From owner-freebsd-hackers  Thu Jun  1 23:57:34 1995
Return-Path: hackers-owner
Received: (from majordom@localhost)
          by freefall.cdrom.com (8.6.10/8.6.6) id XAA09338
          for hackers-outgoing; Thu, 1 Jun 1995 23:57:34 -0700
Received: from crh.cl.msu.edu (crh.cl.msu.edu [35.8.1.24])
          by freefall.cdrom.com (8.6.10/8.6.6) with SMTP id XAA09330
          for <freebsd-hackers@freebsd.org>; Thu, 1 Jun 1995 23:57:31 -0700
Message-Id: <199506020657.XAA09330@freefall.cdrom.com>
Received: by crh.cl.msu.edu
	(1.38.193.4/16.2) id AA20536; Fri, 2 Jun 1995 02:57:30 -0400
From: Charles Henrich <henrich@crh.cl.msu.edu>
Subject: A performance mystery
To: freebsd-hackers@FreeBSD.ORG
Date: Fri, 2 Jun 1995 02:57:30 -0400 (EDT)
X-Mailer: ELM [version 2.4 PL23]
Content-Type: text
Content-Length: 772       
Sender: hackers-owner@FreeBSD.ORG
Precedence: bulk

I have a mystery for you folks.  Consider this situation:

a Compaq Prolinea 575 (75mhz Pentium)
24mb ram
3gb of "oldish" Seagate Disk on a Buslogic 946C

and a

Micron P90 Powerstation,
64mb ram
Adaptec 2940
And a brand new Connor drive

IOZONE rates disk access for the two systems at virtually the same (+- fudge)
IOMem gives the compaq 10mb/7mb while its 10mb/20mb on the Micron

Doing a time make of a specific configuration (kernel build) takes 9:30 on the
Micron, but on the Compaq its only 8:30.  Same exact config/source (brand new
2.0.5-A installs).  Nothing else is going on on either boxes.

Can anyone explain this to me?

-Crh

    Charles Henrich     Michigan State University     henrich@crh.cl.msu.edu

                     http://rs560.msu.edu/~henrich/