Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!wasatch!cs.utexas.edu!husc6!ogccse!blake!uw-beaver!ssc-vax!shuksan!tahoma!prl3546
From: prl3546@tahoma.UUCP (Philip R. Lindberg)
Newsgroups: comp.sys.apple
Subject: Re: SCSI TIMER & V5.0
Message-ID: <571@tahoma.UUCP>
Date: 23 Aug 89 19:13:05 GMT
References: <661@mountn.dec.com>
Organization: The Boeing Co., BCA FSL, Seattle, WA
Lines: 34

From article <661@mountn.dec.com>, by shatara@memit.dec.com (Chris Shatara):
> I'm wondering if I should rerun SCSI Timer and SCSI Hacker on my hard disk 
> to optimize the interleave for the faster scsc driver in V5.0.
> 
> Does this make sense or is the speed basically limited by the scsi 
> interface card and drive?

This is a very interesting question.  I have a homebrew hard drive so I ran
these routines when I put mine together.  I assumed that they optimized to
the hardware only, and then when I did the highlevel formatt with the ADU it
did any optimization for the operating system.  If this is true, then
rerunning these should not make any difference.  So my question would be:
is there any advantage to redoing a highlevel formatt under V5.0?  (I would
guess not.)

> I have already optimized the interleave under V4.0 with a 40% improvement 
> in read times and was wondering if the interleave should change because 
> of the SCSI driver improvements in System 5.0

When you reran these and got a 40% improvement was it because you changed
the interleaf?  (Or maybe it was because of the driver/ADU improvements in
V4.0?)  (I really am asking.  I'm not trying to put words in your mouth.  I
would like to know since I formatted my drive under version three.)

> /chris

+---------------------------------------------------------+
|	     The Apple //'s will live forever!!		  |
|  Phil Lindberg	    snail mail: 13845 S.E. 131 ST |
| INET: prl3546@tahoma.UUCP		Renton, WA 98056  |
| UUCP: ..!uw-beaver!ssc-vax!shuksan!tahoma!prl3546	  |
|    Disclaimer: I don't speak for my employer (and I not |
|		 sure they even know I exist....)	  |
+---------------------------------------------------------+