Question

std::mutex与CRITICAL_SECTION的效果相比如何？它是否相提并论？

我需要轻量级同步对象（不需要是进程间对象）是否有任何STL类接近CRITICAL_SECTION以外的std::mutex？

Answer 1

请在答案结尾处查看我的更新，自Visual Studio 2015以来情况发生了巨大变化。原始答案如下。

我做了一个非常简单的测试，根据我的测量结果，std::mutex比CRITICAL_SECTION慢了约50-70倍。

std::mutex:       18140574us
CRITICAL_SECTION: 296874us

编辑：经过一些测试后，结果显示它取决于线程数（拥塞）和CPU核心数。通常，std::mutex较慢，但多少，取决于使用。以下是更新的测试结果（在带有Core i5-4258U，Windows 10，Bootcamp的MacBook Pro上测试）：

Iterations: 1000000
Thread count: 1
std::mutex:       78132us
CRITICAL_SECTION: 31252us
Thread count: 2
std::mutex:       687538us
CRITICAL_SECTION: 140648us
Thread count: 4
std::mutex:       1031277us
CRITICAL_SECTION: 703180us
Thread count: 8
std::mutex:       86779418us
CRITICAL_SECTION: 1634123us
Thread count: 16
std::mutex:       172916124us
CRITICAL_SECTION: 3390895us

以下是产生此输出的代码。使用Visual Studio 2012编译，默认项目设置，Win32发布配置。请注意，此测试可能不完全正确，但在将代码从使用CRITICAL_SECTION转换为std::mutex之前，我会三思而行。

#include "stdafx.h"
#include <Windows.h>
#include <mutex>
#include <thread>
#include <vector>
#include <chrono>
#include <iostream>

const int g_cRepeatCount = 1000000;
const int g_cThreadCount = 16;

double g_shmem = 8;
std::mutex g_mutex;
CRITICAL_SECTION g_critSec;

void sharedFunc( int i )
{
    if ( i % 2 == 0 )
        g_shmem = sqrt(g_shmem);
    else
        g_shmem *= g_shmem;
}

void threadFuncCritSec() {
    for ( int i = 0; i < g_cRepeatCount; ++i ) {
        EnterCriticalSection( &g_critSec );
        sharedFunc(i);
        LeaveCriticalSection( &g_critSec );
    }
}

void threadFuncMutex() {
    for ( int i = 0; i < g_cRepeatCount; ++i ) {
        g_mutex.lock();
        sharedFunc(i);
        g_mutex.unlock();
    }
}

void testRound(int threadCount)
{
    std::vector<std::thread> threads;

    auto startMutex = std::chrono::high_resolution_clock::now();
    for (int i = 0; i<threadCount; ++i)
        threads.push_back(std::thread( threadFuncMutex ));
    for ( std::thread& thd : threads )
        thd.join();
    auto endMutex = std::chrono::high_resolution_clock::now();

    std::cout << "std::mutex:       ";
    std::cout << std::chrono::duration_cast<std::chrono::microseconds>(endMutex - startMutex).count();
    std::cout << "us \n\r";

    threads.clear();
    auto startCritSec = std::chrono::high_resolution_clock::now();
    for (int i = 0; i<threadCount; ++i)
        threads.push_back(std::thread( threadFuncCritSec ));
    for ( std::thread& thd : threads )
        thd.join();
    auto endCritSec = std::chrono::high_resolution_clock::now();

    std::cout << "CRITICAL_SECTION: ";
    std::cout << std::chrono::duration_cast<std::chrono::microseconds>(endCritSec - startCritSec).count();
    std::cout << "us \n\r";
}

int _tmain(int argc, _TCHAR* argv[]) {
    InitializeCriticalSection( &g_critSec );

    std::cout << "Iterations: " << g_cRepeatCount << "\n\r";

    for (int i = 1; i <= g_cThreadCount; i = i*2) {
        std::cout << "Thread count: " << i << "\n\r";
        testRound(i);
        Sleep(1000);
    }

    DeleteCriticalSection( &g_critSec );

    // Added 10/27/2017 to try to prevent the compiler to completely
    // optimize out the code around g_shmem if it wouldn't be used anywhere.
    std::cout << "Shared variable value: " << g_shmem << std::endl;
    getchar();
    return 0;
}

更新10/27/2017（1）：一些答案表明这不是一个现实的测试或不代表“现实世界”的情景。这是真的，这个测试试图测量std::mutex的开销，它并没有试图证明99％的应用程序的差异可以忽略不计。

