mirror of
https://github.com/facebook/rocksdb.git
synced 2024-12-03 14:52:53 +00:00
06e593376c
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
352 lines
11 KiB
C++
352 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).
|
|
|
|
#include "table/mock_table.h"
|
|
|
|
#include "db/dbformat.h"
|
|
#include "env/composite_env_wrapper.h"
|
|
#include "file/random_access_file_reader.h"
|
|
#include "port/port.h"
|
|
#include "rocksdb/table_properties.h"
|
|
#include "table/get_context.h"
|
|
#include "util/coding.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
namespace mock {
|
|
|
|
KVVector MakeMockFile(std::initializer_list<KVPair> l) { return KVVector(l); }
|
|
|
|
void SortKVVector(KVVector* kv_vector, const Comparator* ucmp) {
|
|
InternalKeyComparator icmp(ucmp);
|
|
std::sort(kv_vector->begin(), kv_vector->end(),
|
|
[icmp](KVPair a, KVPair b) -> bool {
|
|
return icmp.Compare(a.first, b.first) < 0;
|
|
});
|
|
}
|
|
|
|
class MockTableReader : public TableReader {
|
|
public:
|
|
explicit MockTableReader(const KVVector& table) : table_(table) {}
|
|
|
|
InternalIterator* NewIterator(const ReadOptions&,
|
|
const SliceTransform* prefix_extractor,
|
|
Arena* arena, bool skip_filters,
|
|
TableReaderCaller caller,
|
|
size_t compaction_readahead_size = 0,
|
|
bool allow_unprepared_value = false) override;
|
|
|
|
Status Get(const ReadOptions& readOptions, const Slice& key,
|
|
GetContext* get_context, const SliceTransform* prefix_extractor,
|
|
bool skip_filters = false) override;
|
|
|
|
uint64_t ApproximateOffsetOf(const ReadOptions& /*read_options*/,
|
|
const Slice& /*key*/,
|
|
TableReaderCaller /*caller*/) override {
|
|
return 0;
|
|
}
|
|
|
|
uint64_t ApproximateSize(const ReadOptions& /*read_options*/,
|
|
const Slice& /*start*/, const Slice& /*end*/,
|
|
TableReaderCaller /*caller*/) override {
|
|
return 0;
|
|
}
|
|
|
|
size_t ApproximateMemoryUsage() const override { return 0; }
|
|
|
|
void SetupForCompaction() override {}
|
|
|
|
std::shared_ptr<const TableProperties> GetTableProperties() const override;
|
|
|
|
~MockTableReader() = default;
|
|
|
|
private:
|
|
const KVVector& table_;
|
|
};
|
|
|
|
class MockTableIterator : public InternalIterator {
|
|
public:
|
|
explicit MockTableIterator(const KVVector& table) : table_(table) {
|
|
itr_ = table_.end();
|
|
}
|
|
|
|
bool Valid() const override { return itr_ != table_.end(); }
|
|
|
|
void SeekToFirst() override { itr_ = table_.begin(); }
|
|
|
|
void SeekToLast() override {
|
|
itr_ = table_.end();
|
|
--itr_;
|
|
}
|
|
|
|
void Seek(const Slice& target) override {
|
|
KVPair target_pair(target.ToString(), "");
|
|
InternalKeyComparator icmp(BytewiseComparator());
|
|
itr_ = std::lower_bound(table_.begin(), table_.end(), target_pair,
|
|
[icmp](KVPair a, KVPair b) -> bool {
|
|
return icmp.Compare(a.first, b.first) < 0;
|
|
});
|
|
}
|
|
|
|
void SeekForPrev(const Slice& target) override {
|
|
KVPair target_pair(target.ToString(), "");
|
|
InternalKeyComparator icmp(BytewiseComparator());
|
|
itr_ = std::upper_bound(table_.begin(), table_.end(), target_pair,
|
|
[icmp](KVPair a, KVPair b) -> bool {
|
|
return icmp.Compare(a.first, b.first) < 0;
|
|
});
|
|
Prev();
|
|
}
|
|
|
|
void Next() override { ++itr_; }
|
|
|
|
void Prev() override {
|
|
if (itr_ == table_.begin()) {
|
|
itr_ = table_.end();
|
|
} else {
|
|
--itr_;
|
|
}
|
|
}
|
|
|
|
Slice key() const override { return Slice(itr_->first); }
|
|
|
|
Slice value() const override { return Slice(itr_->second); }
|
|
|
|
Status status() const override { return Status::OK(); }
|
|
|
|
private:
|
|
const KVVector& table_;
|
|
KVVector::const_iterator itr_;
|
|
};
|
|
|
|
class MockTableBuilder : public TableBuilder {
|
|
public:
|
|
MockTableBuilder(uint32_t id, MockTableFileSystem* file_system,
|
|
MockTableFactory::MockCorruptionMode corrupt_mode =
|
|
MockTableFactory::kCorruptNone,
|
|
size_t key_value_size = 1)
|
|
: id_(id),
|
|
file_system_(file_system),
|
|
corrupt_mode_(corrupt_mode),
|
|
key_value_size_(key_value_size) {
|
|
table_ = MakeMockFile({});
|
|
}
|
|
|
|
// REQUIRES: Either Finish() or Abandon() has been called.
