Path: utzoo!utgpu!attcan!uunet!husc6!rutgers!bellcore!tness7!texbell!sugar!peter
From: peter@sugar.uu.net (Peter da Silva)
Newsgroups: comp.sys.amiga
Subject: Re: CRETIN MANOR MAIL
Message-ID: <2847@sugar.uu.net>
Date: 17 Oct 88 11:12:52 GMT
References: <7699@gryphon.CTS.COM> <3220@hubcap.UUCP> <10062@cup.portal.com>
Organization: Sugar Land Unix - Houston, TX
Lines: 23

In article <10062@cup.portal.com>, thad@cup.portal.com (Thad Thad Floryan) writes:
> Also from UNIX REVIEW (Vol.6, No.9, Sept. 1988) page 96, we see (for reads):
  [list of disks/computers/interfaces/operating systems/and benchmarks
   elided]

> Do you still wonder why I doubt *****'s veracity?

I suspect that may be a raw transfer rate for a contiguous file. In any case
I would expect the Amiga to perform pretty well in this sort of test because
it has way less O/S overhead than UNIX, and a lot better I/O design than MSDOS.

The test may have been performed by sending out a bunch of read requests and
waiting on all of them, but out of all the systems listed only the Amiga lets
you do this easily. It's misleading, perhaps, but not false. I use a program
every day that does this sort of performance hack: Matt Dillon's 'DTerm'.

    Speaking of which, I urge everybody to try it out. It's not packed with
    features but it's *very* well integrated with Intuition and the console
    device. Maybe if enough people use it he'll put some of the recent DME
    hacks into it.
-- 
		Peter da Silva  `-_-'  peter@sugar.uu.net
		 Have you hugged  U  your wolf today?