mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 16:30:56 +00:00
151242ce46
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
335 lines
12 KiB
C++
335 lines
12 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.
|
|
|
|
#pragma once
|
|
|
|
#include "db/version_builder.h"
|
|
#include "db/version_edit.h"
|
|
#include "db/version_set.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
struct FileMetaData;
|
|
|
|
class VersionEditHandlerBase {
|
|
public:
|
|
explicit VersionEditHandlerBase(const ReadOptions& read_options)
|
|
: read_options_(read_options),
|
|
max_manifest_read_size_(std::numeric_limits<uint64_t>::max()) {}
|
|
|
|
virtual ~VersionEditHandlerBase() {}
|
|
|
|
void Iterate(log::Reader& reader, Status* log_read_status);
|
|
|
|
const Status& status() const { return status_; }
|
|
|
|
AtomicGroupReadBuffer& GetReadBuffer() { return read_buffer_; }
|
|
|
|
protected:
|
|
explicit VersionEditHandlerBase(const ReadOptions& read_options,
|
|
uint64_t max_read_size)
|
|
: read_options_(read_options), max_manifest_read_size_(max_read_size) {}
|
|
virtual Status Initialize() { return Status::OK(); }
|
|
|
|
virtual Status ApplyVersionEdit(VersionEdit& edit,
|
|
ColumnFamilyData** cfd) = 0;
|
|
|
|
virtual void CheckIterationResult(const log::Reader& /*reader*/,
|
|
Status* /*s*/) {}
|
|
|
|
void ClearReadBuffer() { read_buffer_.Clear(); }
|
|
|
|
Status status_;
|
|
|
|
const ReadOptions& read_options_;
|
|
|
|
private:
|
|
AtomicGroupReadBuffer read_buffer_;
|
|
const uint64_t max_manifest_read_size_;
|
|
};
|
|
|
|
class ListColumnFamiliesHandler : public VersionEditHandlerBase {
|
|
public:
|
|
explicit ListColumnFamiliesHandler(const ReadOptions& read_options)
|
|
: VersionEditHandlerBase(read_options) {}
|
|
|
|
~ListColumnFamiliesHandler() override {}
|
|
|
|
const std::map<uint32_t, std::string> GetColumnFamilyNames() const {
|
|
return column_family_names_;
|
|
}
|
|
|
|
protected:
|
|
Status ApplyVersionEdit(VersionEdit& edit,
|
|
ColumnFamilyData** /*unused*/) override;
|
|
|
|
private:
|
|
// default column family is always implicitly there
|
|
std::map<uint32_t, std::string> column_family_names_{
|
|
{0, kDefaultColumnFamilyName}};
|
|
};
|
|
|
|
class FileChecksumRetriever : public VersionEditHandlerBase {
|
|
public:
|
|
FileChecksumRetriever(const ReadOptions& read_options, uint64_t max_read_size,
|
|
FileChecksumList& file_checksum_list)
|
|
: VersionEditHandlerBase(read_options, max_read_size),
|
|
file_checksum_list_(file_checksum_list) {}
|
|
|
|
~FileChecksumRetriever() override {}
|
|
|
|
protected:
|
|
Status ApplyVersionEdit(VersionEdit& edit,
|
|
ColumnFamilyData** /*unused*/) override;
|
|
|
|
private:
|
|
FileChecksumList& file_checksum_list_;
|
|
};
|
|
|
|
using VersionBuilderUPtr = std::unique_ptr<BaseReferencedVersionBuilder>;
|
|
|
|
// A class used for scanning MANIFEST file.
|
|
// VersionEditHandler reads a MANIFEST file, parses the version edits, and
|
|
// builds the version set's in-memory state, e.g. the version storage info for
|
|
// the versions of column families.
|
|
// To use this class and its subclasses,
|
|
// 1. Create an object of VersionEditHandler or its subclasses.
|
|
// VersionEditHandler handler(read_only, column_families, version_set,
|
|
// track_missing_files,
|
|
// no_error_if_files_missing);
|
|
// 2. Status s = handler.Iterate(reader, &db_id);
|
|
// 3. Check s and handle possible errors.
|
|
//
|
|
// Not thread-safe, external synchronization is necessary if an object of
|
|
// VersionEditHandler is shared by multiple threads.