|
|
~MockTableBuilder() = default;
|
|
|
|
// Add key,value to the table being constructed.
|
|
// REQUIRES: key is after any previously added key according to comparator.
|
|
// REQUIRES: Finish(), Abandon() have not been called
|
|
void Add(const Slice& key, const Slice& value) override {
|
|
if (corrupt_mode_ == MockTableFactory::kCorruptValue) {
|
|
// Corrupt the value
|
|
table_.push_back({key.ToString(), value.ToString() + " "});
|
|
corrupt_mode_ = MockTableFactory::kCorruptNone;
|
|
} else if (corrupt_mode_ == MockTableFactory::kCorruptKey) {
|
|
table_.push_back({key.ToString() + " ", value.ToString()});
|
|
corrupt_mode_ = MockTableFactory::kCorruptNone;
|
|
} else if (corrupt_mode_ == MockTableFactory::kCorruptReorderKey) {
|
|
if (prev_key_.empty()) {
|
|
prev_key_ = key.ToString();
|
|
prev_value_ = value.ToString();
|
|
} else {
|
|
table_.push_back({key.ToString(), value.ToString()});
|
|
table_.push_back({prev_key_, prev_value_});
|
|
corrupt_mode_ = MockTableFactory::kCorruptNone;
|
|
}
|
|
} else {
|
|
table_.push_back({key.ToString(), value.ToString()});
|
|
}
|
|
}
|
|
|
|
// Return non-ok iff some error has been detected.
|
|
Status status() const override { return Status::OK(); }
|
|
|
|
// Return non-ok iff some error happens during IO.
|
|
IOStatus io_status() const override { return IOStatus::OK(); }
|
|
|
|
Status Finish() override {
|
|
MutexLock lock_guard(&file_system_->mutex);
|
|
file_system_->files.insert({id_, table_});
|
|
return Status::OK();
|
|
}
|
|
|
|
void Abandon() override {}
|
|
|
|
uint64_t NumEntries() const override { return table_.size(); }
|
|
|
|
uint64_t FileSize() const override { return table_.size() * key_value_size_; }
|
|
|
|
TableProperties GetTableProperties() const override {
|
|
return TableProperties();
|
|
}
|
|
|
|
// Get file checksum
|
|
std::string GetFileChecksum() const override { return kUnknownFileChecksum; }
|
|
// Get file checksum function name
|
|
const char* GetFileChecksumFuncName() const override {
|
|
return kUnknownFileChecksumFuncName;
|
|
}
|
|
|
|
private:
|
|
uint32_t id_;
|
|
std::string prev_key_;
|
|
std::string prev_value_;
|
|
MockTableFileSystem* file_system_;
|
|
int corrupt_mode_;
|
|
KVVector table_;
|
|
size_t key_value_size_;
|
|
};
|
|
|
|
InternalIterator* MockTableReader::NewIterator(
|
|
const ReadOptions&, const SliceTransform* /* prefix_extractor */,
|
|
Arena* /*arena*/, bool /*skip_filters*/, TableReaderCaller /*caller*/,
|
|
size_t /*compaction_readahead_size*/, bool /* allow_unprepared_value */) {
|
|
return new MockTableIterator(table_);
|
|
}
|
|
|
|
Status MockTableReader::Get(const ReadOptions&, const Slice& key,
|
|
GetContext* get_context,
|
|
const SliceTransform* /*prefix_extractor*/,
|
|
bool /*skip_filters*/) {
|
|
std::unique_ptr<MockTableIterator> iter(new MockTableIterator(table_));
|
|
for (iter->Seek(key); iter->Valid(); iter->Next()) {
|
|
ParsedInternalKey parsed_key;
|
|
Status pik_status =
|
|
ParseInternalKey(iter->key(), &parsed_key, true /* log_err_key */);
|
|
if (!pik_status.ok()) {
|
|
return pik_status;
|
|
}
|
|
|
|
bool dont_care __attribute__((__unused__));
|
|
if (!get_context->SaveValue(parsed_key, iter->value(), &dont_care)) {
|
|
break;
|
|
}
|
|
}
|
|
return Status::OK();
|
|
}
|
|
|
|
std::shared_ptr<const TableProperties> MockTableReader::GetTableProperties()
|
|
const {
|
|
TableProperties* tp = new TableProperties();
|
|
tp->num_entries = table_.size();
|
|
tp->num_range_deletions = 0;
|
|
tp->raw_key_size = 1;
|
|
tp->raw_value_size = 1;
|
|
|
|
return std::shared_ptr<const TableProperties>(tp);
|
|
}
