678ba5e41c
Summary:
The first parameter of SyncPoint::Process is "const std::string&". The majority, maybe all, of the actual calls to this function use a "const char *". The conversion before entering the function requires a construction of a std::string object on the heap. This std::object is then typically not needed because first use of the string is a rocksdb::Slice which has a less costly conversion of char * to slice.
Example:
We have a load and iterate test. The test loads 10m keys and iterates most via 10 rocksdb::Iterator objects. We used TCMALLOC to gather information about allocation and space usage during iterators.
- Before this PR: test took 32 min 17 sec
- After this PR: test took 1 min 14 sec
The TCMALLOC top object list before this PR:
<pre>
Total: 5105999 objects
5003717 98.0% 98.0% 5009471 98.1% rocksdb::DBIter::MergeValuesNewToOld (inline)
20260 0.4% 98.4% 20260 0.4% std::__cxx11::basic_string::_M_mutate
15214 0.3% 98.7% 15214 0.3% rocksdb::UncompressBlockContentsForCompressionType (inline)
13408 0.3% 99.0% 13408 0.3% std::_Rb_tree::_M_emplace_hint_unique [clone .constprop.416] (inline)
12957 0.3% 99.2% 12957 0.3% std::_Rb_tree::_M_emplace_hint_unique [clone .constprop.405] (inline)
9327 0.2% 99.4% 9327 0.2% std::_Rb_tree::_M_copy (inline)
7691 0.2% 99.5% 9919 0.2% JVM_FindSignal
2859 0.1% 99.6% 2859 0.1% rocksdb::Cleanable::RegisterCleanup
2844 0.1% 99.7% 2844 0.1% std::map::operator[] (inline)
</pre>
The "MergeValuesNewToOld (inline)" objects are the #define wrappers to SyncPoint::Process. We discovered this in a 5.18 rocksdb release. There TCMALLOC was more specific that std::basic_string was being constructed. I believe that was before SyncPoint::Process was declared inline in subsequent releases.
The TCMALLOC top object list after this PR:
<pre>
Total: 104911 objects
45090 43.0% 43.0% 45090 43.0% rocksdb::Cleanable::RegisterCleanup
29995 28.6% 71.6% 29995 28.6% rocksdb::LRUCacheShard::Insert
15229 14.5% 86.1% 15229 14.5% rocksdb::UncompressBlockContentsForCompressionType (inline)
4373 4.2% 90.3% 4551 4.3% JVM_FindSignal
2881 2.7% 93.0% 2881 2.7% rocksdb::::ReadBlockFromFile (inline)
1162 1.1% 94.1% 1176 1.1% rocksdb::BlockFetcher::ReadBlockContents (inline)
1036 1.0% 95.1% 1036 1.0% std::__cxx11::basic_string::_M_mutate
869 0.8% 95.9% 869 0.8% std::vector::_M_realloc_insert (inline)
806 0.8% 96.7% 806 0.8% SnmpAgent::GetVariables (inline)
</pre>
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9023
Reviewed By: pdillinger
Differential Revision: D31610907
Pulled By: mrambacher
fbshipit-source-id: 574ff51b639dd46ad253a8e664a575f06b7cc85d
102 lines
3.1 KiB
C++
102 lines
3.1 KiB
C++
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
|
|
#include <assert.h>
|
|
|
|
#include <atomic>
|
|
#include <condition_variable>
|
|
#include <functional>
|
|
#include <mutex>
|
|
#include <string>
|
|
#include <thread>
|
|
#include <unordered_map>
|
|
#include <unordered_set>
|
|
|
|
#include "memory/concurrent_arena.h"
|
|
#include "port/port.h"
|
|
#include "test_util/sync_point.h"
|
|
#include "util/dynamic_bloom.h"
|
|
#include "util/random.h"
|
|
|
|
#pragma once
|
|
|
|
#ifndef NDEBUG
|
|
namespace ROCKSDB_NAMESPACE {
|
|
// A hacky allocator for single use.
|
|
// Arena depends on SyncPoint and create circular dependency.
|
|
class SingleAllocator : public Allocator {
|
|
public:
|
|
char* Allocate(size_t) override {
|
|
assert(false);
|
|
return nullptr;
|
|
}
|
|
char* AllocateAligned(size_t bytes, size_t, Logger*) override {
|
|
buf_.resize(bytes);
|
|
return const_cast<char*>(buf_.data());
|
|
}
|
|
size_t BlockSize() const override {
|
|
assert(false);
|
|
return 0;
|
|
}
|
|
|
|
private:
|
|
std::string buf_;
|
|
};
|
|
|
|
struct SyncPoint::Data {
|
|
Data() : point_filter_(&alloc_, /*total_bits=*/8192), enabled_(false) {}
|
|
// Enable proper deletion by subclasses
|
|
virtual ~Data() {}
|
|
// successor/predecessor map loaded from LoadDependency
|
|
std::unordered_map<std::string, std::vector<std::string>> successors_;
|
|
std::unordered_map<std::string, std::vector<std::string>> predecessors_;
|
|
std::unordered_map<std::string, std::function<void(void*)> > callbacks_;
|
|
std::unordered_map<std::string, std::vector<std::string> > markers_;
|
|
std::unordered_map<std::string, std::thread::id> marked_thread_id_;
|
|
|
|
std::mutex mutex_;
|
|
std::condition_variable cv_;
|
|
// sync points that have been passed through
|
|
std::unordered_set<std::string> cleared_points_;
|
|
SingleAllocator alloc_;
|
|
// A filter before holding mutex to speed up process.
|
|
DynamicBloom point_filter_;
|
|
std::atomic<bool> enabled_;
|
|
int num_callbacks_running_ = 0;
|
|
|
|
void LoadDependency(const std::vector<SyncPointPair>& dependencies);
|
|
void LoadDependencyAndMarkers(const std::vector<SyncPointPair>& dependencies,
|
|
const std::vector<SyncPointPair>& markers);
|
|
bool PredecessorsAllCleared(const std::string& point);
|
|
void SetCallBack(const std::string& point,
|
|
const std::function<void(void*)>& callback) {
|
|
std::lock_guard<std::mutex> lock(mutex_);
|
|
callbacks_[point] = callback;
|
|
point_filter_.Add(point);
|
|
}
|
|
|
|
void ClearCallBack(const std::string& point);
|
|
void ClearAllCallBacks();
|
|
void EnableProcessing() {
|
|
enabled_ = true;
|
|
}
|
|
void DisableProcessing() {
|
|
enabled_ = false;
|
|
}
|
|
void ClearTrace() {
|
|
std::lock_guard<std::mutex> lock(mutex_);
|
|
cleared_points_.clear();
|
|
}
|
|
bool DisabledByMarker(const std::string& point,
|
|
std::thread::id thread_id) {
|
|
auto marked_point_iter = marked_thread_id_.find(point);
|
|
return marked_point_iter != marked_thread_id_.end() &&
|
|
thread_id != marked_point_iter->second;
|
|
}
|
|
void Process(const Slice& point, void* cb_arg);
|
|
};
|
|
} // namespace ROCKSDB_NAMESPACE
|
|
#endif // NDEBUG
|