与 win32 CRITICAL_SECTION 相比的 std::mutex 性能

Following is the code that produced this output. Compiled with Visual Studio 2012, default project settings, Win32 release configuration. Please note that this test may not be perfectly correct but it made me think twice before switching my code from using CRITICAL_SECTION to std::mutex.

#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 
";

    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 
";
}

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

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

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

2017 年 10 月 27 日更新 (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"的场景.确实如此，此测试试图测量 std::mutex 的开销，并不是要证明差异对于 99% 的应用程序可以忽略不计.