From owner-freebsd-hackers  Sat Sep  2 13:32:31 1995
Return-Path: hackers-owner
Received: (from majordom@localhost)
          by freefall.FreeBSD.org (8.6.11/8.6.6) id NAA04485
          for hackers-outgoing; Sat, 2 Sep 1995 13:32:31 -0700
Received: from gndrsh.aac.dev.com (gndrsh.aac.dev.com [198.145.92.241])
          by freefall.FreeBSD.org (8.6.11/8.6.6) with ESMTP id NAA04471
          for <freebsd-hackers@FreeBSD.org>; Sat, 2 Sep 1995 13:32:24 -0700
Received: (from rgrimes@localhost) by gndrsh.aac.dev.com (8.6.11/8.6.9) id NAA16013; Sat, 2 Sep 1995 13:31:26 -0700
From: "Rodney W. Grimes" <rgrimes@gndrsh.aac.dev.com>
Message-Id: <199509022031.NAA16013@gndrsh.aac.dev.com>
Subject: Re: 4GB Drives
To: julian@ref.tfs.com (Julian Elischer)
Date: Sat, 2 Sep 1995 13:31:26 -0700 (PDT)
Cc: vernick@CS.SunySB.EDU, freebsd-hackers@FreeBSD.org
In-Reply-To: <199509022024.NAA05005@ref.tfs.com> from "Julian Elischer" at Sep 2, 95 01:24:46 pm
X-Mailer: ELM [version 2.4 PL24]
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Content-Length: 1589      
Sender: hackers-owner@FreeBSD.org
Precedence: bulk

...
> > Your thinking to simple, if the data was in the cache when the I/O
> > hit the drive it would immediatly go to data phase preventing me from
> > issuing another I/O to the next drive.  I actually _dont_ want the
> > drive to come on the bus yet.  I need to be able to get all transfer
> > operations to the drives before _any_ drive grabs the bus for a data
> > transfer.  This causes all drives to operate as a parallel unit.
> > 
> > To simplify my problem with this I have gone to one drive per controller
> > for developement purposes, but am still trying to work the issue of how
> > do I make 4 drives on one bus all operate such that I can get the commands
> > to all 4 drives before anyone of them grabs the bus for what is a rather
> > long data transfer phase.
> you can issue a SCSI seek command first to all the devices
> then issue a read as a second round of commands
> that way they will all give you instant response on the read
> 
> seek1
> seek2
> seek3
> read1-data-phase
> read2-data-phase
> read3-data-phase.
> 
> seek is command 2B, though it is an optional command..

Well, I could do that if I was at the drive level, but my code sits
above the standard drivers, and actually just looks like another
disk driver to the upper layers.

I don't even know what scsi driver is doing the I/O as far as my code
is concerned.  The seek abstraction is missing from the layer between
me and the driver :-(.

...

-- 
Rod Grimes                                      rgrimes@gndrsh.aac.dev.com
Accurate Automation Company                 Reliable computers for FreeBSD