From owner-freebsd-stable  Sat Mar 30 16:25:11 1996
Return-Path: owner-stable
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.3/8.7.3) id QAA25494
          for stable-outgoing; Sat, 30 Mar 1996 16:25:11 -0800 (PST)
Received: from haven.uniserve.com (haven.uniserve.com [198.53.215.121])
          by freefall.freebsd.org (8.7.3/8.7.3) with ESMTP id QAA25486
          for <stable@FreeBSD.org>; Sat, 30 Mar 1996 16:25:00 -0800 (PST)
Received: by haven.uniserve.com id <30769-23288>; Sat, 30 Mar 1996 16:27:42 -0800
Date: 	Sat, 30 Mar 1996 16:27:38 -0800 (PST)
From: Tom Samplonius <tom@uniserve.com>
To: "Marc G. Fournier" <scrappy@ki.net>
cc: stable@FreeBSD.org
Subject: Re: SCSI Performance under -stable/-current
In-Reply-To: <Pine.BSF.3.91.960330161449.3268C-100000@ki.net>
Message-ID: <Pine.BSF.3.91.960330162155.29246A-100000@haven.uniserve.com>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: owner-stable@FreeBSD.org
X-Loop: FreeBSD.org
Precedence: bulk


On Sat, 30 Mar 1996, Marc G. Fournier wrote:

> 	I'm also sending this to -current, in case there are bugs in
> -stable that are fixed in -current, that might be reflected here :)
> 
> 	My results show:
> 
> 	ncr:sd0 - 1.95write/3.01read - Conner CFP1060S 
> 	ncr:sd1 - 1.75write/2.50read - Conner CFA540S
> 	aha:sd2 - 1.06write/1.06read - Quantum LPS340S
> 	aha:sd3 - 1.12write/0.94read - Quantum LP240S
> 
> 	ncr == ASUS SC-200 PCI Controller
> 	aha == Adaptec 1542CF ISA Controller
> 
> 	Do those values from IOzone look right?  Looking at the aha:sd?
> values, they look low to me, especially considering that when I ran IOzone
> on it, there would have been zero activity on those drives except for
> their respective swap partitions:

  The aha results seem alright.  Remember the 1542 is only a 16bit 
controller.  

  The ncr results should be higher, unless your drives are slow.  On a 
-stable system with a 2940 and a Quantum Fireball, I see over 6MB/sec on 
file I/O.

Tom