/* 
 * Program to measure high-res timer latency.
 *
 */
#include <stdint.h>
#include <stdbool.h>
#include <sys/types.h>
#include <unistd.h>
#include <time.h>
#include <errno.h>
#include <alloca.h>
#include <string.h>
#include <stdio.h>
#include <stdlib.h>

#ifndef N_SAMPLES
#define N_SAMPLES 100
#endif
#define _STR(_S_) #_S_
#define STR(_S_) _STR(_S_)

#define TS2NS(_TS_) ((((unsigned long long)(_TS_).tv_sec)*1000000000ULL) + (((unsigned long long)((_TS_).tv_nsec)))) 

int main(int argc, char *const* argv, char *const* envp)
{ struct timespec sample[N_SAMPLES+1];
  unsigned int cnt=N_SAMPLES, s=0 , avg_n=0;
  unsigned long long
    deltas [ N_SAMPLES ]
    , t1, t2, sum=0, zd=0, ic=0, d
    , t_start, avg_ns, *avgs=0;
  clockid_t clk = CLOCK_MONOTONIC_RAW;
  bool do_dump = false;
  int argn=1, repeat=1;
  for(; argn < argc; argn+=1)
    if( argv[argn] != NULL )
      if( *(argv[argn]) == '-')
	switch( *(argv[argn]+1) )
	{ case 'm':
	  case 'M':
	    clk = CLOCK_MONOTONIC;
	    break;
	  case 'd':
	  case 'D':
	    do_dump = true;
	    break;
     	  case 'r':
      	  case 'R':
	    if( (argn < argc) && (argv[argn+1] != NULL))
	      repeat = atoi(argv[argn+=1]);
	    break;
	  case '?':
	  case 'h':
	  case 'u':
	  case 'U':
	  case 'H':
	    fprintf(stderr,"Usage: timer_latency [\n\t-m : use CLOCK_MONOTONIC clock (not CLOCK_MONOTONIC_RAW)\n\t-d : dump timespec contents. N_SAMPLES: " STR(N_SAMPLES) "\n\t"
	            "-r <repeat count>\n]\t" 
	            "Calculates average timer latency (minimum time that can be measured) over N_SAMPLES.\n"
	           );
	    return 0;
	}
  if( repeat > 1 )
  { avgs=alloca(sizeof(unsigned long long) * (N_SAMPLES + 1));
    if( ((unsigned long) avgs) & 7 )
      avgs = ((unsigned long long*)(((unsigned char*)avgs)+(8-((unsigned long) avgs) & 7)));
  }
  do {
    cnt=N_SAMPLES;
    s=0;
  do
  { if( 0 != clock_gettime(clk, &sample[s++]) )
    { fprintf(stderr,"oops, clock_gettime() failed: %d: '%s'.\n", errno, strerror(errno));
      return 1;
    }
  }while( --cnt );
  clock_gettime(clk, &sample[s]);
  for(s=1; s < (N_SAMPLES+1); s+=1)
  { t1 = TS2NS(sample[s-1]);
    t2 = TS2NS(sample[s]);
    if ( (t1 > t2)
       ||(sample[s-1].tv_sec > sample[s].tv_sec)
       ||((sample[s-1].tv_sec == sample[s].tv_sec)
        &&(sample[s-1].tv_nsec > sample[s].tv_nsec)
         )
       )
    { fprintf(stderr,"Inconsistency: %llu %llu %lu.%lu %lu.%lu\n", t1 , t2
            , sample[s-1].tv_sec, sample[s-1].tv_nsec
            , sample[s].tv_sec,   sample[s].tv_nsec
      );
      ic+=1;
      continue;
    }
    d = t2 - t1;
    if ( d == 0 )
    {  zd += 1;
    }
    deltas[s-1] = d;
    if(do_dump)
      fprintf(stderr, "%lu %lu %llu\n",
              sample[s].tv_sec, sample[s].tv_nsec, d
             );
  }
  for(s = 0, sum=0; s < N_SAMPLES; s+=1)
    sum += deltas[s];
  fprintf(stderr,"sum: %llu\n",sum);
  avg_ns = sum / N_SAMPLES;
  t_start = TS2NS(sample[0]);
  t1=(t2 - t_start);
  printf("Total time: %1.1llu.%9.9lluS - Average Latency: %1.1llu.%9.9lluS N zero deltas: %u N inconsistent deltas: %u\n",
          t1 / 1000000000,       t1 % 1000000000,
          avg_ns / 1000000000,   avg_ns % 1000000000 ,
          zd, ic
        );
  if (avgs != ((void*)0UL))
    avgs[avg_n++] = avg_ns;
  } while (--repeat);
  if (avgs != ((void*)0UL))
  { for( s=0, sum=0; s < avg_n; s+=1)
      sum += avgs[s];
    printf("Average of %u average latencies of " STR(N_SAMPLES) " samples : %1.1llu.%9.9lluS\n"
          , avg_n, (sum / N_SAMPLES) / 1000000000, (sum / N_SAMPLES) % 1000000000
          );
  }
  return 0;
}