From owner-freebsd-hackers  Mon May  8 15:02:36 1995
Return-Path: hackers-owner
Received: (from majordom@localhost)
          by freefall.cdrom.com (8.6.10/8.6.6) id PAA23830
          for hackers-outgoing; Mon, 8 May 1995 15:02:36 -0700
Received: from ref.tfs.com (ref.tfs.com [140.145.254.251])
          by freefall.cdrom.com (8.6.10/8.6.6) with ESMTP id PAA23821
          for <hackers@FreeBSD.org>; Mon, 8 May 1995 15:02:34 -0700
Received: (from julian@localhost) by ref.tfs.com (8.6.8/8.6.6) id PAA14965; Mon, 8 May 1995 15:02:18 -0700
From: Julian Elischer <julian@ref.tfs.com>
Message-Id: <199505082202.PAA14965@ref.tfs.com>
Subject: Re: Is a 486 fast enough for SCSI?
To: rgrimes@gndrsh.aac.dev.com (Rodney W. Grimes)
Date: Mon, 8 May 1995 15:02:18 -0700 (PDT)
Cc: tom@haven.uniserve.com, hackers@FreeBSD.org
In-Reply-To: <199505081929.MAA01292@gndrsh.aac.dev.com> from "Rodney W. Grimes" at May 8, 95 12:29:49 pm
Content-Type: text
Content-Length: 749       
Sender: hackers-owner@FreeBSD.org
Precedence: bulk

> 
> > 
> > 
> You also failed to mention the model of the drives, a parameters like
> RPM that greatly effect the raw data rate of the drive (if you have
> the media transfer rate number that is the best one to use, it is
> usually a range of values due to ZBR recording.  The higher number is
> what you get for the outer cyclinders, the lower number for the inner
> cylinders).
one other thing that should be mentionned is that it is possible
to DE_TUNE your filesystem so it will slow down..

try tunefs 
and set you maxcontig to 64 and the seektime to 0 ms
It also helps to tell newfs that you have only 1 head
but a LOT of sectors per track.. this defeats some code
that makes the wrong choices for SCSI type disks (and some IDE now)


julian