From owner-freebsd-hackers  Fri Jun  2 21:49:35 1995
Return-Path: hackers-owner
Received: (from majordom@localhost)
          by freefall.cdrom.com (8.6.10/8.6.6) id VAA24513
          for hackers-outgoing; Fri, 2 Jun 1995 21:49:35 -0700
Received: from gndrsh.aac.dev.com (gndrsh.aac.dev.com [198.145.92.241])
          by freefall.cdrom.com (8.6.10/8.6.6) with ESMTP id VAA24499
          for <freebsd-hackers@freebsd.org>; Fri, 2 Jun 1995 21:49:32 -0700
Received: (from rgrimes@localhost) by gndrsh.aac.dev.com (8.6.11/8.6.9) id VAA09321; Fri, 2 Jun 1995 21:49:15 -0700
From: "Rodney W. Grimes" <rgrimes@gndrsh.aac.dev.com>
Message-Id: <199506030449.VAA09321@gndrsh.aac.dev.com>
Subject: Re: A performance mystery
To: henrich@crh.cl.msu.edu (Charles Henrich)
Date: Fri, 2 Jun 1995 21:49:15 -0700 (PDT)
Cc: henrich@crh.cl.msu.edu, freebsd-hackers@freebsd.org
In-Reply-To: <199506030336.UAA09183@gndrsh.aac.dev.com> from "Charles Henrich" at Jun 2, 95 11:36:09 pm
X-Mailer: ELM [version 2.4 PL24]
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Content-Length: 1127      
Sender: hackers-owner@freebsd.org
Precedence: bulk

> 
> > ram-speed is a cache defeat program, it will *NOT* approximate bcopy rates,
> > that is why I asked you to do iozone on 1/4 memory size.  I already saw
> > your ram-speed results in the first posting.
> 
> Here goes with iozone auto, no delete (Micron has 64mb ram, Compaq 24mb)

We are not going to get the results I was looking for unless you
are going to follow directions a *little* closer.

``repeat 10 iozone 16 8192''

>         16      8192    2687714             14221746

You said this was a Pentium right??  If it is that number is low for
a triton board:  (ASUS PCI/I-P54TP4, 90Mhz CPU, 64MB memory)
Writing the 16 Megabyte file, 'iozone.tmp'...8.757812 seconds
Reading the file...0.921875 seconds

IOZONE performance measurements:
        1915685 bytes/second for writing the file
	18199013 bytes/second for reading the file

>     16      8192    3360694             2890287

Ding... very low memory bandwidth :-(.  Makes for a very slow
compile :-(


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