From owner-freebsd-hackers  Thu Mar 28 00:29:42 1996
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.3/8.7.3) id AAA08596
          for hackers-outgoing; Thu, 28 Mar 1996 00:29:42 -0800 (PST)
Received: from schizo.cdsnet.net (schizo.cdsnet.net [204.118.244.32])
          by freefall.freebsd.org (8.7.3/8.7.3) with SMTP id AAA08589
          for <hackers@freebsd.org>; Thu, 28 Mar 1996 00:29:40 -0800 (PST)
Received: (from mrcpu@localhost) by schizo.cdsnet.net (8.6.12/8.6.12) id AAA26572; Thu, 28 Mar 1996 00:34:22 -0800
Date: Thu, 28 Mar 1996 00:34:22 -0800 (PST)
From: Jaye Mathisen <mrcpu@cdsnet.net>
To: hackers@freebsd.org
Subject: FreeBSD performance vs BSD/OS
Message-ID: <Pine.BSF.3.91.960328003117.16907d-100000@schizo.cdsnet.net>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: owner-hackers@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk



W/o any real hard numbers, I noticed that when running the perl 5.002 
testsuite that BSD/OS 2.0 on a P5-90 runs the tests more quickly than my
P5-120 running -stable.


BSD/OS 2.0.1 numbers for make test:
All tests successful.
u=0.65  s=1.03333  cu=11.8667  cs=12.6833  files=94  tests=2105

FreeBSD 2.1-stable numbers:
All tests successful.
u=1  s=1.8  cu=26.0667  cs=15.5  files=94  tests=2103


I do not know why the number of tests differ, unless it's related to 
dynamic loading turned on in FreeBSD and static in BSD/OS.  outside of 
the dynamic vs static settings, everything else was defaulted.  Of 
course, there are compiler differences and such

Not really anything to get excited about, just a datapoint.