From owner-freebsd-current  Wed Jul 30 13:00:51 1997
Return-Path: <owner-freebsd-current>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.5/8.8.5) id NAA29533
          for current-outgoing; Wed, 30 Jul 1997 13:00:51 -0700 (PDT)
Received: from Octopussy.MI.Uni-Koeln.DE (Octopussy.MI.Uni-Koeln.DE [134.95.166.20])
          by hub.freebsd.org (8.8.5/8.8.5) with SMTP id NAA29513
          for <freebsd-current@freebsd.org>; Wed, 30 Jul 1997 13:00:43 -0700 (PDT)
Received: from x14.mi.uni-koeln.de (annexr3-2.slip.Uni-Koeln.DE) by Octopussy.MI.Uni-Koeln.DE with SMTP id AA20131
  (5.67b/IDA-1.5 for <freebsd-current@FreeBSD.ORG>); Wed, 30 Jul 1997 22:00:40 +0200
Received: (from se@localhost) by x14.mi.uni-koeln.de (8.8.6/8.6.9) id WAA12751; Wed, 30 Jul 1997 22:00:38 +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: <19970730220038.02422@mi.uni-koeln.de>
Date: Wed, 30 Jul 1997 22:00:38 +0200
From: Stefan Esser <se@FreeBSD.ORG>
To: Andrew Gallatin <gallatin@cs.duke.edu>
Cc: freebsd-current@FreeBSD.ORG
Subject: Re: code talks:  announcing EIDE bus master patches
References: <19970729210723.18104@mi.uni-koeln.de> <199707291949.VAA00271@sos.freebsd.dk> <19970729221036.52544@mi.uni-koeln.de> <199707301924.PAA08936@hurricane.cs.duke.edu>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
X-Mailer: Mutt 0.74
In-Reply-To: <199707301924.PAA08936@hurricane.cs.duke.edu>; from Andrew Gallatin on Wed, Jul 30, 1997 at 03:24:54PM -0400
Sender: owner-freebsd-current@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

On Jul 30, Andrew Gallatin <gallatin@CS.Duke.EDU> wrote:
> Speaking of PIO vs. DMA, an interesting data point is the bandwidth
> differences between PIO & DMA.
> 
> For example, on a 200Mhz P. Pro (Asus XP6NP5, Intel 82440FX chipset)
> we can use PIO to move an 8k chunks of memory to a PCI device(*) at a
> rate of 29.1 MB/sec, but using PIO for reads gives us bandwidth of
> only 8.1MB/sec.  Other platforms (Intel Triton @ 13MB/sec) show
> similar results.  However, using DMA we see b/w of 114.4MB/sec (host
> -> PCI device) and 121.5 MB/sec (PCI -> host memory).

Is this PIO to an I/O port, or to a memory mapped port ?

But in any case: In order to use PCI burst transfers, you
have to write to sequential memory addresses, e.g. to some
double-mapped SRAM buffer.

PCI is slow, if you can't take advantage of burst transfers!

> So.. if IDE disks can really supply data at > 8MB/sec, you may
> actually be running into a b/w limitation of PIO.

If you assume 8 PCI clocks for a non-burst transfer, the
limit comes out as 16MB/s. (The minimum is 4 clocks for 
such a transfer, but don't assume your chip-set does
support that :)

> (*) PCI device == a Myrinet M2F-PCI32 card.  This is a programmable
> gigabit networking card.  It has a 256k bank of SRAM on the card, and
> is very good for doing things like measuring PCI b/w.   The tests were
> done from user space operating on mmap'ed device memory & a kernel
> allocated chunk of RAM to do DMA xfers to/from.  It also runs IP
> traffic at better than 300Mb/sec.

This was a memory mapped device buffer ?

That's *very* different from an I/O port, and you should be able
to copy data to that SRAM at a much higher rate than 8 or 13MB/s!


Regards, STefan