|
|
class VersionEditHandler : public VersionEditHandlerBase {
|
|
public:
|
|
explicit VersionEditHandler(
|
|
bool read_only,
|
|
const std::vector<ColumnFamilyDescriptor>& column_families,
|
|
VersionSet* version_set, bool track_missing_files,
|
|
bool no_error_if_files_missing,
|
|
const std::shared_ptr<IOTracer>& io_tracer,
|
|
const ReadOptions& read_options,
|
|
EpochNumberRequirement epoch_number_requirement =
|
|
EpochNumberRequirement::kMustPresent)
|
|
: VersionEditHandler(
|
|
read_only, column_families, version_set, track_missing_files,
|
|
no_error_if_files_missing, io_tracer, read_options,
|
|
/*skip_load_table_files=*/false, epoch_number_requirement) {}
|
|
|
|
~VersionEditHandler() override {}
|
|
|
|
const VersionEditParams& GetVersionEditParams() const {
|
|
return version_edit_params_;
|
|
}
|
|
|
|
bool HasMissingFiles() const;
|
|
|
|
void GetDbId(std::string* db_id) const {
|
|
if (db_id && version_edit_params_.has_db_id_) {
|
|
*db_id = version_edit_params_.db_id_;
|
|
}
|
|
}
|
|
|
|
protected:
|
|
explicit VersionEditHandler(
|
|
bool read_only, std::vector<ColumnFamilyDescriptor> column_families,
|
|
VersionSet* version_set, bool track_missing_files,
|
|
bool no_error_if_files_missing,
|
|
const std::shared_ptr<IOTracer>& io_tracer,
|
|
const ReadOptions& read_options, bool skip_load_table_files,
|
|
EpochNumberRequirement epoch_number_requirement =
|
|
EpochNumberRequirement::kMustPresent);
|
|
|
|
Status ApplyVersionEdit(VersionEdit& edit, ColumnFamilyData** cfd) override;
|
|
|
|
virtual Status OnColumnFamilyAdd(VersionEdit& edit, ColumnFamilyData** cfd);
|
|
|
|
Status OnColumnFamilyDrop(VersionEdit& edit, ColumnFamilyData** cfd);
|
|
|
|
Status OnNonCfOperation(VersionEdit& edit, ColumnFamilyData** cfd);
|
|
|
|
Status OnWalAddition(VersionEdit& edit);
|
|
|
|
Status OnWalDeletion(VersionEdit& edit);
|
|
|
|
Status Initialize() override;
|
|
|
|
void CheckColumnFamilyId(const VersionEdit& edit, bool* cf_in_not_found,
|
|
bool* cf_in_builders) const;
|
|
|
|
void CheckIterationResult(const log::Reader& reader, Status* s) override;
|
|
|
|
ColumnFamilyData* CreateCfAndInit(const ColumnFamilyOptions& cf_options,
|
|
const VersionEdit& edit);
|
|
|
|
virtual ColumnFamilyData* DestroyCfAndCleanup(const VersionEdit& edit);
|
|
|
|
virtual Status MaybeCreateVersion(const VersionEdit& edit,
|
|
ColumnFamilyData* cfd,
|
|
bool force_create_version);
|
|
|
|
virtual Status LoadTables(ColumnFamilyData* cfd,
|
|
bool prefetch_index_and_filter_in_cache,
|
|
bool is_initial_load);
|
|
|
|
virtual bool MustOpenAllColumnFamilies() const { return !read_only_; }
|
|
|
|
const bool read_only_;
|
|
std::vector<ColumnFamilyDescriptor> column_families_;
|
|
VersionSet* version_set_;
|
|
std::unordered_map<uint32_t, VersionBuilderUPtr> builders_;
|
|
std::unordered_map<std::string, ColumnFamilyOptions> name_to_options_;
|
|
// Keeps track of column families in manifest that were not found in
|
|
// column families parameters. if those column families are not dropped
|
|
// by subsequent manifest records, Recover() will return failure status.
|
|
std::unordered_map<uint32_t, std::string> column_families_not_found_;
|
|
VersionEditParams version_edit_params_;
|
|
const bool track_missing_files_;
|
|
std::unordered_map<uint32_t, std::unordered_set<uint64_t>>
|
|
cf_to_missing_files_;
|
|
std::unordered_map<uint32_t, uint64_t> cf_to_missing_blob_files_high_;
|
|
bool no_error_if_files_missing_;
|
|
std::shared_ptr<IOTracer> io_tracer_;
|
|
bool skip_load_table_files_;
|
|
bool initialized_;
|
|
std::unique_ptr<std::unordered_map<uint32_t, std::string>> cf_to_cmp_names_;
|
|
EpochNumberRequirement epoch_number_requirement_;
|
|
|
|
private:
|
|
Status ExtractInfoFromVersionEdit(ColumnFamilyData* cfd,
|
|
const VersionEdit& edit);
|
|
};
|
|
|
|
// A class similar to its base class, i.e. VersionEditHandler.
|
|
// VersionEditHandlerPointInTime restores the versions to the most recent point
|
|
// in time such that at this point, the version does not have missing files.
|
|
//
|
|
// Not thread-safe, external synchronization is necessary if an object of
|
|
// VersionEditHandlerPointInTime is shared by multiple threads.
