Hi Viresh,
On 04/04/2013 07:54 AM, Viresh Kumar wrote:
> Hi Stratos,
>
> Yes, your results show some improvements. BUT if performance is the only thing
> we were looking for, then we will never use ondemand governor but performance
> governor.
>
> I suspect this little increase in performance must have increased power
> numbers
> too (significantly). So, if you can get numbers in the form of
> power/performance
> with and without your patch, it will be great.
>
> --
> viresh
>
I run some more tests. I increased the number of iterations to 100 (from 20).
I also test for counter 1,000,000 (~4200us), 5,000,000 (~10000us), 15,000,000
(~30000us).
This time, I also extracted statistics from cpufreq_stats driver. I think this
will be an
indication for power consumption. Below the results and attached the program I
used for to
get these numbers.
Thanks for your time,
Stratos
--------------------------
counter 1,000,000
average diff: 0.184%
run 0
-----
cpufreq off on
------- ------- ----
3401000 686 702
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 0 0
2000000 0 0
1900000 0 0
1700000 0 0
1600000 4957 4940
early_demand off: 4207 us
early_demand on: 4214 us
diff: -0.17%
run 1
-----
cpufreq off on
------- ------- ----
3401000 513 665
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 0 0
2000000 0 0
1900000 0 0
1700000 0 0
1600000 5130 4978
early_demand off: 4208 us
early_demand on: 4194 us
diff: 0.33%
run 2
-----
cpufreq off on
------- ------- ----
3401000 630 487
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 0 0
2000000 0 0
1900000 0 0
1700000 0 0
1600000 5013 5155
early_demand off: 4210 us
early_demand on: 4200 us
diff: 0.24%
run 3
-----
cpufreq off on
------- ------- ----
3401000 666 602
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 0 0
2000000 0 0
1900000 0 0
1700000 0 0
1600000 4976 5040
early_demand off: 4205 us
early_demand on: 4183 us
diff: 0.52%
run 4
-----
cpufreq off on
------- ------- ----
3401000 527 725
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 0 0
2000000 0 0
1900000 0 0
1700000 0 0
1600000 5116 4917
early_demand off: 4193 us
early_demand on: 4193 us
diff: 0.00%
-------------------------
counter 5,000,000
average diff: 1.184%
run 0
-----
cpufreq off on
------- ------- ----
3401000 1994 2294
3400000 0 0
3300000 0 49
3100000 40 0
3000000 11 1
2900000 0 49
2800000 0 1
2600000 0 0
2500000 0 0
2400000 55 0
2200000 0 4
2100000 0 0
2000000 0 0
1900000 46 1
1700000 0 0
1600000 3558 3304
early_demand off: 10423 us
early_demand on: 10441 us
diff: -0.17%
run 1
-----
cpufreq off on
------- ------- ----
3401000 2112 2174
3400000 0 0
3300000 7 38
3100000 0 0
3000000 49 0
2900000 0 49
2800000 39 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 0 1
2000000 0 0
1900000 37 38
1700000 44 11
1600000 3416 3390
early_demand off: 10538 us
early_demand on: 10239 us
diff: 2.83%
run 2
-----
cpufreq off on
------- ------- ----
3401000 2107 2296
3400000 0 0
3300000 0 0
3100000 0 22
3000000 95 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 49 11
2200000 0 0
2100000 0 0
2000000 0 49
1900000 11 34
1700000 0 0
1600000 3443 3291
early_demand off: 10434 us
early_demand on: 10439 us
diff: -0.05%
run 3
-----
cpufreq off on
------- ------- ----
3401000 2106 2308
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 11
2900000 0 0
2800000 0 0
2600000 0 0
2500000 59 0
2400000 13 46
2200000 0 0
2100000 0 0
2000000 0 0
1900000 0 4
1700000 0 0
1600000 3527 3333
early_demand off: 10541 us
early_demand on: 10238 us
diff: 2.87%
run 4
-----
cpufreq off on
------- ------- ----
3401000 1899 2197
3400000 0 0
3300000 0 0
3100000 49 99
3000000 0 0
2900000 0 0
2800000 21 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 0 0
2000000 20 0
1900000 4 11
1700000 0 14
1600000 3710 3383
early_demand off: 10432 us
early_demand on: 10339 us
diff: 0.89%
--------------------------
counter 10,000,000
average diff: 0.336%
run 0
-----
cpufreq off on
------- ------- ----
3401000 2106 2232
3400000 0 0
3300000 0 42
3100000 29 0
3000000 0 0
2900000 0 0
2800000 49 0
2600000 0 0
2500000 0 0
2400000 11 49
2200000 0 0
2100000 0 0
2000000 52 0
1900000 47 0
1700000 0 0
1600000 3507 3478
early_demand off: 20169 us
early_demand on: 20036 us
diff: 0.66%
run 1
-----
cpufreq off on
------- ------- ----
3401000 2210 2146
3400000 0 0
3300000 44 0
3100000 49 10
3000000 0 0
2900000 3 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 0 0
2000000 0 0
1900000 0 3
1700000 0 0
1600000 3496 3643
early_demand off: 20142 us
early_demand on: 20137 us
diff: 0.03%
run 2
-----
cpufreq off on
------- ------- ----
3401000 2133 2135
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 35
2600000 0 0
2500000 21 0
2400000 53 39
2200000 0 0
2100000 0 0
2000000 49 0
1900000 38 49
1700000 0 48
1600000 3506 3495
early_demand off: 20037 us
early_demand on: 19934 us
diff: 0.51%
run 3
-----
cpufreq off on
------- ------- ----
3401000 2166 2125
3400000 0 0
3300000 0 0
3100000 0 5
3000000 11 0
2900000 43 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 0 55
2200000 28 0
2100000 8 54
2000000 0 0
1900000 0 34
1700000 11 0
1600000 3535 3525
early_demand off: 20038 us
early_demand on: 19940 us
diff: 0.49%
run 4
-----
cpufreq off on
------- ------- ----
3401000 2122 2125
3400000 0 0
3300000 25 0
3100000 0 5
3000000 29 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 0 55
2200000 0 0
2100000 0 54
2000000 0 0
1900000 0 34
1700000 0 0
1600000 3626 3525
early_demand off: 20037 us
early_demand on: 20039 us
diff: -0.01%
--------------------------
counter 15,000,000
average diff: 0.21%
run 0
-----
cpufreq off on
------- ------- ----
3401000 2226 2262
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 22 0
2200000 0 0
2100000 0 49
2000000 38 0
1900000 60 0
1700000 0 0
1600000 3555 3592
early_demand off: 29940 us
early_demand on: 30038 us
diff: -0.33%
run 1
-----
cpufreq off on
------- ------- ----
3401000 2466 2582
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 38
2400000 37 0
2200000 0 11
2100000 0 0
2000000 0 11
1900000 0 0
1700000 0 0
1600000 3400 3260
early_demand off: 30033 us
early_demand on: 29934 us
diff: 0.33%
run 2
-----
cpufreq off on
------- ------- ----
3401000 2545 2195
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 24 4
2200000 0 4
2100000 34 0
2000000 6 0
1900000 0 0
1700000 0 0
1600000 3294 3700
early_demand off: 30131 us
early_demand on: 30028 us
diff: 0.34%
run 3
-----
cpufreq off on
------- ------- ----
3401000 2327 2362
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 2 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 11 0
2000000 0 1
1900000 0 0
1700000 4 39
1600000 3558 3500
early_demand off: 29938 us
early_demand on: 29930 us
diff: 0.03%
run 4
-----
cpufreq off on
------- ------- ----
3401000 2303 2246
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 11
2500000 9 0
2400000 56 0
2200000 0 0
2100000 11 0
2000000 0 0
1900000 0 49
1700000 0 0
1600000 3525 3596
early_demand off: 30137 us
early_demand on: 29931 us
diff: 0.68%
--------------------------
counter 20,000,000
average diff: 0.038%
run 0
-----
cpufreq off on
------- ------- ----
