Path: utzoo!utgpu!attcan!uunet!tank!nic.MR.NET!hal!cwjcc!ukma!rutgers!iuvax!inuxc!att!ihlpf!straka
From: straka@ihlpf.ATT.COM (Straka)
Newsgroups: comp.sys.mac
Subject: Re: DiskTimer II results for verious disks wanted.
Message-ID: <6544@ihlpf.ATT.COM>
Date: 3 Nov 88 19:07:42 GMT
References: <1449@ucsfcca.ucsf.edu> <29@eplrx7.UUCP>
Reply-To: straka@ihlpf.UUCP (55223-Straka,R.J.)
Distribution: comp
Organization: AT&T Bell Laboratories - Naperville, Illinois
Lines: 54

In article <29@eplrx7.UUCP> lad@eplrx7.UUCP (lad) writes:
>From article <1449@ucsfcca.ucsf.edu>, by rampil@cca.ucsf.edu (Ira Rampil):
>> In article <16@eplrx7.UUCP> lad@eplrx7.UUCP (lad) writes:
|||
|||	If you're looking to compare the performance of SCSI
|||	disks Disktimer is NOT the way to do it.  Disktimer is
|||	not a benchmark,  it favors disks with a 1:1 interleave
|||	and it's results do not reflect real-world disk
|||	performance.  Supermac based their whole marketing
|||	scheme around Disktimer,  saying their disks were
|||	faster because Disktimer said so.

|||        Lawrence A. Deleski             |       E.I. Dupont Co.

||	Could it be that DiskTimer favors 1:1 interleave disks because
||	they ARE faster?  Is this in dispute?

|	1:1 disks are faster only if the machine they're working on
|	supports 1:1.  For example,  Apple claims that a 3:1
|	interleave is optimal for a Mac Plus,  so a disk formatted
|	to 1:1 is going perform slower.  Disktimer's problem is that
|	it totally bypassed the driver and made calls directly to
|	the low-level SCSI routines,  totally ignoring the OS.  Any
|	disk with a 1:1 interleave performed better in Disktimer no
|	matter what machine it was being run on.  There are several
|	other reasons why Disktimer should not be seriously
|	considered when evaluating SCSI disk performance, but they
|	are very technical in nature.

If the disk controller that is used has implemented sufficient buffering to
store a track's worth of data as a sector cache, running a 1:1 interleave CAN
result in increased data transfer rate regardless of the Mac that the disk is
hung off of.  Only ONE rotation is required for the track, period.  The Mac
then takes the data from the controller's buffer at the max data rate.

As I recall, the OMTI 31xx controller (from SMS, their parent company) that
SuperMac used in their XP series had such buffering so that 1:1 would work
efficiently (read full-tilt) on ANY Mac without reformatting. THAT was their
marketing strategy.  

Before making blanket statements like that above, please make sure that all
the facts are out on the table.  May I assume that you have detailed facts to
back up your claims?

Standard Disclaimer:  I have no financial interest in SuperMac, SMS, Micah,
Apple, or any other company associated with this discussion except as an
occasional customer.

I additionally have no particular opinion on DiskTimer IIa, or whatever,
except that I want the best information all on the table.
-- 
Rich Straka     att!ihlpf!straka

Avoid BrainDamage: MSDOS - just say no!