rocksdb/db/db_test_util.h

1428 lines
47 KiB
C
Raw Normal View History

// 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 <fcntl.h>
#include <algorithm>
#include <cinttypes>
#include <map>
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
#include <memory>
#include <set>
#include <string>
#include <thread>
#include <unordered_set>
#include <utility>
#include <vector>
#include "db/db_impl/db_impl.h"
#include "file/filename.h"
Fix/improve temperature handling for file ingestion (#12402) Summary: Partly following up on leftovers from https://github.com/facebook/rocksdb/issues/12388 In terms of public API: * Make it clear that IngestExternalFileArg::file_temperature is just a hint for opening the existing file, though it was previously used for both copy-from temp hint and copy-to temp, which was bizarre. * Specify how IngestExternalFile assigns temperature to file ingested into DB. (See details in comments.) This approach is not perfect in terms of matching how the DB assigns temperatures, but was the simplest way to get close. The key complication for matching DB temperature assignments is that ingestion files are copied (to a destination temp) before their target level is determined (in general). * Add a temperature option to SstFileWriter::Open so that files intended for ingestion can be initially written to a chosen temperature. * Note that "fail_if_not_bottommost_level" is obsolete/confusing use of "bottommost" In terms of the implementation, there was a similar bit of oddness with the internal CopyFile API, which only took one temperature, ambiguously applicable to the source, destination, or both. This is also fixed. Eventual suggested follow-up: * Before copying files for ingestion, determine a tentative level assignment to use for destination temperature, and keep that even if final level assignment happens to be different at commit time (rare). * More temperature handling for CreateColumnFamilyWithImport and Checkpoints. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12402 Test Plan: Deeply revamped ExternalSSTFileBasicTest.IngestWithTemperature to test the new changes. Previously this test was insufficient because it was only looking at temperatures according to the DB manifest. Incorporating FileTemperatureTestFS allows us to also test the temperatures in the storage layer. Used macros instead of functions for better tracing to critical source location on test failures. Some enhancements to FileTemperatureTestFS in the process of developing the revamped test. Reviewed By: jowlyzhang Differential Revision: D54442794 Pulled By: pdillinger fbshipit-source-id: 41d9d0afdc073e6a983304c10bbc07c70cc7e995
2024-03-06 00:56:08 +00:00
#include "options/options_helper.h"
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
#include "rocksdb/advanced_options.h"
#include "rocksdb/cache.h"
#include "rocksdb/compaction_filter.h"
#include "rocksdb/convenience.h"
#include "rocksdb/db.h"
#include "rocksdb/env.h"
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
#include "rocksdb/file_system.h"
#include "rocksdb/filter_policy.h"
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
#include "rocksdb/io_status.h"
#include "rocksdb/options.h"
#include "rocksdb/slice.h"
#include "rocksdb/sst_file_writer.h"
#include "rocksdb/statistics.h"
#include "rocksdb/table.h"
#include "rocksdb/utilities/checkpoint.h"
#include "table/mock_table.h"
#include "test_util/sync_point.h"
#include "test_util/testharness.h"
#include "util/cast_util.h"
#include "util/compression.h"
#include "util/mutexlock.h"
#include "util/string_util.h"
#include "utilities/merge_operators.h"
// In case defined by Windows headers
#undef small
namespace ROCKSDB_NAMESPACE {
class MockEnv;
namespace anon {
class AtomicCounter {
public:
explicit AtomicCounter(Env* env = NULL)
: env_(env), cond_count_(&mu_), count_(0) {}
void Increment() {
MutexLock l(&mu_);
count_++;
cond_count_.SignalAll();
}
int Read() {
MutexLock l(&mu_);
return count_;
}
bool WaitFor(int count) {
MutexLock l(&mu_);
uint64_t start = env_->NowMicros();
while (count_ < count) {
uint64_t now = env_->NowMicros();
cond_count_.TimedWait(now + /*1s*/ 1 * 1000 * 1000);
if (env_->NowMicros() - start > /*10s*/ 10 * 1000 * 1000) {
return false;
}
if (count_ < count) {
GTEST_LOG_(WARNING) << "WaitFor is taking more time than usual";
}
}
return true;
}
void Reset() {
MutexLock l(&mu_);
count_ = 0;
cond_count_.SignalAll();
}
private:
Env* env_;
port::Mutex mu_;
port::CondVar cond_count_;
int count_;
};
struct OptionsOverride {
std::shared_ptr<const FilterPolicy> filter_policy = nullptr;
// These will be used only if filter_policy is set
bool partition_filters = false;
Eliminate unnecessary (slow) block cache Ref()ing in MultiGet (#9899) Summary: When MultiGet() determines that multiple query keys can be served by examining the same data block in block cache (one Lookup()), each PinnableSlice referring to data in that data block needs to hold on to the block in cache so that they can be released at arbitrary times by the API user. Historically this is accomplished with extra calls to Ref() on the Handle from Lookup(), with each PinnableSlice cleanup calling Release() on the Handle, but this creates extra contention on the block cache for the extra Ref()s and Release()es, especially because they hit the same cache shard repeatedly. In the case of merge operands (possibly more cases?), the problem was compounded by doing an extra Ref()+eventual Release() for each merge operand for a key reusing a block (which could be the same key!), rather than one Ref() per key. (Note: the non-shared case with `biter` was already one per key.) This change optimizes MultiGet not to rely on these extra, contentious Ref()+Release() calls by instead, in the shared block case, wrapping the cache Release() cleanup in a refcounted object referenced by the PinnableSlices, such that after the last wrapped reference is released, the cache entry is Release()ed. Relaxed atomic refcounts should be much faster than mutex-guarded Ref() and Release(), and much less prone to a performance cliff when MultiGet() does a lot of block sharing. Note that I did not use std::shared_ptr, because that would require an extra indirection object (shared_ptr itself new/delete) in order to associate a ref increment/decrement with a Cleanable cleanup entry. (If I assumed it was the size of two pointers, I could do some hackery to make it work without the extra indirection, but that's too fragile.) Some details: * Fixed (removed) extra block cache tracing entries in cases of cache entry reuse in MultiGet, but it's likely that in some other cases traces are missing (XXX comment inserted) * Moved existing implementations for cleanable.h from iterator.cc to new cleanable.cc * Improved API comments on Cleanable * Added a public SharedCleanablePtr class to cleanable.h in case others could benefit from the same pattern (potentially many Cleanables and/or smart pointers referencing a shared Cleanable) * Add a typedef for MultiGetContext::Mask * Some variable renaming for clarity Pull Request resolved: https://github.com/facebook/rocksdb/pull/9899 Test Plan: Added unit tests for SharedCleanablePtr. Greatly enhanced ability of existing tests to detect cache use-after-free. * Release PinnableSlices from MultiGet as they are read rather than in bulk (in db_test_util wrapper). * In ASAN build, default to using a trivially small LRUCache for block_cache so that entries are immediately erased when unreferenced. (Updated two tests that depend on caching.) New ASAN testsuite running time seems OK to me. If I introduce a bug into my implementation where we skip the shared cleanups on block reuse, ASAN detects the bug in `db_basic_test *MultiGet*`. If I remove either of the above testing enhancements, the bug is not detected. Consider for follow-up work: manipulate or randomize ordering of PinnableSlice use and release from MultiGet db_test_util wrapper. But in typical cases, natural ordering gives pretty good functional coverage. Performance test: In the extreme (but possible) case of MultiGetting the same or adjacent keys in a batch, throughput can improve by an order of magnitude. `./db_bench -benchmarks=multireadrandom -db=/dev/shm/testdb -readonly -num=5 -duration=10 -threads=20 -multiread_batched -batch_size=200` Before ops/sec, num=5: 1,384,394 Before ops/sec, num=500: 6,423,720 After ops/sec, num=500: 10,658,794 After ops/sec, num=5: 16,027,257 Also note that previously, with high parallelism, having query keys concentrated in a single block was worse than spreading them out a bit. Now concentrated in a single block is faster than spread out, which is hopefully consistent with natural expectation. Random query performance: with num=1000000, over 999 x 10s runs running before & after simultaneously (each -threads=12): Before: multireadrandom [AVG 999 runs] : 1088699 (± 7344) ops/sec; 120.4 (± 0.8 ) MB/sec After: multireadrandom [AVG 999 runs] : 1090402 (± 7230) ops/sec; 120.6 (± 0.8 ) MB/sec Possibly better, possibly in the noise. Reviewed By: anand1976 Differential Revision: D35907003 Pulled By: pdillinger fbshipit-source-id: bbd244d703649a8ca12d476f2d03853ed9d1a17e
2022-04-27 04:59:24 +00:00
// Force using a default block cache. (Setting to false allows ASAN build
// use a trivially small block cache for better UAF error detection.)
bool full_block_cache = false;
uint64_t metadata_block_size = 1024;
// Used as a bit mask of individual enums in which to skip an XF test point
int skip_policy = 0;
Make option `level_compaction_dynamic_level_bytes` true by default (#11525) Summary: after https://github.com/facebook/rocksdb/issues/11321 and https://github.com/facebook/rocksdb/issues/11340 (both included in RocksDB v8.2), migration from `level_compaction_dynamic_level_bytes=false` to `level_compaction_dynamic_level_bytes=true` is automatic by RocksDB and requires no manual compaction from user. Making the option true by default as it has several advantages: 1. better space amplification guarantee (a more stable LSM shape). 2. compaction is more adaptive to write traffic. 3. automatic draining of unneeded levels. Wiki is updated with more detail: https://github.com/facebook/rocksdb/wiki/Leveled-Compaction#option-level_compaction_dynamic_level_bytes-and-levels-target-size. The PR mostly contains fixes for unit tests as they assumed `level_compaction_dynamic_level_bytes=false`. Most notable change is commit https://github.com/facebook/rocksdb/pull/11525/commits/f742be330ca1a7abc33107b00df99818f71c387b and https://github.com/facebook/rocksdb/pull/11525/commits/b1928e42b34c0d4f1cc5d5239149870c6dc7a737 which override the default option in DBTestBase to still set `level_compaction_dynamic_level_bytes=false` by default. This helps to reduce the change needed for unit tests. I think this default option override in unit tests is okay since the behavior of `level_compaction_dynamic_level_bytes=true` is tested by explicitly setting this option. Also, `level_compaction_dynamic_level_bytes=false` may be more desired in unit tests as it makes it easier to create a desired LSM shape. Comment for option `level_compaction_dynamic_level_bytes` is updated to reflect this change and change made in https://github.com/facebook/rocksdb/issues/10057. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11525 Test Plan: `make -j32 J=32 check` several times to try to catch flaky tests due to this option change. Reviewed By: ajkr Differential Revision: D46654256 Pulled By: cbi42 fbshipit-source-id: 6b5827dae124f6f1fdc8cca2ac6f6fcd878830e1
2023-06-16 04:12:39 +00:00
// The default value for this option is changed from false to true.
// Keeping the default to false for unit tests as old unit tests assume
// this behavior. Tests for level_compaction_dynamic_level_bytes
// will set the option to true explicitly.
bool level_compaction_dynamic_level_bytes = false;
};
} // namespace anon
enum SkipPolicy { kSkipNone = 0, kSkipNoSnapshot = 1, kSkipNoPrefix = 2 };
// Special Env used to delay background operations
class SpecialEnv : public EnvWrapper {
public:
Fix+clean up handling of mock sleeps (#7101) Summary: We have a number of tests hanging on MacOS and windows due to mishandling of code for mock sleeps. In addition, the code was in terrible shape because the same variable (addon_time_) would sometimes refer to microseconds and sometimes to seconds. One test even assumed it was nanoseconds but was written to pass anyway. This has been cleaned up so that DB tests generally use a SpecialEnv function to mock sleep, for either some number of microseconds or seconds depending on the function called. But to call one of these, the test must first call SetMockSleep (precondition enforced with assertion), which also turns sleeps in RocksDB into mock sleeps. To also removes accounting for actual clock time, call SetTimeElapseOnlySleepOnReopen, which implies SetMockSleep (on DB re-open). This latter setting only works by applying on DB re-open, otherwise havoc can ensue if Env goes back in time with DB open. More specifics: Removed some unused test classes, and updated comments on the general problem. Fixed DBSSTTest.GetTotalSstFilesSize using a sync point callback instead of mock time. For this we have the only modification to production code, inserting a sync point callback in flush_job.cc, which is not a change to production behavior. Removed unnecessary resetting of mock times to 0 in many tests. RocksDB deals in relative time. Any behaviors relying on absolute date/time are likely a bug. (The above test DBSSTTest.GetTotalSstFilesSize was the only one clearly injecting a specific absolute time for actual testing convenience.) Just in case I misunderstood some test, I put this note in each replacement: // NOTE: Presumed unnecessary and removed: resetting mock time in env Strengthened some tests like MergeTestTime, MergeCompactionTimeTest, and FilterCompactionTimeTest in db_test.cc stats_history_test and blob_db_test are each their own beast, rather deeply dependent on MockTimeEnv. Each gets its own variant of a work-around for TimedWait in a mock time environment. (Reduces redundancy and inconsistency in stats_history_test.) Intended follow-up: Remove TimedWait from the public API of InstrumentedCondVar, and only make that accessible through Env by passing in an InstrumentedCondVar and a deadline. Then the Env implementations mocking time can fix this problem without using sync points. (Test infrastructure using sync points interferes with individual tests' control over sync points.) With that change, we can simplify/consolidate the scattered work-arounds. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7101 Test Plan: make check on Linux and MacOS Reviewed By: zhichao-cao Differential Revision: D23032815 Pulled By: pdillinger fbshipit-source-id: 7f33967ada8b83011fb54e8279365c008bd6610b
2020-08-11 19:39:49 +00:00
explicit SpecialEnv(Env* base, bool time_elapse_only_sleep = false);
static const char* kClassName() { return "SpecialEnv"; }
const char* Name() const override { return kClassName(); }
Status NewWritableFile(const std::string& f, std::unique_ptr<WritableFile>* r,
const EnvOptions& soptions) override {
class SSTableFile : public WritableFile {
private:
SpecialEnv* env_;
std::unique_ptr<WritableFile> base_;
public:
SSTableFile(SpecialEnv* env, std::unique_ptr<WritableFile>&& base)
: env_(env), base_(std::move(base)) {}
Status Append(const Slice& data) override {
if (env_->table_write_callback_) {
(*env_->table_write_callback_)();
}
if (env_->drop_writes_.load(std::memory_order_acquire)) {
// Drop writes on the floor
return Status::OK();
} else if (env_->no_space_.load(std::memory_order_acquire)) {
return Status::NoSpace("No space left on device");
} else {
env_->bytes_written_ += data.size();
return base_->Append(data);
}
}
Status Append(
const Slice& data,
const DataVerificationInfo& /* verification_info */) override {
return Append(data);
}
Status PositionedAppend(const Slice& data, uint64_t offset) override {
if (env_->table_write_callback_) {
(*env_->table_write_callback_)();
}
if (env_->drop_writes_.load(std::memory_order_acquire)) {
// Drop writes on the floor
return Status::OK();
} else if (env_->no_space_.load(std::memory_order_acquire)) {
return Status::NoSpace("No space left on device");
} else {
env_->bytes_written_ += data.size();
return base_->PositionedAppend(data, offset);
}
}
Status PositionedAppend(
const Slice& data, uint64_t offset,
const DataVerificationInfo& /* verification_info */) override {
return PositionedAppend(data, offset);
}
Status Truncate(uint64_t size) override { return base_->Truncate(size); }
Status RangeSync(uint64_t offset, uint64_t nbytes) override {
Status s = base_->RangeSync(offset, nbytes);
#if !(defined NDEBUG) || !defined(OS_WIN)
TEST_SYNC_POINT_CALLBACK("SpecialEnv::SStableFile::RangeSync", &s);
#endif // !(defined NDEBUG) || !defined(OS_WIN)
return s;
}
Status Close() override {
// SyncPoint is not supported in Released Windows Mode.
#if !(defined NDEBUG) || !defined(OS_WIN)
// Check preallocation size
// preallocation size is never passed to base file.
size_t preallocation_size = preallocation_block_size();
TEST_SYNC_POINT_CALLBACK("DBTestWritableFile.GetPreallocationStatus",
&preallocation_size);
#endif // !(defined NDEBUG) || !defined(OS_WIN)
Status s = base_->Close();
#if !(defined NDEBUG) || !defined(OS_WIN)
TEST_SYNC_POINT_CALLBACK("SpecialEnv::SStableFile::Close", &s);
#endif // !(defined NDEBUG) || !defined(OS_WIN)
return s;
}
Status Flush() override { return base_->Flush(); }
Status Sync() override {
++env_->sync_counter_;
while (env_->delay_sstable_sync_.load(std::memory_order_acquire)) {
env_->SleepForMicroseconds(100000);
}
Status s;
if (!env_->skip_fsync_) {
s = base_->Sync();
}
#if !(defined NDEBUG) || !defined(OS_WIN)
TEST_SYNC_POINT_CALLBACK("SpecialEnv::SStableFile::Sync", &s);
#endif // !(defined NDEBUG) || !defined(OS_WIN)
return s;
}
void SetIOPriority(Env::IOPriority pri) override {
base_->SetIOPriority(pri);
}
Env::IOPriority GetIOPriority() override {
return base_->GetIOPriority();
}
bool use_direct_io() const override { return base_->use_direct_io(); }
Status Allocate(uint64_t offset, uint64_t len) override {
return base_->Allocate(offset, len);
}
size_t GetUniqueId(char* id, size_t max_size) const override {
return base_->GetUniqueId(id, max_size);
}
uint64_t GetFileSize() final { return base_->GetFileSize(); }
};
class ManifestFile : public WritableFile {
public:
ManifestFile(SpecialEnv* env, std::unique_ptr<WritableFile>&& b)
: env_(env), base_(std::move(b)) {}
Status Append(const Slice& data) override {
if (env_->manifest_write_error_.load(std::memory_order_acquire)) {
return Status::IOError("simulated writer error");
} else {
return base_->Append(data);
}
}
Status Append(
const Slice& data,
const DataVerificationInfo& /*verification_info*/) override {
return Append(data);
}
Refactor to support file_reader_writer on Windows. Summary. A change https://reviews.facebook.net/differential/diff/224721/ Has attempted to move common functionality out of platform dependent code to a new facility called file_reader_writer. This includes: - perf counters - Buffering - RateLimiting However, the change did not attempt to refactor Windows code. To mitigate, we introduce new quering interfaces such as UseOSBuffer(), GetRequiredBufferAlignment() and ReaderWriterForward() for pure forwarding where required. Introduce WritableFile got a new method Truncate(). This is to communicate to the file as to how much data it has on close. - When space is pre-allocated on Linux it is filled with zeros implicitly, no such thing exist on Windows so we must truncate file on close. - When operating in unbuffered mode the last page is filled with zeros but we still want to truncate. Previously, Close() would take care of it but now buffer management is shifted to the wrappers and the file has no idea about the file true size. This means that Close() on the wrapper level must always include Truncate() as well as wrapper __dtor should call Close() and against double Close(). Move buffered/unbuffered write logic to the wrapper. Utilize Aligned buffer class. Adjust tests and implement Truncate() where necessary. Come up with reasonable defaults for new virtual interfaces. Forward calls for RandomAccessReadAhead class to avoid double buffering and locking (double locking in unbuffered mode on WIndows).
