From owner-freebsd-hackers  Thu Jun 19 00:00:43 1997
Return-Path: <owner-hackers>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.5/8.8.5) id AAA11604
          for hackers-outgoing; Thu, 19 Jun 1997 00:00:43 -0700 (PDT)
Received: from verdi.nethelp.no (verdi.nethelp.no [195.1.171.130])
          by hub.freebsd.org (8.8.5/8.8.5) with SMTP id AAA11599
          for <hackers@FreeBSD.ORG>; Thu, 19 Jun 1997 00:00:38 -0700 (PDT)
From: sthaug@nethelp.no
Received: (qmail 6927 invoked by uid 1001); 19 Jun 1997 07:00:23 +0000 (GMT)
To: tom@sdf.com
Cc: ccsanady@scl.ameslab.gov, hackers@FreeBSD.ORG, matt@3am-software.com
Subject: Re: Network concurrency problems!?
In-Reply-To: Your message of "Wed, 18 Jun 1997 18:16:49 -0700 (PDT)"
References: <Pine.BSF.3.95q.970618181004.11965A-100000@misery.sdf.com>
X-Mailer: Mew version 1.05+ on Emacs 19.28.2
Mime-Version: 1.0
Content-Type: Text/Plain; charset=us-ascii
Date: Thu, 19 Jun 1997 09:00:23 +0200
Message-ID: <6925.866703623@verdi.nethelp.no>
Sender: owner-hackers@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

> > There has been a good deal of debate on whether offloading is really the
> > best idea for network protocol implementations. A lot of people have tried
> > it, and a lot of people have failed.  If you look at Van Jacobson't work
> > you'll find him arguing in the opposite direction: A "stupid" (in reality:
> > simple and efficient) controller, and a very efficient protocol stack
> > implementation.
> 
>   Not really what I was refering to.  I was thinking about controllers
> that minimize interupt calls, use DMA, avoid PIO, and align data
> transfered to the host.

With the possible exception of the data alignment issue, which of these do
you think are *not* used by the 100 Mbps cards supported by FreeBSD?

(I mention the alignment issue because the DEC 21040 used to have a problem
here. Not sure if the 21140 has the same problem.)

Steinar Haug, Nethelp consulting, sthaug@nethelp.no