3401000 2498 2483
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 0 0
2000000 1 0
1900000 0 19
1700000 0 33
1600000 3504 3468
early_demand off: 39917 us
early_demand on: 39925 us
diff: -0.02%
run 1
-----
cpufreq off on
------- ------- ----
3401000 2338 2405
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 0 0
2000000 0 0
1900000 75 9
1700000 0 0
1600000 3593 3589
early_demand off: 40130 us
early_demand on: 39927 us
diff: 0.51%
run 2
-----
cpufreq off on
------- ------- ----
3401000 2344 2342
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 17 49
2000000 0 0
1900000 32 0
1700000 0 0
1600000 3610 3612
early_demand off: 39930 us
early_demand on: 39930 us
diff: 0.00%
run 3
-----
cpufreq off on
------- ------- ----
3401000 2631 2490
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 0 0
2000000 0 0
1900000 0 37
1700000 0 12
1600000 3373 3465
early_demand off: 39937 us
early_demand on: 39938 us
diff: 0.00%
run 4
-----
cpufreq off on
------- ------- ----
3401000 2298 2451
3400000 0 0
3300000 0 0
3100000 0 0
3000000 0 0
2900000 0 0
2800000 0 0
2600000 0 0
2500000 0 0
2400000 0 0
2200000 0 0
2100000 0 0
2000000 0 0
1900000 0 0
1700000 0 0
1600000 3708 3553
early_demand off: 40126 us
early_demand on: 39937 us
diff: 0.47%
#define _GNU_SOURCE
#include <pthread.h>
#include <stdio.h>
#include <sys/time.h>
#include <unistd.h>
#include <sched.h>
struct timeval start, end;
unsigned long long i, cnt;
long utime, seconds, useconds;
void enable_early() {
system("echo 1 > /sys/devices/system/cpu/cpufreq/ondemand/early_demand");
system("rmmod cpufreq_stats");
system("modprobe cpufreq_stats");
}
void disable_early() {
system("echo 0 > /sys/devices/system/cpu/cpufreq/ondemand/early_demand");
system("rmmod cpufreq_stats");
system("modprobe cpufreq_stats");
}
void calibrate()
{
sleep(1);
gettimeofday(&start, NULL);
for (i = 0; i < 1000000000; i++);
gettimeofday(&end, NULL);
seconds = end.tv_sec - start.tv_sec;
useconds = end.tv_usec - start.tv_usec;
utime = seconds * 1000000 + useconds;
printf("Calibrating\n");
printf("Elapsed time: %ld microseconds\n", utime);
/* find the counter for 10ms */
cnt = i * 10000 / utime;
printf("cnt: %ld\n", cnt);
}
long do_bench()
{
gettimeofday(&start, NULL);
for (i = 0; i < cnt; i++);
gettimeofday(&end, NULL);
seconds = end.tv_sec - start.tv_sec;
useconds = end.tv_usec - start.tv_usec;
utime = seconds * 1000000 + useconds;
printf("Elapsed time: %ld microseconds\n", utime);
return utime;
}
void benchmark()
{
const int iter = 100;
long total_off = 0;
long total_on = 0;
double diff_perc;
unsigned int i;
/* calibrate(); */
cnt = 1000000;
disable_early();
sleep(1);
do_bench(); /* do a first benchmark but do not count in total */
sleep(5);
for (i = 0; i < iter; i++) {
total_off += do_bench();
usleep(500000);
}
total_off /= iter;
system("cat /sys/devices/system/cpu/cpu2/cpufreq/stats/time_in_state");
enable_early();
sleep(1);
do_bench(); /* do a first benchmark but do not count in total */
sleep(5);
for (i = 0; i < iter; i++) {
total_on += do_bench();
usleep(500000);
}
total_on /= iter;
system("cat /sys/devices/system/cpu/cpu2/cpufreq/stats/time_in_state");
diff_perc = (total_off - total_on) * 100;
diff_perc /= total_off;
printf("early_demand off: %ld us\n", total_off);
printf("early_demand on: %ld us\n", total_on);
printf("diff: %f\n", diff_perc);
}
main ()
{
int i;
cpu_set_t mask;
CPU_ZERO(&mask);
CPU_SET(2, &mask);
sched_setaffinity(0, sizeof(mask), &mask);
printf("Starting benchmark\n");
for (i = 0; i < 5; i++) {
printf("run %i\n", i);
benchmark();
}
}
