From owner-freebsd-current  Mon Mar 11 08:32:16 1996
Return-Path: owner-current
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.3/8.7.3) id IAA19701
          for current-outgoing; Mon, 11 Mar 1996 08:32:16 -0800 (PST)
Received: from brasil.moneng.mei.com (brasil.moneng.mei.com [151.186.109.160])
          by freefall.freebsd.org (8.7.3/8.7.3) with ESMTP id IAA19695
          for <current@FreeBSD.ORG>; Mon, 11 Mar 1996 08:32:12 -0800 (PST)
Received: (from jgreco@localhost) by brasil.moneng.mei.com (8.7.Beta.1/8.7.Beta.1) id KAA17767; Mon, 11 Mar 1996 10:30:39 -0600
From: Joe Greco <jgreco@brasil.moneng.mei.com>
Message-Id: <199603111630.KAA17767@brasil.moneng.mei.com>
Subject: Re: AMD doesn't like SNAP! (panic: unwire: page not in pmap)
To: rgrimes@gndrsh.aac.dev.com (Rodney W. Grimes)
Date: Mon, 11 Mar 1996 10:30:39 -0600 (CST)
Cc: jehamby@lightside.com, current@FreeBSD.ORG, jkh@time.cdrom.com,
        toor@dyson.iquest.net
In-Reply-To: <199603100445.UAA10659@GndRsh.aac.dev.com> from "Rodney W. Grimes" at Mar 9, 96 08:45:51 pm
X-Mailer: ELM [version 2.4 PL24]
Content-Type: text
Sender: owner-current@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

> > So far three people, including myself, have reported the above panic
> > message when booting the 3/3 SNAP kernel.  All three of us have AMD DX4
> > processors (100 and 120MHz).  This has got to be the problem!  John,
> > Jordan, people working on the VM system, take note..  Thanks! 
> 
> Can all three of you tell me if you have A80486DX4-100NV8T's or
> A80486DX4-100SV8B's?  The difference is the SV8B is the write back
> enhanced DX4 and unless you have a motherboard that understands
> how to deal with this you are going to have a cache coherency problem
> between the internal and external cache.
> 
> I have yet to see a MB deal with this correctly when faced with 
> a bus master SCSI controller, though I have seen some that work fine
> as long as no bus mastering is occuring.  Far more don't work than
> do work.
> 
> If you don't have SV8B's or are not running them in WB mode, then
> I don't have any idea what has gone wrong...

Ummmm.  Ummmm..  that may explain a problem I have been seeing.  :-)

I have a pair of DX4/120's ("Enhanced"), one with IDE disk, one with 1542
and SCSI disk.  The one with SCSI disk is unhappy during big compiles (make
world, etc).  I haven't _noticed_ problems with the IDE disk.  Same MB/cpu,
etc.

Rod, you seem to imply that by NOT running them in WB mode, the problem may
not manifest itself (dependent upon the MB).  Is this what you meant to
imply?

Can you recommend a good 486 motherboard (preferably PCI)?

Argh, I just got the fingers on my left hand wired to equipment in the next
office..  hard to type..

I noticed ASUS seems to have several other offerings besides the SP3G..

Thx,

... JG