2015-09-11 16:57:02 +00:00
Status Truncate(uint64_t size) override { return base_->Truncate(size); }
Status Close() override { return base_->Close(); }
Status Flush() override { return base_->Flush(); }
Status Sync() override {
++env_->sync_counter_;
if (env_->manifest_sync_error_.load(std::memory_order_acquire)) {
return Status::IOError("simulated sync error");
} else {
if (env_->skip_fsync_) {
return Status::OK();
} else {
return base_->Sync();
}
}
}
uint64_t GetFileSize() override { return base_->GetFileSize(); }
Status Allocate(uint64_t offset, uint64_t len) override {
return base_->Allocate(offset, len);
}
private:
SpecialEnv* env_;
std::unique_ptr<WritableFile> base_;
};
class SpecialWalFile : public WritableFile {
public:
SpecialWalFile(SpecialEnv* env, std::unique_ptr<WritableFile>&& b)
: env_(env), base_(std::move(b)) {
env_->num_open_wal_file_.fetch_add(1);
}
virtual ~SpecialWalFile() { env_->num_open_wal_file_.fetch_add(-1); }
Status Append(const Slice& data) override {
#if !(defined NDEBUG) || !defined(OS_WIN)
TEST_SYNC_POINT("SpecialEnv::SpecialWalFile::Append:1");
#endif
Status s;
if (env_->log_write_error_.load(std::memory_order_acquire)) {
s = Status::IOError("simulated writer error");
} else {
int slowdown =
env_->log_write_slowdown_.load(std::memory_order_acquire);
if (slowdown > 0) {
env_->SleepForMicroseconds(slowdown);
}
s = base_->Append(data);
}
#if !(defined NDEBUG) || !defined(OS_WIN)
TEST_SYNC_POINT("SpecialEnv::SpecialWalFile::Append:2");
#endif
return s;
}
Status Append(
const Slice& data,
const DataVerificationInfo& /* verification_info */) override {
return Append(data);
}
Refactor to support file_reader_writer on Windows. Summary. A change https://reviews.facebook.net/differential/diff/224721/ Has attempted to move common functionality out of platform dependent code to a new facility called file_reader_writer. This includes: - perf counters - Buffering - RateLimiting However, the change did not attempt to refactor Windows code. To mitigate, we introduce new quering interfaces such as UseOSBuffer(), GetRequiredBufferAlignment() and ReaderWriterForward() for pure forwarding where required. Introduce WritableFile got a new method Truncate(). This is to communicate to the file as to how much data it has on close. - When space is pre-allocated on Linux it is filled with zeros implicitly, no such thing exist on Windows so we must truncate file on close. - When operating in unbuffered mode the last page is filled with zeros but we still want to truncate. Previously, Close() would take care of it but now buffer management is shifted to the wrappers and the file has no idea about the file true size. This means that Close() on the wrapper level must always include Truncate() as well as wrapper __dtor should call Close() and against double Close(). Move buffered/unbuffered write logic to the wrapper. Utilize Aligned buffer class. Adjust tests and implement Truncate() where necessary. Come up with reasonable defaults for new virtual interfaces. Forward calls for RandomAccessReadAhead class to avoid double buffering and locking (double locking in unbuffered mode on WIndows).
2015-09-11 16:57:02 +00:00
Status Truncate(uint64_t size) override { return base_->Truncate(size); }
void PrepareWrite(size_t offset, size_t len) override {
base_->PrepareWrite(offset, len);
}
void SetPreallocationBlockSize(size_t size) override {
base_->SetPreallocationBlockSize(size);
}
Status Close() override {
// SyncPoint is not supported in Released Windows Mode.
#if !(defined NDEBUG) || !defined(OS_WIN)
// Check preallocation size
size_t block_size, last_allocated_block;
base_->GetPreallocationStatus(&block_size, &last_allocated_block);
TEST_SYNC_POINT_CALLBACK("DBTestWalFile.GetPreallocationStatus",
&block_size);
#endif // !(defined NDEBUG) || !defined(OS_WIN)
return base_->Close();
}
Status Flush() override { return base_->Flush(); }
Status Sync() override {
++env_->sync_counter_;
if (env_->corrupt_in_sync_) {
EXPECT_OK(Append(std::string(33000, ' ')));
return Status::IOError("Ingested Sync Failure");
}
if (env_->skip_fsync_) {
return Status::OK();
} else {
return base_->Sync();
}
}
bool IsSyncThreadSafe() const override {
return env_->is_wal_sync_thread_safe_.load();
}
Status Allocate(uint64_t offset, uint64_t len) override {
return base_->Allocate(offset, len);
}
uint64_t GetFileSize() final { return base_->GetFileSize(); }
private:
SpecialEnv* env_;
std::unique_ptr<WritableFile> base_;
};
class OtherFile : public WritableFile {
public:
OtherFile(SpecialEnv* env, std::unique_ptr<WritableFile>&& b)
: env_(env), base_(std::move(b)) {}
Status Append(const Slice& data) override { return base_->Append(data); }
Status Append(
const Slice& data,
const DataVerificationInfo& /*verification_info*/) override {
return Append(data);
}
Status Truncate(uint64_t size) override { return base_->Truncate(size); }
Status Close() override { return base_->Close(); }
Status Flush() override { return base_->Flush(); }
Status Sync() override {
if (env_->skip_fsync_) {
return Status::OK();
} else {
return base_->Sync();
}
}
uint64_t GetFileSize() override { return base_->GetFileSize(); }
Status Allocate(uint64_t offset, uint64_t len) override {
return base_->Allocate(offset, len);
}
private:
SpecialEnv* env_;
std::unique_ptr<WritableFile> base_;
};
Handle rename() failure in non-local FS (#8192) Summary: In a distributed environment, a file `rename()` operation can succeed on server (remote) side, but the client can somehow return non-ok status to RocksDB. Possible reasons include network partition, connection issue, etc. This happens in `rocksdb::SetCurrentFile()`, which can be called in `LogAndApply() -> ProcessManifestWrites()` if RocksDB tries to switch to a new MANIFEST. We currently always delete the new MANIFEST if an error occurs. This is problematic in distributed world. If the server-side successfully updates the CURRENT file via renaming, then a subsequent `DB::Open()` will try to look for the new MANIFEST and fail. As a fix, we can track the execution result of IO operations on the new MANIFEST. - If IO operations on the new MANIFEST fail, then we know the CURRENT must point to the original MANIFEST. Therefore, it is safe to remove the new MANIFEST. - If IO operations on the new MANIFEST all succeed, but somehow we end up in the clean up code block, then we do not know whether CURRENT points to the new or old MANIFEST. (For local POSIX-compliant FS, it should still point to old MANIFEST, but it does not matter if we keep the new MANIFEST.) Therefore, we keep the new MANIFEST. - Any future `LogAndApply()` will switch to a new MANIFEST and update CURRENT. - If process reopens the db immediately after the failure, then the CURRENT file can point to either the new MANIFEST or the old one, both of which exist. Therefore, recovery can succeed and ignore the other. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8192 Test Plan: make check Reviewed By: zhichao-cao Differential Revision: D27804648 Pulled By: riversand963 fbshipit-source-id: 9c16f2a5ce41bc6aadf085e48449b19ede8423e4
2021-04-20 01:10:23 +00:00
if (no_file_overwrite_.load(std::memory_order_acquire) &&
target()->FileExists(f).ok()) {
return Status::NotSupported("SpecialEnv::no_file_overwrite_ is true.");
}
if (non_writeable_rate_.load(std::memory_order_acquire) > 0) {
uint32_t random_number;
{
MutexLock l(&rnd_mutex_);
random_number = rnd_.Uniform(100);
}
if (random_number < non_writeable_rate_.load()) {
return Status::IOError("simulated random write error");
}
}
new_writable_count_++;
if (non_writable_count_.load() > 0) {
non_writable_count_--;
return Status::IOError("simulated write error");
}
EnvOptions optimized = soptions;
if (strstr(f.c_str(), "MANIFEST") != nullptr ||
strstr(f.c_str(), "log") != nullptr) {
optimized.use_mmap_writes = false;
optimized.use_direct_writes = false;
}
Status s = target()->NewWritableFile(f, r, optimized);
if (s.ok()) {
if (strstr(f.c_str(), ".sst") != nullptr) {
r->reset(new SSTableFile(this, std::move(*r)));
} else if (strstr(f.c_str(), "MANIFEST") != nullptr) {
r->reset(new ManifestFile(this, std::move(*r)));
} else if (strstr(f.c_str(), "log") != nullptr) {
r->reset(new SpecialWalFile(this, std::move(*r)));
} else {
r->reset(new OtherFile(this, std::move(*r)));
}
}
return s;
}
Status NewRandomAccessFile(const std::string& f,
std::unique_ptr<RandomAccessFile>* r,
const EnvOptions& soptions) override {
class CountingFile : public RandomAccessFile {
public:
CountingFile(std::unique_ptr<RandomAccessFile>&& target,
anon::AtomicCounter* counter,
std::atomic<size_t>* bytes_read)
: target_(std::move(target)),
counter_(counter),
bytes_read_(bytes_read) {}
Status Read(uint64_t offset, size_t n, Slice* result,
char* scratch) const override {
counter_->Increment();
Status s = target_->Read(offset, n, result, scratch);
*bytes_read_ += result->size();
return s;
}
Status Prefetch(uint64_t offset, size_t n) override {
Status s = target_->Prefetch(offset, n);
*bytes_read_ += n;
return s;
}
private:
std::unique_ptr<RandomAccessFile> target_;
anon::AtomicCounter* counter_;
std::atomic<size_t>* bytes_read_;
};
class RandomFailureFile : public RandomAccessFile {
public:
RandomFailureFile(std::unique_ptr<RandomAccessFile>&& target,
std::atomic<uint64_t>* failure_cnt, uint32_t fail_odd)
: target_(std::move(target)),
fail_cnt_(failure_cnt),
fail_odd_(fail_odd) {}
Status Read(uint64_t offset, size_t n, Slice* result,
char* scratch) const override {
if (Random::GetTLSInstance()->OneIn(fail_odd_)) {
fail_cnt_->fetch_add(1);
return Status::IOError("random error");
}
return target_->Read(offset, n, result, scratch);
}
Status Prefetch(uint64_t offset, size_t n) override {
return target_->Prefetch(offset, n);
}
private:
std::unique_ptr<RandomAccessFile> target_;
std::atomic<uint64_t>* fail_cnt_;
uint32_t fail_odd_;
};
Status s = target()->NewRandomAccessFile(f, r, soptions);
random_file_open_counter_++;
if (s.ok()) {
if (count_random_reads_) {
r->reset(new CountingFile(std::move(*r), &random_read_counter_,
&random_read_bytes_counter_));
} else if (rand_reads_fail_odd_ > 0) {
r->reset(new RandomFailureFile(std::move(*r), &num_reads_fails_,
rand_reads_fail_odd_));
}
}
if (s.ok() && soptions.compaction_readahead_size > 0) {
compaction_readahead_size_ = soptions.compaction_readahead_size;
}
return s;
}
Status NewSequentialFile(const std::string& f,
std::unique_ptr<SequentialFile>* r,
const EnvOptions& soptions) override {
class CountingFile : public SequentialFile {
public:
CountingFile(std::unique_ptr<SequentialFile>&& target,
anon::AtomicCounter* counter)
: target_(std::move(target)), counter_(counter) {}
Status Read(size_t n, Slice* result, char* scratch) override {
counter_->Increment();
return target_->Read(n, result, scratch);
}
Status Skip(uint64_t n) override { return target_->Skip(n); }
private:
std::unique_ptr<SequentialFile> target_;
anon::AtomicCounter* counter_;
};
Status s = target()->NewSequentialFile(f, r, soptions);
if (s.ok() && count_sequential_reads_) {
r->reset(new CountingFile(std::move(*r), &sequential_read_counter_));
}
return s;
}
void SleepForMicroseconds(int micros) override {
sleep_counter_.Increment();
if (no_slowdown_ || time_elapse_only_sleep_) {
Fix+clean up handling of mock sleeps (#7101) Summary: We have a number of tests hanging on MacOS and windows due to mishandling of code for mock sleeps. In addition, the code was in terrible shape because the same variable (addon_time_) would sometimes refer to microseconds and sometimes to seconds. One test even assumed it was nanoseconds but was written to pass anyway. This has been cleaned up so that DB tests generally use a SpecialEnv function to mock sleep, for either some number of microseconds or seconds depending on the function called. But to call one of these, the test must first call SetMockSleep (precondition enforced with assertion), which also turns sleeps in RocksDB into mock sleeps. To also removes accounting for actual clock time, call SetTimeElapseOnlySleepOnReopen, which implies SetMockSleep (on DB re-open). This latter setting only works by applying on DB re-open, otherwise havoc can ensue if Env goes back in time with DB open. More specifics: Removed some unused test classes, and updated comments on the general problem. Fixed DBSSTTest.GetTotalSstFilesSize using a sync point callback instead of mock time. For this we have the only modification to production code, inserting a sync point callback in flush_job.cc, which is not a change to production behavior. Removed unnecessary resetting of mock times to 0 in many tests. RocksDB deals in relative time. Any behaviors relying on absolute date/time are likely a bug. (The above test DBSSTTest.GetTotalSstFilesSize was the only one clearly injecting a specific absolute time for actual testing convenience.) Just in case I misunderstood some test, I put this note in each replacement: // NOTE: Presumed unnecessary and removed: resetting mock time in env Strengthened some tests like MergeTestTime, MergeCompactionTimeTest, and FilterCompactionTimeTest in db_test.cc stats_history_test and blob_db_test are each their own beast, rather deeply dependent on MockTimeEnv. Each gets its own variant of a work-around for TimedWait in a mock time environment. (Reduces redundancy and inconsistency in stats_history_test.) Intended follow-up: Remove TimedWait from the public API of InstrumentedCondVar, and only make that accessible through Env by passing in an InstrumentedCondVar and a deadline. Then the Env implementations mocking time can fix this problem without using sync points. (Test infrastructure using sync points interferes with individual tests' control over sync points.) With that change, we can simplify/consolidate the scattered work-arounds. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7101 Test Plan: make check on Linux and MacOS Reviewed By: zhichao-cao Differential Revision: D23032815 Pulled By: pdillinger fbshipit-source-id: 7f33967ada8b83011fb54e8279365c008bd6610b
2020-08-11 19:39:49 +00:00
addon_microseconds_.fetch_add(micros);
}
if (!no_slowdown_) {
target()->SleepForMicroseconds(micros);
}
}
Fix+clean up handling of mock sleeps (#7101) Summary: We have a number of tests hanging on MacOS and windows due to mishandling of code for mock sleeps. In addition, the code was in terrible shape because the same variable (addon_time_) would sometimes refer to microseconds and sometimes to seconds. One test even assumed it was nanoseconds but was written to pass anyway. This has been cleaned up so that DB tests generally use a SpecialEnv function to mock sleep, for either some number of microseconds or seconds depending on the function called. But to call one of these, the test must first call SetMockSleep (precondition enforced with assertion), which also turns sleeps in RocksDB into mock sleeps. To also removes accounting for actual clock time, call SetTimeElapseOnlySleepOnReopen, which implies SetMockSleep (on DB re-open). This latter setting only works by applying on DB re-open, otherwise havoc can ensue if Env goes back in time with DB open. More specifics: Removed some unused test classes, and updated comments on the general problem. Fixed DBSSTTest.GetTotalSstFilesSize using a sync point callback instead of mock time. For this we have the only modification to production code, inserting a sync point callback in flush_job.cc, which is not a change to production behavior. Removed unnecessary resetting of mock times to 0 in many tests. RocksDB deals in relative time. Any behaviors relying on absolute date/time are likely a bug. (The above test DBSSTTest.GetTotalSstFilesSize was the only one clearly injecting a specific absolute time for actual testing convenience.) Just in case I misunderstood some test, I put this note in each replacement: // NOTE: Presumed unnecessary and removed: resetting mock time in env Strengthened some tests like MergeTestTime, MergeCompactionTimeTest, and FilterCompactionTimeTest in db_test.cc stats_history_test and blob_db_test are each their own beast, rather deeply dependent on MockTimeEnv. Each gets its own variant of a work-around for TimedWait in a mock time environment. (Reduces redundancy and inconsistency in stats_history_test.) Intended follow-up: Remove TimedWait from the public API of InstrumentedCondVar, and only make that accessible through Env by passing in an InstrumentedCondVar and a deadline. Then the Env implementations mocking time can fix this problem without using sync points. (Test infrastructure using sync points interferes with individual tests' control over sync points.) With that change, we can simplify/consolidate the scattered work-arounds. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7101 Test Plan: make check on Linux and MacOS Reviewed By: zhichao-cao Differential Revision: D23032815 Pulled By: pdillinger fbshipit-source-id: 7f33967ada8b83011fb54e8279365c008bd6610b
2020-08-11 19:39:49 +00:00
void MockSleepForMicroseconds(int64_t micros) {
sleep_counter_.Increment();
assert(no_slowdown_);
addon_microseconds_.fetch_add(micros);
}
void MockSleepForSeconds(int64_t seconds) {
sleep_counter_.Increment();
assert(no_slowdown_);
addon_microseconds_.fetch_add(seconds * 1000000);
}
Status GetCurrentTime(int64_t* unix_time) override {
Status s;
if (time_elapse_only_sleep_) {
*unix_time = maybe_starting_time_;
} else {
s = target()->GetCurrentTime(unix_time);
}
if (s.ok()) {
Fix+clean up handling of mock sleeps (#7101) Summary: We have a number of tests hanging on MacOS and windows due to mishandling of code for mock sleeps. In addition, the code was in terrible shape because the same variable (addon_time_) would sometimes refer to microseconds and sometimes to seconds. One test even assumed it was nanoseconds but was written to pass anyway. This has been cleaned up so that DB tests generally use a SpecialEnv function to mock sleep, for either some number of microseconds or seconds depending on the function called. But to call one of these, the test must first call SetMockSleep (precondition enforced with assertion), which also turns sleeps in RocksDB into mock sleeps. To also removes accounting for actual clock time, call SetTimeElapseOnlySleepOnReopen, which implies SetMockSleep (on DB re-open). This latter setting only works by applying on DB re-open, otherwise havoc can ensue if Env goes back in time with DB open. More specifics: Removed some unused test classes, and updated comments on the general problem. Fixed DBSSTTest.GetTotalSstFilesSize using a sync point callback instead of mock time. For this we have the only modification to production code, inserting a sync point callback in flush_job.cc, which is not a change to production behavior. Removed unnecessary resetting of mock times to 0 in many tests. RocksDB deals in relative time. Any behaviors relying on absolute date/time are likely a bug. (The above test DBSSTTest.GetTotalSstFilesSize was the only one clearly injecting a specific absolute time for actual testing convenience.) Just in case I misunderstood some test, I put this note in each replacement: // NOTE: Presumed unnecessary and removed: resetting mock time in env Strengthened some tests like MergeTestTime, MergeCompactionTimeTest, and FilterCompactionTimeTest in db_test.cc stats_history_test and blob_db_test are each their own beast, rather deeply dependent on MockTimeEnv. Each gets its own variant of a work-around for TimedWait in a mock time environment. (Reduces redundancy and inconsistency in stats_history_test.) Intended follow-up: Remove TimedWait from the public API of InstrumentedCondVar, and only make that accessible through Env by passing in an InstrumentedCondVar and a deadline. Then the Env implementations mocking time can fix this problem without using sync points. (Test infrastructure using sync points interferes with individual tests' control over sync points.) With that change, we can simplify/consolidate the scattered work-arounds. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7101 Test Plan: make check on Linux and MacOS Reviewed By: zhichao-cao Differential Revision: D23032815 Pulled By: pdillinger fbshipit-source-id: 7f33967ada8b83011fb54e8279365c008bd6610b
2020-08-11 19:39:49 +00:00
// mock microseconds elapsed to seconds of time
*unix_time += addon_microseconds_.load() / 1000000;
}
return s;
}
uint64_t NowCPUNanos() override {
now_cpu_count_.fetch_add(1);
return target()->NowCPUNanos();
}
uint64_t NowNanos() override {
return (time_elapse_only_sleep_ ? 0 : target()->NowNanos()) +
