Re: [Xenomai-help] Re: A fairly small rtnet/Xenomai...

[Philippe Gerum <rpm@xenomai.org>]

On Thu, 2007-01-04 at 21:57 +0100, Niklaus Giger wrote:
> Am Dienstag, 2. Januar 2007 10:53 schrieb Philippe Gerum:
> > On Tue, 2007-01-02 at 09:23 +0100, M. Koehrer wrote:
> > > Happy new year to all!
> > >
> > > Back in the office, I tried out the patches from Chilles and Philippe.
> > > And yes, it is working now! No crash!
> > > Using these patches, I can now call a system() call out of a rea ltime
> > > task that is followed by a rt_task_sleep() and a printf() without crash
> > > on a 2.6.19 kernel.
> > >
> > > Thanks for the support!
> > >
> > > Best regards
> > >
> > > Mathias
> > >
> > > > > here comes a workaround for the COW issue on Linux 2.6.19. The patch
> > > > > relies on a new VM_NOCOW flag which should be set for real-time
> > > > > application if you use Xenomai trunk.
> > > > >
> > > > > It would be nice if you could test it.
> > > >
> > > > You will additionally need to apply this patch to the Xenomai tree in
> > > > order to activate the COW-disable feature:
> >
> > Great, thanks. Niklaus, could you check the vm-nocow patch for 2.6.14 on
> > the ppc board (the hcu, IIRC) that exhibited strange faults in
> > user-space while running the latency test, especially when enabling the
> > nucleus debug option (the one which also used to cause secondary switch
> > warnings being sent by Xenomai to the kernel log)? TIA,
> Here the results. I had no problems running xeno-test.
> 

Nice.

> I did set in my .config
> CONFIG_XENO_OPT_DEBUG=y
> CONFIG_XENO_OPT_DEBUG_NUCLEUS=y
> 
> Attached is my .config and the output of xeno-test.
> 
> If you need the results of another combination just let me know.

That's fine, thanks.

-- 
Philippe.