*BSD News Article 13229


Return to BSD News archive

Path: sserve!newshost.anu.edu.au!munnari.oz.au!constellation!convex!convex!darwin.sura.net!jhunix.hcf.jhu.edu!jhunix.hcf.jhu.edu!not-for-mail
From: philippe@jhunix.hcf.jhu.edu (Philippe Pouliquen)
Newsgroups: comp.os.386bsd.bugs
Subject: Re: IOZONE results
Date: 23 Mar 1993 13:17:34 -0500
Organization: Electrical and Computer Engineering, Johns Hopkins University, Baltimore, Md, USA
Lines: 19
Sender: philippe@zeus.ece.jhu.edu
Message-ID: <1onk7uINNf87@jhunix.hcf.jhu.edu>
References: <C43MBo.3owM@austin.ibm.com>
NNTP-Posting-Host: jhunix.hcf.jhu.edu

In article <C43MBo.3owM@austin.ibm.com> fredriks@austin.ibm.com (Lars Fredriksen) writes:
>	I ran iozone auto on my machine and got the maximum of 500K/s
>throughtput. I saw a report from someone running Interactive Unix on
>a 50MHz 486 with a Bustek controller getting 4.5M/s.
>

Although this may not be the answer to your problem (I'm not familiar
with iozone), I did encounter a similar effect with an Adaptec 8500
tape drive. Although the SCSI rate is around 4M/s, this is a burst
rate and can only be sustained for about 250Kbytes (despite the
tape drive having a 1Mbyte buffer). The sustained rate is only 500K/s.

I'd be interested in *anyone* who can sustain more than 1M/s on a SCSI
hard disk for over 100Mbyte transfers (ie transfer at least 100Mbytes in
less than 100 seconds). (please reply by e-mail. No RAID devices)

Philippe Pouliquen
philippe@zeus.ece.jhu.edu (zeus is at 128.220.14.9 on the internet)