Fix+clean up handling of mock sleeps (#7101) Summary: We have a number of tests hanging on MacOS and windows due to mishandling of code for mock sleeps. In addition, the code was in terrible shape because the same variable (addon_time_) would sometimes refer to microseconds and sometimes to seconds. One test even assumed it was nanoseconds but was written to pass anyway. This has been cleaned up so that DB tests generally use a SpecialEnv function to mock sleep, for either some number of microseconds or seconds depending on the function called. But to call one of these, the test must first call SetMockSleep (precondition enforced with assertion), which also turns sleeps in RocksDB into mock sleeps. To also removes accounting for actual clock time, call SetTimeElapseOnlySleepOnReopen, which implies SetMockSleep (on DB re-open). This latter setting only works by applying on DB re-open, otherwise havoc can ensue if Env goes back in time with DB open. More specifics: Removed some unused test classes, and updated comments on the general problem. Fixed DBSSTTest.GetTotalSstFilesSize using a sync point callback instead of mock time. For this we have the only modification to production code, inserting a sync point callback in flush_job.cc, which is not a change to production behavior. Removed unnecessary resetting of mock times to 0 in many tests. RocksDB deals in relative time. Any behaviors relying on absolute date/time are likely a bug. (The above test DBSSTTest.GetTotalSstFilesSize was the only one clearly injecting a specific absolute time for actual testing convenience.) Just in case I misunderstood some test, I put this note in each replacement: // NOTE: Presumed unnecessary and removed: resetting mock time in env Strengthened some tests like MergeTestTime, MergeCompactionTimeTest, and FilterCompactionTimeTest in db_test.cc stats_history_test and blob_db_test are each their own beast, rather deeply dependent on MockTimeEnv. Each gets its own variant of a work-around for TimedWait in a mock time environment. (Reduces redundancy and inconsistency in stats_history_test.) Intended follow-up: Remove TimedWait from the public API of InstrumentedCondVar, and only make that accessible through Env by passing in an InstrumentedCondVar and a deadline. Then the Env implementations mocking time can fix this problem without using sync points. (Test infrastructure using sync points interferes with individual tests' control over sync points.) With that change, we can simplify/consolidate the scattered work-arounds. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7101 Test Plan: make check on Linux and MacOS Reviewed By: zhichao-cao Differential Revision: D23032815 Pulled By: pdillinger fbshipit-source-id: 7f33967ada8b83011fb54e8279365c008bd6610b
2020-08-11 19:39:49 +00:00
addon_microseconds_.load() * 1000;
}
uint64_t NowMicros() override {
return (time_elapse_only_sleep_ ? 0 : target()->NowMicros()) +
Fix+clean up handling of mock sleeps (#7101) Summary: We have a number of tests hanging on MacOS and windows due to mishandling of code for mock sleeps. In addition, the code was in terrible shape because the same variable (addon_time_) would sometimes refer to microseconds and sometimes to seconds. One test even assumed it was nanoseconds but was written to pass anyway. This has been cleaned up so that DB tests generally use a SpecialEnv function to mock sleep, for either some number of microseconds or seconds depending on the function called. But to call one of these, the test must first call SetMockSleep (precondition enforced with assertion), which also turns sleeps in RocksDB into mock sleeps. To also removes accounting for actual clock time, call SetTimeElapseOnlySleepOnReopen, which implies SetMockSleep (on DB re-open). This latter setting only works by applying on DB re-open, otherwise havoc can ensue if Env goes back in time with DB open. More specifics: Removed some unused test classes, and updated comments on the general problem. Fixed DBSSTTest.GetTotalSstFilesSize using a sync point callback instead of mock time. For this we have the only modification to production code, inserting a sync point callback in flush_job.cc, which is not a change to production behavior. Removed unnecessary resetting of mock times to 0 in many tests. RocksDB deals in relative time. Any behaviors relying on absolute date/time are likely a bug. (The above test DBSSTTest.GetTotalSstFilesSize was the only one clearly injecting a specific absolute time for actual testing convenience.) Just in case I misunderstood some test, I put this note in each replacement: // NOTE: Presumed unnecessary and removed: resetting mock time in env Strengthened some tests like MergeTestTime, MergeCompactionTimeTest, and FilterCompactionTimeTest in db_test.cc stats_history_test and blob_db_test are each their own beast, rather deeply dependent on MockTimeEnv. Each gets its own variant of a work-around for TimedWait in a mock time environment. (Reduces redundancy and inconsistency in stats_history_test.) Intended follow-up: Remove TimedWait from the public API of InstrumentedCondVar, and only make that accessible through Env by passing in an InstrumentedCondVar and a deadline. Then the Env implementations mocking time can fix this problem without using sync points. (Test infrastructure using sync points interferes with individual tests' control over sync points.) With that change, we can simplify/consolidate the scattered work-arounds. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7101 Test Plan: make check on Linux and MacOS Reviewed By: zhichao-cao Differential Revision: D23032815 Pulled By: pdillinger fbshipit-source-id: 7f33967ada8b83011fb54e8279365c008bd6610b
2020-08-11 19:39:49 +00:00
addon_microseconds_.load();
}
Status DeleteFile(const std::string& fname) override {
delete_count_.fetch_add(1);
return target()->DeleteFile(fname);
}
Fix+clean up handling of mock sleeps (#7101) Summary: We have a number of tests hanging on MacOS and windows due to mishandling of code for mock sleeps. In addition, the code was in terrible shape because the same variable (addon_time_) would sometimes refer to microseconds and sometimes to seconds. One test even assumed it was nanoseconds but was written to pass anyway. This has been cleaned up so that DB tests generally use a SpecialEnv function to mock sleep, for either some number of microseconds or seconds depending on the function called. But to call one of these, the test must first call SetMockSleep (precondition enforced with assertion), which also turns sleeps in RocksDB into mock sleeps. To also removes accounting for actual clock time, call SetTimeElapseOnlySleepOnReopen, which implies SetMockSleep (on DB re-open). This latter setting only works by applying on DB re-open, otherwise havoc can ensue if Env goes back in time with DB open. More specifics: Removed some unused test classes, and updated comments on the general problem. Fixed DBSSTTest.GetTotalSstFilesSize using a sync point callback instead of mock time. For this we have the only modification to production code, inserting a sync point callback in flush_job.cc, which is not a change to production behavior. Removed unnecessary resetting of mock times to 0 in many tests. RocksDB deals in relative time. Any behaviors relying on absolute date/time are likely a bug. (The above test DBSSTTest.GetTotalSstFilesSize was the only one clearly injecting a specific absolute time for actual testing convenience.) Just in case I misunderstood some test, I put this note in each replacement: // NOTE: Presumed unnecessary and removed: resetting mock time in env Strengthened some tests like MergeTestTime, MergeCompactionTimeTest, and FilterCompactionTimeTest in db_test.cc stats_history_test and blob_db_test are each their own beast, rather deeply dependent on MockTimeEnv. Each gets its own variant of a work-around for TimedWait in a mock time environment. (Reduces redundancy and inconsistency in stats_history_test.) Intended follow-up: Remove TimedWait from the public API of InstrumentedCondVar, and only make that accessible through Env by passing in an InstrumentedCondVar and a deadline. Then the Env implementations mocking time can fix this problem without using sync points. (Test infrastructure using sync points interferes with individual tests' control over sync points.) With that change, we can simplify/consolidate the scattered work-arounds. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7101 Test Plan: make check on Linux and MacOS Reviewed By: zhichao-cao Differential Revision: D23032815 Pulled By: pdillinger fbshipit-source-id: 7f33967ada8b83011fb54e8279365c008bd6610b
2020-08-11 19:39:49 +00:00
void SetMockSleep(bool enabled = true) { no_slowdown_ = enabled; }
Status NewDirectory(const std::string& name,
std::unique_ptr<Directory>* result) override {
if (!skip_fsync_) {
return target()->NewDirectory(name, result);
} else {
class NoopDirectory : public Directory {
public:
NoopDirectory() {}
~NoopDirectory() {}
Status Fsync() override { return Status::OK(); }
Status Close() override { return Status::OK(); }
};
result->reset(new NoopDirectory());
return Status::OK();
}
}
Status RenameFile(const std::string& src, const std::string& dest) override {
rename_count_.fetch_add(1);
if (rename_error_.load(std::memory_order_acquire)) {
return Status::NotSupported("Simulated `RenameFile()` error.");
}
return target()->RenameFile(src, dest);
}
// Something to return when mocking current time
const int64_t maybe_starting_time_;
Random rnd_;
port::Mutex rnd_mutex_; // Lock to pretect rnd_
// sstable Sync() calls are blocked while this pointer is non-nullptr.
std::atomic<bool> delay_sstable_sync_;
// Drop writes on the floor while this pointer is non-nullptr.
std::atomic<bool> drop_writes_;
// Simulate no-space errors while this pointer is non-nullptr.
std::atomic<bool> no_space_;
// Simulate non-writable file system while this pointer is non-nullptr
std::atomic<bool> non_writable_;
// Force sync of manifest files to fail while this pointer is non-nullptr
std::atomic<bool> manifest_sync_error_;
// Force write to manifest files to fail while this pointer is non-nullptr
std::atomic<bool> manifest_write_error_;
// Force write to log files to fail while this pointer is non-nullptr
std::atomic<bool> log_write_error_;
// Force `RenameFile()` to fail while this pointer is non-nullptr
std::atomic<bool> rename_error_{false};
// Slow down every log write, in micro-seconds.
std::atomic<int> log_write_slowdown_;
Handle rename() failure in non-local FS (#8192) Summary: In a distributed environment, a file `rename()` operation can succeed on server (remote) side, but the client can somehow return non-ok status to RocksDB. Possible reasons include network partition, connection issue, etc. This happens in `rocksdb::SetCurrentFile()`, which can be called in `LogAndApply() -> ProcessManifestWrites()` if RocksDB tries to switch to a new MANIFEST. We currently always delete the new MANIFEST if an error occurs. This is problematic in distributed world. If the server-side successfully updates the CURRENT file via renaming, then a subsequent `DB::Open()` will try to look for the new MANIFEST and fail. As a fix, we can track the execution result of IO operations on the new MANIFEST. - If IO operations on the new MANIFEST fail, then we know the CURRENT must point to the original MANIFEST. Therefore, it is safe to remove the new MANIFEST. - If IO operations on the new MANIFEST all succeed, but somehow we end up in the clean up code block, then we do not know whether CURRENT points to the new or old MANIFEST. (For local POSIX-compliant FS, it should still point to old MANIFEST, but it does not matter if we keep the new MANIFEST.) Therefore, we keep the new MANIFEST. - Any future `LogAndApply()` will switch to a new MANIFEST and update CURRENT. - If process reopens the db immediately after the failure, then the CURRENT file can point to either the new MANIFEST or the old one, both of which exist. Therefore, recovery can succeed and ignore the other. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8192 Test Plan: make check Reviewed By: zhichao-cao Differential Revision: D27804648 Pulled By: riversand963 fbshipit-source-id: 9c16f2a5ce41bc6aadf085e48449b19ede8423e4
2021-04-20 01:10:23 +00:00
// If true, returns Status::NotSupported for file overwrite.
std::atomic<bool> no_file_overwrite_;
// Number of WAL files that are still open for write.
std::atomic<int> num_open_wal_file_;
bool count_random_reads_;
uint32_t rand_reads_fail_odd_ = 0;
std::atomic<uint64_t> num_reads_fails_;
anon::AtomicCounter random_read_counter_;
std::atomic<size_t> random_read_bytes_counter_;
std::atomic<int> random_file_open_counter_;
bool count_sequential_reads_;
anon::AtomicCounter sequential_read_counter_;
anon::AtomicCounter sleep_counter_;
std::atomic<int64_t> bytes_written_;
std::atomic<int> sync_counter_;
// If true, all fsync to files and directories are skipped.
bool skip_fsync_ = false;
// If true, ingest the corruption to file during sync.
bool corrupt_in_sync_ = false;
std::atomic<uint32_t> non_writeable_rate_;
std::atomic<uint32_t> new_writable_count_;
std::atomic<uint32_t> non_writable_count_;
std::function<void()>* table_write_callback_;
std::atomic<int> now_cpu_count_;
std::atomic<int> delete_count_;
std::atomic<int> rename_count_{0};
std::atomic<bool> is_wal_sync_thread_safe_{true};
std::atomic<size_t> compaction_readahead_size_{};
Fix+clean up handling of mock sleeps (#7101) Summary: We have a number of tests hanging on MacOS and windows due to mishandling of code for mock sleeps. In addition, the code was in terrible shape because the same variable (addon_time_) would sometimes refer to microseconds and sometimes to seconds. One test even assumed it was nanoseconds but was written to pass anyway. This has been cleaned up so that DB tests generally use a SpecialEnv function to mock sleep, for either some number of microseconds or seconds depending on the function called. But to call one of these, the test must first call SetMockSleep (precondition enforced with assertion), which also turns sleeps in RocksDB into mock sleeps. To also removes accounting for actual clock time, call SetTimeElapseOnlySleepOnReopen, which implies SetMockSleep (on DB re-open). This latter setting only works by applying on DB re-open, otherwise havoc can ensue if Env goes back in time with DB open. More specifics: Removed some unused test classes, and updated comments on the general problem. Fixed DBSSTTest.GetTotalSstFilesSize using a sync point callback instead of mock time. For this we have the only modification to production code, inserting a sync point callback in flush_job.cc, which is not a change to production behavior. Removed unnecessary resetting of mock times to 0 in many tests. RocksDB deals in relative time. Any behaviors relying on absolute date/time are likely a bug. (The above test DBSSTTest.GetTotalSstFilesSize was the only one clearly injecting a specific absolute time for actual testing convenience.) Just in case I misunderstood some test, I put this note in each replacement: // NOTE: Presumed unnecessary and removed: resetting mock time in env Strengthened some tests like MergeTestTime, MergeCompactionTimeTest, and FilterCompactionTimeTest in db_test.cc stats_history_test and blob_db_test are each their own beast, rather deeply dependent on MockTimeEnv. Each gets its own variant of a work-around for TimedWait in a mock time environment. (Reduces redundancy and inconsistency in stats_history_test.) Intended follow-up: Remove TimedWait from the public API of InstrumentedCondVar, and only make that accessible through Env by passing in an InstrumentedCondVar and a deadline. Then the Env implementations mocking time can fix this problem without using sync points. (Test infrastructure using sync points interferes with individual tests' control over sync points.) With that change, we can simplify/consolidate the scattered work-arounds. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7101 Test Plan: make check on Linux and MacOS Reviewed By: zhichao-cao Differential Revision: D23032815 Pulled By: pdillinger fbshipit-source-id: 7f33967ada8b83011fb54e8279365c008bd6610b
2020-08-11 19:39:49 +00:00
private: // accessing these directly is prone to error
friend class DBTestBase;
std::atomic<int64_t> addon_microseconds_{0};
// Do not modify in the env of a running DB (could cause deadlock)
std::atomic<bool> time_elapse_only_sleep_;
bool no_slowdown_;
};
class FileTemperatureTestFS : public FileSystemWrapper {
public:
explicit FileTemperatureTestFS(const std::shared_ptr<FileSystem>& fs)
: FileSystemWrapper(fs) {}
static const char* kClassName() { return "FileTemperatureTestFS"; }
const char* Name() const override { return kClassName(); }
IOStatus NewSequentialFile(const std::string& fname, const FileOptions& opts,
std::unique_ptr<FSSequentialFile>* result,
IODebugContext* dbg) override {
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
IOStatus s = target()->NewSequentialFile(fname, opts, result, dbg);
uint64_t number;
FileType type;
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
if (ParseFileName(GetFileName(fname), &number, &type) &&
type == kTableFile) {
MutexLock lock(&mu_);
requested_sst_file_temperatures_.emplace_back(number, opts.temperature);
if (s.ok()) {
if (opts.temperature != Temperature::kUnknown) {
// Be extra picky and don't open if a wrong non-unknown temperature is
// provided
auto e = current_sst_file_temperatures_.find(number);
if (e != current_sst_file_temperatures_.end() &&
e->second != opts.temperature) {
result->reset();
Fix/improve temperature handling for file ingestion (#12402) Summary: Partly following up on leftovers from https://github.com/facebook/rocksdb/issues/12388 In terms of public API: * Make it clear that IngestExternalFileArg::file_temperature is just a hint for opening the existing file, though it was previously used for both copy-from temp hint and copy-to temp, which was bizarre. * Specify how IngestExternalFile assigns temperature to file ingested into DB. (See details in comments.) This approach is not perfect in terms of matching how the DB assigns temperatures, but was the simplest way to get close. The key complication for matching DB temperature assignments is that ingestion files are copied (to a destination temp) before their target level is determined (in general). * Add a temperature option to SstFileWriter::Open so that files intended for ingestion can be initially written to a chosen temperature. * Note that "fail_if_not_bottommost_level" is obsolete/confusing use of "bottommost" In terms of the implementation, there was a similar bit of oddness with the internal CopyFile API, which only took one temperature, ambiguously applicable to the source, destination, or both. This is also fixed. Eventual suggested follow-up: * Before copying files for ingestion, determine a tentative level assignment to use for destination temperature, and keep that even if final level assignment happens to be different at commit time (rare). * More temperature handling for CreateColumnFamilyWithImport and Checkpoints. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12402 Test Plan: Deeply revamped ExternalSSTFileBasicTest.IngestWithTemperature to test the new changes. Previously this test was insufficient because it was only looking at temperatures according to the DB manifest. Incorporating FileTemperatureTestFS allows us to also test the temperatures in the storage layer. Used macros instead of functions for better tracing to critical source location on test failures. Some enhancements to FileTemperatureTestFS in the process of developing the revamped test. Reviewed By: jowlyzhang Differential Revision: D54442794 Pulled By: pdillinger fbshipit-source-id: 41d9d0afdc073e6a983304c10bbc07c70cc7e995
2024-03-06 00:56:08 +00:00
return IOStatus::PathNotFound(
"Read requested temperature " +
temperature_to_string[opts.temperature] +
" but stored with temperature " +
temperature_to_string[e->second] + " for " + fname);
}
}
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
*result = WrapWithTemperature<FSSequentialFileOwnerWrapper>(
number, std::move(*result));
}
}
return s;
}
IOStatus NewRandomAccessFile(const std::string& fname,
const FileOptions& opts,
std::unique_ptr<FSRandomAccessFile>* result,
IODebugContext* dbg) override {
IOStatus s = target()->NewRandomAccessFile(fname, opts, result, dbg);
uint64_t number;
FileType type;
if (ParseFileName(GetFileName(fname), &number, &type) &&
type == kTableFile) {
MutexLock lock(&mu_);
requested_sst_file_temperatures_.emplace_back(number, opts.temperature);
if (s.ok()) {
if (opts.temperature != Temperature::kUnknown) {
// Be extra picky and don't open if a wrong non-unknown temperature is
