From owner-freebsd-current  Wed Nov 13 09:13:41 1996
Return-Path: owner-current
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.5/8.7.3) id JAA28982
          for current-outgoing; Wed, 13 Nov 1996 09:13:41 -0800 (PST)
Received: from verdi.nethelp.no (verdi.nethelp.no [193.91.212.2])
          by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id JAA28968
          for <freebsd-current@FreeBSD.org>; Wed, 13 Nov 1996 09:13:34 -0800 (PST)
From: sthaug@nethelp.no
Received: (qmail 22585 invoked by uid 1001); 13 Nov 1996 17:13:18 +0000 (GMT)
To: bmah@cs.berkeley.edu
Cc: ccsanady@friley216.res.iastate.edu, dyson@FreeBSD.org,
        gibbs@freefall.freebsd.org, roberto@keltia.freenix.fr,
        freebsd-current@FreeBSD.org
Subject: Re: pbufs (was: Re: ufs is too slow?) 
In-Reply-To: Your message of "Wed, 13 Nov 1996 08:22:26 -0800"
References: <199611131622.IAA03524@premise.CS.Berkeley.EDU>
X-Mailer: Mew version 1.05+ on Emacs 19.28.2
Mime-Version: 1.0
Content-Type: Text/Plain; charset=iso-8859-1
Content-Transfer-Encoding: 8bit
Date: Wed, 13 Nov 1996 18:13:18 +0100
Message-ID: <22583.847905198@verdi.nethelp.no>
Sender: owner-current@FreeBSD.org
X-Loop: FreeBSD.org
Precedence: bulk

> (Editorial note:  Packet traces have shown that many packets, at least on 
> LANs, tend to be small.  So it's not clear to me what effect this would have 
> for "typical" network traffic, though the wins for large bulk transfers have 
> shown to be substantial.)

It's also likely to help *latency* for smaller packets quite a bit.

> Somewhere in the mess I call a desk I think I have hardcopies from a talk he 
> gave on this stuff at a Gigabit TCP workshop a few years ago, but a cursory 
> search has not revealed it.

See	http://ee.lbl.gov/nrg-talks.html

In particular, the 1992 talk "Design Changes to the Kernel Network
Architecture for 4.4BSD", and the 1993 talk "Some Design Issues for
High-speed Networks".

Steinar Haug, Nethelp consulting, sthaug@nethelp.no