|
|
class VersionEditHandlerPointInTime : public VersionEditHandler {
|
|
public:
|
|
VersionEditHandlerPointInTime(
|
|
bool read_only, std::vector<ColumnFamilyDescriptor> column_families,
|
|
VersionSet* version_set, const std::shared_ptr<IOTracer>& io_tracer,
|
|
const ReadOptions& read_options,
|
|
EpochNumberRequirement epoch_number_requirement =
|
|
EpochNumberRequirement::kMustPresent);
|
|
~VersionEditHandlerPointInTime() override;
|
|
|
|
protected:
|
|
void CheckIterationResult(const log::Reader& reader, Status* s) override;
|
|
ColumnFamilyData* DestroyCfAndCleanup(const VersionEdit& edit) override;
|
|
Status MaybeCreateVersion(const VersionEdit& edit, ColumnFamilyData* cfd,
|
|
bool force_create_version) override;
|
|
virtual Status VerifyFile(ColumnFamilyData* cfd, const std::string& fpath,
|
|
int level, const FileMetaData& fmeta);
|
|
virtual Status VerifyBlobFile(ColumnFamilyData* cfd, uint64_t blob_file_num,
|
|
const BlobFileAddition& blob_addition);
|
|
|
|
Status LoadTables(ColumnFamilyData* cfd,
|
|
bool prefetch_index_and_filter_in_cache,
|
|
bool is_initial_load) override;
|
|
|
|
std::unordered_map<uint32_t, Version*> versions_;
|
|
};
|
|
|
|
class ManifestTailer : public VersionEditHandlerPointInTime {
|
|
public:
|
|
explicit ManifestTailer(std::vector<ColumnFamilyDescriptor> column_families,
|
|
VersionSet* version_set,
|
|
const std::shared_ptr<IOTracer>& io_tracer,
|
|
const ReadOptions& read_options,
|
|
EpochNumberRequirement epoch_number_requirement =
|
|
EpochNumberRequirement::kMustPresent)
|
|
: VersionEditHandlerPointInTime(/*read_only=*/false, column_families,
|
|
version_set, io_tracer, read_options,
|
|
epoch_number_requirement),
|
|
mode_(Mode::kRecovery) {}
|
|
|
|
void PrepareToReadNewManifest() {
|
|
initialized_ = false;
|
|
ClearReadBuffer();
|
|
}
|
|
|
|
std::unordered_set<ColumnFamilyData*>& GetUpdatedColumnFamilies() {
|
|
return cfds_changed_;
|
|
}
|
|
|
|
protected:
|
|
Status Initialize() override;
|
|
|
|
bool MustOpenAllColumnFamilies() const override { return false; }
|
|
|
|
Status ApplyVersionEdit(VersionEdit& edit, ColumnFamilyData** cfd) override;
|
|
|
|
Status OnColumnFamilyAdd(VersionEdit& edit, ColumnFamilyData** cfd) override;
|
|
|
|
void CheckIterationResult(const log::Reader& reader, Status* s) override;
|
|
|
|
Status VerifyFile(ColumnFamilyData* cfd, const std::string& fpath, int level,
|
|
const FileMetaData& fmeta) override;
|
|
|
|
enum Mode : uint8_t {
|
|
kRecovery = 0,
|
|
kCatchUp = 1,
|
|
};
|
|
|
|
Mode mode_;
|
|
std::unordered_set<ColumnFamilyData*> cfds_changed_;
|
|
};
|
|
|
|
class DumpManifestHandler : public VersionEditHandler {
|
|
public:
|
|
DumpManifestHandler(std::vector<ColumnFamilyDescriptor> column_families,
|
|
VersionSet* version_set,
|
|
const std::shared_ptr<IOTracer>& io_tracer,
|
|
const ReadOptions& read_options, bool verbose, bool hex,
|
|
bool json)
|
|
: VersionEditHandler(
|
|
/*read_only=*/true, column_families, version_set,
|
|
/*track_missing_files=*/false,
|
|
/*no_error_if_files_missing=*/false, io_tracer, read_options,
|
|
/*skip_load_table_files=*/true),
|
|
verbose_(verbose),
|
|
hex_(hex),
|
|
json_(json),
|
|
count_(0) {
|
|
cf_to_cmp_names_.reset(new std::unordered_map<uint32_t, std::string>());
|
|
}
|
|
|
|
~DumpManifestHandler() override {}
|
|
|
|
Status ApplyVersionEdit(VersionEdit& edit, ColumnFamilyData** cfd) override {
|
|
// Write out each individual edit
|
|
if (verbose_ && !json_) {
|
|
// Print out DebugStrings. Can include non-terminating null characters.
|
|
fwrite(edit.DebugString(hex_).data(), sizeof(char),
|
|
edit.DebugString(hex_).size(), stdout);
|
|
} else if (json_) {
|
|
// Print out DebugStrings. Can include non-terminating null characters.
|
|
fwrite(edit.DebugString(hex_).data(), sizeof(char),
|
|
edit.DebugString(hex_).size(), stdout);
|
|
}
|
|
++count_;
|
|
return VersionEditHandler::ApplyVersionEdit(edit, cfd);
|
|
}
|
|
|
|
void CheckIterationResult(const log::Reader& reader, Status* s) override;
|
|
|
|
private:
|
|
const bool verbose_;
|
|
const bool hex_;
|
|
const bool json_;
|
|
int count_;
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|