From owner-freebsd-stable@FreeBSD.ORG  Sun Jul 11 23:19:24 2004
Return-Path: <owner-freebsd-stable@FreeBSD.ORG>
Delivered-To: freebsd-stable@freebsd.org
Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP id E1AC016A4CE
	for <freebsd-stable@freebsd.org>;
	Sun, 11 Jul 2004 23:19:24 +0000 (GMT)
Received: from mailhost.xciv.org (vantage.xciv.org [217.158.13.13])
	by mx1.FreeBSD.org (Postfix) with ESMTP id 6283C43D46
	for <freebsd-stable@freebsd.org>;
	Sun, 11 Jul 2004 23:19:24 +0000 (GMT)	(envelope-from paul@xciv.org)
Received: from localhost ([127.0.0.1] helo=xciv.org)
	by mailhost.xciv.org with esmtp
	id 1BjnbM-000Evy-00; Mon, 12 Jul 2004 00:19:20 +0100
X-Mailer: exmh version 2.6.3 04/04/2003 with nmh-1.0.4
To: freebsd-stable@freebsd.org
Organization: XCIV, London UK
In-reply-to: Your message of "Sun, 11 Jul 2004 15:34:52 PDT."
             <20040711153233.D76940@carver.gumbysoft.com> 
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Date: Mon, 12 Jul 2004 00:19:20 +0100
Message-ID: <57409.1089587960@xciv.org>
From: Paul Civati <paul@xciv.org>
X-XCIV-MailScanner: Found to be clean
Subject: Re: SMP and NMI errors (4.10)
X-BeenThere: freebsd-stable@freebsd.org
X-Mailman-Version: 2.1.1
Precedence: list
Reply-To: paul@xciv.org
List-Id: Production branch of FreeBSD source code
	<freebsd-stable.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-stable>,
	<mailto:freebsd-stable-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-stable>
List-Post: <mailto:freebsd-stable@freebsd.org>
List-Help: <mailto:freebsd-stable-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-stable>,
	<mailto:freebsd-stable-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Sun, 11 Jul 2004 23:19:25 -0000

Doug White <dwhite@gumbysoft.com> wrote:

> NMIs sometimes get triggered for ECC corrections, which is why a
> memtester wouldn't see it. 

Doh, yeah.

> I think there is a kernel option somewhere that hooks
> NMI and attempts to get information from the platform as to what DIMM
> triggered it.

Can't see anything for that, and there is only one DIMM, I have a 
second one to go in that I can swap to test.

> Otherwise you might check the Event Log in the BIOS for ECC events.

Alas no BIOS event log for this mobo.

> > If I boot a uniprocessor kernel this problem doesn't occur.
> It might be temperature related then :)

I was hoping no-one would say that :)

This is a 1U rack mount and currently seems to run at about ~40 deg. C
on CPU1, ~30 deg. C on CPU2 and ~33 deg. C system temp.  First CPU 
is a little hot perhaps but I don't think too high to be a problem?

-Paul-