From owner-freebsd-hackers  Sun Oct  8 10:15:28 1995
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.6.12/8.6.6) id KAA07523
          for hackers-outgoing; Sun, 8 Oct 1995 10:15:28 -0700
Received: from pelican.com (pelican.com [134.24.4.62])
          by freefall.freebsd.org (8.6.12/8.6.6) with SMTP id KAA07518
          for <hackers@freebsd.org>; Sun, 8 Oct 1995 10:15:25 -0700
Received: from puffin.pelican.com by pelican.com with smtp
	(Smail3.1.28.1 #5) id m0t1zJi-000K2mC; Sun, 8 Oct 95 10:15 WET DST
Received: by puffin.pelican.com (Smail3.1.29.1 #9)
	id m0t1zJi-0000ReC; Sun, 8 Oct 95 10:15 PDT
Message-Id: <m0t1zJi-0000ReC@puffin.pelican.com>
Date: Sun, 8 Oct 95 10:15 PDT
From: pete@puffin.pelican.com (Pete Carah)
To: bde@zeta.org.au
Subject: Re: VLB Disk Controllers
Newsgroups: freebsd.hackers
In-Reply-To: <199510080916.TAA26226@godzilla.zeta.org.au>
Cc: hackers@freebsd.org
Sender: owner-hackers@freebsd.org
Precedence: bulk

In article <199510080916.TAA26226@godzilla.zeta.org.au> you write:
.....
>No, the program is supposed to be transferring data out of the drive's
>cache, so its speed should be independent of the drive position unless
>the cache is smaller than 8K or is otherwise braindamaged.  Apparently
>the seacrates' caches are braindamaged :-).  They show that SGI SCSI is
>6 times slower than slow IDE :-).

Now that rings a bell; IRIX 3 wanted the drive cache turned off and
I think this drive was left over from then...  Don't have a scsi utility
handy on that machine, though, to check (we use one on a mac to set
code pages :-)

-- Pete