From owner-freebsd-smp  Wed Nov 20 19:37:10 1996
Return-Path: owner-smp
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.5/8.7.3) id TAA01899
          for smp-outgoing; Wed, 20 Nov 1996 19:37:10 -0800 (PST)
Received: from dyson.iquest.net ([198.70.144.127])
          by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id TAA01891
          for <freebsd-smp@freebsd.org>; Wed, 20 Nov 1996 19:37:01 -0800 (PST)
Received: (from root@localhost) by dyson.iquest.net (8.8.2/8.6.9) id WAA02859; Wed, 20 Nov 1996 22:36:12 -0500 (EST)
From: "John S. Dyson" <toor@dyson.iquest.net>
Message-Id: <199611210336.WAA02859@dyson.iquest.net>
Subject: Re: vm_page_alloc(ZERO): missing pages...
To: peter@spinner.dialix.com (Peter Wemm)
Date: Wed, 20 Nov 1996 22:36:11 -0500 (EST)
Cc: smp@csn.net, ccsanady@friley216.res.iastate.edu, freebsd-smp@freebsd.org
In-Reply-To: <199611210321.LAA19697@spinner.DIALix.COM> from "Peter Wemm" at Nov 21, 96 11:21:10 am
Reply-To: dyson@freebsd.org
X-Mailer: ELM [version 2.4 PL24 ME8]
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: owner-smp@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

> 
> "John S. Dyson" wrote:
> > > 
> > > if it happens with only 1 processor running I would think it rules out the 
>     tlb 
> > > theory...
> > > 
> > Is the SMP code totally sync'ed with -current?  There was a severe problem
> > in earlier versions (and could have manifest the problem that you
> > describe.)  vm_page.c had the problem.
> > 
> > John
> 
> I agree - it is looking much more like the VM problem..  The smp code has 
> not recently been sync'ed with -current (like: 6-8 weeks ago), I'm in the 
> middle of that right at the moment..
> 
BTW, I now have an SMP capable P6 MB (SuperMicro P6DNF) with only one
processor (so far.)  I do have some filesystem, etc agendas in the offing,
but hope (soon) to be able to help/test the SMP code.  I know that my efforts
are best spent where I am most knowledgable, but do want to sync up and
help with the fine grained effort (whatever that might be) in the future.
(I certainly am not expert in SMP enough to architect the SMP code -- you
all seem to be doing really well, but am willing to help (participate) in
implementation of you all's good ideas :-)).

John