From owner-freebsd-current  Mon May 20 14:14:41 1996
Return-Path: owner-current
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.3/8.7.3) id OAA17550
          for current-outgoing; Mon, 20 May 1996 14:14:41 -0700 (PDT)
Received: from dyson.iquest.net (dyson.iquest.net [198.70.144.127])
          by freefall.freebsd.org (8.7.3/8.7.3) with ESMTP id OAA17543;
          Mon, 20 May 1996 14:14:20 -0700 (PDT)
Received: (from root@localhost) by dyson.iquest.net (8.7.5/8.6.9) id QAA04198; Mon, 20 May 1996 16:14:11 -0500 (EST)
From: John Dyson <dyson@dyson.iquest.net>
Message-Id: <199605202114.QAA04198@dyson.iquest.net>
Subject: Re: VM changes
To: coredump@nervosa.com (Chris J. Layne)
Date: Mon, 20 May 1996 16:14:11 -0500 (EST)
Cc: freebsd-current@freebsd.org, dyson@freebsd.org
In-Reply-To: <Pine.BSF.3.91.960520135805.1005A-100000@onyx.nervosa.com> from "Chris J. Layne" at May 20, 96 01:59:45 pm
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-current@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

> Well, so far the VM changes are working fine for me, I don't notice any 
> apparent performance differences while forking, if I did it would most 
> likely be psychological, but these changes are going along quite stable 
> as opposed to last time :-)
> 
Forks were running about 700-800usecs before, and now are about 600usecs
on my P5-166.  (Some new changes are coming from another front that
will likely drop the 600usecs to about 500usecs.)  You *certainly*
would not notice the difference, unless you would be testing 100's of
them. :-).

Many of the new changes were simplifications, so it was easier to get
them right.  One thing though, how does the paging performance seem?

John
dyson@freebsd.org