From owner-freebsd-current  Sat Sep 14 10:29:16 1996
Return-Path: owner-current
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.5/8.7.3) id KAA26511
          for current-outgoing; Sat, 14 Sep 1996 10:29:16 -0700 (PDT)
Received: from GndRsh.aac.dev.com (GndRsh.aac.dev.com [198.145.92.241])
          by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id KAA26500;
          Sat, 14 Sep 1996 10:29:11 -0700 (PDT)
Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.6.12/8.6.12) id KAA04566; Sat, 14 Sep 1996 10:28:01 -0700
From: "Rodney W. Grimes" <rgrimes@GndRsh.aac.dev.com>
Message-Id: <199609141728.KAA04566@GndRsh.aac.dev.com>
Subject: Re: VM/kernel problems?
To: simonm@dcs.gla.ac.uk (Simon Marlow)
Date: Sat, 14 Sep 1996 10:28:00 -0700 (PDT)
Cc: jmb@freefall.freebsd.org, michaelh@cet.co.jp, mrcpu@cdsnet.net,
        jhs@freebsd.org, sysseh@devetir.qld.gov.au, current@freebsd.org
In-Reply-To: <199609141315.GAA04505@GndRsh.aac.dev.com> from Simon Marlow at "Sep 14, 96 02:15:40 pm"
X-Mailer: ELM [version 2.4ME+ PL11 (25)]
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: owner-current@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

> 
> Rod Grimes writes:
> 
> > The default value could still be 64K incase none of the cache sizeable
> > chipsets are found, but in my experience the only things that ever had
> > 64K or 128K caches on them are old 386 boards and some of the earlier
> > 486 boards.  Thus if CPU >= I586 your going to have a 256K cache....
> 
> What about laptops that don't have a cache at all?  If it doesn't hurt
> too much, then fair enough, but otherwise we still need a way to
> fiddle the setting at boot or kernel-compile time.

Hummm... okay, but more correctly, what about laptops that only have
an internal cache of either 0K, 4K or 8K-I/8K-D.  (Any Pentium PRO laptops
out there yet :-) :-))

I really doubt that this cache coloring is going to have much effect on
machines without external cache, infact now that I think about it a little
it should not matter what address patern is giving to external memory, it
just won't effect performance.

-- 
Rod Grimes                                      rgrimes@gndrsh.aac.dev.com
Accurate Automation Company                 Reliable computers for FreeBSD