Linuxperf_event_open
系统调用与config = PERF_COUNT_HW_CPU_CYCLES
此系统调用对以下内容具有显式控制:
因此,即使多个进程同时运行,它也会正确计算周期。
有关更多详细信息,请参阅此答案:如何从 C++ 获取 x86_64 中的 CPU 周期计数?
perf_event_open.c
#include <asm/unistd.h>
#include <linux/perf_event.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/ioctl.h>
#include <unistd.h>
#include <inttypes.h>
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;
}
int
main(int argc, char **argv)
{
struct perf_event_attr pe;
long long count;
int fd;
uint64_t n;
if (argc > 1) {
n = strtoll(argv[1], NULL, 0);
} else {
n = 10000;
}
memset(&pe, 0, sizeof(struct perf_event_attr));
pe.type = PERF_TYPE_HARDWARE;
pe.size = sizeof(struct perf_event_attr);
pe.config = PERF_COUNT_HW_CPU_CYCLES;
pe.disabled = 1;
pe.exclude_kernel = 1;
// Don't count hypervisor events.
pe.exclude_hv = 1;
fd = perf_event_open(&pe, 0, -1, -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);
/* Loop n times, should be good enough for -O0. */
__asm__ (
"1:;\n"
"sub $1, %[n];\n"
"jne 1b;\n"
: [n] "+r" (n)
:
:
);
ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
read(fd, &count, sizeof(long long));
printf("%lld\n", count);
close(fd);
}