|
|
|
|
MockTableFactory::MockTableFactory()
|
|
: next_id_(1), corrupt_mode_(MockTableFactory::kCorruptNone) {}
|
|
|
|
Status MockTableFactory::NewTableReader(
|
|
const ReadOptions& /*ro*/,
|
|
const TableReaderOptions& /*table_reader_options*/,
|
|
std::unique_ptr<RandomAccessFileReader>&& file, uint64_t /*file_size*/,
|
|
std::unique_ptr<TableReader>* table_reader,
|
|
bool /*prefetch_index_and_filter_in_cache*/) const {
|
|
uint32_t id;
|
|
Status s = GetIDFromFile(file.get(), &id);
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
|
|
MutexLock lock_guard(&file_system_.mutex);
|
|
|
|
auto it = file_system_.files.find(id);
|
|
if (it == file_system_.files.end()) {
|
|
return Status::IOError("Mock file not found");
|
|
}
|
|
|
|
table_reader->reset(new MockTableReader(it->second));
|
|
|
|
return Status::OK();
|
|
}
|
|
|
|
TableBuilder* MockTableFactory::NewTableBuilder(
|
|
const TableBuilderOptions& /*table_builder_options*/,
|
|
WritableFileWriter* file) const {
|
|
uint32_t id;
|
|
Status s = GetAndWriteNextID(file, &id);
|
|
assert(s.ok());
|
|
|
|
return new MockTableBuilder(id, &file_system_, corrupt_mode_,
|
|
key_value_size_);
|
|
}
|
|
|
|
Status MockTableFactory::CreateMockTable(Env* env, const std::string& fname,
|
|
KVVector file_contents) {
|
|
std::unique_ptr<WritableFileWriter> file_writer;
|
|
Status s = WritableFileWriter::Create(env->GetFileSystem(), fname,
|
|
FileOptions(), &file_writer, nullptr);
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
uint32_t id;
|
|
s = GetAndWriteNextID(file_writer.get(), &id);
|
|
if (s.ok()) {
|
|
file_system_.files.insert({id, std::move(file_contents)});
|
|
}
|
|
return s;
|
|
}
|
|
|
|
Status MockTableFactory::GetAndWriteNextID(WritableFileWriter* file,
|
|
uint32_t* next_id) const {
|
|
*next_id = next_id_.fetch_add(1);
|
|
char buf[4];
|
|
EncodeFixed32(buf, *next_id);
|
|
return file->Append(IOOptions(), Slice(buf, 4));
|
|
}
|
|
|
|
Status MockTableFactory::GetIDFromFile(RandomAccessFileReader* file,
|
|
uint32_t* id) const {
|
|
char buf[4];
|
|
Slice result;
|
|
Status s = file->Read(IOOptions(), 0, 4, &result, buf, nullptr);
|
|
assert(result.size() == 4);
|
|
*id = DecodeFixed32(buf);
|
|
return s;
|
|
}
|
|
|
|
void MockTableFactory::AssertSingleFile(const KVVector& file_contents) {
|
|
ASSERT_EQ(file_system_.files.size(), 1U);
|
|
ASSERT_EQ(file_contents, file_system_.files.begin()->second);
|
|
}
|
|
|
|
void MockTableFactory::AssertLatestFiles(
|
|
const std::vector<KVVector>& files_contents) {
|
|
ASSERT_GE(file_system_.files.size(), files_contents.size());
|
|
auto it = file_system_.files.rbegin();
|
|
for (auto expect = files_contents.rbegin(); expect != files_contents.rend();
|
|
expect++, it++) {
|
|
ASSERT_TRUE(it != file_system_.files.rend());
|
|
if (*expect != it->second) {
|
|
std::cout << "Wrong content! Content of file, expect:" << std::endl;
|
|
for (const auto& kv : *expect) {
|
|
ParsedInternalKey ikey;
|
|
std::string key, value;
|
|
std::tie(key, value) = kv;
|
|
ASSERT_OK(ParseInternalKey(Slice(key), &ikey, true /* log_err_key */));
|
|
std::cout << ikey.DebugString(true, false) << " -> " << value
|
|
<< std::endl;
|
|
}
|
|
std::cout << "actual:" << std::endl;
|
|
for (const auto& kv : it->second) {
|
|
ParsedInternalKey ikey;
|
|
std::string key, value;
|
|
std::tie(key, value) = kv;
|
|
ASSERT_OK(ParseInternalKey(Slice(key), &ikey, true /* log_err_key */));
|
|
std::cout << ikey.DebugString(true, false) << " -> " << value
|
|
<< std::endl;
|
|
}
|
|
FAIL();
|
|
}
|
|
}
|
|
}
|
|
|
|
} // namespace mock
|
|
} // namespace ROCKSDB_NAMESPACE
|