前阵子接触到一道关于数组内部链表(多用于内存池技术)的数据结构的题, 这种数据结构能够比普通链表在cache中更容易命中, 理由很简单, 就是因为其在地址上是连续的(=.=!), 借这个机会, 就对cpu cache进行了一个研究, 今天做一个简单的分享, 首先先来普及一下cpu cache的知识, 这里的cache是指cpu的高速缓存. 在我们程序员看来, 缓存是一个透明部件. 因此, 程序员通常无法直接干预对缓存的操作. 但是, 确实可以根据缓存的特点对程序代码实施特定优化, 从而更好地利用高速缓存. 

#define EXEC_COUNT (100 * 1000 * 1000)

struct bits_t
{
    int a;
    char placeholder[64];
    int b;
};

struct bits_t bits;

int which_cpu(const char* prefix_)
{
    #ifdef ENABLE_WHCIH_CPU
    cpu_set_t cur_cpu;
    CPU_ZERO(&cur_cpu);
    if (sched_getaffinity(0, sizeof(cur_cpu), &cur_cpu) == -1) 
    { 
        printf("warning: cound not get cpu affinity, continuing...\\n"); 
        return -1;
    } 
    int num = sysconf(_SC_NPROCESSORS_CONF);
    for (int i = 0; i < num; i++) 
    { 
        if (CPU_ISSET(i, &cur_cpu)) 
        { 
            printf("[%s] this process %d is running processor : %d\\n", prefix_, getpid(), i); 
        } 
    } 
    #endif

    return 0;
}

int set_cpu(int cpu_id_)
{
    #ifdef ENABLE_SET_CPU
    cpu_set_t mask;
    CPU_ZERO(&mask); 
    CPU_SET(cpu_id_, &mask); 
    if (sched_setaffinity(0, sizeof(mask), &mask) == -1) 
    { 
        printf("warning: could not set CPU affinity, continuing...\\n"); 
        return -1;
    } 
    #endif

    return 0;
}

void* thd_func1(void* arg_)
{
    set_cpu(0);
    which_cpu("thread 1 start");
    timeval begin_tv;
    gettimeofday(&begin_tv, NULL);

    for (int i = 0; i < EXEC_COUNT; i++)
    {
        bits.a += 1;
        int a = bits.a;
    }

    timeval end_tv;
    gettimeofday(&end_tv, NULL);
    printf("thd1 perf:[%lu]us\\n", (end_tv.tv_sec * 1000 * 1000 + end_tv.tv_usec) - (begin_tv.tv_sec * 1000 * 1000 + begin_tv.tv_usec));
    which_cpu("thread 1 end");

    return NULL;
}

void* thd_func2(void* arg_)
{
    set_cpu(1);
    which_cpu("thread 2 start");
    timeval begin_tv;
    gettimeofday(&begin_tv, NULL);

    for (int i = 0; i < EXEC_COUNT; i++)
    {
        bits.b += 2;
        int b = bits.b;
    }

    timeval end_tv;
    gettimeofday(&end_tv, NULL);
    printf("thd2 perf:[%lu]us\\n", (end_tv.tv_sec * 1000 * 1000 + end_tv.tv_usec) - (begin_tv.tv_sec * 1000 * 1000 + begin_tv.tv_usec));
    which_cpu("thread 2 end");

    return NULL;
}

int main(int argc_, char* argv_[])
{
    int num = sysconf(_SC_NPROCESSORS_CONF);
    printf("system has %d processor(s).\\n", num);
    cpu_set_t cpu_mask;
    cpu_set_t cur_cpu_info;

    memset((void*)&bits, 0, sizeof(bits_t));
    set_cpu(0);
    which_cpu("main thread");

    pthread_t pid1;
    pthread_create(&pid1, NULL, thd_func1, NULL);

    pthread_t pid2;
    pthread_create(&pid2, NULL, thd_func2, NULL);

    pthread_join(pid1, NULL);
    pthread_join(pid2, NULL);

    return 0;
}

     情况二测试结果:

     情况四测试结果:

建议继续学习：

1. 进程上下文切换 – 残酷的性能杀手（上）    (阅读：3310)