From p2pi-bounces@ietf.org  Mon Nov  3 12:38:24 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 68AE428C24F;
	Mon,  3 Nov 2008 12:38:24 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id ADC5628C167
	for <p2pi@core3.amsl.com>; Mon,  3 Nov 2008 12:38:23 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -0.319
X-Spam-Level: 
X-Spam-Status: No, score=-0.319 tagged_above=-999 required=5 tests=[AWL=0.145, 
	BAYES_00=-2.599, HELO_EQ_MODEMCABLE=0.768,
	HOST_EQ_MODEMCABLE=1.368]
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 eKO39hStMGDZ for <p2pi@core3.amsl.com>;
	Mon,  3 Nov 2008 12:38:23 -0800 (PST)
Received: from pacdcimo01.cable.comcast.com (PacdcIMO01.cable.comcast.com
	[24.40.8.145]) by core3.amsl.com (Postfix) with ESMTP id 510DE28C2E1
	for <p2pi@ietf.org>; Mon,  3 Nov 2008 12:36:46 -0800 (PST)
Received: from ([10.52.116.30])
	by pacdcimo01.cable.comcast.com with ESMTP  id 5503620.18430978;
	Mon, 03 Nov 2008 15:35:43 -0500
Received: from PACDCEXCMB04.cable.comcast.com ([24.40.15.86]) by
	PAOAKEXCSMTP01.cable.comcast.com with Microsoft
	SMTPSVC(6.0.3790.3959); Mon, 3 Nov 2008 15:35:43 -0500
X-MimeOLE: Produced By Microsoft Exchange V6.5
Content-class: urn:content-classes:message
MIME-Version: 1.0
Date: Mon, 3 Nov 2008 15:35:04 -0500
Message-ID: <45AEC6EF95942140888406588E1A660205B9E870@PACDCEXCMB04.cable.comcast.com>
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Thread-Topic: draft-livingood-woundy-p4p-experiences-02 posted
Thread-Index: Ack986aY/WfQloYCRXeJo2Sm/bVnGw==
From: "Livingood, Jason" <Jason_Livingood@cable.comcast.com>
To: <p2pi@ietf.org>
X-OriginalArrivalTime: 03 Nov 2008 20:35:43.0346 (UTC)
	FILETIME=[BE28C520:01C93DF3]
Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

A draft at
http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
es-02.txt may be of interest to folks that have been interested in P2Pi
and ALTO.  We have requested time on the ALTO agenda at IETF 73 to
present this.

Regards
Jason
_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Mon Nov  3 12:52:49 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 87EF93A6C63;
	Mon,  3 Nov 2008 12:52:49 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 4EFEF3A6B20
	for <p2pi@core3.amsl.com>; Mon,  3 Nov 2008 12:52:48 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -0.333
X-Spam-Level: 
X-Spam-Status: No, score=-0.333 tagged_above=-999 required=5 tests=[AWL=0.130, 
	BAYES_00=-2.599, HELO_EQ_MODEMCABLE=0.768,
	HOST_EQ_MODEMCABLE=1.368]
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 1bbqNWEgrXXE for <p2pi@core3.amsl.com>;
	Mon,  3 Nov 2008 12:52:41 -0800 (PST)
Received: from paoakoavas10.cable.comcast.com (paoakoavas10.cable.comcast.com
	[208.17.35.59]) by core3.amsl.com (Postfix) with ESMTP id 9C7663A6C7F
	for <p2pi@ietf.org>; Mon,  3 Nov 2008 12:51:14 -0800 (PST)
Received: from ([10.195.246.152])
	by paoakoavas10.cable.comcast.com with ESMTP  id KP-TDCH7.52695954;
	Mon, 03 Nov 2008 15:50:09 -0500
Received: from PACDCEXCMB04.cable.comcast.com ([24.40.15.86]) by
	NJMDCEXCRLY01.cable.comcast.com with Microsoft
	SMTPSVC(6.0.3790.3959); Mon, 3 Nov 2008 15:50:09 -0500
X-MimeOLE: Produced By Microsoft Exchange V6.5
Content-class: urn:content-classes:message
MIME-Version: 1.0
Date: Mon, 3 Nov 2008 15:49:59 -0500
Message-ID: <45AEC6EF95942140888406588E1A660205B9E872@PACDCEXCMB04.cable.comcast.com>
In-Reply-To: <45AEC6EF95942140888406588E1A660205B9E870@PACDCEXCMB04.cable.comcast.com>
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Thread-Topic: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
Thread-Index: Ack986aY/WfQloYCRXeJo2Sm/bVnGwAAgOvA
References: <45AEC6EF95942140888406588E1A660205B9E870@PACDCEXCMB04.cable.comcast.com>
From: "Livingood, Jason" <Jason_Livingood@cable.comcast.com>
To: <p2pi@ietf.org>
X-OriginalArrivalTime: 03 Nov 2008 20:50:09.0151 (UTC)
	FILETIME=[C23820F0:01C93DF5]
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

For some reason the URL was cut to two lines - trying again:

http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
es-02.txt



> -----Original Message-----
> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On 
> Behalf Of Livingood, Jason
> Sent: Monday, November 03, 2008 3:35 PM
> To: p2pi@ietf.org
> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> 
> A draft at
> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
> -experienc
> es-02.txt may be of interest to folks that have been 
> interested in P2Pi and ALTO.  We have requested time on the 
> ALTO agenda at IETF 73 to present this.
> 
> Regards
> Jason
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi
> 
_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Mon Nov  3 14:42:05 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 689413A6C9A;
	Mon,  3 Nov 2008 14:42:05 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id C37BB3A6C9A
	for <p2pi@core3.amsl.com>; Mon,  3 Nov 2008 14:42:03 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -6.599
X-Spam-Level: 
X-Spam-Status: No, score=-6.599 tagged_above=-999 required=5
	tests=[BAYES_00=-2.599, RCVD_IN_DNSWL_MED=-4]
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 LKeoXzTObmXt for <p2pi@core3.amsl.com>;
	Mon,  3 Nov 2008 14:42:03 -0800 (PST)
Received: from www.cdt.org (www.cdt.org [72.3.253.41])
	by core3.amsl.com (Postfix) with ESMTP id DF3B83A6AA9
	for <p2pi@ietf.org>; Mon,  3 Nov 2008 14:42:02 -0800 (PST)
Received: from [10.0.1.38] (66.safeclick.net [63.119.245.66])
	(authenticated bits=0)
	by www.cdt.org (8.12.11.20060308/8.12.11) with ESMTP id mA3Mg0c7027417
	for <p2pi@ietf.org>; Mon, 3 Nov 2008 17:42:00 -0500
Message-Id: <164B4670-C779-46BD-AF07-935B4CA18B33@cdt.org>
From: Alissa Cooper <acooper@cdt.org>
To: p2pi@ietf.org
Mime-Version: 1.0 (Apple Message framework v926)
Date: Mon, 3 Nov 2008 17:42:00 -0500
References: <20081024210447.E66D23A69E3@core3.amsl.com>
X-Mailer: Apple Mail (2.926)
Subject: [p2pi] Fwd: New Version Notification for
	draft-p2pi-cooper-workshop-report-00
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset="us-ascii"; Format="flowed"; DelSp="yes"
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

For those who may have missed this, the draft at http://www.ietf.org/internet-drafts/draft-p2pi-cooper-workshop-report-00.txt 
  is a report that Jon Peterson and I put together on the p2pi  
workshop held back in May. Feel free to send comments to the list or  
to me directly.