更新10/27/2017（2）：从Visual Studio 2015（VC140）开始，似乎情况发生了变化，有利于std::mutex。我使用了VS2017 IDE，与上面的代码完全相同，x64版本配置，禁用了优化，我只是为每个测试切换了“Platform Toolset”。结果非常令人惊讶，我真的很好奇VC140中挂了什么。

Answer 2

沃尔德兹在这里的测试是不现实的，它基本上模拟了100％的争用。通常，这正是您在多线程代码中不想要的。下面是一个修改过的测试，可以进行一些共享计算我用这段代码得到的结果是不同的：

Tasks: 160000
Thread count: 1
std::mutex:       12096ms
CRITICAL_SECTION: 12060ms
Thread count: 2
std::mutex:       5206ms
CRITICAL_SECTION: 5110ms
Thread count: 4
std::mutex:       2643ms
CRITICAL_SECTION: 2625ms
Thread count: 8
std::mutex:       1632ms
CRITICAL_SECTION: 1702ms
Thread count: 12
std::mutex:       1227ms
CRITICAL_SECTION: 1244ms

你可以在这里看到，对我来说（使用VS2013）std :: mutex和CRITICAL_SECTION之间的数字非常接近。请注意，此代码执行固定数量的任务（160,000），这就是为什么性能通常随着更多线程而改善的原因。我在这里有12个核心，这就是为什么我在12点停下来。

与其他测试相比，我并不是说这是对还是错，但它确实强调时间问题通常是特定领域的。

#include "stdafx.h"
#include <Windows.h>
#include <mutex>
#include <thread>
#include <vector>
#include <chrono>
#include <iostream>

const int tastCount = 160000;
int numThreads;
const int MAX_THREADS = 16;

double g_shmem = 8;
std::mutex g_mutex;
CRITICAL_SECTION g_critSec;

void sharedFunc(int i, double &data)
{
    for (int j = 0; j < 100; j++)
    {
        if (j % 2 == 0)
            data = sqrt(data);
        else
            data *= data;
    }
}

void threadFuncCritSec() {
    double lMem = 8;
    int iterations = tastCount / numThreads;
    for (int i = 0; i < iterations; ++i) {
        for (int j = 0; j < 100; j++)
            sharedFunc(j, lMem);
        EnterCriticalSection(&g_critSec);
        sharedFunc(i, g_shmem);
        LeaveCriticalSection(&g_critSec);
    }
    printf("results: %f\n", lMem);
}

void threadFuncMutex() {
    double lMem = 8;
    int iterations = tastCount / numThreads;
    for (int i = 0; i < iterations; ++i) {
        for (int j = 0; j < 100; j++)
            sharedFunc(j, lMem);
        g_mutex.lock();
        sharedFunc(i, g_shmem);
        g_mutex.unlock();
    }
    printf("results: %f\n", lMem);
}

void testRound()
{
    std::vector<std::thread> threads;

    auto startMutex = std::chrono::high_resolution_clock::now();
    for (int i = 0; i < numThreads; ++i)
        threads.push_back(std::thread(threadFuncMutex));
    for (std::thread& thd : threads)
        thd.join();
    auto endMutex = std::chrono::high_resolution_clock::now();

    std::cout << "std::mutex:       ";
    std::cout << std::chrono::duration_cast<std::chrono::milliseconds>(endMutex - startMutex).count();
    std::cout << "ms \n\r";

    threads.clear();
    auto startCritSec = std::chrono::high_resolution_clock::now();
    for (int i = 0; i < numThreads; ++i)
        threads.push_back(std::thread(threadFuncCritSec));
    for (std::thread& thd : threads)
        thd.join();
    auto endCritSec = std::chrono::high_resolution_clock::now();

    std::cout << "CRITICAL_SECTION: ";
    std::cout << std::chrono::duration_cast<std::chrono::milliseconds>(endCritSec - startCritSec).count();
    std::cout << "ms \n\r";
}

int _tmain(int argc, _TCHAR* argv[]) {
    InitializeCriticalSection(&g_critSec);

    std::cout << "Tasks: " << tastCount << "\n\r";

    for (numThreads = 1; numThreads <= MAX_THREADS; numThreads = numThreads * 2) {
        if (numThreads == 16)
            numThreads = 12;
        Sleep(100);
        std::cout << "Thread count: " << numThreads << "\n\r";
        testRound();
    }

