From owner-freebsd-hackers  Mon May 26 04:53:43 1997
Return-Path: <owner-hackers>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.5/8.8.5) id EAA13464
          for hackers-outgoing; Mon, 26 May 1997 04:53:43 -0700 (PDT)
Received: from Sisyphos.MI.Uni-Koeln.DE (Sisyphos.MI.Uni-Koeln.DE [134.95.212.10])
          by hub.freebsd.org (8.8.5/8.8.5) with SMTP id EAA13459
          for <hackers@freebsd.org>; Mon, 26 May 1997 04:53:40 -0700 (PDT)
Received: from x14.mi.uni-koeln.de (annexr3-16.slip.Uni-Koeln.DE) by Sisyphos.MI.Uni-Koeln.DE with SMTP id AA02622
  (5.67b/IDA-1.5 for <hackers@freebsd.org>); Mon, 26 May 1997 13:53:16 +0200
Received: (from se@localhost) by x14.mi.uni-koeln.de (8.8.5/8.6.9) id NAA14927; Mon, 26 May 1997 13:53:05 +0200 (CEST)
X-Face: "<d]#=8pzx);RzeqSKI86OVa7=!0/(uRa.+B.9Z9\eNUn@UG?!`y7yt2dFNn%k4'.}](uE%
 yCO)$e&Y1%3EO~ifu6Q-#YUM&JZ't,}JkPnAz,8Dj33u%@GBi%[Y#LHz$]h7a<p4)-jKI7~sKjlP-^
 EvA[G;]v&0]W!EL%shs,{7x0|oqN4YVIs5,NI#,V{9"WF):5&RkOhyj*#-IAG}Tnu;YCF,d
Message-Id: <19970526135305.44861@x14.mi.uni-koeln.de>
Date: Mon, 26 May 1997 13:53:05 +0200
From: Stefan Esser <se@FreeBSD.ORG>
To: Sxren Schmidt <sos@sos.freebsd.dk>
Cc: Bruce Evans <bde@zeta.org.au>, hackers@FreeBSD.ORG, j@uriah.heep.sax.de
Subject: Re: Controler for SCSI
References: <199705241036.UAA02991@godzilla.zeta.org.au> <199705241107.NAA00317@sos.freebsd.dk>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
X-Mailer: Mutt 0.73
In-Reply-To: <199705241107.NAA00317@sos.freebsd.dk>; from S\xren Schmidt on Sat, May 24, 1997 at 01:07:23PM +0200
Sender: owner-hackers@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

On May 24, "S\xren Schmidt" <sos@sos.freebsd.dk> wrote:
> In reply to Bruce Evans who wrote:
> While we are on the subject: I just bought two Maxtor 84000 (4gig) drives
> and I plan to play a little with DMA for those (they only do 16.6MB/sec)
> They are pretty fast btw, faster than my Empire and SureStore SCSI2
> disks, I'm surprised they even use less CPU than my SCSI setup (above
> drives and NCR ctrl), not bad at all and CHEAP!!.

While these drives are cheap, no doubt, I'd really see Bonnie
numbers, not just sequential throughput. (And BTW: Neither the
Empire nor SureStore drives are fast by todays standards, it is
not hard to beat them. Compare to my two year old Quantum Atlas,
for a fairer test. Those have been sold quite cheap for about
one year, and the 1GB version appears to be on sale for some
US$210 (+VAT) in Germany, which makes them very attractive for
fast CCD arrays :)

And another BTW: Since the data transfer for the EIDE drive is
mostly done in the interrupt handler, your process just does not
get the cycles accounted. Please repeat the tests and monitor
total system time and interrupt time ...

But I'd also like to have decent bus-master DMA drivers at least
for the Triton and Triton II EIDE controllers. I'm thinking about
buying one, to be able to test changes to the NCR driver, which
I have been holding back for far to long out of fear, my system
might become inoperational, and I rely on it for my daily work ...

Regards, STefan