Alissa
--
----------------------------------------------------
Alissa Cooper
Center for Democracy and Technology


Begin forwarded message:

> From: IETF I-D Submission Tool <idsubmission@ietf.org>
> Date: October 24, 2008 5:04:47 PM EDT
> To: acooper@cdt.org
> Cc: jon.peterson@neustar.biz
> Subject: New Version Notification for  draft-p2pi-cooper-workshop- 
> report-00
>
>
> A new version of I-D, draft-p2pi-cooper-workshop-report-00.txt has  
> been successfuly submitted by Alissa Cooper and posted to the IETF  
> repository.
>
> Filename:	 draft-p2pi-cooper-workshop-report
> Revision:	 00
> Title:		 Report from the IETF workshop on P2P Infrastructure, May  
> 28, 2008
> Creation_date:	 2008-10-24
> WG ID:		 Independent Submission
> Number_of_pages: 23
>
> Abstract:
> This document reports the outcome of a workshop organized by the
> Real-time Applications and Infrastructure Area Directors of the IETF
> to discuss network delay and congestion issues resulting from
> increased P2P traffic volumes.  The workshop was held on May 28, 2008
> at MIT in Cambridge, MA, USA.  The goals of the workshop were
> twofold: to understand the technical problems ISPs and end users are
> experiencing as a result of high volumes of P2P traffic, and to begin
> to understand how the IETF may be helpful in addressing these
> problems.  Gaining an understanding of where in the IETF this work
> might be pursued and how to extract out feasible work items were
> highlighted as important tasks in pursuit of the latter goal.  The
> workshop was very well attended and produced several work items that
> have since been taken up by members of the IETF community.
>
>
>
> The IETF Secretariat.
>







_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Mon Nov  3 17:56:22 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 513833A6AAB;
	Mon,  3 Nov 2008 17:56:22 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 78DC13A6AAB
	for <p2pi@core3.amsl.com>; Mon,  3 Nov 2008 17:56:21 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.999
X-Spam-Level: 
X-Spam-Status: No, score=-1.999 tagged_above=-999 required=5 tests=[AWL=0.600, 
	BAYES_00=-2.599]
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 u8hLJijs8EKo for <p2pi@core3.amsl.com>;
	Mon,  3 Nov 2008 17:56:20 -0800 (PST)
Received: from szxga04-in.huawei.com (szxga04-in.huawei.com [119.145.14.67])
	by core3.amsl.com (Postfix) with ESMTP id AAFF23A693A
	for <p2pi@ietf.org>; Mon,  3 Nov 2008 17:56:20 -0800 (PST)
Received: from huawei.com (szxga04-in [172.24.2.12])
	by szxga04-in.huawei.com (iPlanet Messaging Server 5.2 HotFix 2.14
	(built Aug
	8 2006)) with ESMTP id <0K9S004A8DDCF9@szxga04-in.huawei.com> for
	p2pi@ietf.org; Tue, 04 Nov 2008 09:56:00 +0800 (CST)
Received: from huawei.com ([172.24.1.12])
	by szxga04-in.huawei.com (iPlanet Messaging Server 5.2 HotFix 2.14
	(built Aug
	8 2006)) with ESMTP id <0K9S00DF8DDCH4@szxga04-in.huawei.com> for
	p2pi@ietf.org; Tue, 04 Nov 2008 09:56:00 +0800 (CST)
Received: from s64081 ([10.164.12.12])
	by szxml05-in.huawei.com (iPlanet Messaging Server 5.2 HotFix 2.14
	(built Aug
	8 2006)) with ESMTPA id <0K9S007BKDDBW1@szxml05-in.huawei.com> for
	p2pi@ietf.org; Tue, 04 Nov 2008 09:56:00 +0800 (CST)
Date: Tue, 04 Nov 2008 09:55:59 +0800
From: Song Haibin <melodysong@huawei.com>
To: p2pi@ietf.org
Message-id: <046301c93e20$7c301010$0c0ca40a@china.huawei.com>
MIME-version: 1.0
X-MIMEOLE: Produced By Microsoft MimeOLE V6.00.2900.3350
X-Mailer: Microsoft Office Outlook 11
Thread-index: Ack+IHvtr38jNQkmQn2+LAdA3xFIJw==
Subject: [p2pi] I-D ACTION:draft-zheng-p2psip-diagnose-03.txt
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

A New Internet-Draft is available from the on-line Internet-Drafts
directories.

	Title		: Diagnose P2PSIP Overlay Network Failures
	Author(s)   	: S. Haibin, H. Zhang, X. Jiang
	Filename	    : draft-zheng-p2psip-diagnose-03.txt
	Pages		: 21
	Date		    : 2008-11-3
	
This document describes P2PSIP diagnostics. It extends the methods defined
in the base protocol for the diagnostics in P2PSIP overlay network. A new
method Echo is an efficient method used in the trusted overlays for
retrieving useful diagnostic information. The methods and message formats
are consistent with P2PSIP base protocol RELOAD, and the diagnostic
information mainly comes from the previous version-02 of this document.

A URL for this Internet-Draft is:
http://www.ietf.org/internet-drafts/draft-zheng-p2psip-diagnose-03.txt

Comments are appreciated!

Best Regards,
Song Haibin
Email: melodysong@huawei.com
Skype: alexsonghw




_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Mon Nov  3 18:07:58 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 782D23A6CBA;
	Mon,  3 Nov 2008 18:07:58 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 6BA423A6CBA
	for <p2pi@core3.amsl.com>; Mon,  3 Nov 2008 18:07:57 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.299
X-Spam-Level: 
X-Spam-Status: No, score=-2.299 tagged_above=-999 required=5 tests=[AWL=0.300, 
	BAYES_00=-2.599]
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 1kZ-EHO-42ob for <p2pi@core3.amsl.com>;
	Mon,  3 Nov 2008 18:07:56 -0800 (PST)
Received: from szxga04-in.huawei.com (szxga04-in.huawei.com [119.145.14.67])
	by core3.amsl.com (Postfix) with ESMTP id 93D333A6BA2
	for <p2pi@ietf.org>; Mon,  3 Nov 2008 18:07:56 -0800 (PST)
Received: from huawei.com (szxga04-in [172.24.2.12])
	by szxga04-in.huawei.com (iPlanet Messaging Server 5.2 HotFix 2.14
	(built Aug
	8 2006)) with ESMTP id <0K9S00GL8DX5CP@szxga04-in.huawei.com> for
	p2pi@ietf.org; Tue, 04 Nov 2008 10:07:53 +0800 (CST)
Received: from huawei.com ([172.24.1.24])
	by szxga04-in.huawei.com (iPlanet Messaging Server 5.2 HotFix 2.14
	(built Aug
	8 2006)) with ESMTP id <0K9S002CUDX58Y@szxga04-in.huawei.com> for
	p2pi@ietf.org; Tue, 04 Nov 2008 10:07:53 +0800 (CST)
Received: from s64081 ([10.164.12.12])
	by szxml04-in.huawei.com (iPlanet Messaging Server 5.2 HotFix 2.14
	(built Aug
	8 2006)) with ESMTPA id <0K9S00K85DX5F9@szxml04-in.huawei.com> for
	p2pi@ietf.org; Tue, 04 Nov 2008 10:07:53 +0800 (CST)
Date: Tue, 04 Nov 2008 10:07:53 +0800
From: Song Haibin <melodysong@huawei.com>
In-reply-to: <046301c93e20$7c301010$0c0ca40a@china.huawei.com>
To: p2pi@ietf.org
Message-id: <046501c93e22$256a8d80$0c0ca40a@china.huawei.com>
MIME-version: 1.0
X-MIMEOLE: Produced By Microsoft MimeOLE V6.00.2900.3350
X-Mailer: Microsoft Office Outlook 11
Thread-index: Ack+IHvtr38jNQkmQn2+LAdA3xFIJwAAVmTg
Subject: Re: [p2pi] I-D ACTION:draft-zheng-p2psip-diagnose-03.txt
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

Sorry for the wrong distribution list. I meant to send it to
p2psip@ietf.org. Please ignore this email if your receive it.