// provided
auto e = current_sst_file_temperatures_.find(number);
if (e != current_sst_file_temperatures_.end() &&
e->second != opts.temperature) {
result->reset();
Fix/improve temperature handling for file ingestion (#12402) Summary: Partly following up on leftovers from https://github.com/facebook/rocksdb/issues/12388 In terms of public API: * Make it clear that IngestExternalFileArg::file_temperature is just a hint for opening the existing file, though it was previously used for both copy-from temp hint and copy-to temp, which was bizarre. * Specify how IngestExternalFile assigns temperature to file ingested into DB. (See details in comments.) This approach is not perfect in terms of matching how the DB assigns temperatures, but was the simplest way to get close. The key complication for matching DB temperature assignments is that ingestion files are copied (to a destination temp) before their target level is determined (in general). * Add a temperature option to SstFileWriter::Open so that files intended for ingestion can be initially written to a chosen temperature. * Note that "fail_if_not_bottommost_level" is obsolete/confusing use of "bottommost" In terms of the implementation, there was a similar bit of oddness with the internal CopyFile API, which only took one temperature, ambiguously applicable to the source, destination, or both. This is also fixed. Eventual suggested follow-up: * Before copying files for ingestion, determine a tentative level assignment to use for destination temperature, and keep that even if final level assignment happens to be different at commit time (rare). * More temperature handling for CreateColumnFamilyWithImport and Checkpoints. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12402 Test Plan: Deeply revamped ExternalSSTFileBasicTest.IngestWithTemperature to test the new changes. Previously this test was insufficient because it was only looking at temperatures according to the DB manifest. Incorporating FileTemperatureTestFS allows us to also test the temperatures in the storage layer. Used macros instead of functions for better tracing to critical source location on test failures. Some enhancements to FileTemperatureTestFS in the process of developing the revamped test. Reviewed By: jowlyzhang Differential Revision: D54442794 Pulled By: pdillinger fbshipit-source-id: 41d9d0afdc073e6a983304c10bbc07c70cc7e995
2024-03-06 00:56:08 +00:00
return IOStatus::PathNotFound(
"Read requested temperature " +
temperature_to_string[opts.temperature] +
" but stored with temperature " +
temperature_to_string[e->second] + " for " + fname);
}
}
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
*result = WrapWithTemperature<FSRandomAccessFileOwnerWrapper>(
number, std::move(*result));
}
}
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
return s;
}
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
void PopRequestedSstFileTemperatures(
std::vector<std::pair<uint64_t, Temperature>>* out = nullptr) {
MutexLock lock(&mu_);
if (out) {
*out = std::move(requested_sst_file_temperatures_);
assert(requested_sst_file_temperatures_.empty());
} else {
requested_sst_file_temperatures_.clear();
}
}
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
IOStatus NewWritableFile(const std::string& fname, const FileOptions& opts,
std::unique_ptr<FSWritableFile>* result,
IODebugContext* dbg) override {
uint64_t number;
FileType type;
if (ParseFileName(GetFileName(fname), &number, &type) &&
type == kTableFile) {
MutexLock lock(&mu_);
current_sst_file_temperatures_[number] = opts.temperature;
}
return target()->NewWritableFile(fname, opts, result, dbg);
}
Fix/improve temperature handling for file ingestion (#12402) Summary: Partly following up on leftovers from https://github.com/facebook/rocksdb/issues/12388 In terms of public API: * Make it clear that IngestExternalFileArg::file_temperature is just a hint for opening the existing file, though it was previously used for both copy-from temp hint and copy-to temp, which was bizarre. * Specify how IngestExternalFile assigns temperature to file ingested into DB. (See details in comments.) This approach is not perfect in terms of matching how the DB assigns temperatures, but was the simplest way to get close. The key complication for matching DB temperature assignments is that ingestion files are copied (to a destination temp) before their target level is determined (in general). * Add a temperature option to SstFileWriter::Open so that files intended for ingestion can be initially written to a chosen temperature. * Note that "fail_if_not_bottommost_level" is obsolete/confusing use of "bottommost" In terms of the implementation, there was a similar bit of oddness with the internal CopyFile API, which only took one temperature, ambiguously applicable to the source, destination, or both. This is also fixed. Eventual suggested follow-up: * Before copying files for ingestion, determine a tentative level assignment to use for destination temperature, and keep that even if final level assignment happens to be different at commit time (rare). * More temperature handling for CreateColumnFamilyWithImport and Checkpoints. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12402 Test Plan: Deeply revamped ExternalSSTFileBasicTest.IngestWithTemperature to test the new changes. Previously this test was insufficient because it was only looking at temperatures according to the DB manifest. Incorporating FileTemperatureTestFS allows us to also test the temperatures in the storage layer. Used macros instead of functions for better tracing to critical source location on test failures. Some enhancements to FileTemperatureTestFS in the process of developing the revamped test. Reviewed By: jowlyzhang Differential Revision: D54442794 Pulled By: pdillinger fbshipit-source-id: 41d9d0afdc073e6a983304c10bbc07c70cc7e995
2024-03-06 00:56:08 +00:00
IOStatus DeleteFile(const std::string& fname, const IOOptions& options,
IODebugContext* dbg) override {
IOStatus ios = target()->DeleteFile(fname, options, dbg);
if (ios.ok()) {
uint64_t number;
FileType type;
if (ParseFileName(GetFileName(fname), &number, &type) &&
type == kTableFile) {
MutexLock lock(&mu_);
current_sst_file_temperatures_.erase(number);
}
}
return ios;
}
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
void CopyCurrentSstFileTemperatures(std::map<uint64_t, Temperature>* out) {
MutexLock lock(&mu_);
*out = current_sst_file_temperatures_;
}
Fix/improve temperature handling for file ingestion (#12402) Summary: Partly following up on leftovers from https://github.com/facebook/rocksdb/issues/12388 In terms of public API: * Make it clear that IngestExternalFileArg::file_temperature is just a hint for opening the existing file, though it was previously used for both copy-from temp hint and copy-to temp, which was bizarre. * Specify how IngestExternalFile assigns temperature to file ingested into DB. (See details in comments.) This approach is not perfect in terms of matching how the DB assigns temperatures, but was the simplest way to get close. The key complication for matching DB temperature assignments is that ingestion files are copied (to a destination temp) before their target level is determined (in general). * Add a temperature option to SstFileWriter::Open so that files intended for ingestion can be initially written to a chosen temperature. * Note that "fail_if_not_bottommost_level" is obsolete/confusing use of "bottommost" In terms of the implementation, there was a similar bit of oddness with the internal CopyFile API, which only took one temperature, ambiguously applicable to the source, destination, or both. This is also fixed. Eventual suggested follow-up: * Before copying files for ingestion, determine a tentative level assignment to use for destination temperature, and keep that even if final level assignment happens to be different at commit time (rare). * More temperature handling for CreateColumnFamilyWithImport and Checkpoints. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12402 Test Plan: Deeply revamped ExternalSSTFileBasicTest.IngestWithTemperature to test the new changes. Previously this test was insufficient because it was only looking at temperatures according to the DB manifest. Incorporating FileTemperatureTestFS allows us to also test the temperatures in the storage layer. Used macros instead of functions for better tracing to critical source location on test failures. Some enhancements to FileTemperatureTestFS in the process of developing the revamped test. Reviewed By: jowlyzhang Differential Revision: D54442794 Pulled By: pdillinger fbshipit-source-id: 41d9d0afdc073e6a983304c10bbc07c70cc7e995
2024-03-06 00:56:08 +00:00
size_t CountCurrentSstFilesWithTemperature(Temperature temp) {
MutexLock lock(&mu_);
size_t count = 0;
for (const auto& e : current_sst_file_temperatures_) {
if (e.second == temp) {
++count;
}
}
return count;
}
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
void OverrideSstFileTemperature(uint64_t number, Temperature temp) {
MutexLock lock(&mu_);
current_sst_file_temperatures_[number] = temp;
}
protected:
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
port::Mutex mu_;
std::vector<std::pair<uint64_t, Temperature>>
requested_sst_file_temperatures_;
std::map<uint64_t, Temperature> current_sst_file_temperatures_;
std::string GetFileName(const std::string& fname) {
auto filename = fname.substr(fname.find_last_of(kFilePathSeparator) + 1);
// workaround only for Windows that the file path could contain both Windows
// FilePathSeparator and '/'
filename = filename.substr(filename.find_last_of('/') + 1);
return filename;
}
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
template <class FileOwnerWrapperT, /*inferred*/ class FileT>
std::unique_ptr<FileT> WrapWithTemperature(uint64_t number,
std::unique_ptr<FileT>&& t) {
class FileWithTemp : public FileOwnerWrapperT {
public:
FileWithTemp(FileTemperatureTestFS* fs, uint64_t number,
std::unique_ptr<FileT>&& t)
: FileOwnerWrapperT(std::move(t)), fs_(fs), number_(number) {}
Temperature GetTemperature() const override {
MutexLock lock(&fs_->mu_);
return fs_->current_sst_file_temperatures_[number_];
}
private:
FileTemperatureTestFS* fs_;
uint64_t number_;
};
return std::make_unique<FileWithTemp>(this, number, std::move(t));
}
};
class OnFileDeletionListener : public EventListener {
public:
OnFileDeletionListener() : matched_count_(0), expected_file_name_("") {}
const char* Name() const override { return kClassName(); }
static const char* kClassName() { return "OnFileDeletionListener"; }
void SetExpectedFileName(const std::string file_name) {
expected_file_name_ = file_name;
}
void VerifyMatchedCount(size_t expected_value) {
ASSERT_EQ(matched_count_, expected_value);
}
void OnTableFileDeleted(const TableFileDeletionInfo& info) override {
if (expected_file_name_ != "") {
ASSERT_EQ(expected_file_name_, info.file_path);
expected_file_name_ = "";
matched_count_++;
}
}
private:
size_t matched_count_;
std::string expected_file_name_;
};
class FlushCounterListener : public EventListener {
public:
const char* Name() const override { return kClassName(); }
static const char* kClassName() { return "FlushCounterListener"; }
std::atomic<int> count{0};
std::atomic<FlushReason> expected_flush_reason{FlushReason::kOthers};
void OnFlushBegin(DB* /*db*/, const FlushJobInfo& flush_job_info) override {
count++;
ASSERT_EQ(expected_flush_reason.load(), flush_job_info.flush_reason);
}
};
// A test merge operator mimics put but also fails if one of merge operands is
// "corrupted", "corrupted_try_merge", or "corrupted_must_merge".
class TestPutOperator : public MergeOperator {
public:
bool FullMergeV2(const MergeOperationInput& merge_in,
MergeOperationOutput* merge_out) const override {
static const std::map<std::string, MergeOperator::OpFailureScope>
bad_operand_to_op_failure_scope = {
{"corrupted", MergeOperator::OpFailureScope::kDefault},
{"corrupted_try_merge", MergeOperator::OpFailureScope::kTryMerge},
{"corrupted_must_merge",
MergeOperator::OpFailureScope::kMustMerge}};
auto check_operand =
[](Slice operand_val,
MergeOperator::OpFailureScope* op_failure_scope) -> bool {
auto iter = bad_operand_to_op_failure_scope.find(operand_val.ToString());
if (iter != bad_operand_to_op_failure_scope.end()) {
*op_failure_scope = iter->second;
return false;
}
return true;
};
if (merge_in.existing_value != nullptr &&
!check_operand(*merge_in.existing_value,
&merge_out->op_failure_scope)) {
return false;
}
for (auto value : merge_in.operand_list) {
if (!check_operand(value, &merge_out->op_failure_scope)) {
return false;
}
}
merge_out->existing_operand = merge_in.operand_list.back();
return true;
}
const char* Name() const override { return "TestPutOperator"; }
};
Rewrite memory-charging feature's option API (#9926) Summary: **Context:** Previous PR https://github.com/facebook/rocksdb/pull/9748, https://github.com/facebook/rocksdb/pull/9073, https://github.com/facebook/rocksdb/pull/8428 added separate flag for each charged memory area. Such API design is not scalable as we charge more and more memory areas. Also, we foresee an opportunity to consolidate this feature with other cache usage related features such as `cache_index_and_filter_blocks` using `CacheEntryRole`. Therefore we decided to consolidate all these flags with `CacheUsageOptions cache_usage_options` and this PR serves as the first step by consolidating memory-charging related flags. **Summary:** - Replaced old API reference with new ones, including making `kCompressionDictionaryBuildingBuffer` opt-out and added a unit test for that - Added missing db bench/stress test for some memory charging features - Renamed related test suite to indicate they are under the same theme of memory charging - Refactored a commonly used mocked cache component in memory charging related tests to reduce code duplication - Replaced the phrases "memory tracking" / "cache reservation" (other than CacheReservationManager-related ones) with "memory charging" for standard description of this feature. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9926 Test Plan: - New unit test for opt-out `kCompressionDictionaryBuildingBuffer` `TEST_F(ChargeCompressionDictionaryBuildingBufferTest, Basic)` - New unit test for option validation/sanitization `TEST_F(CacheUsageOptionsOverridesTest, SanitizeAndValidateOptions)` - CI - db bench (in case querying new options introduces regression) **+0.5% micros/op**: `TEST_TMPDIR=/dev/shm/testdb ./db_bench -benchmarks=fillseq -db=$TEST_TMPDIR -charge_compression_dictionary_building_buffer=1(remove this for comparison) -compression_max_dict_bytes=10000 -disable_auto_compactions=1 -write_buffer_size=100000 -num=4000000 | egrep 'fillseq'` #-run | (pre-PR) avg micros/op | std micros/op | (post-PR) micros/op | std micros/op | change (%) -- | -- | -- | -- | -- | -- 10 | 3.9711 | 0.264408 | 3.9914 | 0.254563 | 0.5111933721 20 | 3.83905 | 0.0664488 | 3.8251 | 0.0695456 | **-0.3633711465** 40 | 3.86625 | 0.136669 | 3.8867 | 0.143765 | **0.5289363078** - db_stress: `python3 tools/db_crashtest.py blackbox -charge_compression_dictionary_building_buffer=1 -charge_filter_construction=1 -charge_table_reader=1 -cache_size=1` killed as normal Reviewed By: ajkr Differential Revision: D36054712 Pulled By: hx235 fbshipit-source-id: d406e90f5e0c5ea4dbcb585a484ad9302d4302af
2022-05-17 22:01:51 +00:00
/*
* A cache wrapper that tracks certain CacheEntryRole's cache charge, its
* peaks and increments
*
* p0
* / \ p1
* / \ /\
* / \/ \
* a / b \
* peaks = {p0, p1}
* increments = {p1-a, p2-b}
*/
template <CacheEntryRole R>
class TargetCacheChargeTrackingCache : public CacheWrapper {
public:
explicit TargetCacheChargeTrackingCache(std::shared_ptr<Cache> target);
const char* Name() const override { return "TargetCacheChargeTrackingCache"; }
Major Cache refactoring, CPU efficiency improvement (#10975) Summary: This is several refactorings bundled into one to avoid having to incrementally re-modify uses of Cache several times. Overall, there are breaking changes to Cache class, and it becomes more of low-level interface for implementing caches, especially block cache. New internal APIs make using Cache cleaner than before, and more insulated from block cache evolution. Hopefully, this is the last really big block cache refactoring, because of rather effectively decoupling the implementations from the uses. This change also removes the EXPERIMENTAL designation on the SecondaryCache support in Cache. It seems reasonably mature at this point but still subject to change/evolution (as I warn in the API docs for Cache). The high-level motivation for this refactoring is to minimize code duplication / compounding complexity in adding SecondaryCache support to HyperClockCache (in a later PR). Other benefits listed below. * static_cast lines of code +29 -35 (net removed 6) * reinterpret_cast lines of code +6 -32 (net removed 26) ## cache.h and secondary_cache.h * Always use CacheItemHelper with entries instead of just a Deleter. There are several motivations / justifications: * Simpler for implementations to deal with just one Insert and one Lookup. * Simpler and more efficient implementation because we don't have to track which entries are using helpers and which are using deleters * Gets rid of hack to classify cache entries by their deleter. Instead, the CacheItemHelper includes a CacheEntryRole. This simplifies a lot of code (cache_entry_roles.h almost eliminated). Fixes https://github.com/facebook/rocksdb/issues/9428. * Makes it trivial to adjust SecondaryCache behavior based on kind of block (e.g. don't re-compress filter blocks). * It is arguably less convenient for many direct users of Cache, but direct users of Cache are now rare with introduction of typed_cache.h (below). * I considered and rejected an alternative approach in which we reduce customizability by assuming each secondary cache compatible value starts with a Slice referencing the uncompressed block contents (already true or mostly true), but we apparently intend to stack secondary caches. Saving an entry from a compressed secondary to a lower tier requires custom handling offered by SaveToCallback, etc. * Make CreateCallback part of the helper and introduce CreateContext to work with it (alternative to https://github.com/facebook/rocksdb/issues/10562). This cleans up the interface while still allowing context to be provided for loading/parsing values into primary cache. This model works for async lookup in BlockBasedTable reader (reader owns a CreateContext) under the assumption that it always waits on secondary cache operations to finish. (Otherwise, the CreateContext could be destroyed while async operation depending on it continues.) This likely contributes most to the observed performance improvement because it saves an std::function backed by a heap allocation. * Use char* for serialized data, e.g. in SaveToCallback, where void* was confusingly used. (We use `char*` for serialized byte data all over RocksDB, with many advantages over `void*`. `memcpy` etc. are legacy APIs that should not be mimicked.) * Add a type alias Cache::ObjectPtr = void*, so that we can better indicate the intent of the void* when it is to be the object associated with a Cache entry. Related: started (but did not complete) a refactoring to move away from "value" of a cache entry toward "object" or "obj". (It is confusing to call Cache a key-value store (like DB) when it is really storing arbitrary in-memory objects, not byte strings.) * Remove unnecessary key param from DeleterFn. This is good for efficiency in HyperClockCache, which does not directly store the cache key in memory. (Alternative to https://github.com/facebook/rocksdb/issues/10774) * Add allocator to Cache DeleterFn. This is a kind of future-proofing change in case we get more serious about using the Cache allocator for memory tracked by the Cache. Right now, only the uncompressed block contents are allocated using the allocator, and a pointer to that allocator is saved as part of the cached object so that the deleter can use it. (See CacheAllocationPtr.) If in the future we are able to "flatten out" our Cache objects some more, it would be good not to have to track the allocator as part of each object. * Removes legacy `ApplyToAllCacheEntries` and changes `ApplyToAllEntries` signature for Deleter->CacheItemHelper change. ## typed_cache.h Adds various "typed" interfaces to the Cache as internal APIs, so that most uses of Cache can use simple type safe code without casting and without explicit deleters, etc. Almost all of the non-test, non-glue code uses of Cache have been