Re: transparent tcp improvements

Mike Jagdis <jaggy@purplet.demon.co.uk> Mon, 15 April 2002 09:06 UTC

X-Authentication-Warning: west-finchley.inpharmatica.co.uk: Host localhost [127.0.0.1] claimed to be purplet.demon.co.uk
Message-ID: <3CBA9808.6030401@purplet.demon.co.uk>
Date: Mon, 15 Apr 2002 10:06:16 +0100
From: Mike Jagdis <jaggy@purplet.demon.co.uk>
User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:0.9.4) Gecko/20011126 Netscape6/6.2.1
X-Accept-Language: en, fr, de
MIME-Version: 1.0
To: karl.jonas@ieee.org
Cc: tcpsat@grc.nasa.gov
Subject: Re: transparent tcp improvements
References: <OHEFJNMPOIMBPIIHGBDCCEMMCFAA.karl.jonas@fokus.fhg.de>
Content-Type: text/plain; charset=us-ascii; format=flowed
Content-Transfer-Encoding: 7bit
Sender: owner-tcpsat@grc.nasa.gov
Precedence: bulk
Status: RO
Content-Length: 644
Lines: 19

Karl Jonas wrote:

> having a mobile device attached to a long-delay wireless link,
> I would like to improve tcp's performance by sending early ACKs
> from a box at the 'end' of the terrestrial network towards the
> tcp sender in the terrestrial network:


You mean ACK data befoe you've actually received it? Isn't that
a little dodgy unless you have some other underlying protocol
guaranteeing a perfect link?

Anyway, it sounds very like Stefan Savage's[1] work on TCP with
misbehaving receivers[2] (aka "Daytona TCP")

				Mike

[1] http://www.cs.washington.edu/homes/savage/
[2] http://www.cs.washington.edu/homes/savage/papers/CCR99.pdf

transparent tcp improvements Karl Jonas
Re: transparent tcp improvements Mike Jagdis
Re: transparent tcp improvements David Carek
Re: transparent tcp improvements Joseph Ishac