Best Regards,
Song Haibin
Email: melodysong@huawei.com
Skype: alexsonghw



>-----Original Message-----
>From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
Song
>Haibin
>Sent: Tuesday, November 04, 2008 9:56 AM
>To: p2pi@ietf.org
>Subject: [p2pi] I-D ACTION:draft-zheng-p2psip-diagnose-03.txt
>
>A New Internet-Draft is available from the on-line Internet-Drafts
>directories.
>
>	Title		: Diagnose P2PSIP Overlay Network Failures
>	Author(s)   	: S. Haibin, H. Zhang, X. Jiang
>	Filename	    : draft-zheng-p2psip-diagnose-03.txt
>	Pages		: 21
>	Date		    : 2008-11-3
>
>This document describes P2PSIP diagnostics. It extends the methods defined
>in the base protocol for the diagnostics in P2PSIP overlay network. A new
>method Echo is an efficient method used in the trusted overlays for
>retrieving useful diagnostic information. The methods and message formats
>are consistent with P2PSIP base protocol RELOAD, and the diagnostic
>information mainly comes from the previous version-02 of this document.
>
>A URL for this Internet-Draft is:
>http://www.ietf.org/internet-drafts/draft-zheng-p2psip-diagnose-03.txt
>
>Comments are appreciated!
>
>Best Regards,
>Song Haibin
>Email: melodysong@huawei.com
>Skype: alexsonghw
>
>
>
>
>_______________________________________________
>p2pi mailing list
>p2pi@ietf.org
>https://www.ietf.org/mailman/listinfo/p2pi

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Wed Nov  5 07:44:33 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id B3C2C3A6A3D;
	Wed,  5 Nov 2008 07:44:33 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 368473A6A22
	for <p2pi@core3.amsl.com>; Wed,  5 Nov 2008 07:44:33 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -0.719
X-Spam-Level: 
X-Spam-Status: No, score=-0.719 tagged_above=-999 required=5
	tests=[BAYES_00=-2.599, HELO_EQ_IT=0.635, HOST_EQ_IT=1.245]
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 L3+lDDA4dRuD for <p2pi@core3.amsl.com>;
	Wed,  5 Nov 2008 07:44:32 -0800 (PST)
Received: from maild.telecomitalia.it (maild.telecomitalia.it [156.54.233.30])
	by core3.amsl.com (Postfix) with ESMTP id CBF233A63D2
	for <p2pi@ietf.org>; Wed,  5 Nov 2008 07:44:31 -0800 (PST)
Received: from ptpxch008ba020.idc.cww.telecomitalia.it ([156.54.240.51]) by
	maild.telecomitalia.it with Microsoft SMTPSVC(6.0.3790.1830); 
	Wed, 5 Nov 2008 16:41:00 +0100
Received: from ptpxch006ba020.idc.cww.telecomitalia.it ([156.54.240.45]) by
	ptpxch008ba020.idc.cww.telecomitalia.it with Microsoft
	SMTPSVC(6.0.3790.1830); Wed, 5 Nov 2008 16:41:00 +0100
Received: from [10.229.8.106] ([10.229.8.106]) by
	ptpxch006ba020.idc.cww.telecomitalia.it over TLS secured
	channel with Microsoft SMTPSVC(6.0.3790.1830); 
	Wed, 5 Nov 2008 16:40:59 +0100
Message-ID: <4911BE88.7090409@telecomitalia.it>
Date: Wed, 05 Nov 2008 16:40:56 +0100
From: Enrico Marocco <enrico.marocco@telecomitalia.it>
User-Agent: Mozilla-Thunderbird 2.0.0.17 (X11/20081018)
MIME-Version: 1.0
To: "p2pi@ietf.org" <p2pi@ietf.org>
References: <49089104.2010406@telecomitalia.it>
	<490893A5.4000705@telecomitalia.it>
In-Reply-To: <490893A5.4000705@telecomitalia.it>
X-Enigmail-Version: 0.95.0
X-OriginalArrivalTime: 05 Nov 2008 15:40:59.0248 (UTC)
	FILETIME=[E6710F00:01C93F5C]
Subject: Re: [p2pi] Agenda requests for Minneapolis
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: multipart/mixed; boundary="===============1464666832=="
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

This is a cryptographically signed message in MIME format.

--===============1464666832==
Content-Type: multipart/signed; protocol="application/x-pkcs7-signature"; micalg=sha1; boundary="------------ms060800050909050103080900"

This is a cryptographically signed message in MIME format.

--------------ms060800050909050103080900
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit

The current draft agenda is now online, available at
http://www.ietf.org/proceedings/08nov/agenda/alto.html.

Please take a look and let us know of any comments.

Enrico

Enrico Marocco wrote:
> Of course the session is confirmed for _Tuesday_, not Thursday. My bad.
> 
> Enrico
> 
> Enrico Marocco wrote:
>> The ALTO session for Minneapolis is confirmed for Thu afternoon also on
>> the "final" agenda (which, as usual, is never really final). If you want
>> to request a slot, please send a private message to me and Vijay
>> indicating the subject of the presentation and how much time you think
>> will be needed.
>>
>> Factors considered in allocating slots will include how much attention
>> the subject has received on the list, whether there is a draft
>> associated to the presentation and whether the session will be a BoF or
>> a WG meeting.

--------------ms060800050909050103080900
Content-Type: application/x-pkcs7-signature; name="smime.p7s"
Content-Transfer-Encoding: base64
Content-Disposition: attachment; filename="smime.p7s"
Content-Description: S/MIME Cryptographic Signature
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--------------ms060800050909050103080900--

--===============1464666832==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi

--===============1464666832==--


From p2pi-bounces@ietf.org  Wed Nov  5 08:27:48 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id EC78C3A6BEC;
	Wed,  5 Nov 2008 08:27:48 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 1CD853A6ADE
	for <p2pi@core3.amsl.com>; Wed,  5 Nov 2008 08:27:48 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -6.599
X-Spam-Level: 
X-Spam-Status: No, score=-6.599 tagged_above=-999 required=5
	tests=[BAYES_00=-2.599, RCVD_IN_DNSWL_MED=-4]
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 H2uetdMEhXqM for <p2pi@core3.amsl.com>;
	Wed,  5 Nov 2008 08:27:47 -0800 (PST)
Received: from exprod7og116.obsmtp.com (exprod7ob116.obsmtp.com [64.18.2.218])
	by core3.amsl.com (Postfix) with ESMTP id 167423A6C10
	for <p2pi@ietf.org>; Wed,  5 Nov 2008 08:27:43 -0800 (PST)
Received: from source ([66.129.228.6]) by exprod7ob116.postini.com
	([64.18.6.12]) with SMTP; Wed, 05 Nov 2008 08:27:45 PST
Received: from pi-smtp.jnpr.net ([10.10.2.36]) by p-emsmtp03.jnpr.net with
	Microsoft SMTPSVC(6.0.3790.3959); Wed, 5 Nov 2008 08:23:45 -0800
Received: from proton.jnpr.net ([10.10.2.37]) by pi-smtp.jnpr.net with
	Microsoft SMTPSVC(5.0.2195.6713); Wed, 5 Nov 2008 11:23:44 -0500
Received: from 172.23.1.75 ([172.23.1.75]) by proton.jnpr.net ([10.10.2.37])
	with Microsoft Exchange Server HTTP-DAV ; 
	Wed,  5 Nov 2008 16:23:44 +0000
User-Agent: Microsoft-Entourage/12.13.0.080930
Date: Wed, 05 Nov 2008 08:23:29 -0800
From: Reinaldo Penno <rpenno@juniper.net>
To: "Livingood, Jason" <Jason_Livingood@cable.comcast.com>,
	<p2pi@ietf.org>
Message-ID: <C5370881.14992%rpenno@juniper.net>
Thread-Topic: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
Thread-Index: Ack986aY/WfQloYCRXeJo2Sm/bVnGwAAgOvAAFtK/O4=
In-Reply-To: <45AEC6EF95942140888406588E1A660205B9E872@PACDCEXCMB04.cable.comcast.com>
Mime-version: 1.0
X-OriginalArrivalTime: 05 Nov 2008 16:23:44.0338 (UTC)
	FILETIME=[DF5ABB20:01C93F62]
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

Hello Jason/Rich,

This is such an interesting draft. I'm surprised there are no questions
about it. Maybe everybody else is part of P4P one way or another and I'm not
in the 'in' crowd (;-) so I have questions.

* What was the file size in those experiments? Some post long ago said the
file size in some P4P experiments was really small, as opposed to the top
100 torrents where the file size is ~1Gb. I was curious what is the
optimization payback in terms of download time for large files as opposed
small files. 

* How long would it take to download the file in the three different
scenarios? I know that more consumed bandwidth in access might lead one to
conclude that file was downloaded faster but I'm not sure this is a
straightforward conclusion.

* Was the file already seeded in Comcast's network? More specifically, how
was file propagation done? All clients started from scratch and had to start
pulling the file from some other side of the world and then exchanging
pieces? This is mainly due to the discussion in 4.2.

* Was PEX, DHT and others enabled in the clients?

* Was local peer discovery enabled in the clients? BTW, can
broadcast/multicast peer discovery work in Cable networks?

* If more clients finish downloading faster and become seeders you would
think that for popular content Comcast's upstream bandwidth would increase
due to the number of seeder in its network. So, were clients allowed to
become seeders to the outside of Comcast's network? How much of the swarm
was within Comcast and outside?

Thanks,

Reinaldo

On 11/3/08 12:49 PM, "Livingood, Jason" <Jason_Livingood@cable.comcast.com>
wrote:

> For some reason the URL was cut to two lines - trying again:
> 
> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
> es-02.txt
> 
> 
> 
>> -----Original Message-----
>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
>> Behalf Of Livingood, Jason
>> Sent: Monday, November 03, 2008 3:35 PM
>> To: p2pi@ietf.org
>> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>> 
>> A draft at
>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
>> -experienc
>> es-02.txt may be of interest to folks that have been
>> interested in P2Pi and ALTO.  We have requested time on the
>> ALTO agenda at IETF 73 to present this.
>> 
>> Regards
>> Jason
>> _______________________________________________
>> p2pi mailing list
>> p2pi@ietf.org
>> https://www.ietf.org/mailman/listinfo/p2pi
>> 
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Wed Nov  5 14:31:52 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 091733A6452;
	Wed,  5 Nov 2008 14:31:52 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 44C603A6452
	for <p2pi@core3.amsl.com>; Wed,  5 Nov 2008 14:31:50 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -0.463
X-Spam-Level: 
X-Spam-Status: No, score=-0.463 tagged_above=-999 required=5
	tests=[BAYES_00=-2.599, HELO_EQ_MODEMCABLE=0.768,
	HOST_EQ_MODEMCABLE=1.368]
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 n8V9bEvr8Fqi for <p2pi@core3.amsl.com>;
	Wed,  5 Nov 2008 14:31:49 -0800 (PST)
Received: from pacdcimo01.cable.comcast.com (PacdcIMO01.cable.comcast.com
	[24.40.8.145]) by core3.amsl.com (Postfix) with ESMTP id EEDBC3A63D2
	for <p2pi@ietf.org>; Wed,  5 Nov 2008 14:31:48 -0800 (PST)
Received: from ([24.40.15.118])
	by pacdcimo01.cable.comcast.com with ESMTP  id 5503620.18689742;
	Wed, 05 Nov 2008 17:30:01 -0500
Received: from PACDCEXCMB06.cable.comcast.com ([24.40.15.22]) by
	PACDCEXCSMTP04.cable.comcast.com with Microsoft
	SMTPSVC(6.0.3790.3959); Wed, 5 Nov 2008 17:30:00 -0500
X-MimeOLE: Produced By Microsoft Exchange V6.5
Content-class: urn:content-classes:message
MIME-Version: 1.0
Date: Wed, 5 Nov 2008 17:29:45 -0500
Message-ID: <74CCBBDF76102846AFA7B29F3A98D3F602896489@PACDCEXCMB06.cable.comcast.com>
In-Reply-To: <C5370881.14992%rpenno@juniper.net>
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Thread-Topic: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
Thread-Index: Ack986aY/WfQloYCRXeJo2Sm/bVnGwAAgOvAAFtK/O4ABmJ0YA==
References: <45AEC6EF95942140888406588E1A660205B9E872@PACDCEXCMB04.cable.comcast.com>
	<C5370881.14992%rpenno@juniper.net>
From: "Woundy, Richard" <Richard_Woundy@cable.comcast.com>
To: "Reinaldo Penno" <rpenno@juniper.net>,
	<p2pi@ietf.org>
X-OriginalArrivalTime: 05 Nov 2008 22:30:00.0718 (UTC)
	FILETIME=[0A4C32E0:01C93F96]
Cc: "Woundy, Richard" <Richard_Woundy@cable.comcast.com>, "Livingood,
	Jason" <Jason_Livingood@cable.comcast.com>
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

Reinaldo,

I can answer the easy questions. We will need some assistance from Pando
(and Yale) for some of the other ones.

>What was the file size in those experiments?

21 megabytes. From section 2: "Pando distributed a special 21 MB
licensed video file as in order to measure the effectiveness of P4P
iTrackers."

>How long would it take to download the file in the three different
scenarios? I know that more consumed bandwidth in access might lead one
to conclude that file was downloaded faster...

To clarify, most of the raw data (download speed and Internet
peering/transit traffic volumes) were collected by Pando Networks from
their P2P clients, not collected by Comcast across its links. So my
assumption is that the Pando client used the content size (21 MB), and
divided by the download time to get the speed.

>Was the file already seeded in Comcast's network? More specifically,
how
was file propagation done?

Any seeding happened outside of Comcast's network, and outside of
Comcast's control. That's really a question for Pando.

>Was PEX, DHT and others enabled in the clients?

Pando would know whether PEX was enabled. It would be safe to assume
that with respect to this trial, DHT was NOT enabled, since Pando
supplied the tracker. (The pTracker in the draft is a tracker operated
by Pando.)

>Was local peer discovery enabled in the clients?

Pando would know.

>BTW, can broadcast/multicast peer discovery work in Cable networks?

Do you mean something like this:
http://bittorrent.org/beps/bep_0026.html?

