551615
compaction_readahead_size=0
keep_log_file_num=10
skip_stats_update_on_db_open=false
max_manifest_file_size=18446744073709551615
db_log_dir=
writable_file_max_buffer_size=1048576
paranoid_checks=true
is_fd_close_on_exec=true
bytes_per_sync=1048576
enable_thread_tracking=true
recycle_log_file_num=0
create_missing_column_families=false
log_file_time_to_roll=0
max_background_flushes=1
create_if_missing=true
error_if_exists=false
delayed_write_rate=1048576
manifest_preallocation_size=4194304
allow_mmap_reads=false
allow_mmap_writes=false
use_direct_reads=false
use_direct_io_for_flush_and_compaction=false
stats_dump_period_sec=600
allow_fallocate=true
max_log_file_size=83886080
random_access_max_buffer_size=1048576
advise_random_on_open=true
dump_malloc_stats=true
[CFOptions "default"]
compaction_filter_factory=nullptr
table_factory=BlockBasedTable
prefix_extractor=nullptr
comparator=leveldb.BytewiseComparator
compression_per_level=
max_bytes_for_level_base=104857600
bloom_locality=0
target_file_size_base=10485760
memtable_huge_page_size=0
max_successive_merges=1000
max_sequential_skip_in_iterations=8
arena_block_size=52428800
target_file_size_multiplier=1
source_compaction_factor=1
min_write_buffer_number_to_merge=1
max_write_buffer_number=2
write_buffer_size=419430400
max_grandparent_overlap_factor=10
max_bytes_for_level_multiplier=10
memtable_factory=SkipListFactory
compression=kNoCompression
min_partial_merge_operands=2
level0_stop_writes_trigger=100
num_levels=1
level0_slowdown_writes_trigger=50
level0_file_num_compaction_trigger=10
expanded_compaction_factor=25
max_write_buffer_number_to_maintain=0
max_write_buffer_size_to_maintain=0
verify_checksums_in_compaction=true
merge_operator=nullptr
memtable_prefix_bloom_bits=0
memtable_whole_key_filtering=true
paranoid_file_checks=false
inplace_update_num_locks=10000
optimize_filters_for_hits=false
level_compaction_dynamic_level_bytes=false
inplace_update_support=false
compaction_style=kCompactionStyleUniversal
memtable_prefix_bloom_probes=6
filter_deletes=false
hard_pending_compaction_bytes_limit=0
disable_auto_compactions=false
compaction_measure_io_stats=false
enable_blob_files=true
min_blob_size=16
blob_file_size=10485760
blob_compression_type=kNoCompression
enable_blob_garbage_collection=true
blob_garbage_collection_age_cutoff=0.5
blob_garbage_collection_force_threshold=0.75
blob_compaction_readahead_size=262144
blob_file_starting_level=0
prepopulate_blob_cache=kDisable;
[TableOptions/BlockBasedTable "default"]
format_version=0
skip_table_builder_flush=false
cache_index_and_filter_blocks=false
flush_block_policy_factory=FlushBlockBySizePolicyFactory
index_type=kBinarySearch
whole_key_filtering=true
checksum=kCRC32c
no_block_cache=false
block_size=32768
block_size_deviation=10
block_restart_interval=16
filter_policy=rocksdb.BuiltinBloomFilter
)OPTIONS_FILE";
TEST_F(DBBenchTest, OptionsFileFromFile) {
const std::string kOptionsFileName = test_path_ + "/OPTIONS_flash";
std::unique_ptr<WritableFile> writable;
ASSERT_OK(Env::Default()->NewWritableFile(kOptionsFileName, &writable,
EnvOptions()));
ASSERT_OK(writable->Append(options_file_content));
ASSERT_OK(writable->Close());
DBOptions db_opt;
ConfigOptions config_opt;
config_opt.ignore_unknown_options = false;
config_opt.input_strings_escaped = true;
config_opt.env = Env::Default();
std::vector<ColumnFamilyDescriptor> cf_descs;
ASSERT_OK(
LoadOptionsFromFile(config_opt, kOptionsFileName, &db_opt, &cf_descs));
Options opt(db_opt, cf_descs[0].options);
opt.create_if_missing = true;
// override the following options as db_bench will not take these
// options from the options file
opt.wal_dir = wal_path_;
RunDbBench(kOptionsFileName);
VerifyOptions(SanitizeOptions(db_path_, opt));
}
} // namespace ROCKSDB_NAMESPACE
int main(int argc, char** argv) {
ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
::testing::InitGoogleTest(&argc, argv);
GFLAGS_NAMESPACE::ParseCommandLineFlags(&argc, &argv, true);
return RUN_ALL_TESTS();
}
#else
int main(int argc, char** argv) {
printf("Skip db_bench_tool_test as the required library GFLAG is missing.");
}
#endif // #ifdef GFLAGS