migrated. (Follow-up work: CompressedSecondaryCache deserves deeper attention to migrate.) This change expands RocksDB's internal usage of metaprogramming and SFINAE (https://en.cppreference.com/w/cpp/language/sfinae). The existing usages of Cache are divided up at a high level into these new interfaces. See updated existing uses of Cache for examples of how these are used. * PlaceholderCacheInterface - Used for making cache reservations, with entries that have a charge but no value. * BasicTypedCacheInterface<TValue> - Used for primary cache storage of objects of type TValue, which can be cleaned up with std::default_delete<TValue>. The role is provided by TValue::kCacheEntryRole or given in an optional template parameter. * FullTypedCacheInterface<TValue, TCreateContext> - Used for secondary cache compatible storage of objects of type TValue. In addition to BasicTypedCacheInterface constraints, we require TValue::ContentSlice() to return persistable data. This simplifies usage for the normal case of simple secondary cache compatibility (can give you a Slice to the data already in memory). In addition to TCreateContext performing the role of Cache::CreateContext, it is also expected to provide a factory function for creating TValue. * For each of these, there's a "Shared" version (e.g. FullTypedSharedCacheInterface) that holds a shared_ptr to the Cache, rather than assuming external ownership by holding only a raw `Cache*`. These interfaces introduce specific handle types for each interface instantiation, so that it's easy to see what kind of object is controlled by a handle. (Ultimately, this might not be worth the extra complexity, but it seems OK so far.) Note: I attempted to make the cache 'charge' automatically inferred from the cache object type, such as by expecting an ApproximateMemoryUsage() function, but this is not so clean because there are cases where we need to compute the charge ahead of time and don't want to re-compute it. ## block_cache.h This header is essentially the replacement for the old block_like_traits.h. It includes various things to support block cache access with typed_cache.h for block-based table. ## block_based_table_reader.cc Before this change, accessing the block cache here was an awkward mix of static polymorphism (template TBlocklike) and switch-case on a dynamic BlockType value. This change mostly unifies on static polymorphism, relying on minor hacks in block_cache.h to distinguish variants of Block. We still check BlockType in some places (especially for stats, which could be improved in follow-up work) but at least the BlockType is a static constant from the template parameter. (No more awkward partial redundancy between static and dynamic info.) This likely contributes to the overall performance improvement, but hasn't been tested in isolation. The other key source of simplification here is a more unified system of creating block cache objects: for directly populating from primary cache and for promotion from secondary cache. Both use BlockCreateContext, for context and for factory functions. ## block_based_table_builder.cc, cache_dump_load_impl.cc Before this change, warming caches was super ugly code. Both of these source files had switch statements to basically transition from the dynamic BlockType world to the static TBlocklike world. None of that mess is needed anymore as there's a new, untyped WarmInCache function that handles all the details just as promotion from SecondaryCache would. (Fixes `TODO akanksha: Dedup below code` in block_based_table_builder.cc.) ## Everything else Mostly just updating Cache users to use new typed APIs when reasonably possible, or changed Cache APIs when not. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10975 Test Plan: tests updated Performance test setup similar to https://github.com/facebook/rocksdb/issues/10626 (by cache size, LRUCache when not "hyper" for HyperClockCache): 34MB 1thread base.hyper -> kops/s: 0.745 io_bytes/op: 2.52504e+06 miss_ratio: 0.140906 max_rss_mb: 76.4844 34MB 1thread new.hyper -> kops/s: 0.751 io_bytes/op: 2.5123e+06 miss_ratio: 0.140161 max_rss_mb: 79.3594 34MB 1thread base -> kops/s: 0.254 io_bytes/op: 1.36073e+07 miss_ratio: 0.918818 max_rss_mb: 45.9297 34MB 1thread new -> kops/s: 0.252 io_bytes/op: 1.36157e+07 miss_ratio: 0.918999 max_rss_mb: 44.1523 34MB 32thread base.hyper -> kops/s: 7.272 io_bytes/op: 2.88323e+06 miss_ratio: 0.162532 max_rss_mb: 516.602 34MB 32thread new.hyper -> kops/s: 7.214 io_bytes/op: 2.99046e+06 miss_ratio: 0.168818 max_rss_mb: 518.293 34MB 32thread base -> kops/s: 3.528 io_bytes/op: 1.35722e+07 miss_ratio: 0.914691 max_rss_mb: 264.926 34MB 32thread new -> kops/s: 3.604 io_bytes/op: 1.35744e+07 miss_ratio: 0.915054 max_rss_mb: 264.488 233MB 1thread base.hyper -> kops/s: 53.909 io_bytes/op: 2552.35 miss_ratio: 0.0440566 max_rss_mb: 241.984 233MB 1thread new.hyper -> kops/s: 62.792 io_bytes/op: 2549.79 miss_ratio: 0.044043 max_rss_mb: 241.922 233MB 1thread base -> kops/s: 1.197 io_bytes/op: 2.75173e+06 miss_ratio: 0.103093 max_rss_mb: 241.559 233MB 1thread new -> kops/s: 1.199 io_bytes/op: 2.73723e+06 miss_ratio: 0.10305 max_rss_mb: 240.93 233MB 32thread base.hyper -> kops/s: 1298.69 io_bytes/op: 2539.12 miss_ratio: 0.0440307 max_rss_mb: 371.418 233MB 32thread new.hyper -> kops/s: 1421.35 io_bytes/op: 2538.75 miss_ratio: 0.0440307 max_rss_mb: 347.273 233MB 32thread base -> kops/s: 9.693 io_bytes/op: 2.77304e+06 miss_ratio: 0.103745 max_rss_mb: 569.691 233MB 32thread new -> kops/s: 9.75 io_bytes/op: 2.77559e+06 miss_ratio: 0.103798 max_rss_mb: 552.82 1597MB 1thread base.hyper -> kops/s: 58.607 io_bytes/op: 1449.14 miss_ratio: 0.0249324 max_rss_mb: 1583.55 1597MB 1thread new.hyper -> kops/s: 69.6 io_bytes/op: 1434.89 miss_ratio: 0.0247167 max_rss_mb: 1584.02 1597MB 1thread base -> kops/s: 60.478 io_bytes/op: 1421.28 miss_ratio: 0.024452 max_rss_mb: 1589.45 1597MB 1thread new -> kops/s: 63.973 io_bytes/op: 1416.07 miss_ratio: 0.0243766 max_rss_mb: 1589.24 1597MB 32thread base.hyper -> kops/s: 1436.2 io_bytes/op: 1357.93 miss_ratio: 0.0235353 max_rss_mb: 1692.92 1597MB 32thread new.hyper -> kops/s: 1605.03 io_bytes/op: 1358.04 miss_ratio: 0.023538 max_rss_mb: 1702.78 1597MB 32thread base -> kops/s: 280.059 io_bytes/op: 1350.34 miss_ratio: 0.023289 max_rss_mb: 1675.36 1597MB 32thread new -> kops/s: 283.125 io_bytes/op: 1351.05 miss_ratio: 0.0232797 max_rss_mb: 1703.83 Almost uniformly improving over base revision, especially for hot paths with HyperClockCache, up to 12% higher throughput seen (1597MB, 32thread, hyper). The improvement for that is likely coming from much simplified code for providing context for secondary cache promotion (CreateCallback/CreateContext), and possibly from less branching in block_based_table_reader. And likely a small improvement from not reconstituting key for DeleterFn. Reviewed By: anand1976 Differential Revision: D42417818 Pulled By: pdillinger fbshipit-source-id: f86bfdd584dce27c028b151ba56818ad14f7a432
2023-01-11 22:20:40 +00:00
Status Insert(const Slice& key, ObjectPtr value,
const CacheItemHelper* helper, size_t charge,
Support compressed and local flash secondary cache stacking (#11812) Summary: This PR implements support for a three tier cache - primary block cache, compressed secondary cache, and a nvm (local flash) secondary cache. This allows more effective utilization of the nvm cache, and minimizes the number of reads from local flash by caching compressed blocks in the compressed secondary cache. The basic design is as follows - 1. A new secondary cache implementation, ```TieredSecondaryCache```, is introduced. It keeps the compressed and nvm secondary caches and manages the movement of blocks between them and the primary block cache. To setup a three tier cache, we allocate a ```CacheWithSecondaryAdapter```, with a ```TieredSecondaryCache``` instance as the secondary cache. 2. The table reader passes both the uncompressed and compressed block to ```FullTypedCacheInterface::InsertFull```, allowing the block cache to optionally store the compressed block. 3. When there's a miss, the block object is constructed and inserted in the primary cache, and the compressed block is inserted into the nvm cache by calling ```InsertSaved```. This avoids the overhead of recompressing the block, as well as avoiding putting more memory pressure on the compressed secondary cache. 4. When there's a hit in the nvm cache, we attempt to insert the block in the compressed secondary cache and the primary cache, subject to the admission policy of those caches (i.e admit on second access). Blocks/items evicted from any tier are simply discarded. We can easily implement additional admission policies if desired. Todo (In a subsequent PR): 1. Add to db_bench and run benchmarks 2. Add to db_stress Pull Request resolved: https://github.com/facebook/rocksdb/pull/11812 Reviewed By: pdillinger Differential Revision: D49461842 Pulled By: anand1976 fbshipit-source-id: b40ac1330ef7cd8c12efa0a3ca75128e602e3a0b
2023-09-22 03:30:53 +00:00
Handle** handle = nullptr, Priority priority = Priority::LOW,
const Slice& compressed = Slice(),
CompressionType type = kNoCompression) override;
Rewrite memory-charging feature's option API (#9926) Summary: **Context:** Previous PR https://github.com/facebook/rocksdb/pull/9748, https://github.com/facebook/rocksdb/pull/9073, https://github.com/facebook/rocksdb/pull/8428 added separate flag for each charged memory area. Such API design is not scalable as we charge more and more memory areas. Also, we foresee an opportunity to consolidate this feature with other cache usage related features such as `cache_index_and_filter_blocks` using `CacheEntryRole`. Therefore we decided to consolidate all these flags with `CacheUsageOptions cache_usage_options` and this PR serves as the first step by consolidating memory-charging related flags. **Summary:** - Replaced old API reference with new ones, including making `kCompressionDictionaryBuildingBuffer` opt-out and added a unit test for that - Added missing db bench/stress test for some memory charging features - Renamed related test suite to indicate they are under the same theme of memory charging - Refactored a commonly used mocked cache component in memory charging related tests to reduce code duplication - Replaced the phrases "memory tracking" / "cache reservation" (other than CacheReservationManager-related ones) with "memory charging" for standard description of this feature. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9926 Test Plan: - New unit test for opt-out `kCompressionDictionaryBuildingBuffer` `TEST_F(ChargeCompressionDictionaryBuildingBufferTest, Basic)` - New unit test for option validation/sanitization `TEST_F(CacheUsageOptionsOverridesTest, SanitizeAndValidateOptions)` - CI - db bench (in case querying new options introduces regression) **+0.5% micros/op**: `TEST_TMPDIR=/dev/shm/testdb ./db_bench -benchmarks=fillseq -db=$TEST_TMPDIR -charge_compression_dictionary_building_buffer=1(remove this for comparison) -compression_max_dict_bytes=10000 -disable_auto_compactions=1 -write_buffer_size=100000 -num=4000000 | egrep 'fillseq'` #-run | (pre-PR) avg micros/op | std micros/op | (post-PR) micros/op | std micros/op | change (%) -- | -- | -- | -- | -- | -- 10 | 3.9711 | 0.264408 | 3.9914 | 0.254563 | 0.5111933721 20 | 3.83905 | 0.0664488 | 3.8251 | 0.0695456 | **-0.3633711465** 40 | 3.86625 | 0.136669 | 3.8867 | 0.143765 | **0.5289363078** - db_stress: `python3 tools/db_crashtest.py blackbox -charge_compression_dictionary_building_buffer=1 -charge_filter_construction=1 -charge_table_reader=1 -cache_size=1` killed as normal Reviewed By: ajkr Differential Revision: D36054712 Pulled By: hx235 fbshipit-source-id: d406e90f5e0c5ea4dbcb585a484ad9302d4302af
2022-05-17 22:01:51 +00:00
using Cache::Release;
bool Release(Handle* handle, bool erase_if_last_ref = false) override;
std::size_t GetCacheCharge() { return cur_cache_charge_; }
std::deque<std::size_t> GetChargedCachePeaks() { return cache_charge_peaks_; }
std::size_t GetChargedCacheIncrementSum() {
return cache_charge_increments_sum_;
}
private:
Major Cache refactoring, CPU efficiency improvement (#10975) Summary: This is several refactorings bundled into one to avoid having to incrementally re-modify uses of Cache several times. Overall, there are breaking changes to Cache class, and it becomes more of low-level interface for implementing caches, especially block cache. New internal APIs make using Cache cleaner than before, and more insulated from block cache evolution. Hopefully, this is the last really big block cache refactoring, because of rather effectively decoupling the implementations from the uses. This change also removes the EXPERIMENTAL designation on the SecondaryCache support in Cache. It seems reasonably mature at this point but still subject to change/evolution (as I warn in the API docs for Cache). The high-level motivation for this refactoring is to minimize code duplication / compounding complexity in adding SecondaryCache support to HyperClockCache (in a later PR). Other benefits listed below. * static_cast lines of code +29 -35 (net removed 6) * reinterpret_cast lines of code +6 -32 (net removed 26) ## cache.h and secondary_cache.h * Always use CacheItemHelper with entries instead of just a Deleter. There are several motivations / justifications: * Simpler for implementations to deal with just one Insert and one Lookup. * Simpler and more efficient implementation because we don't have to track which entries are using helpers and which are using deleters * Gets rid of hack to classify cache entries by their deleter. Instead, the CacheItemHelper includes a CacheEntryRole. This simplifies a lot of code (cache_entry_roles.h almost eliminated). Fixes https://github.com/facebook/rocksdb/issues/9428. * Makes it trivial to adjust SecondaryCache behavior based on kind of block (e.g. don't re-compress filter blocks). * It is arguably less convenient for many direct users of Cache, but direct users of Cache are now rare with introduction of typed_cache.h (below). * I considered and rejected an alternative approach in which we reduce customizability by assuming each secondary cache compatible value starts with a Slice referencing the uncompressed block contents (already true or mostly true), but we apparently intend to stack secondary caches. Saving an entry from a compressed secondary to a lower tier requires custom handling offered by SaveToCallback, etc. * Make CreateCallback part of the helper and introduce CreateContext to work with it (alternative to https://github.com/facebook/rocksdb/issues/10562). This cleans up the interface while still allowing context to be provided for loading/parsing values into primary cache. This model works for async lookup in BlockBasedTable reader (reader owns a CreateContext) under the assumption that it always waits on secondary cache operations to finish. (Otherwise, the CreateContext could be destroyed while async operation depending on it continues.) This likely contributes most to the observed performance improvement because it saves an std::function backed by a heap allocation. * Use char* for serialized data, e.g. in SaveToCallback, where void* was confusingly used. (We use `char*` for serialized byte data all over RocksDB, with many advantages over `void*`. `memcpy` etc. are legacy APIs that should not be mimicked.) * Add a type alias Cache::ObjectPtr = void*, so that we can better indicate the intent of the void* when it is to be the object associated with a Cache entry. Related: started (but did not complete) a refactoring to move away from "value" of a cache entry toward "object" or "obj". (It is confusing to call Cache a key-value store (like DB) when it is really storing arbitrary in-memory objects, not byte strings.) * Remove unnecessary key param from DeleterFn. This is good for efficiency in HyperClockCache, which does not directly store the cache key in memory. (Alternative to https://github.com/facebook/rocksdb/issues/10774) * Add allocator to Cache DeleterFn. This is a kind of future-proofing change in case we get more serious about using the Cache allocator for memory tracked by the Cache. Right now, only the uncompressed block contents are allocated using the allocator, and a pointer to that allocator is saved as part of the cached object so that the deleter can use it. (See CacheAllocationPtr.) If in the future we are able to "flatten out" our Cache objects some more, it would be good not to have to track the allocator as part of each object. * Removes legacy `ApplyToAllCacheEntries` and changes `ApplyToAllEntries` signature for Deleter->CacheItemHelper change. ## typed_cache.h Adds various "typed" interfaces to the Cache as internal APIs, so that most uses of Cache can use simple type safe code without casting and without explicit deleters, etc. Almost all of the non-test, non-glue code uses of Cache have been migrated. (Follow-up work: CompressedSecondaryCache deserves deeper attention to migrate.) This change expands RocksDB's internal usage of metaprogramming and SFINAE (https://en.cppreference.com/w/cpp/language/sfinae). The existing usages of Cache are divided up at a high level into these new interfaces. See updated existing uses of Cache for examples of how these are used. * PlaceholderCacheInterface - Used for making cache reservations, with entries that have a charge but no value. * BasicTypedCacheInterface<TValue> - Used for primary cache storage of objects of type TValue, which can be cleaned up with std::default_delete<TValue>. The role is provided by TValue::kCacheEntryRole or given in an optional template parameter. * FullTypedCacheInterface<TValue, TCreateContext> - Used for secondary cache compatible storage of objects of type TValue. In addition to BasicTypedCacheInterface constraints, we require TValue::ContentSlice() to return persistable data. This simplifies usage for the normal case of simple secondary cache compatibility (can give you a Slice to the data already in memory). In addition to TCreateContext performing the role of Cache::CreateContext, it is also expected to provide a factory function for creating TValue. * For each of these, there's a "Shared" version (e.g. FullTypedSharedCacheInterface) that holds a shared_ptr to the Cache, rather than assuming external ownership by holding only a raw `Cache*`. These interfaces introduce specific handle types for each interface instantiation, so that it's easy to see what kind of object is controlled by a handle. (Ultimately, this might not be worth the extra complexity, but it seems OK so far.) Note: I attempted to make the cache 'charge' automatically inferred from the cache object type, such as by expecting an ApproximateMemoryUsage() function, but this is not so clean because there are cases where we need to compute the charge ahead of time and don't want to re-compute it. ## block_cache.h This header is essentially the replacement for the old block_like_traits.h. It includes various things to support block cache access with typed_cache.h for block-based table. ## block_based_table_reader.cc Before this change, accessing the block cache here was an awkward mix of static polymorphism (template TBlocklike) and switch-case on a dynamic BlockType value. This change mostly unifies on static polymorphism, relying on minor hacks in block_cache.h to distinguish variants of Block. We still check BlockType in some places (especially for stats, which could be improved in follow-up work) but at least the BlockType is a static constant from the template parameter. (No more awkward partial redundancy between static and dynamic info.) This likely contributes to the overall performance improvement, but hasn't been tested in isolation. The other key source of simplification here is a more unified system of creating block cache objects: for directly populating from primary cache and for promotion from secondary cache. Both use BlockCreateContext, for context and for factory functions. ## block_based_table_builder.cc, cache_dump_load_impl.cc Before this change, warming caches was super ugly code. Both of these source files had switch statements to basically transition from the dynamic BlockType world to the static TBlocklike world. None of that mess is needed anymore as there's a new, untyped WarmInCache function that handles all the details just as promotion from SecondaryCache would. (Fixes `TODO akanksha: Dedup below code` in block_based_table_builder.cc.) ## Everything else Mostly just updating Cache users to use new typed APIs when reasonably possible, or changed Cache APIs when not. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10975 Test Plan: tests updated Performance test setup similar to https://github.com/facebook/rocksdb/issues/10626 (by cache size, LRUCache when not "hyper" for HyperClockCache): 34MB 1thread base.hyper -> kops/s: 0.745 io_bytes/op: 2.52504e+06 miss_ratio: 0.140906 max_rss_mb: 76.4844 34MB 1thread new.hyper -> kops/s: 0.751 io_bytes/op: 2.5123e+06 miss_ratio: 0.140161 max_rss_mb: 79.3594 34MB 1thread base -> kops/s: 0.254 io_bytes/op: 1.36073e+07 miss_ratio: 0.918818 max_rss_mb: 45.9297 34MB 1thread new -> kops/s: 0.252 io_bytes/op: 1.36157e+07 miss_ratio: 0.918999 max_rss_mb: 44.1523 34MB 32thread base.hyper -> kops/s: 7.272 io_bytes/op: 2.88323e+06 miss_ratio: 0.162532 max_rss_mb: 516.602 34MB 32thread new.hyper -> kops/s: 7.214 io_bytes/op: 2.99046e+06 miss_ratio: 0.168818 max_rss_mb: 518.293 34MB 32thread base -> kops/s: 3.528 io_bytes/op: 1.35722e+07 miss_ratio: 0.914691 max_rss_mb: 264.926 34MB 32thread new -> kops/s: 3.604 io_bytes/op: 1.35744e+07 miss_ratio: 0.915054 max_rss_mb: 264.488 233MB 1thread base.hyper -> kops/s: 53.909 io_bytes/op: 2552.35 miss_ratio: 0.0440566 max_rss_mb: 241.984 233MB 1thread new.hyper -> kops/s: 62.792 io_bytes/op: 2549.79 miss_ratio: 0.044043 max_rss_mb: 241.922 233MB 1thread base -> kops/s: 1.197 io_bytes/op: 2.75173e+06 miss_ratio: 0.103093 max_rss_mb: 241.559 233MB 1thread new -> kops/s: 1.199 io_bytes/op: 2.73723e+06 miss_ratio: 0.10305 max_rss_mb: 240.93 233MB 32thread base.hyper -> kops/s: 1298.69 io_bytes/op: 2539.12 miss_ratio: 0.0440307 max_rss_mb: 371.418 233MB 32thread new.hyper -> kops/s: 1421.35 io_bytes/op: 2538.75 miss_ratio: 0.0440307 max_rss_mb: 347.273 233MB 32thread base -> kops/s: 9.693 io_bytes/op: 2.77304e+06 miss_ratio: 0.103745 max_rss_mb: 569.691 233MB 32thread new -> kops/s: 9.75 io_bytes/op: 2.77559e+06 miss_ratio: 0.103798 max_rss_mb: 552.82 1597MB 1thread base.hyper -> kops/s: 58.607 io_bytes/op: 1449.14 miss_ratio: 0.0249324 max_rss_mb: 1583.55 1597MB 1thread new.hyper -> kops/s: 69.6 io_bytes/op: 1434.89 miss_ratio: 0.0247167 max_rss_mb: 1584.02 1597MB 1thread base -> kops/s: 60.478 io_bytes/op: 1421.28 miss_ratio: 0.024452 max_rss_mb: 1589.45 1597MB 1thread new -> kops/s: 63.973 io_bytes/op: 1416.07 miss_ratio: 0.0243766 max_rss_mb: 1589.24 1597MB 32thread base.hyper -> kops/s: 1436.2 io_bytes/op: 1357.93 miss_ratio: 0.0235353 max_rss_mb: 1692.92 1597MB 32thread new.hyper -> kops/s: 1605.03 io_bytes/op: 1358.04 miss_ratio: 0.023538 max_rss_mb: 1702.78 1597MB 32thread base -> kops/s: 280.059 io_bytes/op: 1350.34 miss_ratio: 0.023289 max_rss_mb: 1675.36 1597MB 32thread new -> kops/s: 283.125 io_bytes/op: 1351.05 miss_ratio: 0.0232797 max_rss_mb: 1703.83 Almost uniformly improving over base revision, especially for hot paths with HyperClockCache, up to 12% higher throughput seen (1597MB, 32thread, hyper). The improvement for that is likely coming from much simplified code for providing context for secondary cache promotion (CreateCallback/CreateContext), and possibly from less branching in block_based_table_reader. And likely a small improvement from not reconstituting key for DeleterFn. Reviewed By: anand1976 Differential Revision: D42417818 Pulled By: pdillinger fbshipit-source-id: f86bfdd584dce27c028b151ba56818ad14f7a432
2023-01-11 22:20:40 +00:00
static const Cache::CacheItemHelper* kCrmHelper;
Rewrite memory-charging feature's option API (#9926) Summary: **Context:** Previous PR https://github.com/facebook/rocksdb/pull/9748, https://github.com/facebook/rocksdb/pull/9073, https://github.com/facebook/rocksdb/pull/8428 added separate flag for each charged memory area. Such API design is not scalable as we charge more and more memory areas. Also, we foresee an opportunity to consolidate this feature with other cache usage related features such as `cache_index_and_filter_blocks` using `CacheEntryRole`. Therefore we decided to consolidate all these flags with `CacheUsageOptions cache_usage_options` and this PR serves as the first step by consolidating memory-charging related flags. **Summary:** - Replaced old API reference with new ones, including making `kCompressionDictionaryBuildingBuffer` opt-out and added a unit test for that - Added missing db bench/stress test for some memory charging features - Renamed related test suite to indicate they are under the same theme of memory charging - Refactored a commonly used mocked cache component in memory charging related tests to reduce code duplication - Replaced the phrases "memory tracking" / "cache reservation" (other than CacheReservationManager-related ones) with "memory charging" for standard description of this feature. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9926 Test Plan: - New unit test for opt-out `kCompressionDictionaryBuildingBuffer` `TEST_F(ChargeCompressionDictionaryBuildingBufferTest, Basic)` - New unit test for option validation/sanitization `TEST_F(CacheUsageOptionsOverridesTest, SanitizeAndValidateOptions)` - CI - db bench (in case querying new options introduces regression) **+0.5% micros/op**: `TEST_TMPDIR=/dev/shm/testdb ./db_bench -benchmarks=fillseq -db=$TEST_TMPDIR -charge_compression_dictionary_building_buffer=1(remove this for comparison) -compression_max_dict_bytes=10000 -disable_auto_compactions=1 -write_buffer_size=100000 -num=4000000 | egrep 'fillseq'` #-run | (pre-PR) avg micros/op | std micros/op | (post-PR) micros/op | std micros/op | change (%) -- | -- | -- | -- | -- | -- 10 | 3.9711 | 0.264408 | 3.9914 | 0.254563 | 0.5111933721 20 | 3.83905 | 0.0664488 | 3.8251 | 0.0695456 | **-0.3633711465** 40 | 3.86625 | 0.136669 | 3.8867 | 0.143765 | **0.5289363078** - db_stress: `python3 tools/db_crashtest.py blackbox -charge_compression_dictionary_building_buffer=1 -charge_filter_construction=1 -charge_table_reader=1 -cache_size=1` killed as normal Reviewed By: ajkr Differential Revision: D36054712 Pulled By: hx235 fbshipit-source-id: d406e90f5e0c5ea4dbcb585a484ad9302d4302af
2022-05-17 22:01:51 +00:00
std::size_t cur_cache_charge_;
std::size_t cache_charge_peak_;
std::size_t cache_charge_increment_;
bool last_peak_tracked_;
std::deque<std::size_t> cache_charge_peaks_;
std::size_t cache_charge_increments_sum_;
};
class DBTestBase : public testing::Test {
public:
// Sequence of option configurations to try
enum OptionConfig : int {
kDefault = 0,
kBlockBasedTableWithPrefixHashIndex = 1,
kBlockBasedTableWithWholeKeyHashIndex = 2,
kPlainTableFirstBytePrefix = 3,
kPlainTableCappedPrefix = 4,
kPlainTableCappedPrefixNonMmap = 5,
kPlainTableAllBytesPrefix = 6,
kVectorRep = 7,
kHashLinkList = 8,
kMergePut = 9,
kFilter = 10,
kFullFilterWithNewTableReaderForCompactions = 11,
kUncompressed = 12,
kNumLevel_3 = 13,
kDBLogDir = 14,
kWalDirAndMmapReads = 15,
kManifestFileSize = 16,
kPerfOptions = 17,
kHashSkipList = 18,
kUniversalCompaction = 19,
kUniversalCompactionMultiLevel = 20,
kInfiniteMaxOpenFiles = 21,
kCRC32cChecksum = 22,
kFIFOCompaction = 23,
kOptimizeFiltersForHits = 24,
kRowCache = 25,
kRecycleLogFiles = 26,
kConcurrentSkipList = 27,
kPipelinedWrite = 28,
kConcurrentWALWrites = 29,
kDirectIO,
kLevelSubcompactions,
kBlockBasedTableWithIndexRestartInterval,
kBlockBasedTableWithPartitionedIndex,
kBlockBasedTableWithPartitionedIndexFormat4,
kBlockBasedTableWithLatestFormat,
kPartitionedFilterWithNewTableReaderForCompactions,
kUniversalSubcompactions,
Unordered Writes (#5218) Summary: Performing unordered writes in rocksdb when unordered_write option is set to true. When enabled the writes to memtable are done without joining any write thread. This offers much higher write throughput since the upcoming writes would not have to wait for the slowest memtable write to finish. The tradeoff is that the writes visible to a snapshot might change over time. If the application cannot tolerate that, it should implement its own mechanisms to work around that. Using TransactionDB with WRITE_PREPARED write policy is one way to achieve that. Doing so increases the max throughput by 2.2x without however compromising the snapshot guarantees. The patch is prepared based on an original by siying Existing unit tests are extended to include unordered_write option. Benchmark Results: ``` TEST_TMPDIR=/dev/shm/ ./db_bench_unordered --benchmarks=fillrandom --threads=32 --num=10000000 -max_write_buffer_number=16 --max_background_jobs=64 --batch_size=8 --writes=3000000 -level0_file_num_compaction_trigger=99999 --level0_slowdown_writes_trigger=99999 --level0_stop_writes_trigger=99999 -enable_pipelined_write=false -disable_auto_compactions --unordered_write=1 ``` With WAL - Vanilla RocksDB: 78.6 MB/s - WRITER_PREPARED with unordered_write: 177.8 MB/s (2.2x) - unordered_write: 368.9 MB/s (4.7x with relaxed snapshot guarantees) Without WAL - Vanilla RocksDB: 111.3 MB/s - WRITER_PREPARED with unordered_write: 259.3 MB/s MB/s (2.3x) - unordered_write: 645.6 MB/s (5.8x with relaxed snapshot guarantees) - WRITER_PREPARED with unordered_write disable concurrency control: 185.3 MB/s MB/s (2.35x) Limitations: - The feature is not yet extended to `max_successive_merges` > 0. The feature is also incompatible with `enable_pipelined_write` = true as well as with `allow_concurrent_memtable_write` = false. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5218 Differential Revision: D15219029 Pulled By: maysamyabandeh fbshipit-source-id: 38f2abc4af8780148c6128acdba2b3227bc81759
2019-05-14 00:43:47 +00:00
kUnorderedWrite,
kBlockBasedTableWithBinarySearchWithFirstKeyIndex,
// This must be the last line
kEnd,
};
public:
std::string dbname_;
std::string alternative_wal_dir_;
std::string alternative_db_log_dir_;
MockEnv* mem_env_;
Encryption at rest support Summary: This PR adds support for encrypting data stored by RocksDB when written to disk. It adds an `EncryptedEnv` override of the `Env` class with matching overrides for sequential&random access files. The encryption itself is done through a configurable `EncryptionProvider`. This class creates is asked to create `BlockAccessCipherStream` for a file. This is where the actual encryption/decryption is being done. Currently there is a Counter mode implementation of `BlockAccessCipherStream` with a `ROT13` block cipher (NOTE the `ROT13` is for demo purposes only!!). The Counter operation mode uses an initial counter & random initialization vector (IV). Both are created randomly for each file and stored in a 4K (default size) block that is prefixed to that file. The `EncryptedEnv` implementation is such that clients of the `Env` class do not see this prefix (nor data, nor in filesize). The largest part of the prefix block is also encrypted, and there is room left for implementation specific settings/values/keys in there. To test the encryption, the `DBTestBase` class has been extended to consider a new environment variable called `ENCRYPTED_ENV`. If set, the test will setup a encrypted instance of the `Env` class to use for all tests. Typically you would run it like this: ``` ENCRYPTED_ENV=1 make check_some ``` There is also an added test that checks that some data inserted into the database is or is not "visible" on disk. With `ENCRYPTED_ENV` active it must not find plain text strings, with `ENCRYPTED_ENV` unset, it must find the plain text strings. Closes https://github.com/facebook/rocksdb/pull/2424 Differential Revision: D5322178 Pulled By: sdwilsh fbshipit-source-id: 253b0a9c2c498cc98f580df7f2623cbf7678a27f
2017-06-26 23:52:06 +00:00
Env* encrypted_env_;
SpecialEnv* env_;
std::shared_ptr<Env> env_guard_;
DB* db_;
std::vector<ColumnFamilyHandle*> handles_;
int option_config_;
Options last_options_;
// Skip some options, as they may not be applicable to a specific test.
// To add more skip constants, use values 4, 8, 16, etc.
enum OptionSkip {
kNoSkip = 0,
kSkipDeletesFilterFirst = 1,
kSkipUniversalCompaction = 2,
kSkipMergePut = 4,
kSkipPlainTable = 8,
kSkipHashIndex = 16,
kSkipNoSeekToLast = 32,
kSkipFIFOCompaction = 128,
kSkipMmapReads = 256,
kSkipRowCache = 512,
};
const int kRangeDelSkipConfigs =
// Plain tables do not support range deletions.
kSkipPlainTable |
// MmapReads disables the iterator pinning that RangeDelAggregator
// requires.
kSkipMmapReads |
// Not compatible yet.
kSkipRowCache;
// `env_do_fsync` decides whether the special Env would do real
// fsync for files and directories. Skipping fsync can speed up
// tests, but won't cover the exact fsync logic.
DBTestBase(const std::string path, bool env_do_fsync);
~DBTestBase();
static std::string Key(int i) {
char buf[100];
snprintf(buf, sizeof(buf), "key%06d", i);
return std::string(buf);
}
static bool ShouldSkipOptions(int option_config, int skip_mask = kNoSkip);
// Switch to a fresh database with the next option configuration to
// test. Return false if there are no more configurations to test.
bool ChangeOptions(int skip_mask = kNoSkip);
// Switch between different compaction styles.
bool ChangeCompactOptions();
// Switch between different WAL-realted options.
bool ChangeWalOptions();
// Switch between different filter policy
// Jump from kDefault to kFilter to kFullFilter
bool ChangeFilterOptions();
// Switch between different DB options for file ingestion tests.
bool ChangeOptionsForFileIngestionTest();
// Return the current option configuration.
Options CurrentOptions(const anon::OptionsOverride& options_override =
anon::OptionsOverride()) const;
Options CurrentOptions(const Options& default_options,
const anon::OptionsOverride& options_override =
anon::OptionsOverride()) const;
Fix many tests to run with MEM_ENV and ENCRYPTED_ENV; Introduce a MemoryFileSystem class (#7566) Summary: This PR does a few things: 1. The MockFileSystem class was split out from the MockEnv. This change would theoretically allow a MockFileSystem to be used by other Environments as well (if we created a means of constructing one). The MockFileSystem implements a FileSystem in its entirety and does not rely on any Wrapper implementation. 2. Make the RocksDB test suite work when MOCK_ENV=1 and ENCRYPTED_ENV=1 are set. To accomplish this, a few things were needed: - The tests that tried to use the "wrong" environment (Env::Default() instead of env_) were updated - The MockFileSystem was changed to support the features it was missing or mishandled (such as recursively deleting files in a directory or supporting renaming of a directory). 3. Updated the test framework to have a ROCKSDB_GTEST_SKIP macro. This can be used to flag tests that are skipped. Currently, this defaults to doing nothing (marks the test as SUCCESS) but will mark the tests as SKIPPED when RocksDB is upgraded to a version of gtest that supports this (gtest-1.10). I have run a full "make check" with MEM_ENV, ENCRYPTED_ENV, both, and neither under both MacOS and RedHat. A few tests were disabled/skipped for the MEM/ENCRYPTED cases. The error_handler_fs_test fails/hangs for MEM_ENV (presumably a timing problem) and I will introduce another PR/issue to track that problem. (I will also push a change to disable those tests soon). There is one more test in DBTest2 that also fails which I need to investigate or skip before this PR is merged. Theoretically, this PR should also allow the test suite to run against an Env loaded from the registry, though I do not have one to try it with currently. Finally, once this is accepted, it would be nice if there was a CircleCI job to run these tests on a checkin so this effort does not become stale. I do not know how to do that, so if someone could write that job, it would be appreciated :) Pull Request resolved: https://github.com/facebook/rocksdb/pull/7566 Reviewed By: zhichao-cao Differential Revision: D24408980 Pulled By: jay-zhuang fbshipit-source-id: 911b1554a4d0da06fd51feca0c090a4abdcb4a5f
2020-10-27 17:31:34 +00:00
Options GetDefaultOptions() const;
Fix many tests to run with MEM_ENV and ENCRYPTED_ENV; Introduce a MemoryFileSystem class (#7566) Summary: This PR does a few things: 1. The MockFileSystem class was split out from the MockEnv. This change would theoretically allow a MockFileSystem to be used by other Environments as well (if we created a means of constructing one). The MockFileSystem implements a FileSystem in its entirety and does not rely on any Wrapper implementation. 2. Make the RocksDB test suite work when MOCK_ENV=1 and ENCRYPTED_ENV=1 are set. To accomplish this, a few things were needed: - The tests that tried to use the "wrong" environment (Env::Default() instead of env_) were updated - The MockFileSystem was changed to support the features it was missing or mishandled (such as recursively deleting files in a directory or supporting renaming of a directory). 3. Updated the test framework to have a ROCKSDB_GTEST_SKIP macro. This can be used to flag tests that are skipped. Currently, this defaults to doing nothing (marks the test as SUCCESS) but will mark the tests as SKIPPED when RocksDB is upgraded to a version of gtest that supports this (gtest-1.10). I have run a full "make check" with MEM_ENV, ENCRYPTED_ENV, both, and neither under both MacOS and RedHat. A few tests were disabled/skipped for the MEM/ENCRYPTED cases. The error_handler_fs_test fails/hangs for MEM_ENV (presumably a timing problem) and I will introduce another PR/issue to track that problem. (I will also push a change to disable those tests soon). There is one more test in DBTest2 that also fails which I need to investigate or skip before this PR is merged. Theoretically, this PR should also allow the test suite to run against an Env loaded from the registry, though I do not have one to try it with currently. Finally, once this is accepted, it would be nice if there was a CircleCI job to run these tests on a checkin so this effort does not become stale. I do not know how to do that, so if someone could write that job, it would be appreciated :) Pull Request resolved: https://github.com/facebook/rocksdb/pull/7566 Reviewed By: zhichao-cao Differential Revision: D24408980 Pulled By: jay-zhuang fbshipit-source-id: 911b1554a4d0da06fd51feca0c090a4abdcb4a5f
2020-10-27 17:31:34 +00:00
Options GetOptions(int option_config) const {
return GetOptions(option_config, GetDefaultOptions());
}
Options GetOptions(int option_config, const Options& default_options,
const anon::OptionsOverride& options_override =
anon::OptionsOverride()) const;
DBImpl* dbfull() { return static_cast_with_check<DBImpl>(db_); }
void CreateColumnFamilies(const std::vector<std::string>& cfs,
const Options& options);
void CreateAndReopenWithCF(const std::vector<std::string>& cfs,
const Options& options);
void ReopenWithColumnFamilies(const std::vector<std::string>& cfs,
const std::vector<Options>& options);
void ReopenWithColumnFamilies(const std::vector<std::string>& cfs,
const Options& options);
Status TryReopenWithColumnFamilies(const std::vector<std::string>& cfs,
const std::vector<Options>& options);
Status TryReopenWithColumnFamilies(const std::vector<std::string>& cfs,
const Options& options);
void Reopen(const Options& options);
void Close();
void DestroyAndReopen(const Options& options);
void Destroy(const Options& options, bool delete_cf_paths = false);
Status ReadOnlyReopen(const Options& options);
Status TryReopen(const Options& options);
bool IsDirectIOSupported();
Encryption at rest support Summary: This PR adds support for encrypting data stored by RocksDB when written to disk. It adds an `EncryptedEnv` override of the `Env` class with matching overrides for sequential&random access files. The encryption itself is done through a configurable `EncryptionProvider`. This class creates is asked to create `BlockAccessCipherStream` for a file. This is where the actual encryption/decryption is being done. Currently there is a Counter mode implementation of `BlockAccessCipherStream` with a `ROT13` block cipher (NOTE the `ROT13` is for demo purposes only!!). The Counter operation mode uses an initial counter & random initialization vector (IV). Both are created randomly for each file and stored in a 4K (default size) block that is prefixed to that file. The `EncryptedEnv` implementation is such that clients of the `Env` class do not see this prefix (nor data, nor in filesize). The largest part of the prefix block is also encrypted, and there is room left for implementation specific settings/values/keys in there. To test the encryption, the `DBTestBase` class has been extended to consider a new environment variable called `ENCRYPTED_ENV`. If set, the test will setup a encrypted instance of the `Env` class to use for all tests. Typically you would run it like this: ``` ENCRYPTED_ENV=1 make check_some ``` There is also an added test that checks that some data inserted into the database is or is not "visible" on disk. With `ENCRYPTED_ENV` active it must not find plain text strings, with `ENCRYPTED_ENV` unset, it must find the plain text strings. Closes https://github.com/facebook/rocksdb/pull/2424 Differential Revision: D5322178 Pulled By: sdwilsh fbshipit-source-id: 253b0a9c2c498cc98f580df7f2623cbf7678a27f