If so, peer discovery probably would not work over the typical last mile
cable network. Maybe I'm wrong, but I see this protocol as intended for
peer discovery within one's home network / LAN / WiFi network, not over
a cable network.

>So, were clients allowed to become seeders to the outside of Comcast's
network?

Yes, they were.

As a related item, look closely at section 4.2. The amount of aggregate
uploaded data from Comcast clients (per swarm) was about 140,000 MB. The
amount of aggregate downloaded data from Comcast clients (per swarm) was
about 60,000 MB or so. So the typical Comcast client uploaded more than
twice the amount of data that it downloaded. 

>How much of the swarm was within Comcast and outside?

Most of the swarm was outside of Comcast. Unfortunately I don't have
access to the size of the global swarm, but I would guess that Comcast
clients represented no more than 15% of the swarm, and maybe as little
as 5%. Those guesses are based on the behavior of the random swarm, e.g.
Comcast clients uploaded to non-Comcast clients 94% of the time in the
random swarm.

-- Rich

-----Original Message-----
From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
Reinaldo Penno
Sent: Wednesday, November 05, 2008 11:23 AM
To: Livingood, Jason; p2pi@ietf.org
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted

Hello Jason/Rich,

This is such an interesting draft. I'm surprised there are no questions
about it. Maybe everybody else is part of P4P one way or another and I'm
not
in the 'in' crowd (;-) so I have questions.

* What was the file size in those experiments? Some post long ago said
the
file size in some P4P experiments was really small, as opposed to the
top
100 torrents where the file size is ~1Gb. I was curious what is the
optimization payback in terms of download time for large files as
opposed
small files. 

* How long would it take to download the file in the three different
scenarios? I know that more consumed bandwidth in access might lead one
to
conclude that file was downloaded faster but I'm not sure this is a
straightforward conclusion.

* Was the file already seeded in Comcast's network? More specifically,
how
was file propagation done? All clients started from scratch and had to
start
pulling the file from some other side of the world and then exchanging
pieces? This is mainly due to the discussion in 4.2.

* Was PEX, DHT and others enabled in the clients?

* Was local peer discovery enabled in the clients? BTW, can
broadcast/multicast peer discovery work in Cable networks?

* If more clients finish downloading faster and become seeders you would
think that for popular content Comcast's upstream bandwidth would
increase
due to the number of seeder in its network. So, were clients allowed to
become seeders to the outside of Comcast's network? How much of the
swarm
was within Comcast and outside?

Thanks,

Reinaldo

On 11/3/08 12:49 PM, "Livingood, Jason"
<Jason_Livingood@cable.comcast.com>
wrote:

> For some reason the URL was cut to two lines - trying again:
> 
>
http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
> es-02.txt
> 
> 
> 
>> -----Original Message-----
>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
>> Behalf Of Livingood, Jason
>> Sent: Monday, November 03, 2008 3:35 PM
>> To: p2pi@ietf.org
>> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>> 
>> A draft at
>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
>> -experienc
>> es-02.txt may be of interest to folks that have been
>> interested in P2Pi and ALTO.  We have requested time on the
>> ALTO agenda at IETF 73 to present this.
>> 
>> Regards
>> Jason
>> _______________________________________________
>> p2pi mailing list
>> p2pi@ietf.org
>> https://www.ietf.org/mailman/listinfo/p2pi
>> 
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi
_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Wed Nov  5 14:43:49 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 148DF3A6774;
	Wed,  5 Nov 2008 14:43:49 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id D2DB33A6774
	for <p2pi@core3.amsl.com>; Wed,  5 Nov 2008 14:43:47 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.475
X-Spam-Level: 
X-Spam-Status: No, score=-1.475 tagged_above=-999 required=5 tests=[AWL=0.501, 
	BAYES_00=-2.599, FM_FORGED_GMAIL=0.622, HTML_MESSAGE=0.001]
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 00Q1f9n6XT44 for <p2pi@core3.amsl.com>;
	Wed,  5 Nov 2008 14:43:46 -0800 (PST)
Received: from rv-out-0506.google.com (rv-out-0506.google.com [209.85.198.231])
	by core3.amsl.com (Postfix) with ESMTP id 537BB3A63D2
	for <p2pi@ietf.org>; Wed,  5 Nov 2008 14:43:46 -0800 (PST)
Received: by rv-out-0506.google.com with SMTP id b25so242615rvf.49
	for <p2pi@ietf.org>; Wed, 05 Nov 2008 14:42:51 -0800 (PST)
Received: by 10.141.137.16 with SMTP id p16mr739593rvn.180.1225924971408;
	Wed, 05 Nov 2008 14:42:51 -0800 (PST)
Received: by 10.141.69.3 with HTTP; Wed, 5 Nov 2008 14:42:51 -0800 (PST)
Message-ID: <3efc39a60811051442o34057671ga5a976342f33872b@mail.gmail.com>
Date: Wed, 5 Nov 2008 14:42:51 -0800
From: "Robb Topolski" <robb@funchords.com>
To: "Woundy, Richard" <Richard_Woundy@cable.comcast.com>
In-Reply-To: <74CCBBDF76102846AFA7B29F3A98D3F602896489@PACDCEXCMB06.cable.comcast.com>
MIME-Version: 1.0
References: <45AEC6EF95942140888406588E1A660205B9E872@PACDCEXCMB04.cable.comcast.com>
	<C5370881.14992%rpenno@juniper.net>
	<74CCBBDF76102846AFA7B29F3A98D3F602896489@PACDCEXCMB06.cable.comcast.com>
Cc: "Livingood, Jason" <Jason_Livingood@cable.comcast.com>, p2pi@ietf.org
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: multipart/mixed; boundary="===============0868357491=="
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

--===============0868357491==
Content-Type: multipart/alternative; 
	boundary="----=_Part_7224_18719526.1225924971380"

------=_Part_7224_18719526.1225924971380
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

I don't get the part where access network download consumption increased as
a result of using P4P (section 4.2).  Can someone explain how that could
happen?

Robb

On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard <
Richard_Woundy@cable.comcast.com> wrote:

