No subject

[Unknown]

de> <46995FB0.1080108 at netphreax.net>
From: Joerg Sonnenberger <joerg at britannica.bec.de>
Mail-Followup-To: kernel at crater.dragonflybsd.org
Subject: Re: 4mb PAGES for mbuf clusters
Date: Sun, 15 Jul 2007 01:50:36 +0200
BestServHost: crater.dragonflybsd.org
List-Post: <mailto:kernel at crater.dragonflybsd.org>
List-Subscribe: <mailto:kernel-request at crater.dragonflybsd.org?body=subscribe>
List-Unsubscribe: <mailto:kernel-request at crater.dragonflybsd.org?body=unsubscribe>
List-Help: <mailto:kernel-request at crater.dragonflybsd.org?body=help>
List-Owner: <mailto:owner-kernel at crater.dragonflybsd.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <46995FB0.1080108 at netphreax.net>
Sender: kernel-errors at crater.dragonflybsd.org
Errors-To: kernel-errors at crater.dragonflybsd.org
Lines: 15
NNTP-Posting-Host: 216.240.41.25
X-Trace: 1184457470 crater_reader.dragonflybsd.org 796 216.240.41.25
Xref: crater_reader.dragonflybsd.org dragonfly.kernel:11252

On Sat, Jul 14, 2007 at 11:43:44PM +0000, Thomas E. Spanjaard wrote:
> >no.  and PAE is stupid, so we won't do that.  it's really stupid.  really.
> 
> Actually, we will do that. Perhaps not on x86-32, but it sure is a 
> requirement for 64bit long mode on x86-64...

PAE for long mode is quite different for PAE for 32bit mode.

The question is whether the VM subsystem and many lower parts of the
kernel have to deal with kernel addresses being larger than pointers or
not. That's opening the box of Pandora for no real gain -- if you need
more than 3.x GB RAM, switch to long mode. That doesn't have this
problem.

Joerg