2017-06-26 23:52:06 +00:00
bool IsMemoryMappedAccessSupported() const;
Status Flush(int cf = 0);
Status Flush(const std::vector<int>& cf_ids);
Status Put(const Slice& k, const Slice& v, WriteOptions wo = WriteOptions());
Status Put(int cf, const Slice& k, const Slice& v,
WriteOptions wo = WriteOptions());
Status TimedPut(const Slice& k, const Slice& v, uint64_t write_unix_time,
WriteOptions wo = WriteOptions());
Add initial support for TimedPut API (#12419) Summary: This PR adds support for `TimedPut` API. We introduced a new type `kTypeValuePreferredSeqno` for entries added to the DB via the `TimedPut` API. The life cycle of such an entry on the write/flush/compaction paths are: 1) It is initially added to memtable as: `<user_key, seq, kTypeValuePreferredSeqno>: {value, write_unix_time}` 2) When it's flushed to L0 sst files, it's converted to: `<user_key, seq, kTypeValuePreferredSeqno>: {value, preferred_seqno}` when we have easy access to the seqno to time mapping. 3) During compaction, if certain conditions are met, we swap in the `preferred_seqno` and the entry will become: `<user_key, preferred_seqno, kTypeValue>: value`. This step helps fast track these entries to the cold tier if they are eligible after the sequence number swap. On the read path: A `kTypeValuePreferredSeqno` entry acts the same as a `kTypeValue` entry, the unix_write_time/preferred seqno part packed in value is completely ignored. Needed follow ups: 1) The seqno to time mapping accessible in flush needs to be extended to cover the `write_unix_time` for possible `kTypeValuePreferredSeqno` entries. This also means we need to track these `write_unix_time` in memtable. 2) Compaction filter support for the new `kTypeValuePreferredSeqno` type for feature parity with other `kTypeValue` and equivalent types. 3) Stress test coverage for the feature Pull Request resolved: https://github.com/facebook/rocksdb/pull/12419 Test Plan: Added unit tests Reviewed By: pdillinger Differential Revision: D54920296 Pulled By: jowlyzhang fbshipit-source-id: c8b43f7a7c465e569141770e93c748371ff1da9e
2024-03-14 22:44:55 +00:00
Status TimedPut(int cf, const Slice& k, const Slice& v,
uint64_t write_unix_time, WriteOptions wo = WriteOptions());
Status Merge(const Slice& k, const Slice& v,
WriteOptions wo = WriteOptions());
Status Merge(int cf, const Slice& k, const Slice& v,
WriteOptions wo = WriteOptions());
Status Delete(const std::string& k);
Status Delete(int cf, const std::string& k);
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 18:42:56 +00:00
Status SingleDelete(const std::string& k);
Status SingleDelete(int cf, const std::string& k);
std::string Get(const std::string& k, const Snapshot* snapshot = nullptr);
std::string Get(int cf, const std::string& k,
const Snapshot* snapshot = nullptr);
Status Get(const std::string& k, PinnableSlice* v);
std::vector<std::string> MultiGet(std::vector<int> cfs,
const std::vector<std::string>& k,
const Snapshot* snapshot,
Multi file concurrency in MultiGet using coroutines and async IO (#9968) Summary: This PR implements a coroutine version of batched MultiGet in order to concurrently read from multiple SST files in a level using async IO, thus reducing the latency of the MultiGet. The API from the user perspective is still synchronous and single threaded, with the RocksDB part of the processing happening in the context of the caller's thread. In Version::MultiGet, the decision is made whether to call synchronous or coroutine code. A good way to review this PR is to review the first 4 commits in order - de773b3, 70c2f70, 10b50e1, and 377a597 - before reviewing the rest. TODO: 1. Figure out how to build it in CircleCI (requires some dependencies to be installed) 2. Do some stress testing with coroutines enabled No regression in synchronous MultiGet between this branch and main - ``` ./db_bench -use_existing_db=true --db=/data/mysql/rocksdb/prefix_scan -benchmarks="readseq,multireadrandom" -key_size=32 -value_size=512 -num=5000000 -batch_size=64 -multiread_batched=true -use_direct_reads=false -duration=60 -ops_between_duration_checks=1 -readonly=true -adaptive_readahead=true -threads=16 -cache_size=10485760000 -async_io=false -multiread_stride=40000 -statistics ``` Branch - ```multireadrandom : 4.025 micros/op 3975111 ops/sec 60.001 seconds 238509056 operations; 2062.3 MB/s (14767808 of 14767808 found)``` Main - ```multireadrandom : 3.987 micros/op 4013216 ops/sec 60.001 seconds 240795392 operations; 2082.1 MB/s (15231040 of 15231040 found)``` More benchmarks in various scenarios are given below. The measurements were taken with ```async_io=false``` (no coroutines) and ```async_io=true``` (use coroutines). For an IO bound workload (with every key requiring an IO), the coroutines version shows a clear benefit, being ~2.6X faster. For CPU bound workloads, the coroutines version has ~6-15% higher CPU utilization, depending on how many keys overlap an SST file. 1. Single thread IO bound workload on remote storage with sparse MultiGet batch keys (~1 key overlap/file) - No coroutines - ```multireadrandom : 831.774 micros/op 1202 ops/sec 60.001 seconds 72136 operations; 0.6 MB/s (72136 of 72136 found)``` Using coroutines - ```multireadrandom : 318.742 micros/op 3137 ops/sec 60.003 seconds 188248 operations; 1.6 MB/s (188248 of 188248 found)``` 2. Single thread CPU bound workload (all data cached) with ~1 key overlap/file - No coroutines - ```multireadrandom : 4.127 micros/op 242322 ops/sec 60.000 seconds 14539384 operations; 125.7 MB/s (14539384 of 14539384 found)``` Using coroutines - ```multireadrandom : 4.741 micros/op 210935 ops/sec 60.000 seconds 12656176 operations; 109.4 MB/s (12656176 of 12656176 found)``` 3. Single thread CPU bound workload with ~2 key overlap/file - No coroutines - ```multireadrandom : 3.717 micros/op 269000 ops/sec 60.000 seconds 16140024 operations; 139.6 MB/s (16140024 of 16140024 found)``` Using coroutines - ```multireadrandom : 4.146 micros/op 241204 ops/sec 60.000 seconds 14472296 operations; 125.1 MB/s (14472296 of 14472296 found)``` 4. CPU bound multi-threaded (16 threads) with ~4 key overlap/file - No coroutines - ```multireadrandom : 4.534 micros/op 3528792 ops/sec 60.000 seconds 211728728 operations; 1830.7 MB/s (12737024 of 12737024 found) ``` Using coroutines - ```multireadrandom : 4.872 micros/op 3283812 ops/sec 60.000 seconds 197030096 operations; 1703.6 MB/s (12548032 of 12548032 found) ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/9968 Reviewed By: akankshamahajan15 Differential Revision: D36348563 Pulled By: anand1976 fbshipit-source-id: c0ce85a505fd26ebfbb09786cbd7f25202038696
2022-05-19 22:36:27 +00:00
const bool batched,
const bool async = false);
Introduce a new MultiGet batching implementation (#5011) Summary: This PR introduces a new MultiGet() API, with the underlying implementation grouping keys based on SST file and batching lookups in a file. The reason for the new API is twofold - the definition allows callers to allocate storage for status and values on stack instead of std::vector, as well as return values as PinnableSlices in order to avoid copying, and it keeps the original MultiGet() implementation intact while we experiment with batching. Batching is useful when there is some spatial locality to the keys being queries, as well as larger batch sizes. The main benefits are due to - 1. Fewer function calls, especially to BlockBasedTableReader::MultiGet() and FullFilterBlockReader::KeysMayMatch() 2. Bloom filter cachelines can be prefetched, hiding the cache miss latency The next step is to optimize the binary searches in the level_storage_info, index blocks and data blocks, since we could reduce the number of key comparisons if the keys are relatively close to each other. The batching optimizations also need to be extended to other formats, such as PlainTable and filter formats. This also needs to be added to db_stress. Benchmark results from db_bench for various batch size/locality of reference combinations are given below. Locality was simulated by offsetting the keys in a batch by a stride length. Each SST file is about 8.6MB uncompressed and key/value size is 16/100 uncompressed. To focus on the cpu benefit of batching, the runs were single threaded and bound to the same cpu to eliminate interference from other system events. The results show a 10-25% improvement in micros/op from smaller to larger batch sizes (4 - 32). Batch Sizes 1 | 2 | 4 | 8 | 16 | 32 Random pattern (Stride length 0) 4.158 | 4.109 | 4.026 | 4.05 | 4.1 | 4.074 - Get 4.438 | 4.302 | 4.165 | 4.122 | 4.096 | 4.075 - MultiGet (no batching) 4.461 | 4.256 | 4.277 | 4.11 | 4.182 | 4.14 - MultiGet (w/ batching) Good locality (Stride length 16) 4.048 | 3.659 | 3.248 | 2.99 | 2.84 | 2.753 4.429 | 3.728 | 3.406 | 3.053 | 2.911 | 2.781 4.452 | 3.45 | 2.833 | 2.451 | 2.233 | 2.135 Good locality (Stride length 256) 4.066 | 3.786 | 3.581 | 3.447 | 3.415 | 3.232 4.406 | 4.005 | 3.644 | 3.49 | 3.381 | 3.268 4.393 | 3.649 | 3.186 | 2.882 | 2.676 | 2.62 Medium locality (Stride length 4096) 4.012 | 3.922 | 3.768 | 3.61 | 3.582 | 3.555 4.364 | 4.057 | 3.791 | 3.65 | 3.57 | 3.465 4.479 | 3.758 | 3.316 | 3.077 | 2.959 | 2.891 dbbench command used (on a DB with 4 levels, 12 million keys)- TEST_TMPDIR=/dev/shm numactl -C 10 ./db_bench.tmp -use_existing_db=true -benchmarks="readseq,multireadrandom" -write_buffer_size=4194304 -target_file_size_base=4194304 -max_bytes_for_level_base=16777216 -num=12000000 -reads=12000000 -duration=90 -threads=1 -compression_type=none -cache_size=4194304000 -batch_size=32 -disable_auto_compactions=true -bloom_bits=10 -cache_index_and_filter_blocks=true -pin_l0_filter_and_index_blocks_in_cache=true -multiread_batched=true -multiread_stride=4 Pull Request resolved: https://github.com/facebook/rocksdb/pull/5011 Differential Revision: D14348703 Pulled By: anand1976 fbshipit-source-id: 774406dab3776d979c809522a67bedac6c17f84b
2019-04-11 21:24:09 +00:00
std::vector<std::string> MultiGet(const std::vector<std::string>& k,
Multi file concurrency in MultiGet using coroutines and async IO (#9968) Summary: This PR implements a coroutine version of batched MultiGet in order to concurrently read from multiple SST files in a level using async IO, thus reducing the latency of the MultiGet. The API from the user perspective is still synchronous and single threaded, with the RocksDB part of the processing happening in the context of the caller's thread. In Version::MultiGet, the decision is made whether to call synchronous or coroutine code. A good way to review this PR is to review the first 4 commits in order - de773b3, 70c2f70, 10b50e1, and 377a597 - before reviewing the rest. TODO: 1. Figure out how to build it in CircleCI (requires some dependencies to be installed) 2. Do some stress testing with coroutines enabled No regression in synchronous MultiGet between this branch and main - ``` ./db_bench -use_existing_db=true --db=/data/mysql/rocksdb/prefix_scan -benchmarks="readseq,multireadrandom" -key_size=32 -value_size=512 -num=5000000 -batch_size=64 -multiread_batched=true -use_direct_reads=false -duration=60 -ops_between_duration_checks=1 -readonly=true -adaptive_readahead=true -threads=16 -cache_size=10485760000 -async_io=false -multiread_stride=40000 -statistics ``` Branch - ```multireadrandom : 4.025 micros/op 3975111 ops/sec 60.001 seconds 238509056 operations; 2062.3 MB/s (14767808 of 14767808 found)``` Main - ```multireadrandom : 3.987 micros/op 4013216 ops/sec 60.001 seconds 240795392 operations; 2082.1 MB/s (15231040 of 15231040 found)``` More benchmarks in various scenarios are given below. The measurements were taken with ```async_io=false``` (no coroutines) and ```async_io=true``` (use coroutines). For an IO bound workload (with every key requiring an IO), the coroutines version shows a clear benefit, being ~2.6X faster. For CPU bound workloads, the coroutines version has ~6-15% higher CPU utilization, depending on how many keys overlap an SST file. 1. Single thread IO bound workload on remote storage with sparse MultiGet batch keys (~1 key overlap/file) - No coroutines - ```multireadrandom : 831.774 micros/op 1202 ops/sec 60.001 seconds 72136 operations; 0.6 MB/s (72136 of 72136 found)``` Using coroutines - ```multireadrandom : 318.742 micros/op 3137 ops/sec 60.003 seconds 188248 operations; 1.6 MB/s (188248 of 188248 found)``` 2. Single thread CPU bound workload (all data cached) with ~1 key overlap/file - No coroutines - ```multireadrandom : 4.127 micros/op 242322 ops/sec 60.000 seconds 14539384 operations; 125.7 MB/s (14539384 of 14539384 found)``` Using coroutines - ```multireadrandom : 4.741 micros/op 210935 ops/sec 60.000 seconds 12656176 operations; 109.4 MB/s (12656176 of 12656176 found)``` 3. Single thread CPU bound workload with ~2 key overlap/file - No coroutines - ```multireadrandom : 3.717 micros/op 269000 ops/sec 60.000 seconds 16140024 operations; 139.6 MB/s (16140024 of 16140024 found)``` Using coroutines - ```multireadrandom : 4.146 micros/op 241204 ops/sec 60.000 seconds 14472296 operations; 125.1 MB/s (14472296 of 14472296 found)``` 4. CPU bound multi-threaded (16 threads) with ~4 key overlap/file - No coroutines - ```multireadrandom : 4.534 micros/op 3528792 ops/sec 60.000 seconds 211728728 operations; 1830.7 MB/s (12737024 of 12737024 found) ``` Using coroutines - ```multireadrandom : 4.872 micros/op 3283812 ops/sec 60.000 seconds 197030096 operations; 1703.6 MB/s (12548032 of 12548032 found) ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/9968 Reviewed By: akankshamahajan15 Differential Revision: D36348563 Pulled By: anand1976 fbshipit-source-id: c0ce85a505fd26ebfbb09786cbd7f25202038696
2022-05-19 22:36:27 +00:00
const Snapshot* snapshot = nullptr,
const bool async = false);
Introduce a new MultiGet batching implementation (#5011) Summary: This PR introduces a new MultiGet() API, with the underlying implementation grouping keys based on SST file and batching lookups in a file. The reason for the new API is twofold - the definition allows callers to allocate storage for status and values on stack instead of std::vector, as well as return values as PinnableSlices in order to avoid copying, and it keeps the original MultiGet() implementation intact while we experiment with batching. Batching is useful when there is some spatial locality to the keys being queries, as well as larger batch sizes. The main benefits are due to - 1. Fewer function calls, especially to BlockBasedTableReader::MultiGet() and FullFilterBlockReader::KeysMayMatch() 2. Bloom filter cachelines can be prefetched, hiding the cache miss latency The next step is to optimize the binary searches in the level_storage_info, index blocks and data blocks, since we could reduce the number of key comparisons if the keys are relatively close to each other. The batching optimizations also need to be extended to other formats, such as PlainTable and filter formats. This also needs to be added to db_stress. Benchmark results from db_bench for various batch size/locality of reference combinations are given below. Locality was simulated by offsetting the keys in a batch by a stride length. Each SST file is about 8.6MB uncompressed and key/value size is 16/100 uncompressed. To focus on the cpu benefit of batching, the runs were single threaded and bound to the same cpu to eliminate interference from other system events. The results show a 10-25% improvement in micros/op from smaller to larger batch sizes (4 - 32). Batch Sizes 1 | 2 | 4 | 8 | 16 | 32 Random pattern (Stride length 0) 4.158 | 4.109 | 4.026 | 4.05 | 4.1 | 4.074 - Get 4.438 | 4.302 | 4.165 | 4.122 | 4.096 | 4.075 - MultiGet (no batching) 4.461 | 4.256 | 4.277 | 4.11 | 4.182 | 4.14 - MultiGet (w/ batching) Good locality (Stride length 16) 4.048 | 3.659 | 3.248 | 2.99 | 2.84 | 2.753 4.429 | 3.728 | 3.406 | 3.053 | 2.911 | 2.781 4.452 | 3.45 | 2.833 | 2.451 | 2.233 | 2.135 Good locality (Stride length 256) 4.066 | 3.786 | 3.581 | 3.447 | 3.415 | 3.232 4.406 | 4.005 | 3.644 | 3.49 | 3.381 | 3.268 4.393 | 3.649 | 3.186 | 2.882 | 2.676 | 2.62 Medium locality (Stride length 4096) 4.012 | 3.922 | 3.768 | 3.61 | 3.582 | 3.555 4.364 | 4.057 | 3.791 | 3.65 | 3.57 | 3.465 4.479 | 3.758 | 3.316 | 3.077 | 2.959 | 2.891 dbbench command used (on a DB with 4 levels, 12 million keys)- TEST_TMPDIR=/dev/shm numactl -C 10 ./db_bench.tmp -use_existing_db=true -benchmarks="readseq,multireadrandom" -write_buffer_size=4194304 -target_file_size_base=4194304 -max_bytes_for_level_base=16777216 -num=12000000 -reads=12000000 -duration=90 -threads=1 -compression_type=none -cache_size=4194304000 -batch_size=32 -disable_auto_compactions=true -bloom_bits=10 -cache_index_and_filter_blocks=true -pin_l0_filter_and_index_blocks_in_cache=true -multiread_batched=true -multiread_stride=4 Pull Request resolved: https://github.com/facebook/rocksdb/pull/5011 Differential Revision: D14348703 Pulled By: anand1976 fbshipit-source-id: 774406dab3776d979c809522a67bedac6c17f84b
2019-04-11 21:24:09 +00:00
uint64_t GetNumSnapshots();
uint64_t GetTimeOldestSnapshots();
uint64_t GetSequenceOldestSnapshots();
// Return a string that contains all key,value pairs in order,
// formatted like "(k1->v1)(k2->v2)".
std::string Contents(int cf = 0);
std::string AllEntriesFor(const Slice& user_key, int cf = 0);
// Similar to AllEntriesFor but this function also covers reopen with fifo.
// Note that test cases with snapshots or entries in memtable should simply
// use AllEntriesFor instead as snapshots and entries in memtable will
// survive after db reopen.
void CheckAllEntriesWithFifoReopen(const std::string& expected_value,
const Slice& user_key, int cf,
const std::vector<std::string>& cfs,
const Options& options);
int NumSortedRuns(int cf = 0);
uint64_t TotalSize(int cf = 0);
uint64_t SizeAtLevel(int level);
size_t TotalLiveFiles(int cf = 0);
Fix flaky test `DBTestUniversalManualCompactionOutputPathId.ManualCompactionOutputPathId` (#11412) Summary: the test is flaky when compiled with `make -j56 COERCE_CONTEXT_SWITCH=1 ./db_universal_compaction_test`. The cause is that a manual compaction `CompactRange()` can finish and return before obsolete files are deleted. One reason for this is that a manual compaction waits until `manual.done` is set here https://github.com/facebook/rocksdb/blob/62fc15f009eba86e65f2f7448829429eae9ad071/db/db_impl/db_impl_compaction_flush.cc#L1978 and the compaction thread can set `manual.done`: https://github.com/facebook/rocksdb/blob/62fc15f009eba86e65f2f7448829429eae9ad071/db/db_impl/db_impl_compaction_flush.cc#L3672 and then temporarily release mutex_: https://github.com/facebook/rocksdb/blob/62fc15f009eba86e65f2f7448829429eae9ad071/db/db_impl/db_impl_files.cc#L317 before purging obsolete files: https://github.com/facebook/rocksdb/blob/62fc15f009eba86e65f2f7448829429eae9ad071/db/db_impl/db_impl_compaction_flush.cc#L3144 With `COERCE_CONTEXT_SWITCH=1`, `bg_cv_.SignalAll()` is called during `mutex_.Lock()`, so the manual compaction thread can wake up and return before obsolete files are deleted. Updated the test to only count live SST files. Also updated `FindObsoleteFiles()` to avoid locking a locked mutex. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11412 Test Plan: `make -j56 COERCE_CONTEXT_SWITCH=1 ./db_universal_compaction_test` Reviewed By: ajkr Differential Revision: D45342242 Pulled By: cbi42 fbshipit-source-id: 955c9796aa3f484e3557d300f97cffacb3ed9b0c
2023-05-03 18:12:20 +00:00
size_t TotalLiveFilesAtPath(int cf, const std::string& path);
size_t CountLiveFiles();
int NumTableFilesAtLevel(int level, int cf = 0);
double CompressionRatioAtLevel(int level, int cf = 0);
int TotalTableFiles(int cf = 0, int levels = -1);
std::vector<uint64_t> GetBlobFileNumbers();
// Return spread of files per level
std::string FilesPerLevel(int cf = 0);
size_t CountFiles();
Status CountFiles(size_t* count);
Status Size(const Slice& start, const Slice& limit, uint64_t* size) {
return Size(start, limit, 0, size);
}
Status Size(const Slice& start, const Slice& limit, int cf, uint64_t* size);
void Compact(int cf, const Slice& start, const Slice& limit,
uint32_t target_path_id);
void Compact(int cf, const Slice& start, const Slice& limit);
void Compact(const Slice& start, const Slice& limit);
// Do n memtable compactions, each of which produces an sstable
// covering the range [small,large].
