On Tue, 2007-02-27 at 13:53 +0000, Daniel Schnell wrote:
> Daniel Schnell wrote:
> > Hi,
> > 
> > I have a bad Kernel-Ooops on my MPC5200B based PPC target.
> > Unfortunately not reproducable with a small application again.
> > I used a 2.4.25 based Denx Kernel (latest and greatest version) and
> > Xenomai - trunk with revision 2256.
> > 
> 
> 
> If I increase MAX_DELAYED_MM in linux/kernel/sched.c from 32 to 64 the
> OOPS disappears ....
> 

Which is normal, since this is the BUG_ON() statement in sched.c:558
that triggers.

> As we have quite a number of concurrent threads running (>50) could
> MAX_DELAYED_MM be depending on the number of threads in the system ?

Some usage patterns involving permanent mode switches inside a large set
of real-time threads that only rarely relinquish the CPU to other
regular Linux tasks may cause this. This is specific to 2.4 kernels. I
will raise this value in the next patch update. Thanks,

-- 
Philippe.



_______________________________________________
Xenomai-help mailing list
[email protected]
https://mail.gna.org/listinfo/xenomai-help

Reply via email to