4

我正在尝试使用perf. 尽管在下面的代码中确实出现了，即使pid参数perf_event_open是0（这应该导致整个进程的分析？），硬件计数器值仅对应于执行线程（与 perf 计数器在线程中求和）过程）inf_loop不被计算在内。

我的问题是：如何分析进程中的所有线程与仅执行perf_event_open如下的线程？perf_event_attr是否需要设置其他配置以启用进程范围的分析？

static long perf_event_open(struct perf_event_attr *hw_event, pid_t pid,
        int cpu, int group_fd, unsigned long flags)
{
    int ret;
    ret = syscall(__NR_perf_event_open, hw_event, pid, cpu,
            group_fd, flags);
    return ret;
}

static int fd;

void setup()
{
   struct perf_event_attr pe;
   memset(&pe, 0, sizeof(pe));
   pe.type     = PERF_TYPE_HARDWARE;
   pe.size     = sizeof(pe);
   pe.config   = PERF_COUNT_HW_INSTRUCTIONS;
   pe.disabled = 1;
   pe.exclude_kernel = 1;
   pe.exclude_hv     = 1;
   pid_t pid = 0;
   int cpu   = -1;
   fd = perf_event_open(&pe, pid, cpu, -1, 0);
   if (fd == -1) {
       fprintf(stderr, "Error opening leader %llx\n", pe.config);
       exit(EXIT_FAILURE);
   }
   ioctl(fd, PERF_EVENT_IOC_RESET, 0);
   ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
}

int64_t read()
{
    int64_t count;
    read(fd, &count, sizeof(count));
    return count;
}

std::size_t k;

// The instruction counts do not reflect the cycles consumed here
void inf_loop()
{
    k = 2;
    volatile size_t *p = &k;
    while (*p)
    {
        ++k;
    }
}

int main(int argc, char **argv)
{
   setup();
   thread t1(inf_loop);
   int count = 0;
   for (uint64_t idx = 0; idx < (1ULL << 54); ++idx)
   {
       if (idx % (1ULL << 32) == 0)
       {
           cout << "Cycles: " << read() << endl;
       }
   }
}
4

1 回答 1

1

您想要的是perf_event_attr'sinherit标志，它将子线程计数合并到父线程中。

于 2021-08-09T04:12:45.700 回答