> Reinaldo,
>
> I can answer the easy questions. We will need some assistance from Pando
> (and Yale) for some of the other ones.
>
> >What was the file size in those experiments?
>
> 21 megabytes. From section 2: "Pando distributed a special 21 MB
> licensed video file as in order to measure the effectiveness of P4P
> iTrackers."
>
> >How long would it take to download the file in the three different
> scenarios? I know that more consumed bandwidth in access might lead one
> to conclude that file was downloaded faster...
>
> To clarify, most of the raw data (download speed and Internet
> peering/transit traffic volumes) were collected by Pando Networks from
> their P2P clients, not collected by Comcast across its links. So my
> assumption is that the Pando client used the content size (21 MB), and
> divided by the download time to get the speed.
>
> >Was the file already seeded in Comcast's network? More specifically,
> how
> was file propagation done?
>
> Any seeding happened outside of Comcast's network, and outside of
> Comcast's control. That's really a question for Pando.
>
> >Was PEX, DHT and others enabled in the clients?
>
> Pando would know whether PEX was enabled. It would be safe to assume
> that with respect to this trial, DHT was NOT enabled, since Pando
> supplied the tracker. (The pTracker in the draft is a tracker operated
> by Pando.)
>
> >Was local peer discovery enabled in the clients?
>
> Pando would know.
>
> >BTW, can broadcast/multicast peer discovery work in Cable networks?
>
> Do you mean something like this:
> http://bittorrent.org/beps/bep_0026.html?
>
> If so, peer discovery probably would not work over the typical last mile
> cable network. Maybe I'm wrong, but I see this protocol as intended for
> peer discovery within one's home network / LAN / WiFi network, not over
> a cable network.
>
> >So, were clients allowed to become seeders to the outside of Comcast's
> network?
>
> Yes, they were.
>
> As a related item, look closely at section 4.2. The amount of aggregate
> uploaded data from Comcast clients (per swarm) was about 140,000 MB. The
> amount of aggregate downloaded data from Comcast clients (per swarm) was
> about 60,000 MB or so. So the typical Comcast client uploaded more than
> twice the amount of data that it downloaded.
>
> >How much of the swarm was within Comcast and outside?
>
> Most of the swarm was outside of Comcast. Unfortunately I don't have
> access to the size of the global swarm, but I would guess that Comcast
> clients represented no more than 15% of the swarm, and maybe as little
> as 5%. Those guesses are based on the behavior of the random swarm, e.g.
> Comcast clients uploaded to non-Comcast clients 94% of the time in the
> random swarm.
>
> -- Rich
>
> -----Original Message-----
> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
> Reinaldo Penno
> Sent: Wednesday, November 05, 2008 11:23 AM
> To: Livingood, Jason; p2pi@ietf.org
> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>
> Hello Jason/Rich,
>
> This is such an interesting draft. I'm surprised there are no questions
> about it. Maybe everybody else is part of P4P one way or another and I'm
> not
> in the 'in' crowd (;-) so I have questions.
>
> * What was the file size in those experiments? Some post long ago said
> the
> file size in some P4P experiments was really small, as opposed to the
> top
> 100 torrents where the file size is ~1Gb. I was curious what is the
> optimization payback in terms of download time for large files as
> opposed
> small files.
>
> * How long would it take to download the file in the three different
> scenarios? I know that more consumed bandwidth in access might lead one
> to
> conclude that file was downloaded faster but I'm not sure this is a
> straightforward conclusion.
>
> * Was the file already seeded in Comcast's network? More specifically,
> how
> was file propagation done? All clients started from scratch and had to
> start
> pulling the file from some other side of the world and then exchanging
> pieces? This is mainly due to the discussion in 4.2.
>
> * Was PEX, DHT and others enabled in the clients?
>
> * Was local peer discovery enabled in the clients? BTW, can
> broadcast/multicast peer discovery work in Cable networks?
>
> * If more clients finish downloading faster and become seeders you would
> think that for popular content Comcast's upstream bandwidth would
> increase
> due to the number of seeder in its network. So, were clients allowed to
> become seeders to the outside of Comcast's network? How much of the
> swarm
> was within Comcast and outside?
>
> Thanks,
>
> Reinaldo
>
> On 11/3/08 12:49 PM, "Livingood, Jason"
> <Jason_Livingood@cable.comcast.com>
> wrote:
>
> > For some reason the URL was cut to two lines - trying again:
> >
> >
> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
> > es-02.txt
> >
> >
> >
> >> -----Original Message-----
> >> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
> >> Behalf Of Livingood, Jason
> >> Sent: Monday, November 03, 2008 3:35 PM
> >> To: p2pi@ietf.org
> >> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> >>
> >> A draft at
> >> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
> >> -experienc
> >> es-02.txt may be of interest to folks that have been
> >> interested in P2Pi and ALTO.  We have requested time on the
> >> ALTO agenda at IETF 73 to present this.
> >>
> >> Regards
> >> Jason
> >> _______________________________________________
> >> p2pi mailing list
> >> p2pi@ietf.org
> >> https://www.ietf.org/mailman/listinfo/p2pi
> >>
> > _______________________________________________
> > p2pi mailing list
> > p2pi@ietf.org
> > https://www.ietf.org/mailman/listinfo/p2pi
>
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi
>



-- 
Robb Topolski (robb@funchords.com)
Hillsboro, Oregon USA
http://www.funchords.com/

------=_Part_7224_18719526.1225924971380
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

I don&#39;t get the part where access network download consumption increased as a result of using P4P (section 4.2).&nbsp; Can someone explain how that could happen?&nbsp; <br><br>Robb<br><br><div class="gmail_quote">On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard <span dir="ltr">&lt;<a href="mailto:Richard_Woundy@cable.comcast.com">Richard_Woundy@cable.comcast.com</a>&gt;</span> wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">Reinaldo,<br>
<br>
I can answer the easy questions. We will need some assistance from Pando<br>
(and Yale) for some of the other ones.<br>
<div class="Ih2E3d"><br>
&gt;What was the file size in those experiments?<br>
<br>
</div>21 megabytes. From section 2: &quot;Pando distributed a special 21 MB<br>
licensed video file as in order to measure the effectiveness of P4P<br>
iTrackers.&quot;<br>
<div class="Ih2E3d"><br>
&gt;How long would it take to download the file in the three different<br>
scenarios? I know that more consumed bandwidth in access might lead one<br>
</div>to conclude that file was downloaded faster...<br>
<br>
To clarify, most of the raw data (download speed and Internet<br>
peering/transit traffic volumes) were collected by Pando Networks from<br>
their P2P clients, not collected by Comcast across its links. So my<br>
assumption is that the Pando client used the content size (21 MB), and<br>
divided by the download time to get the speed.<br>
<div class="Ih2E3d"><br>
&gt;Was the file already seeded in Comcast&#39;s network? More specifically,<br>
how<br>
was file propagation done?<br>
<br>
</div>Any seeding happened outside of Comcast&#39;s network, and outside of<br>
Comcast&#39;s control. That&#39;s really a question for Pando.<br>
<div class="Ih2E3d"><br>
&gt;Was PEX, DHT and others enabled in the clients?<br>
<br>
</div>Pando would know whether PEX was enabled. It would be safe to assume<br>
that with respect to this trial, DHT was NOT enabled, since Pando<br>
supplied the tracker. (The pTracker in the draft is a tracker operated<br>
by Pando.)<br>
<div class="Ih2E3d"><br>
&gt;Was local peer discovery enabled in the clients?<br>
<br>
</div>Pando would know.<br>
<div class="Ih2E3d"><br>
&gt;BTW, can broadcast/multicast peer discovery work in Cable networks?<br>
<br>
</div>Do you mean something like this:<br>
<a href="http://bittorrent.org/beps/bep_0026.html" target="_blank">http://bittorrent.org/beps/bep_0026.html</a>?<br>
<br>
If so, peer discovery probably would not work over the typical last mile<br>
cable network. Maybe I&#39;m wrong, but I see this protocol as intended for<br>
peer discovery within one&#39;s home network / LAN / WiFi network, not over<br>
a cable network.<br>
<div class="Ih2E3d"><br>
&gt;So, were clients allowed to become seeders to the outside of Comcast&#39;s<br>
network?<br>
<br>
</div>Yes, they were.<br>
<br>
As a related item, look closely at section 4.2. The amount of aggregate<br>
uploaded data from Comcast clients (per swarm) was about 140,000 MB. The<br>
amount of aggregate downloaded data from Comcast clients (per swarm) was<br>
about 60,000 MB or so. So the typical Comcast client uploaded more than<br>
twice the amount of data that it downloaded.<br>
<div class="Ih2E3d"><br>
&gt;How much of the swarm was within Comcast and outside?<br>
<br>
</div>Most of the swarm was outside of Comcast. Unfortunately I don&#39;t have<br>
access to the size of the global swarm, but I would guess that Comcast<br>
clients represented no more than 15% of the swarm, and maybe as little<br>
as 5%. Those guesses are based on the behavior of the random swarm, e.g.<br>
Comcast clients uploaded to non-Comcast clients 94% of the time in the<br>
random swarm.<br>
<br>
-- Rich<br>
<div class="Ih2E3d"><br>
-----Original Message-----<br>
From: <a href="mailto:p2pi-bounces@ietf.org">p2pi-bounces@ietf.org</a> [mailto:<a href="mailto:p2pi-bounces@ietf.org">p2pi-bounces@ietf.org</a>] On Behalf Of<br>
</div><div><div></div><div class="Wj3C7c">Reinaldo Penno<br>
Sent: Wednesday, November 05, 2008 11:23 AM<br>
To: Livingood, Jason; <a href="mailto:p2pi@ietf.org">p2pi@ietf.org</a><br>
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted<br>
<br>
Hello Jason/Rich,<br>
<br>
This is such an interesting draft. I&#39;m surprised there are no questions<br>
about it. Maybe everybody else is part of P4P one way or another and I&#39;m<br>
not<br>
in the &#39;in&#39; crowd (;-) so I have questions.<br>
<br>
* What was the file size in those experiments? Some post long ago said<br>
the<br>
file size in some P4P experiments was really small, as opposed to the<br>
top<br>
100 torrents where the file size is ~1Gb. I was curious what is the<br>
optimization payback in terms of download time for large files as<br>
opposed<br>
small files.<br>
<br>
* How long would it take to download the file in the three different<br>
scenarios? I know that more consumed bandwidth in access might lead one<br>
to<br>
conclude that file was downloaded faster but I&#39;m not sure this is a<br>
straightforward conclusion.<br>
<br>
* Was the file already seeded in Comcast&#39;s network? More specifically,<br>
how<br>
was file propagation done? All clients started from scratch and had to<br>
start<br>
pulling the file from some other side of the world and then exchanging<br>
pieces? This is mainly due to the discussion in 4.2.<br>
<br>
* Was PEX, DHT and others enabled in the clients?<br>
<br>
* Was local peer discovery enabled in the clients? BTW, can<br>
broadcast/multicast peer discovery work in Cable networks?<br>
<br>
* If more clients finish downloading faster and become seeders you would<br>
think that for popular content Comcast&#39;s upstream bandwidth would<br>
increase<br>
due to the number of seeder in its network. So, were clients allowed to<br>
become seeders to the outside of Comcast&#39;s network? How much of the<br>
swarm<br>
was within Comcast and outside?<br>
<br>
Thanks,<br>
<br>
Reinaldo<br>
<br>
On 11/3/08 12:49 PM, &quot;Livingood, Jason&quot;<br>
&lt;<a href="mailto:Jason_Livingood@cable.comcast.com">Jason_Livingood@cable.comcast.com</a>&gt;<br>
wrote:<br>
<br>
&gt; For some reason the URL was cut to two lines - trying again:<br>
&gt;<br>
&gt;<br>
<a href="http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc" target="_blank">http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc</a><br>
&gt; es-02.txt<br>
&gt;<br>
&gt;<br>
&gt;<br>
&gt;&gt; -----Original Message-----<br>
&gt;&gt; From: <a href="mailto:p2pi-bounces@ietf.org">p2pi-bounces@ietf.org</a> [mailto:<a href="mailto:p2pi-bounces@ietf.org">p2pi-bounces@ietf.org</a>] On<br>
&gt;&gt; Behalf Of Livingood, Jason<br>
&gt;&gt; Sent: Monday, November 03, 2008 3:35 PM<br>
&gt;&gt; To: <a href="mailto:p2pi@ietf.org">p2pi@ietf.org</a><br>
&gt;&gt; Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted<br>
&gt;&gt;<br>
&gt;&gt; A draft at<br>
&gt;&gt; <a href="http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p" target="_blank">http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p</a><br>
&gt;&gt; -experienc<br>
&gt;&gt; es-02.txt may be of interest to folks that have been<br>
&gt;&gt; interested in P2Pi and ALTO. &nbsp;We have requested time on the<br>
&gt;&gt; ALTO agenda at IETF 73 to present this.<br>
&gt;&gt;<br>
&gt;&gt; Regards<br>
&gt;&gt; Jason<br>
&gt;&gt; _______________________________________________<br>
&gt;&gt; p2pi mailing list<br>
&gt;&gt; <a href="mailto:p2pi@ietf.org">p2pi@ietf.org</a><br>
&gt;&gt; <a href="https://www.ietf.org/mailman/listinfo/p2pi" target="_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
&gt;&gt;<br>
&gt; _______________________________________________<br>
&gt; p2pi mailing list<br>
&gt; <a href="mailto:p2pi@ietf.org">p2pi@ietf.org</a><br>
&gt; <a href="https://www.ietf.org/mailman/listinfo/p2pi" target="_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
<br>
_______________________________________________<br>
p2pi mailing list<br>
<a href="mailto:p2pi@ietf.org">p2pi@ietf.org</a><br>
<a href="https://www.ietf.org/mailman/listinfo/p2pi" target="_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
_______________________________________________<br>
p2pi mailing list<br>
<a href="mailto:p2pi@ietf.org">p2pi@ietf.org</a><br>
<a href="https://www.ietf.org/mailman/listinfo/p2pi" target="_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
</div></div></blockquote></div><br><br clear="all"><br>-- <br>Robb Topolski (<a href="mailto:robb@funchords.com">robb@funchords.com</a>)<br>Hillsboro, Oregon USA<br><a href="http://www.funchords.com/">http://www.funchords.com/</a><br>


------=_Part_7224_18719526.1225924971380--

--===============0868357491==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi

--===============0868357491==--


From p2pi-bounces@ietf.org  Wed Nov  5 15:05:17 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id E15BF3A68C3;
	Wed,  5 Nov 2008 15:05:17 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 6D85F3A68BC
	for <p2pi@core3.amsl.com>; Wed,  5 Nov 2008 15:05:16 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -10.265
X-Spam-Level: 
X-Spam-Status: No, score=-10.265 tagged_above=-999 required=5
	tests=[BAYES_00=-2.599, HABEAS_ACCREDITED_COI=-8,
	IP_NOT_FRIENDLY=0.334]
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 NBoA9751wPcY for <p2pi@core3.amsl.com>;
	Wed,  5 Nov 2008 15:05:12 -0800 (PST)
Received: from dkny.pando.com (dkny.pando.com [67.99.55.163])
	by core3.amsl.com (Postfix) with ESMTP id B08AF3A68B0
	for <p2pi@ietf.org>; Wed,  5 Nov 2008 15:05:11 -0800 (PST)
Received: from localhost (localhost.localdomain [127.0.0.1])
	by dkny.pando.com (Postfix) with ESMTP id CC9C5E10D43;
	Wed,  5 Nov 2008 18:04:47 -0500 (EST)
X-Virus-Scanned: amavisd-new at 
Received: from dkny.pando.com ([127.0.0.1])
	by localhost (dkny.pando.com [127.0.0.1]) (amavisd-new, port 10024)
	with ESMTP id mgMOx2memEK7; Wed,  5 Nov 2008 18:04:33 -0500 (EST)
Received: from dkny.pando.com (dkny.pando.com [10.10.60.11])
	by dkny.pando.com (Postfix) with ESMTP id 8EE27E10BF8;
	Wed,  5 Nov 2008 18:04:33 -0500 (EST)
Date: Wed, 5 Nov 2008 18:04:33 -0500 (EST)
From: Laird Popkin <laird@pando.com>
To: Richard Woundy <Richard_Woundy@cable.comcast.com>
Message-ID: <319184902.76821225926273546.JavaMail.root@dkny.pando.com>
In-Reply-To: <1188551607.76771225925427015.JavaMail.root@dkny.pando.com>
MIME-Version: 1.0
X-Originating-IP: [10.10.20.77]
Cc: p2pi@ietf.org, Jason Livingood <Jason_Livingood@cable.comcast.com>,
	Richard Woundy <Richard_Woundy@cable.comcast.com>
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

Comments below.

