> 2 x Xeon E5-2690 v4 @ 2.60GHz(Turbo Boost ON,HT OFF,共28个逻辑cpu)
> 32GB DDR4 2400内存,四通道

并在每个上安装了Windows 7 SP1(x64)和Windows 10 Creators Update(x64).

然后我们运行了一个小内存基准测试(下面的代码,使用VS2015 Update 3,64位架构构建),它可以同时从多个线程执行内存分配 – 无填充.

#include <Windows.h>
#include <vector>
#include <ppl.h>

unsigned __int64 ZQueryPerformanceCounter()
{
    unsigned __int64 c;
    ::QueryPerformanceCounter((LARGE_INTEGER *)&c);
    return c;
}

unsigned __int64 ZQueryPerformanceFrequency()
{
    unsigned __int64 c;
    ::QueryPerformanceFrequency((LARGE_INTEGER *)&c);
    return c;
}

class CZPerfCounter {
public:
    CZPerfCounter() : m_st(ZQueryPerformanceCounter()) {};
    void reset() { m_st = ZQueryPerformanceCounter(); };
    unsigned __int64 elapsedCount() { return ZQueryPerformanceCounter() - m_st; };
    unsigned long elapsedMS() { return (unsigned long)(elapsedCount() * 1000 / m_freq); };
    unsigned long elapsedMicroSec() { return (unsigned long)(elapsedCount() * 1000 * 1000 / m_freq); };
    static unsigned __int64 frequency() { return m_freq; };
private:
    unsigned __int64 m_st;
    static unsigned __int64 m_freq;
};

unsigned __int64 CZPerfCounter::m_freq = ZQueryPerformanceFrequency();



int main(int argc,char ** argv)
{
    SYSTEM_INFO sysinfo;
    GetSystemInfo(&sysinfo);
    int ncpu = sysinfo.dwNumberOfProcessors;

    if (argc == 2) {
        ncpu = atoi(argv[1]);
    }

    {
        printf("No of threads %d\n",ncpu);

        try {
            concurrency::Scheduler::ResetDefaultSchedulerPolicy();
            int min_threads = 1;
            int max_threads = ncpu;
            concurrency::SchedulerPolicy policy
            (2 // two entries of policy settings,concurrency::MinConcurrency,min_threads,concurrency::MaxConcurrency,max_threads
            );
            concurrency::Scheduler::SetDefaultSchedulerPolicy(policy);
        }
        catch (concurrency::default_scheduler_exists &) {
            printf("Cannot set concurrency runtime scheduler policy (Default scheduler already exists).\n");
        }

        static int cnt = 100;
        static int num_fills = 1;
        CZPerfCounter pcTotal;

        // malloc/free
        printf("malloc/free\n");
        {
            CZPerfCounter pc;
            for (int i = 1 * 1024 * 1024; i <= 8 * 1024 * 1024; i *= 2) {
                concurrency::parallel_for(0,50,[i](size_t x) {
                    std::vector<void *> ptrs;
                    ptrs.reserve(cnt);
                    for (int n = 0; n < cnt; n++) {
                        auto p = malloc(i);
                        ptrs.emplace_back(p);
                    }
                    for (int x = 0; x < num_fills; x++) {
                        for (auto p : ptrs) {
                            memset(p,num_fills,i);
                        }
                    }
                    for (auto p : ptrs) {
                        free(p);
                    }
                });
                printf("size %4d MB,elapsed %8.2f s,\n",i / (1024 * 1024),pc.elapsedMS() / 1000.0);
                pc.reset();
            }
        }
        printf("\n");
        printf("Total %6.2f s\n",pcTotal.elapsedMS() / 1000.0);
    }

    return 0;
}

令人惊讶的是,与Windows 7相比,Windows 10 CU的结果非常糟糕.我将下面的结果绘制为1MB块大小和8MB块大小,将线程数从2,4,…更改为28.当我们增加线程数时,性能略差,Windows 10的可扩展性更差.

我们已尝试确保应用所有Windows更新,更新驱动程序,调整BIOS设置,但未成功.我们还在其他几个硬件平台上运行了相同的基准测试,所有这些都为Windows 10提供了类似的曲线.所以它似乎是Windows 10的一个问题.

有没有人有类似的经历,或者对此有所了解(也许我们错过了什么？).这种行为使我们的多线程应用程序获得了显着的性能损失.

***已编辑

使用https://github.com/google/UIforETW(感谢Bruce Dawson)分析基准测试,我们发现大部分时间都花在内核KiPageFault上.进一步向下挖掘调用树,所有这些都导致ExpWaitForSpinLockExclusiveAndAcquire.似乎锁争用导致此问题.

***已编辑

在同一硬件上收集Server 2012 R2数据. Server 2012 R2也比Win7差,但仍然比Win10 CU好很多.

***已编辑

它也发生在Server 2016中.我添加了标签windows-server-2016.

***已编辑

使用来自@ Ext3h的信息,我修改了基准测试以使用VirtualAlloc和VirtualLock.与不使用VirtualLock时相比,我可以确认显着改进.当使用VirtualAlloc和VirtualLock时,整体Win10仍然比Win7慢30％到40％.