public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Norbert Breun <nbreun@gmx.de>
To: Mark Hahn <hahn@coffee.psychology.mcmaster.ca>
Cc: linux-kernel@vger.kernel.org
Subject: Re: 2.4.0-test12-pre3: kernel: APIC error on CPU0: 08(00) /Gigabyte GA-586DX SMP_BOARD
Date: Thu, 7 Dec 2000 06:59:01 +0100	[thread overview]
Message-ID: <00120706590100.03542@nmb> (raw)
In-Reply-To: <Pine.LNX.4.10.10012010234320.20188-100000@coffee.psychology.mcmaster.ca>
In-Reply-To: <Pine.LNX.4.10.10012010234320.20188-100000@coffee.psychology.mcmaster.ca>

Hallo Mark,

there is one thing, that is some kind of curious:

using 2.4.0-test12pre5 I've many apic errors with CPU1 a n d CPU0:

Dec  7 06:52:04 nmb kernel: APIC error on CPU1: 04(00)
Dec  7 06:52:04 nmb kernel: APIC error on CPU0: 02(00)
Dec  7 06:52:04 nmb kernel: APIC error on CPU0: 04(00)
Dec  7 06:52:07 nmb kernel: APIC error on CPU0: 02(00)
Dec  7 06:52:07 nmb kernel: APIC error on CPU1: 04(00)


running 2.4.0-test11ac4 apic errors only appear with CPU0:

Dec  6 13:41:33 nmb kernel: APIC error on CPU0: 01(00)
Dec  6 13:41:33 nmb kernel: APIC error on CPU0: 02(00)
Dec  6 13:42:07 nmb last message repeated 2 times
Dec  6 13:42:28 nmb last message repeated 10 times
Dec  6 13:42:32 nmb kernel: APIC error on CPU0: 04(00)
Dec  6 13:42:34 nmb kernel: APIC error on CPU0: 02(00)
Dec  6 13:42:39 nmb last message repeated 4 times
Dec  6 13:42:40 nmb kernel: APIC error on CPU0: 08(00)
Dec  6 13:42:49 nmb kernel: APIC error on CPU0: 02(00)
Dec  6 13:42:55 nmb kernel: APIC error on CPU0: 08(00)
Dec  6 13:43:02 nmb kernel: APIC error on CPU0: 02(00)

and n e v e r on CPU1 !
today I will compile 2.4.0-test12pre7 and 'll see....

kind regards
Norbert



On Friday 01 December 2000 08:36, Mark Hahn wrote:
> > > unfortunately, many SMP boards have noisy APIC lines.
> >
> > Hallo Mark,
> >
> > thank you for your immediate reply!
> > Do APIC errors mean => hardware errors? With the actual kernel
>
> they are corrected errors.  that is, the apic checksums its messages
> and retries.  obviously, if the corruption is bad enough, it'll hang.
>
> > (2.4.0-test12pre3) they apear less often...
>
> there have been tweaks to the kernel code that handles the error
> reports, and there have been changes in how the kernel uses apics.
>
> > Can I do anything to solve this problem besides buying a new board (I do
> > not need a new computer ;o))?
>
> nope.  among people who have abit bp6's (very prone to this problem),
> a number of voodoo techniques are used, including >=300W power,
> fan on the BX chipset, bios updates, etc.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/

       reply	other threads:[~2000-12-07  6:31 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <Pine.LNX.4.10.10012010234320.20188-100000@coffee.psychology.mcmaster.ca>
2000-12-07  5:59 ` Norbert Breun [this message]
2000-11-30 12:36 2.4.0-test12-pre3: kernel: APIC error on CPU0: 08(00) /Gigabyte GA-586DX SMP_BOARD Norbert Breun

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=00120706590100.03542@nmb \
    --to=nbreun@gmx.de \
    --cc=hahn@coffee.psychology.mcmaster.ca \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox