Re: [re-ECN] Pls bash: Congestion Exposure (re-ECN) BoF inHiroshima?

<toby.moncaster@bt.com> Thu, 10 September 2009 11:48 UTC

Return-Path: <toby.moncaster@bt.com>
X-Original-To: re-ecn@core3.amsl.com
Delivered-To: re-ecn@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 24A3928C0F1 for <re-ecn@core3.amsl.com>; Thu, 10 Sep 2009 04:48:51 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.89
X-Spam-Level:
X-Spam-Status: No, score=-2.89 tagged_above=-999 required=5 tests=[AWL=0.109, BAYES_00=-2.599, J_CHICKENPOX_91=0.6, RCVD_IN_DNSWL_LOW=-1]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id xMkH7eXSbmah for <re-ecn@core3.amsl.com>; Thu, 10 Sep 2009 04:48:50 -0700 (PDT)
Received: from smtp3.smtp.bt.com (smtp3.smtp.bt.com [217.32.164.138]) by core3.amsl.com (Postfix) with ESMTP id 030263A68F7 for <re-ecn@ietf.org>; Thu, 10 Sep 2009 04:48:49 -0700 (PDT)
Received: from E03MVZ1-UKDY.domain1.systemhost.net ([193.113.30.65]) by smtp3.smtp.bt.com with Microsoft SMTPSVC(6.0.3790.3959); Thu, 10 Sep 2009 12:49:23 +0100
X-MimeOLE: Produced By Microsoft Exchange V6.5
Content-class: urn:content-classes:message
MIME-Version: 1.0
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: base64
Date: Thu, 10 Sep 2009 12:49:22 +0100
Message-ID: <AEDCAF87EEC94F49BA92EBDD49854CC70D01422A@E03MVZ1-UKDY.domain1.systemhost.net>
In-Reply-To: <4AA8D7F8.9090106@ee.ucl.ac.uk>
X-MS-Has-Attach:
X-MS-TNEF-Correlator:
Thread-Topic: [re-ECN] Pls bash: Congestion Exposure (re-ECN) BoF inHiroshima?
Thread-Index: AcoyA21mDqspelNQQhGXGrUFo9UaqgAATsxQ
References: <200909071019.n87AJgBB030579@bagheera.jungle.bt.co.uk><AEDCAF87EEC94F49BA92EBDD49854CC70CEB8418@E03MVZ1-UKDY.domain1.systemhost.net><8A82D1BFEDDE7E4597978355239BBBCB04389F@PACDCEXCMB06.cable.comcast.com><AEDCAF87EEC94F49BA92EBDD49854CC70CF2B7C9@E03MVZ1-UKDY.domain1.systemhost.net><20090907164107.GR8532@verdi><AEDCAF87EEC94F49BA92EBDD49854CC70CF2B885@E03MVZ1-UKDY.domain1.systemhost.net><200909080035.n880Zs1t012039@bagheera.jungle.bt.co.uk><AEDCAF87EEC94F49BA92EBDD49854CC70CF2BAD1@E03MVZ1-UKDY.domain1.systemhost.net><7D6FD9F3-B80E-4227-B215-EA22F20552CF@g11.org.uk> <AEDCAF87EEC94F49BA92EBDD49854CC70CF2BCE5@E03MVZ1-UKDY.domain1.systemhost.net> <AEDCAF87EEC94F49BA92EBDD49854CC70CF81803@E03MVZ1-UKDY.domain1.systemhost.net> <6d30817f6dade196cfbb63326fc12bcb@petri-meat.com> <AEDCAF87EEC94F49BA92EBDD49854CC70CF81B7E@E03MVZ1-UKDY.domain1.systemhost.net> <4AA8D7F8.9090106@ee.ucl.ac.uk>
From: <toby.moncaster@bt.com>
To: <j.araujo@ee.ucl.ac.uk>
X-OriginalArrivalTime: 10 Sep 2009 11:49:23.0407 (UTC) FILETIME=[BD84BDF0:01CA320C]
Cc: re-ecn@ietf.org
Subject: Re: [re-ECN] Pls bash: Congestion Exposure (re-ECN) BoF inHiroshima?
X-BeenThere: re-ecn@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: re-inserted explicit congestion notification <re-ecn.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/re-ecn>, <mailto:re-ecn-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/re-ecn>
List-Post: <mailto:re-ecn@ietf.org>
List-Help: <mailto:re-ecn-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/re-ecn>, <mailto:re-ecn-request@ietf.org?subject=subscribe>
X-List-Received-Date: Thu, 10 Sep 2009 11:48:51 -0000


> -----Original Message-----
> From: João Taveira Araújo [mailto:j.araujo@ee.ucl.ac.uk]
> Sent: 10 September 2009 11:42
> To: Moncaster,T,Toby,DER3 R
> Cc: re-ecn@ietf.org
> Subject: Re: [re-ECN] Pls bash: Congestion Exposure (re-ECN) BoF
> inHiroshima?
> 
> Hi,
> 
> toby.moncaster@bt.com wrote
> >
> > One of the strengths of the Internet is its ability to share capacity
> and avoid congestion collapse by using distributed algorithms executed
> on its end-hosts.  While the resulting allocation of capacity is fair
> in a certain mathematical sense, it is not necessarily fair in other
> economic or philosophical senses.
> >
> > Further, end-hosts have means to "game the system" to increase their
> access to capacity, and to progress communications even in the presence
> of persistent congestion. As a consequence ISPs feel they have to
> police "heavy users" to free up resources for the bulk of their
> customers. This involves making assumptions about the wishes of their
> customers which in turn is eroding trust between ISPs, customers,
> content providers and application writers.
> 
> I'm not entirely sure people unfamiliar with the flow fairness debate
> will understand what "certain mathematical sense" means, or why it's
> suddenly an issue. Suggestion:
> 
> "One of the strengths of the Internet is its ability to share capacity
> and avoid congestion collapse by using distributed algorithms executed
> on its end-hosts. The resulting capacity allocation has reflected a
> single definition of fairness however, and has remained inflexible in
> adapting to differing needs as the Internet has scaled to include new
> and often conflicting stakeholders."

How about something like 

"One of the strengths of the Internet is its ability to share capacity and avoid congestion collapse through the use of distributed algorithms such as TCP running on its endhosts. The resulting capacity allocation is fair in one narrow sense, but is proving poor at adapting to the differing needs of conflicting stakeholders in the ever-more commercialised Internet ["design for tussle"]. "

> 
> I'm fine with the second paragraph, but if you want to avoid the "game
> the system" bit here's my suggestion. Not sure it's clearer though:
> 
> "Further, current capacity allocation is prone to self-interest and
> malice, and has resulted in a system where few can obtain more at the
> expense of many. Faced with such vicarious punishment for the bulk of
> their customers, ISPs resort to policing and throttling "heavy users",
> which in turn is eroding trust between ISPs, customers, content
> providers and application writers."

Still trying to work out how to best to phrase this... getting distracted by lots of other things 

Toby

> 
> Joao.