roland Tollenaar wrote:
>>Just run latency -p 1000 with some load. If you observe abnormal
>>latencies with the latency test, then you have a hardware problem. If
>>you observe normal latencies with the latency test, then your
>>application has a problem.
>
>
> The results:
>
> RTD| 29.333| 31.009| 179.352| 0| 29.333| 204.495
> RTD| 29.333| 31.009| 201.142| 0| 29.333| 204.495
> RTD| 29.333| 31.009| 203.657| 0| 29.333| 204.495
> RTD| 29.333| 31.847| 201.980| 0| 29.333| 204.495
> RTD| 29.333| 31.009| 181.866| 0| 29.333| 204.495
> RTD| 29.333| 31.847| 201.142| 0| 29.333| 204.495
> RTD| 29.333| 31.009| 202.819| 0| 29.333| 204.495
> RTT| 00:00:22 (periodic user-mode task, 1000 us period, priority 99)
> RTH|-----lat min|-----lat avg|-----lat max|-overrun|----lat best|---lat worst
> RTD| 29.333| 31.847| 209.523| 0| 29.333| 209.523
> RTD| 29.333| 31.847| 206.171| 0| 29.333| 209.523
> RTD| 29.333| 31.847| 204.495| 0| 29.333| 209.523
> RTD| 29.333| 31.847| 204.495| 0| 29.333| 209.523
> RTD| 29.333| 31.847| 203.657| 0| 29.333| 209.523
> RTD| 29.333| 31.847| 203.657| 0| 29.333| 209.523
> RTD| 29.333| 31.009| 178.514| 0| 29.333| 209.523
> RTD| 29.333| 30.171| 201.142| 0| 29.333| 209.523
> RTD| 29.333| 30.171| 199.466| 0| 29.333| 209.523
> RTD| 29.333| 31.009| 200.304| 0| 29.333| 209.523
> RTD| 29.333| 30.171| 180.190| 0| 29.333| 209.523
> RTD| 28.495| 31.009| 201.142| 0| 28.495| 209.523
> RTD| 29.333| 31.009| 201.142| 0| 28.495| 209.523
> RTD| 29.333| 31.009| 204.495| 0| 28.495| 209.523
> RTD| 29.333| 31.009| 200.304| 0| 28.495| 209.523
> RTD| 29.333| 31.009| 203.657| 0| 28.495| 209.523
> RTD| 29.333| 31.009| 200.304| 0| 28.495| 209.523
> RTD| 29.333| 30.171| 201.142| 0| 28.495| 209.523
> RTD| 29.333| 30.171| 201.980| 0| 28.495| 209.523
> RTD| 29.333| 31.009| 202.819| 0| 28.495| 209.523
> ---|------------|------------|------------|--------|-------------------------
> RTS| 28.495| 30.171| 209.523| 0| 00:00:42/00:00:42
>
>
> IMHO this looks ok does it not?
To get reliable results, you should run the test for a few hours. Not 22
seconds.
--
Gilles Chanteperdrix
_______________________________________________
Xenomai-help mailing list
[email protected]
https://mail.gna.org/listinfo/xenomai-help
