Detlef Vollmann wrote: > Gilles Chanteperdrix wrote: > > Detlef Vollmann wrote: > > > With that change, first tests look fine. > > > > Thanks, attached the patch with this error corrected. > Thanks. > > > > BTW, on the SA, what results do you get from xeno-test? > > > > latency in user-space easily get above 100 microseconds, if this is what > > you mean. But I guess this is what we should expect on ARM. > Probably yes. The histogram just looks a bit strange, nearly > all in the last column... > > Another point: did you run the switchbench test? > > With '-n 100000' I get a sure softlock.
Probably the default sampling period of 100 us is too hard for ARM, Xenomai never gets out of the timer interrupt handler, you should try and pass -p 1000. -- Gilles Chanteperdrix. _______________________________________________ Xenomai-core mailing list Xenomai-core@gna.org https://mail.gna.org/listinfo/xenomai-core