Re: SpeedStep / Geyserville lockups?
On Mon, May 14, 2001 at 02:28:09PM -0700, Karsten M. Self wrote:
> on Mon, May 14, 2001 at 07:08:40PM +0100, Alexander Clouter (alexander.clouter@ic.ac.uk) wrote:
> > On Sun, 13 May 2001, Karsten M. Self wrote:
> > >
> > > Is anyone else out there seeing lockups under 2.2.x (2.2.18 here) with a
> > > PIII SpeedStep (aka Geyserville) chip?
> > >
> > > I've had lockups over the past week I suspect are due to CPU step-speed
> > > changes resulting from power source switching.
> > >
> > isn't there an option in the bios to banish this 'feature'? I remember
> > there being reference to this in a couple of places. Once disabled I
> > guess you could solely use 'CPU Idle' calls to cool your cpu, which I
> > assume has the same *effect*.
>
> There is.
>
> I've set CPU speed to "maximum" (forget the precise opts, believe they're
> max, min, auto, reverse). System's been up for 19 hours w/o problems,
> previously I was lucky to get an hour.
>
> Note also that SpeedStep is probably more useful under an OS which
> doesn't have preemptive multitasking. My understanding of Win9X/ME was
> that it ran at full tilt unless specifically idled, this information
> coming from VMWare experiences. NT/2K and GNU/Linux have an idle cycle
> which actually idles the CPU.
>
> What's the CPU Idle call you're referringn to?
That's the APM idle, enable it in the BIOS config so the kernel will tell
the BIOS when it is idle. The ordinary idle you're talking about is when
the kernel runs the halt instruction, which does indeed keep the CPU cool
(and save a lot of power if your CPU takes most of the power in the system)
but the BIOS will never know to go into sleep mode.
--
#define X(x,y) x##y
Peter Cordes ; e-mail: X(peter@llama.nslug. , ns.ca)
"The gods confound the man who first found out how to distinguish the hours!
Confound him, too, who in this place set up a sundial, to cut and hack
my day so wretchedly into small pieces!" -- Plautus, 200 BCE
Reply to: