> On Tue, Sep 17, 2002 at 07:11:52PM +0200, Peter Waechtler wrote:
>> Once I had a machine check exception - sine then I lowered the CPU
>> clock.
>> After the box was running fine with 180MHz I switched to 200MHz
>> (yes, I overclocked the CPUs with 233MHz 2 or 3 years - without
>> problems)
>
> I guess this explain the corruption. Please make sure the cpu are not
> overclocked at all and then try to reproduce. You cannot choose 180mhz
> or 200mhz randomly based on which kernel crashes or not, if the cpu are
> 180mhz ppro you should use 180mhz only, 200mhz will break. It won't
> break so easily as 233mhz, but it will, the timings are strict on smp.
> So please try to reproduce at 180mhz if the cpu should run at 180mhz.
>
> I don't want to sound boring but please next times try if you can
> reproduce on non overclocked hardware before reporting anything to l-k.
>
They are 200MHz PPros. So don't be bored.
To minimize the risk, I underclocked them, eh?
I slowed down memory timings - the box survived one night - but it
would be too early to count on this.
-
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/