Profile how much CPU time a system call or any amount of code consumes

profiler.c

#define _GNU_SOURCE
#include <stdio.h>
#include <stdint.h>
#include <time.h>
#include <sched.h>
#include <err.h>
#include <sys/types.h>
#include <sys/syscall.h>
#include <pthread.h>
#include <unistd.h>
#include <stdlib.h>

#define SYSCHK(x) ({            \
    typeof(x) __res = (x);      \
    if (__res == (typeof(x))-1) \
      err(1, "SYSCHK(" #x ")"); \
    __res;                      \
})

void pin_on_cpu(int i) {
    cpu_set_t mask;
    CPU_ZERO(&mask);
    CPU_SET(i, &mask);
    sched_setaffinity(0, sizeof(mask), &mask);
}

static inline long long ts_to_ns(const struct timespec *ts) {
    return (long long)ts->tv_sec * 1000000000LL + (long long)ts->tv_nsec;
}

#define NUM_SAMPLES 100000
static long int clock_gettime_avg = 0;

// Can overflow if `NUM_SAMPLES` is too high, but with simple syscalls,
// this works just fine
long int getpid_avg_cputime_used() {
    struct timespec *ts = malloc(NUM_SAMPLES * sizeof(struct timespec));

    if (clock_gettime_avg == 0) {
        for (int i = 0; i < NUM_SAMPLES; i++) {
            syscall(__NR_clock_gettime, CLOCK_THREAD_CPUTIME_ID, &ts[i]);
        } 
    
        long int total_nsec = 0;
    
        for (int i = 0; i < NUM_SAMPLES-1; i++) {
            long int time_taken = (long int)(ts_to_ns(&ts[i + 1]) - ts_to_ns(&ts[i]));
            total_nsec += time_taken;
        }
    
        clock_gettime_avg = total_nsec / (NUM_SAMPLES-1);
    }

    for (int i = 0; i < NUM_SAMPLES; i++) {
        syscall(__NR_clock_gettime, CLOCK_THREAD_CPUTIME_ID, &ts[i]);
        
        // Do whatever you're measuring here
        syscall(__NR_getpid);
    }

    long int total_nsec = 0;
    for (int i = 0; i < NUM_SAMPLES-1; i++) {
        long int time_taken = (long int)(ts_to_ns(&ts[i + 1]) - ts_to_ns(&ts[i])) - clock_gettime_avg;
        total_nsec += time_taken;
    }

    free(ts);
    return total_nsec / (NUM_SAMPLES-1);
}

int main(int argc, char *argv[]) {
    pin_on_cpu(0); // VERY important to pin to one CPU

    long int timer_settime_avg = getpid_avg_cputime_used();
    printf("clock_gettime avg: %ld ns\n", clock_gettime_avg);
    printf("getpid avg: %ld ns\n", timer_settime_avg);

    return 0;
}