cvs commit: src/sys/kern sched_ule.c

[Kenneth Culver]

Quoting Niki Denev <nike_d at cytexbg.com>:

> Gleb Smirnoff writes:
>
>> On Wed, Jul 07, 2004 at 12:06:34PM -0400, Robert Watson wrote:
>> R> > J> >   Modified files:
>> R> > J> >     sys/kern             sched_ule.c
>> R> > J> >   Log:
>> R> > J> >   Temporarily disable preemption in SCHED_ULE due to 
>> reported panics and
>> R> > J> >   hangs due to recent preemption changes.  This change 
>> appears to remove
>> R> > J> >   the panic that I was running into, but at the cost of increasing
>> R> > J> >   ithread scheduling latency, and as such is a temporary 
>> band-aid until
>> R> > J> >   jhb has a chance to resolve the ule<->preemption 
>> interaction that is
>> R> > J> >   the source of the problem.  If it doesn't fix the 
>> problem for others--
>> R> > J> >   sorry!
>> R> > J> R> > J> It it just broken on SMP?  I actually did the commit 
>> from a UP preemption R> > J> kernel using SCHED_ULE from within X11 
>> with KDE, etc. running.
>> R> > R> > it is broken on UP, too. See thread in -current. R> R> An 
>> SMP kernel on a UP system, or a UP kernel on a UP system?
>>
>> UP kernel on a UP system
>>
>> -- Totus tuus, Glebius.
>> GLEBIUS-RIPN GLEB-RIPE
>
> Well, i'm running UP kernel (and without APIC) on UP machine (Laptop IBM TP
> X31), cvsupped on 5-th, 2 days ago. With SCHED_ULE, and i have not
> experienced any signs of instability... not a single panic :)
>
> --
> niki

Same here, except I'm running with apic on my x86 install, and I also tried to
reproduce this on my amd64 install. Neither one misbehaved at all.

Ken