void MakeTables(int n, const std::string& small, const std::string& large,
int cf = 0);
// Prevent pushing of new sstables into deeper levels by adding
// tables that cover a specified range to all levels.
void FillLevels(const std::string& smallest, const std::string& largest,
int cf);
void MoveFilesToLevel(int level, int cf = 0);
void DumpFileCounts(const char* label);
std::string DumpSSTableList();
static void GetSstFiles(Env* env, std::string path,
std::vector<std::string>* files);
int GetSstFileCount(std::string path);
// this will generate non-overlapping files since it keeps increasing key_idx
void GenerateNewFile(Random* rnd, int* key_idx, bool nowait = false);
void GenerateNewFile(int fd, Random* rnd, int* key_idx, bool nowait = false);
static const int kNumKeysByGenerateNewRandomFile;
static const int KNumKeysByGenerateNewFile = 100;
void GenerateNewRandomFile(Random* rnd, bool nowait = false);
std::string IterStatus(Iterator* iter);
Options OptionsForLogIterTest();
std::string DummyString(size_t len, char c = 'a');
void VerifyIterLast(std::string expected_key, int cf = 0);
// Used to test InplaceUpdate
// If previous value is nullptr or delta is > than previous value,
// sets newValue with delta
// If previous value is not empty,
// updates previous value with 'b' string of previous value size - 1.
static UpdateStatus updateInPlaceSmallerSize(char* prevValue,
uint32_t* prevSize, Slice delta,
std::string* newValue);
static UpdateStatus updateInPlaceSmallerVarintSize(char* prevValue,
uint32_t* prevSize,
Slice delta,
std::string* newValue);
static UpdateStatus updateInPlaceLargerSize(char* prevValue,
uint32_t* prevSize, Slice delta,
std::string* newValue);
static UpdateStatus updateInPlaceNoAction(char* prevValue, uint32_t* prevSize,
Slice delta, std::string* newValue);
// Utility method to test InplaceUpdate
void validateNumberOfEntries(int numValues, int cf = 0);
void CopyFile(const std::string& source, const std::string& destination,
uint64_t size = 0);
Status GetAllDataFiles(const FileType file_type,
std::unordered_map<std::string, uint64_t>* sst_files,
uint64_t* total_size = nullptr);
std::vector<std::uint64_t> ListTableFiles(Env* env, const std::string& path);
void VerifyDBFromMap(
std::map<std::string, std::string> true_data,
size_t* total_reads_res = nullptr, bool tailing_iter = false,
std::map<std::string, Status> status = std::map<std::string, Status>());
void VerifyDBInternal(
std::vector<std::pair<std::string, std::string>> true_data);
Introduce FullMergeV2 (eliminate memcpy from merge operators) Summary: This diff update the code to pin the merge operator operands while the merge operation is done, so that we can eliminate the memcpy cost, to do that we need a new public API for FullMerge that replace the std::deque<std::string> with std::vector<Slice> This diff is stacked on top of D56493 and D56511 In this diff we - Update FullMergeV2 arguments to be encapsulated in MergeOperationInput and MergeOperationOutput which will make it easier to add new arguments in the future - Replace std::deque<std::string> with std::vector<Slice> to pass operands - Replace MergeContext std::deque with std::vector (based on a simple benchmark I ran https://gist.github.com/IslamAbdelRahman/78fc86c9ab9f52b1df791e58943fb187) - Allow FullMergeV2 output to be an existing operand ``` [Everything in Memtable | 10K operands | 10 KB each | 1 operand per key] DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --merge_keys=10000 --num=10000 --disable_auto_compactions --value_size=10240 --write_buffer_size=1000000000 [FullMergeV2] readseq : 0.607 micros/op 1648235 ops/sec; 16121.2 MB/s readseq : 0.478 micros/op 2091546 ops/sec; 20457.2 MB/s readseq : 0.252 micros/op 3972081 ops/sec; 38850.5 MB/s readseq : 0.237 micros/op 4218328 ops/sec; 41259.0 MB/s readseq : 0.247 micros/op 4043927 ops/sec; 39553.2 MB/s [master] readseq : 3.935 micros/op 254140 ops/sec; 2485.7 MB/s readseq : 3.722 micros/op 268657 ops/sec; 2627.7 MB/s readseq : 3.149 micros/op 317605 ops/sec; 3106.5 MB/s readseq : 3.125 micros/op 320024 ops/sec; 3130.1 MB/s readseq : 4.075 micros/op 245374 ops/sec; 2400.0 MB/s ``` ``` [Everything in Memtable | 10K operands | 10 KB each | 10 operand per key] DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --merge_keys=1000 --num=10000 --disable_auto_compactions --value_size=10240 --write_buffer_size=1000000000 [FullMergeV2] readseq : 3.472 micros/op 288018 ops/sec; 2817.1 MB/s readseq : 2.304 micros/op 434027 ops/sec; 4245.2 MB/s readseq : 1.163 micros/op 859845 ops/sec; 8410.0 MB/s readseq : 1.192 micros/op 838926 ops/sec; 8205.4 MB/s readseq : 1.250 micros/op 800000 ops/sec; 7824.7 MB/s [master] readseq : 24.025 micros/op 41623 ops/sec; 407.1 MB/s readseq : 18.489 micros/op 54086 ops/sec; 529.0 MB/s readseq : 18.693 micros/op 53495 ops/sec; 523.2 MB/s readseq : 23.621 micros/op 42335 ops/sec; 414.1 MB/s readseq : 18.775 micros/op 53262 ops/sec; 521.0 MB/s ``` ``` [Everything in Block cache | 10K operands | 10 KB each | 1 operand per key] [FullMergeV2] $ DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --num=100000 --db="/dev/shm/merge-random-10K-10KB" --cache_size=1000000000 --use_existing_db --disable_auto_compactions readseq : 14.741 micros/op 67837 ops/sec; 663.5 MB/s readseq : 1.029 micros/op 971446 ops/sec; 9501.6 MB/s readseq : 0.974 micros/op 1026229 ops/sec; 10037.4 MB/s readseq : 0.965 micros/op 1036080 ops/sec; 10133.8 MB/s readseq : 0.943 micros/op 1060657 ops/sec; 10374.2 MB/s [master] readseq : 16.735 micros/op 59755 ops/sec; 584.5 MB/s readseq : 3.029 micros/op 330151 ops/sec; 3229.2 MB/s readseq : 3.136 micros/op 318883 ops/sec; 3119.0 MB/s readseq : 3.065 micros/op 326245 ops/sec; 3191.0 MB/s readseq : 3.014 micros/op 331813 ops/sec; 3245.4 MB/s ``` ``` [Everything in Block cache | 10K operands | 10 KB each | 10 operand per key] DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --num=100000 --db="/dev/shm/merge-random-10-operands-10K-10KB" --cache_size=1000000000 --use_existing_db --disable_auto_compactions [FullMergeV2] readseq : 24.325 micros/op 41109 ops/sec; 402.1 MB/s readseq : 1.470 micros/op 680272 ops/sec; 6653.7 MB/s readseq : 1.231 micros/op 812347 ops/sec; 7945.5 MB/s readseq : 1.091 micros/op 916590 ops/sec; 8965.1 MB/s readseq : 1.109 micros/op 901713 ops/sec; 8819.6 MB/s [master] readseq : 27.257 micros/op 36687 ops/sec; 358.8 MB/s readseq : 4.443 micros/op 225073 ops/sec; 2201.4 MB/s readseq : 5.830 micros/op 171526 ops/sec; 1677.7 MB/s readseq : 4.173 micros/op 239635 ops/sec; 2343.8 MB/s readseq : 4.150 micros/op 240963 ops/sec; 2356.8 MB/s ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: yhchiang, andrewkr, sdong Reviewed By: sdong Subscribers: lovro, andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D57075
2016-07-20 16:49:03 +00:00
uint64_t GetNumberOfSstFilesForColumnFamily(DB* db,
std::string column_family_name);
uint64_t GetSstSizeHelper(Temperature temperature);
uint64_t TestGetTickerCount(const Options& options, Tickers ticker_type) {
return options.statistics->getTickerCount(ticker_type);
}
uint64_t TestGetAndResetTickerCount(const Options& options,
Tickers ticker_type) {
return options.statistics->getAndResetTickerCount(ticker_type);
}
Much better stats for seeks and prefix filtering (#11460) Summary: We want to know more about opportunities for better range filters, and the effectiveness of our own range filters. Currently the stats are very limited, essentially logging just hits and misses against prefix filters for range scans in BLOOM_FILTER_PREFIX_* without tracking the false positive rate. Perhaps confusingly, when prefix filters are used for point queries, the stats are currently going into the non-PREFIX tickers. This change does several things: * Introduce new stat tickers for seeks and related filtering, \*LEVEL_SEEK\* * Most importantly, allows us to see opportunities for range filtering. Specifically, we can count how many times a seek in an SST file accesses at least one data block, and how many times at least one value() is then accessed. If a data block was accessed but no value(), we can generally assume that the key(s) seen was(were) not of interest so could have been filtered with the right kind of filter, avoiding the data block access. * We can get the same level of detail when a filter (for now, prefix Bloom/ribbon) is used, or not. Specifically, we can infer a false positive rate for prefix filters (not available before) from the seek "false positive" rate: when a data block is accessed but no value() is called. (There can be other explanations for a seek false positive, but in typical iterator usage it would indicate a filter false positive.) * For efficiency, I wanted to avoid making additional calls to the prefix extractor (or key comparisons, etc.), which would be required if we wanted to more precisely detect filter false positives. I believe that instrumenting value() is the best balance of efficiency vs. accurately measuring what we are often interested in. * The stats are divided between last level and non-last levels, to help understand potential tiered storage use cases. * The old BLOOM_FILTER_PREFIX_* stats have a different meaning: no longer referring to iterators but to point queries using prefix filters. BLOOM_FILTER_PREFIX_TRUE_POSITIVE is added for computing the prefix false positive rate on point queries, which can be due to filter false positives as well as different keys with the same prefix. * Similarly, the non-PREFIX BLOOM_FILTER stats are now for whole key filtering only. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11460 Test Plan: unit tests updated, including updating many to pop the stat value since last read to improve test readability and maintainability. Performance test shows a consistent small improvement with these changes, both with clang and with gcc. CPU profile indicates that RecordTick is using less CPU, and this makes sense at least for a high filter miss rate. Before, we were recording two ticks per filter miss in iterators (CHECKED & USEFUL) and now recording just one (FILTERED). Create DB with ``` TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=fillrandom -num=10000000 -disable_wal=1 -write_buffer_size=30000000 -bloom_bits=8 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -prefix_size=8 ``` And run simultaneous before&after with ``` TEST_TMPDIR=/dev/shm ./db_bench -readonly -benchmarks=seekrandom[-X1000] -num=10000000 -bloom_bits=8 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -prefix_size=8 -seek_nexts=1 -duration=20 -seed=43 -threads=8 -cache_size=1000000000 -statistics ``` Before: seekrandom [AVG 275 runs] : 189680 (± 222) ops/sec; 18.4 (± 0.0) MB/sec After: seekrandom [AVG 275 runs] : 197110 (± 208) ops/sec; 19.1 (± 0.0) MB/sec Reviewed By: ajkr Differential Revision: D46029177 Pulled By: pdillinger fbshipit-source-id: cdace79a2ea548d46c5900b068c5b7c3a02e5822
2023-05-19 22:25:49 +00:00
// Short name for TestGetAndResetTickerCount
uint64_t PopTicker(const Options& options, Tickers ticker_type) {
return options.statistics->getAndResetTickerCount(ticker_type);
}
Fix+clean up handling of mock sleeps (#7101) Summary: We have a number of tests hanging on MacOS and windows due to mishandling of code for mock sleeps. In addition, the code was in terrible shape because the same variable (addon_time_) would sometimes refer to microseconds and sometimes to seconds. One test even assumed it was nanoseconds but was written to pass anyway. This has been cleaned up so that DB tests generally use a SpecialEnv function to mock sleep, for either some number of microseconds or seconds depending on the function called. But to call one of these, the test must first call SetMockSleep (precondition enforced with assertion), which also turns sleeps in RocksDB into mock sleeps. To also removes accounting for actual clock time, call SetTimeElapseOnlySleepOnReopen, which implies SetMockSleep (on DB re-open). This latter setting only works by applying on DB re-open, otherwise havoc can ensue if Env goes back in time with DB open. More specifics: Removed some unused test classes, and updated comments on the general problem. Fixed DBSSTTest.GetTotalSstFilesSize using a sync point callback instead of mock time. For this we have the only modification to production code, inserting a sync point callback in flush_job.cc, which is not a change to production behavior. Removed unnecessary resetting of mock times to 0 in many tests. RocksDB deals in relative time. Any behaviors relying on absolute date/time are likely a bug. (The above test DBSSTTest.GetTotalSstFilesSize was the only one clearly injecting a specific absolute time for actual testing convenience.) Just in case I misunderstood some test, I put this note in each replacement: // NOTE: Presumed unnecessary and removed: resetting mock time in env Strengthened some tests like MergeTestTime, MergeCompactionTimeTest, and FilterCompactionTimeTest in db_test.cc stats_history_test and blob_db_test are each their own beast, rather deeply dependent on MockTimeEnv. Each gets its own variant of a work-around for TimedWait in a mock time environment. (Reduces redundancy and inconsistency in stats_history_test.) Intended follow-up: Remove TimedWait from the public API of InstrumentedCondVar, and only make that accessible through Env by passing in an InstrumentedCondVar and a deadline. Then the Env implementations mocking time can fix this problem without using sync points. (Test infrastructure using sync points interferes with individual tests' control over sync points.) With that change, we can simplify/consolidate the scattered work-arounds. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7101 Test Plan: make check on Linux and MacOS Reviewed By: zhichao-cao Differential Revision: D23032815 Pulled By: pdillinger fbshipit-source-id: 7f33967ada8b83011fb54e8279365c008bd6610b
2020-08-11 19:39:49 +00:00
// Note: reverting this setting within the same test run is not yet
// supported
void SetTimeElapseOnlySleepOnReopen(DBOptions* options);
void ResetTableProperties(TableProperties* tp) {
tp->data_size = 0;
tp->index_size = 0;
tp->filter_size = 0;
tp->raw_key_size = 0;
tp->raw_value_size = 0;
tp->num_data_blocks = 0;
tp->num_entries = 0;
tp->num_deletions = 0;
tp->num_merge_operands = 0;
tp->num_range_deletions = 0;
}
void ParseTablePropertiesString(std::string tp_string, TableProperties* tp) {
double dummy_double;
std::replace(tp_string.begin(), tp_string.end(), ';', ' ');
std::replace(tp_string.begin(), tp_string.end(), '=', ' ');
ResetTableProperties(tp);
sscanf(tp_string.c_str(),
"# data blocks %" SCNu64 " # entries %" SCNu64
" # deletions %" SCNu64 " # merge operands %" SCNu64
" # range deletions %" SCNu64 " raw key size %" SCNu64
" raw average key size %lf "
" raw value size %" SCNu64
" raw average value size %lf "
" data block size %" SCNu64 " index block size (user-key? %" SCNu64
", delta-value? %" SCNu64 ") %" SCNu64 " filter block size %" SCNu64,
&tp->num_data_blocks, &tp->num_entries, &tp->num_deletions,
&tp->num_merge_operands, &tp->num_range_deletions, &tp->raw_key_size,
&dummy_double, &tp->raw_value_size, &dummy_double, &tp->data_size,
&tp->index_key_is_user_key, &tp->index_value_is_delta_encoded,
&tp->index_size, &tp->filter_size);
}
Fix+clean up handling of mock sleeps (#7101) Summary: We have a number of tests hanging on MacOS and windows due to mishandling of code for mock sleeps. In addition, the code was in terrible shape because the same variable (addon_time_) would sometimes refer to microseconds and sometimes to seconds. One test even assumed it was nanoseconds but was written to pass anyway. This has been cleaned up so that DB tests generally use a SpecialEnv function to mock sleep, for either some number of microseconds or seconds depending on the function called. But to call one of these, the test must first call SetMockSleep (precondition enforced with assertion), which also turns sleeps in RocksDB into mock sleeps. To also removes accounting for actual clock time, call SetTimeElapseOnlySleepOnReopen, which implies SetMockSleep (on DB re-open). This latter setting only works by applying on DB re-open, otherwise havoc can ensue if Env goes back in time with DB open. More specifics: Removed some unused test classes, and updated comments on the general problem. Fixed DBSSTTest.GetTotalSstFilesSize using a sync point callback instead of mock time. For this we have the only modification to production code, inserting a sync point callback in flush_job.cc, which is not a change to production behavior. Removed unnecessary resetting of mock times to 0 in many tests. RocksDB deals in relative time. Any behaviors relying on absolute date/time are likely a bug. (The above test DBSSTTest.GetTotalSstFilesSize was the only one clearly injecting a specific absolute time for actual testing convenience.) Just in case I misunderstood some test, I put this note in each replacement: // NOTE: Presumed unnecessary and removed: resetting mock time in env Strengthened some tests like MergeTestTime, MergeCompactionTimeTest, and FilterCompactionTimeTest in db_test.cc stats_history_test and blob_db_test are each their own beast, rather deeply dependent on MockTimeEnv. Each gets its own variant of a work-around for TimedWait in a mock time environment. (Reduces redundancy and inconsistency in stats_history_test.) Intended follow-up: Remove TimedWait from the public API of InstrumentedCondVar, and only make that accessible through Env by passing in an InstrumentedCondVar and a deadline. Then the Env implementations mocking time can fix this problem without using sync points. (Test infrastructure using sync points interferes with individual tests' control over sync points.) With that change, we can simplify/consolidate the scattered work-arounds. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7101 Test Plan: make check on Linux and MacOS Reviewed By: zhichao-cao Differential Revision: D23032815 Pulled By: pdillinger fbshipit-source-id: 7f33967ada8b83011fb54e8279365c008bd6610b
2020-08-11 19:39:49 +00:00
private: // Prone to error on direct use
void MaybeInstallTimeElapseOnlySleep(const DBOptions& options);
bool time_elapse_only_sleep_on_reopen_ = false;
};
Experimental support for SST unique IDs (#8990) Summary: * New public header unique_id.h and function GetUniqueIdFromTableProperties which computes a universally unique identifier based on table properties of table files from recent RocksDB versions. * Generation of DB session IDs is refactored so that they are guaranteed unique in the lifetime of a process running RocksDB. (SemiStructuredUniqueIdGen, new test included.) Along with file numbers, this enables SST unique IDs to be guaranteed unique among SSTs generated in a single process, and "better than random" between processes. See https://github.com/pdillinger/unique_id * In addition to public API producing 'external' unique IDs, there is a function for producing 'internal' unique IDs, with functions for converting between the two. In short, the external ID is "safe" for things people might do with it, and the internal ID enables more "power user" features for the future. Specifically, the external ID goes through a hashing layer so that any subset of bits in the external ID can be used as a hash of the full ID, while also preserving uniqueness guarantees in the first 128 bits (bijective both on first 128 bits and on full 192 bits). Intended follow-up: * Use the internal unique IDs in cache keys. (Avoid conflicts with https://github.com/facebook/rocksdb/issues/8912) (The file offset can be XORed into the third 64-bit value of the unique ID.) * Publish the external unique IDs in FileStorageInfo (https://github.com/facebook/rocksdb/issues/8968) Pull Request resolved: https://github.com/facebook/rocksdb/pull/8990 Test Plan: Unit tests added, and checking of unique ids in stress test. NOTE in stress test we do not generate nearly enough files to thoroughly stress uniqueness, but the test trims off pieces of the ID to check for uniqueness so that we can infer (with some assumptions) stronger properties in the aggregate. Reviewed By: zhichao-cao, mrambacher Differential Revision: D31582865 Pulled By: pdillinger fbshipit-source-id: 1f620c4c86af9abe2a8d177b9ccf2ad2b9f48243
2021-10-19 06:28:28 +00:00
// For verifying that all files generated by current version have SST
// unique ids.
void VerifySstUniqueIds(const TablePropertiesCollection& props);
} // namespace ROCKSDB_NAMESPACE