Messages in this thread | | | Date | Wed, 22 Jun 2005 10:44:22 +0200 (METDST) | From | Esben Nielsen <> | Subject | Re: [patch] Real-Time Preemption, -RT-2.6.12-V0.7.49-00 |
| |
On Wed, 22 Jun 2005, Ingo Molnar wrote:
> > * Esben Nielsen <simlo@phys.au.dk> wrote: > > > Yep, just as I pressed sent before I saw the following: > > ok, i'll have to look at the latency trace of this. > > > threshold violated: 28.0% (273usec) > > btw., are you sure this happened with latency timing/tracing disabled? > (the printks will disturb the rtc_wakeup test). > Yes. But I have been running the same load with latence timing on and have not seen traces of more than ~50us.
I do have problems with calibration of the clock in both rtc_wakeup and realfeel2 due to frequency scaling, but it looks like if I have a cpu-hog running it settles itself on the 697MHz as it should. But could this frequency scaling lead to bad readings? If it for some reason scales down the clock during a test it ought to give lower clock counts than the real ones, not higher...
> Ingo >
Esben
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |