Re: APIC error interrupr on CPU

From: Daniel J Blueman (daniel.j.blueman@stud.umist.ac.uk)
Date: Mon Mar 06 2000 - 06:52:41 EST


Hi Rainer,

I've occasionally experienced similar errors on my Abit BP6. I think this is
due to the main Intel BX (or equivalent) chip getting hot (mine hangs around
upto 52C!). This would tie in quite well with reports of people running
non-overclocked processors, but getting errors.

IMHO, the (possible) reason for the Abit BP6 giving these errors, is that
the BX chip gets even hotter due to a small area of voltage regulators
nearby which churn out quite a bit of heat - the iBX chip is known to become
flaky at >50C, and being a plastic BGA package heat dissipation is low
anyway.

Try cooling this instead of your processors.
Does anyone know how to tell is it's the local APIC or the one in the iBX
main chip?

Dan
__________________________
Daniel J Blueman
Undergraduate - BSc Computing Science
UMIST university - Manchester
Direct line: 0161 933 3569
Mobile: 07775 583766
Email: daniel.j.blueman@stud.umist.ac.uk
SMS: daniel.j.blueman@sms.genie.co.uk
----- Original Message -----
From: "Rainer Mager" <rvm@gol.com>
To: <linux-kernel@vger.rutgers.edu>
Sent: Monday, March 06, 2000 4:21 AM
Subject: Re: APIC error interrupr on CPU

> Hi all,
>
> I've received a few replies regarding my APIC errors (thanks!!).
> Basically everyone has said that these are "non-lethal" and usually caused
> by overclocking or by motherboards that aren't designed for the CPU speed
> that is running. Of course this is possible but in my case I am not
> overclocking and (according to the marketing) my MB is designed for my
CPUs
> (PIII 600s).
> I suppose I can live with these messages, especially if they do prove
to
> be non-lethal, but I would much prefer to "fix" the problem if that is
> possible. One possible solution that was given to me was to increase
> cooling. My CPUs are currently running at around 49 deg C right now. My
> understanding is that this is well within reasonable range. If I cooled
> these more, is it truly likely these errors will decrease?
> Another solution that was presented was adding the boot param,
> "nmi_watchdog=0". Can anyone explain what this is, what it does, and if it
> is a good idea or not?
>
> Thanks for the continued assistance,
>
> --Rainer
>
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.rutgers.edu
> Please read the FAQ at http://www.tux.org/lkml/

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Tue Mar 07 2000 - 21:00:19 EST