    DeleteCriticalSection(&g_critSec);
    return 0;
}

Answer 3

我正在使用Visual Studio 2013。

单线程使用的结果与waldez结果类似：

100万次锁定/解锁通话：

CRITICAL_SECTION:       19 ms
std::mutex:             48 ms
std::recursive_mutex:   48 ms

Microsoft更改实现的原因是C ++ 11兼容性。 C ++ 11在std命名空间中有4种互斥：

Microsoft std :: mutex和所有其他互斥锁是关键部分的包装器：

struct _Mtx_internal_imp_t
{   /* Win32 mutex */
    int type; // here MS keeps particular mutex type
    Concurrency::critical_section cs;
    long thread_id;
    int count;
};

至于我，std :: recursive_mutex应该完全匹配临界区。因此，微软应该优化其实现，以减少CPU和内存。

Answer 4

我在这里搜索pthread与临界区基准，但是，由于我的结果与waldez关于该主题的答案不同，我认为分享会很有趣。

代码是@waldez使用的代码，修改为将pthreads添加到比较中，使用GCC编译并且没有优化。我的CPU是AMD A8-3530MX。

Windows 7 Home Edition：

>a.exe
Iterations: 1000000
Thread count: 1
std::mutex:       46800us
CRITICAL_SECTION: 31200us
pthreads:         31200us
Thread count: 2
std::mutex:       171600us
CRITICAL_SECTION: 218400us
pthreads:         124800us
Thread count: 4
std::mutex:       327600us
CRITICAL_SECTION: 374400us
pthreads:         249600us
Thread count: 8
std::mutex:       967201us
CRITICAL_SECTION: 748801us
pthreads:         717601us
Thread count: 16
std::mutex:       2745604us
CRITICAL_SECTION: 1497602us
pthreads:         1903203us

正如您所看到的，差异在统计误差范围内变化很大 - 有时std :: mutex更快，有时则不然。重要的是，我没有观察到原始答案的巨大差异。

我想，也许原因是，当答案发布时，MSVC编译器对新标准不好，并注意到原始答案使用了2012年的版本。

另外，出于好奇，在Archlinux上Wine下的二进制文件：

$ wine a.exe
fixme:winediag:start_process Wine Staging 2.19 is a testing version containing experimental patches.
fixme:winediag:start_process Please mention your exact version when filing bug reports on winehq.org.
Iterations: 1000000
Thread count: 1
std::mutex:       53810us 
CRITICAL_SECTION: 95165us 
pthreads:         62316us 
Thread count: 2
std::mutex:       604418us 
CRITICAL_SECTION: 1192601us 
pthreads:         688960us 
Thread count: 4
std::mutex:       779817us 
CRITICAL_SECTION: 2476287us 
pthreads:         818022us 
Thread count: 8
std::mutex:       1806607us 
CRITICAL_SECTION: 7246986us 
pthreads:         809566us 
Thread count: 16
std::mutex:       2987472us 
CRITICAL_SECTION: 14740350us 
pthreads:         1453991us

瓦尔德兹的代码与我的修改：

#include <math.h>
#include <windows.h>
#include <mutex>
#include <thread>
#include <vector>
#include <chrono>
#include <iostream>
#include <pthread.h>

const int g_cRepeatCount = 1000000;
const int g_cThreadCount = 16;

double g_shmem = 8;
std::mutex g_mutex;
CRITICAL_SECTION g_critSec;
pthread_mutex_t pt_mutex;


void sharedFunc( int i )
{
    if ( i % 2 == 0 )
        g_shmem = sqrt(g_shmem);
    else
        g_shmem *= g_shmem;
}

void threadFuncCritSec() {
    for ( int i = 0; i < g_cRepeatCount; ++i ) {
        EnterCriticalSection( &g_critSec );
        sharedFunc(i);
        LeaveCriticalSection( &g_critSec );
    }
}

void threadFuncMutex() {
    for ( int i = 0; i < g_cRepeatCount; ++i ) {
        g_mutex.lock();
        sharedFunc(i);
        g_mutex.unlock();
    }
}

void threadFuncPTMutex() {
    for ( int i = 0; i < g_cRepeatCount; ++i ) {
        pthread_mutex_lock(&pt_mutex);
        sharedFunc(i);
        pthread_mutex_unlock(&pt_mutex);
    }
}
void testRound(int threadCount)
{
    std::vector<std::thread> threads;

    auto startMutex = std::chrono::high_resolution_clock::now();
    for (int i = 0; i<threadCount; ++i)
        threads.push_back(std::thread( threadFuncMutex ));
    for ( std::thread& thd : threads )
        thd.join();
    auto endMutex = std::chrono::high_resolution_clock::now();

    std::cout << "std::mutex:       ";
    std::cout << std::chrono::duration_cast<std::chrono::microseconds>(endMutex - startMutex).count();
    std::cout << "us \n";
    g_shmem = 0;

    threads.clear();
    auto startCritSec = std::chrono::high_resolution_clock::now();
    for (int i = 0; i<threadCount; ++i)
        threads.push_back(std::thread( threadFuncCritSec ));
    for ( std::thread& thd : threads )
        thd.join();
    auto endCritSec = std::chrono::high_resolution_clock::now();

    std::cout << "CRITICAL_SECTION: ";
    std::cout << std::chrono::duration_cast<std::chrono::microseconds>(endCritSec - startCritSec).count();
    std::cout << "us \n";
    g_shmem = 0;

    threads.clear();
    auto startPThread = std::chrono::high_resolution_clock::now();
    for (int i = 0; i<threadCount; ++i)
        threads.push_back(std::thread( threadFuncPTMutex ));
    for ( std::thread& thd : threads )
        thd.join();
    auto endPThread = std::chrono::high_resolution_clock::now();

    std::cout << "pthreads:         ";
    std::cout << std::chrono::duration_cast<std::chrono::microseconds>(endPThread - startPThread).count();
    std::cout << "us \n";
    g_shmem = 0;
}

int main() {
    InitializeCriticalSection( &g_critSec );
    pthread_mutex_init(&pt_mutex, 0);

    std::cout << "Iterations: " << g_cRepeatCount << "\n";

    for (int i = 1; i <= g_cThreadCount; i = i*2) {
        std::cout << "Thread count: " << i << "\n";
        testRound(i);
        Sleep(1000);
    }

    getchar();
    DeleteCriticalSection( &g_critSec );
    pthread_mutex_destroy(&pt_mutex);
    return 0;
}

Answer 5

Waldez修改为test program与pthreads和boost :: mutex一起运行。

在win10 pro上（使用intel i7-7820X 16核cpu）我从VS {{}}获得了更好的结果来自VS2015 update3上的std :: mutex（更好的是来自boost :: mutex）：

Iterations: 1000000

Thread count: 1
std::mutex:       23403us
boost::mutex:     12574us
CRITICAL_SECTION: 19454us

Thread count: 2
std::mutex:       55031us
boost::mutex:     45263us
CRITICAL_SECTION: 187597us

Thread count: 4
std::mutex:       113964us
boost::mutex:     83699us
CRITICAL_SECTION: 605765us

Thread count: 8
std::mutex:       266091us
boost::mutex:     155265us
CRITICAL_SECTION: 1908491us

Thread count: 16
std::mutex:       633032us
boost::mutex:     300076us
CRITICAL_SECTION: 4015176us

pthreads的结果为CRITICAL_SECTION。

#ifdef _WIN32
#include <Windows.h>
#endif
#include <mutex>
#include <boost/thread/mutex.hpp>
#include <thread>
#include <vector>
#include <chrono>
#include <iostream>

const int g_cRepeatCount = 1000000;
const int g_cThreadCount = 16;

double g_shmem = 8;
std::recursive_mutex g_mutex;
boost::mutex g_boostMutex;

void sharedFunc(int i)
{
    if (i % 2 == 0)
        g_shmem = sqrt(g_shmem);
    else
        g_shmem *= g_shmem;
}

#ifdef _WIN32
CRITICAL_SECTION g_critSec;
void threadFuncCritSec()
{
    for (int i = 0; i < g_cRepeatCount; ++i)
    {
        EnterCriticalSection(&g_critSec);
        sharedFunc(i);
        LeaveCriticalSection(&g_critSec);
    }
}
#else
pthread_mutex_t pt_mutex;
void threadFuncPtMutex()
{
    for (int i = 0; i < g_cRepeatCount; ++i) {
        pthread_mutex_lock(&pt_mutex);
        sharedFunc(i);
        pthread_mutex_unlock(&pt_mutex);
    }
}
#endif

void threadFuncMutex()
{
    for (int i = 0; i < g_cRepeatCount; ++i)
    {
        g_mutex.lock();
        sharedFunc(i);
        g_mutex.unlock();
    }
}

void threadFuncBoostMutex()
{
    for (int i = 0; i < g_cRepeatCount; ++i)
    {
        g_boostMutex.lock();
        sharedFunc(i);
        g_boostMutex.unlock();
    }
}

void testRound(int threadCount)
{
    std::vector<std::thread> threads;

    std::cout << "\nThread count: " << threadCount << "\n\r";

    auto startMutex = std::chrono::high_resolution_clock::now();
    for (int i = 0; i < threadCount; ++i)
        threads.push_back(std::thread(threadFuncMutex));
    for (std::thread& thd : threads)
        thd.join();
    threads.clear();
    auto endMutex = std::chrono::high_resolution_clock::now();

    std::cout << "std::mutex:       ";
    std::cout << std::chrono::duration_cast<std::chrono::microseconds>(endMutex - startMutex).count();
    std::cout << "us \n\r";

    auto startBoostMutex = std::chrono::high_resolution_clock::now();
    for (int i = 0; i < threadCount; ++i)
        threads.push_back(std::thread(threadFuncBoostMutex));
    for (std::thread& thd : threads)
        thd.join();
    threads.clear();
    auto endBoostMutex = std::chrono::high_resolution_clock::now();

    std::cout << "boost::mutex:     ";
    std::cout << std::chrono::duration_cast<std::chrono::microseconds>(endBoostMutex - startBoostMutex).count();
    std::cout << "us \n\r";

#ifdef _WIN32
    auto startCritSec = std::chrono::high_resolution_clock::now();
    for (int i = 0; i < threadCount; ++i)
        threads.push_back(std::thread(threadFuncCritSec));
    for (std::thread& thd : threads)
        thd.join();
    threads.clear();
    auto endCritSec = std::chrono::high_resolution_clock::now();

    std::cout << "CRITICAL_SECTION: ";
    std::cout << std::chrono::duration_cast<std::chrono::microseconds>(endCritSec - startCritSec).count();
    std::cout << "us \n\r";
#else
    auto startPThread = std::chrono::high_resolution_clock::now();
    for (int i = 0; i < threadCount; ++i)
        threads.push_back(std::thread(threadFuncPtMutex));
    for (std::thread& thd : threads)
        thd.join();
    threads.clear();
    auto endPThread = std::chrono::high_resolution_clock::now();

    std::cout << "pthreads:         ";
    std::cout << std::chrono::duration_cast<std::chrono::microseconds>(endPThread - startPThread).count();
    std::cout << "us \n";
#endif
}

int main()
{
#ifdef _WIN32
    InitializeCriticalSection(&g_critSec);
#else
    pthread_mutex_init(&pt_mutex, 0);
#endif

    std::cout << "Iterations: " << g_cRepeatCount << "\n\r";

    for (int i = 1; i <= g_cThreadCount; i = i * 2)
    {
        testRound(i);
        std::this_thread::sleep_for(std::chrono::seconds(1));
    }

#ifdef _WIN32
    DeleteCriticalSection(&g_critSec);
#else
    pthread_mutex_destroy(&pt_mutex);
#endif
    if (rand() % 10000 == 1)
    {
        // Added 10/27/2017 to try to prevent the compiler to completely
        // optimize out the code around g_shmem if it wouldn't be used anywhere.
        std::cout << "Shared variable value: " << g_shmem << std::endl;
    }
    return 0;
}

Answer 6

My results for test1

Iterations: 1000000
Thread count: 1
std::mutex:      27085us
CRITICAL_SECTION: 12035us
Thread count: 2
std::mutex:      40412us
CRITICAL_SECTION: 119952us
Thread count: 4
std::mutex:      123214us
CRITICAL_SECTION: 314774us
Thread count: 8
std::mutex:      387737us
CRITICAL_SECTION: 1664506us
Thread count: 16
std::mutex:      836901us
CRITICAL_SECTION: 3837877us
Shared variable value: 8

测试 2

Tasks: 160000
Thread count: 1
results: 8.000000
std::mutex:       4642ms
results: 8.000000
CRITICAL_SECTION: 4588ms
Thread count: 2
results: 8.000000
results: 8.000000
std::mutex:       2309ms
results: 8.000000
results: 8.000000
CRITICAL_SECTION: 2307ms
Thread count: 4
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
std::mutex:       1169ms
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
CRITICAL_SECTION: 1162ms
Thread count: 8
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
std::mutex:       640ms
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
CRITICAL_SECTION: 628ms
Thread count: 12
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
std::mutex:       745ms
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
results: 8.000000
CRITICAL_SECTION: 672ms

与win32 CRITICAL_SECTION相比，std :: mutex的性能

6 个答案: