diff options
author | Hui Xiao <huixiao@fb.com> | 2023-04-21 09:07:18 -0700 |
---|---|---|
committer | Facebook GitHub Bot <facebook-github-bot@users.noreply.github.com> | 2023-04-21 09:07:18 -0700 |
commit | 151242ce46872dd080f99e0bd42e40db38686e25 (patch) | |
tree | 4947664e1110268444504bb664d82c7a92fd94b6 /file | |
parent | 0a774a102f0be845007e3927dcda228716a771d2 (diff) |
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
Diffstat (limited to 'file')
-rw-r--r-- | file/file_util.cc | 6 | ||||
-rw-r--r-- | file/file_util.h | 2 | ||||
-rw-r--r-- | file/random_access_file_reader.cc | 26 | ||||
-rw-r--r-- | file/random_access_file_reader.h | 5 |
4 files changed, 28 insertions, 11 deletions
diff --git a/file/file_util.cc b/file/file_util.cc index 43608fcdc..46faac67c 100644 --- a/file/file_util.cc +++ b/file/file_util.cc @@ -185,9 +185,9 @@ IOStatus GenerateOneFileChecksum( if (!io_s.ok()) { return io_s; } - reader.reset(new RandomAccessFileReader(std::move(r_file), file_path, - nullptr /*Env*/, io_tracer, nullptr, - 0, nullptr, rate_limiter)); + reader.reset(new RandomAccessFileReader( + std::move(r_file), file_path, nullptr /*Env*/, io_tracer, nullptr, + Histograms::HISTOGRAM_ENUM_MAX, nullptr, rate_limiter)); } // Found that 256 KB readahead size provides the best performance, based on diff --git a/file/file_util.h b/file/file_util.h index d46a7ba0e..e279cfba0 100644 --- a/file/file_util.h +++ b/file/file_util.h @@ -80,6 +80,8 @@ inline IOStatus PrepareIOFromReadOptions(const ReadOptions& ro, } opts.rate_limiter_priority = ro.rate_limiter_priority; + opts.io_activity = ro.io_activity; + return IOStatus::OK(); } diff --git a/file/random_access_file_reader.cc b/file/random_access_file_reader.cc index 226970641..2f8b51667 100644 --- a/file/random_access_file_reader.cc +++ b/file/random_access_file_reader.cc @@ -22,7 +22,11 @@ #include "util/rate_limiter.h" namespace ROCKSDB_NAMESPACE { - +const std::array<Histograms, std::size_t(Env::IOActivity::kUnknown)> + kReadHistograms{{ + FILE_READ_FLUSH_MICROS, + FILE_READ_COMPACTION_MICROS, + }}; inline void RecordIOStats(Statistics* stats, Temperature file_temperature, bool is_last_level, size_t size) { IOSTATS_ADD(bytes_read, size); @@ -94,6 +98,9 @@ IOStatus RandomAccessFileReader::Read( uint64_t elapsed = 0; { StopWatch sw(clock_, stats_, hist_type_, + (opts.io_activity != Env::IOActivity::kUnknown) + ? kReadHistograms[(std::size_t)(opts.io_activity)] + : Histograms::HISTOGRAM_ENUM_MAX, (stats_ != nullptr) ? &elapsed : nullptr, true /*overwrite*/, true /*delay_enabled*/); auto prev_perf_level = GetPerfLevel(); @@ -288,6 +295,9 @@ IOStatus RandomAccessFileReader::MultiRead( uint64_t elapsed = 0; { StopWatch sw(clock_, stats_, hist_type_, + (opts.io_activity != Env::IOActivity::kUnknown) + ? kReadHistograms[(std::size_t)(opts.io_activity)] + : Histograms::HISTOGRAM_ENUM_MAX, (stats_ != nullptr) ? &elapsed : nullptr, true /*overwrite*/, true /*delay_enabled*/); auto prev_perf_level = GetPerfLevel(); @@ -425,7 +435,7 @@ IOStatus RandomAccessFileReader::MultiRead( } IOStatus RandomAccessFileReader::PrepareIOOptions(const ReadOptions& ro, - IOOptions& opts) { + IOOptions& opts) const { if (clock_ != nullptr) { return PrepareIOFromReadOptions(ro, clock_, opts); } else { @@ -476,13 +486,17 @@ IOStatus RandomAccessFileReader::ReadAsync( assert(read_async_info->buf_.CurrentSize() == 0); - StopWatch sw(clock_, nullptr /*stats*/, 0 /*hist_type*/, &elapsed, - true /*overwrite*/, true /*delay_enabled*/); + StopWatch sw(clock_, nullptr /*stats*/, + Histograms::HISTOGRAM_ENUM_MAX /*hist_type*/, + Histograms::HISTOGRAM_ENUM_MAX, &elapsed, true /*overwrite*/, + true /*delay_enabled*/); s = file_->ReadAsync(aligned_req, opts, read_async_callback, read_async_info, io_handle, del_fn, nullptr /*dbg*/); } else { - StopWatch sw(clock_, nullptr /*stats*/, 0 /*hist_type*/, &elapsed, - true /*overwrite*/, true /*delay_enabled*/); + StopWatch sw(clock_, nullptr /*stats*/, + Histograms::HISTOGRAM_ENUM_MAX /*hist_type*/, + Histograms::HISTOGRAM_ENUM_MAX, &elapsed, true /*overwrite*/, + true /*delay_enabled*/); s = file_->ReadAsync(req, opts, read_async_callback, read_async_info, io_handle, del_fn, nullptr /*dbg*/); } diff --git a/file/random_access_file_reader.h b/file/random_access_file_reader.h index 50baa0318..ab4d1e797 100644 --- a/file/random_access_file_reader.h +++ b/file/random_access_file_reader.h @@ -122,7 +122,8 @@ class RandomAccessFileReader { std::unique_ptr<FSRandomAccessFile>&& raf, const std::string& _file_name, SystemClock* clock = nullptr, const std::shared_ptr<IOTracer>& io_tracer = nullptr, - Statistics* stats = nullptr, uint32_t hist_type = 0, + Statistics* stats = nullptr, + uint32_t hist_type = Histograms::HISTOGRAM_ENUM_MAX, HistogramImpl* file_read_hist = nullptr, RateLimiter* rate_limiter = nullptr, const std::vector<std::shared_ptr<EventListener>>& listeners = {}, @@ -197,7 +198,7 @@ class RandomAccessFileReader { bool use_direct_io() const { return file_->use_direct_io(); } - IOStatus PrepareIOOptions(const ReadOptions& ro, IOOptions& opts); + IOStatus PrepareIOOptions(const ReadOptions& ro, IOOptions& opts) const; IOStatus ReadAsync(FSReadRequest& req, const IOOptions& opts, std::function<void(const FSReadRequest&, void*)> cb, |