- Laird Popkin, CTO, Pando Networks
  mobile: 646/465-0570

----- Original Message -----
From: "Richard Woundy" <Richard_Woundy@cable.comcast.com>
To: "Reinaldo Penno" <rpenno@juniper.net>, p2pi@ietf.org
Cc: "Richard Woundy" <Richard_Woundy@cable.comcast.com>, "Jason Livingood" <Jason_Livingood@cable.comcast.com>
Sent: Wednesday, November 5, 2008 5:29:45 PM (GMT-0500) America/New_York
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted

Reinaldo,

I can answer the easy questions. We will need some assistance from Pando
(and Yale) for some of the other ones.

>What was the file size in those experiments?

21 megabytes. From section 2: "Pando distributed a special 21 MB
licensed video file as in order to measure the effectiveness of P4P
iTrackers."

The performance benefit of P4P is that peers much more rapidly find good peers. Over time random peer discovery will also find good peers, and "catch up" in performance. This can take a very long time, however. For example, in a swarm of 100,000 peers, let's look at how long it would take to find the closest peer. If you perform a test transfer with one random peer a second (i.e. typical BitTorrent client behavior), it would take 100,000 seconds to probe 50% of the swarm, meaning that in 28 hours you would have a 50% chance of probing the closest peer. With P4P guidance, you would have a very high chance of probing that closest peer on your first announce. Admittedly this simplifies the network interaction somewhat, but I think that you see the impact of P4P guidance.

For very large downloads, random peer assignment would catch up to P4P in transfer rate, but the random peer download would always be slower by the "ramp up" time. Of course, the cost to ISP would be (on average) less, even when the performance is the same, which seems beneficial as well.

>How long would it take to download the file in the three different
scenarios? I know that more consumed bandwidth in access might lead one
to conclude that file was downloaded faster...

To clarify, most of the raw data (download speed and Internet
peering/transit traffic volumes) were collected by Pando Networks from
their P2P clients, not collected by Comcast across its links. So my
assumption is that the Pando client used the content size (21 MB), and
divided by the download time to get the speed.

LP: Pando's client can capture extended logging, which we enabled for this test. This captures the source and destination IP address of all p2p transfers, the number of bytes transferred, and the start and end timestamps. This gives a precise measurement of the data flow in the network, allowing us to compute not only data transfer volumes but also data flow rates at each point in time. We also capture the times of the start and completion of every download, as well as the average transfer rate observed by the client for the download. As you can imagine, this allowed us to perform extensive analysis of the data flow and the user experience in the network.

>Was the file already seeded in Comcast's network? More specifically,
how
was file propagation done?

Any seeding happened outside of Comcast's network, and outside of
Comcast's control. That's really a question for Pando.

LP: Pando served the data from an origin server external to Comcast's network. This server served about 10 copies of the file, after which all transfers (about 1m downloads) were performed purely p2p.

>Was PEX, DHT and others enabled in the clients?

Pando would know whether PEX was enabled. It would be safe to assume
that with respect to this trial, DHT was NOT enabled, since Pando
supplied the tracker. (The pTracker in the draft is a tracker operated
by Pando.)

LP: Pando starts with tracker-provided peers, then uses peer exchange to discover additional peers. Thus, the starting peers were provided with P4P guidance (90% P4P guidance, 10% random), then later peers discover the entire swarm via either additional announces or peer exchange. What we found is that because the initial P4P-guided peers were quite fast, the later peers did not reduce data localization much, though we believe that it is important for the p2p mesh to be well connected over time so that the swarm remains resilient (and to compensate for cases where P4P cannot provide good guidance).

>Was local peer discovery enabled in the clients?

Pando would know.

LP: Yes, Pando preferentially connects peers on a LAN before internet peers. We don't use multi-cast for this, as we've found other methods that work more generally.

>BTW, can broadcast/multicast peer discovery work in Cable networks?

Do you mean something like this:
http://bittorrent.org/beps/bep_0026.html?

If so, peer discovery probably would not work over the typical last mile
cable network. Maybe I'm wrong, but I see this protocol as intended for
peer discovery within one's home network / LAN / WiFi network, not over
a cable network.

>So, were clients allowed to become seeders to the outside of Comcast's
network?

Yes, they were.

As a related item, look closely at section 4.2. The amount of aggregate
uploaded data from Comcast clients (per swarm) was about 140,000 MB. The
amount of aggregate downloaded data from Comcast clients (per swarm) was
about 60,000 MB or so. So the typical Comcast client uploaded more than
twice the amount of data that it downloaded. 

>How much of the swarm was within Comcast and outside?

Most of the swarm was outside of Comcast. Unfortunately I don't have
access to the size of the global swarm, but I would guess that Comcast
clients represented no more than 15% of the swarm, and maybe as little
as 5%. Those guesses are based on the behavior of the random swarm, e.g.
Comcast clients uploaded to non-Comcast clients 94% of the time in the
random swarm.

-- Rich

-----Original Message-----
From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
Reinaldo Penno
Sent: Wednesday, November 05, 2008 11:23 AM
To: Livingood, Jason; p2pi@ietf.org
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted

Hello Jason/Rich,

This is such an interesting draft. I'm surprised there are no questions
about it. Maybe everybody else is part of P4P one way or another and I'm
not
in the 'in' crowd (;-) so I have questions.

* What was the file size in those experiments? Some post long ago said
the
file size in some P4P experiments was really small, as opposed to the
top
100 torrents where the file size is ~1Gb. I was curious what is the
optimization payback in terms of download time for large files as
opposed
small files. 

* How long would it take to download the file in the three different
scenarios? I know that more consumed bandwidth in access might lead one
to
conclude that file was downloaded faster but I'm not sure this is a
straightforward conclusion.

* Was the file already seeded in Comcast's network? More specifically,
how
was file propagation done? All clients started from scratch and had to
start
pulling the file from some other side of the world and then exchanging
pieces? This is mainly due to the discussion in 4.2.

* Was PEX, DHT and others enabled in the clients?

* Was local peer discovery enabled in the clients? BTW, can
broadcast/multicast peer discovery work in Cable networks?

* If more clients finish downloading faster and become seeders you would
think that for popular content Comcast's upstream bandwidth would
increase
due to the number of seeder in its network. So, were clients allowed to
become seeders to the outside of Comcast's network? How much of the
swarm
was within Comcast and outside?

Thanks,

Reinaldo

On 11/3/08 12:49 PM, "Livingood, Jason"
<Jason_Livingood@cable.comcast.com>
wrote:

> For some reason the URL was cut to two lines - trying again:
> 
>
http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
> es-02.txt
> 
> 
> 
>> -----Original Message-----
>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
>> Behalf Of Livingood, Jason
>> Sent: Monday, November 03, 2008 3:35 PM
>> To: p2pi@ietf.org
>> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>> 
>> A draft at
>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
>> -experienc
>> es-02.txt may be of interest to folks that have been
>> interested in P2Pi and ALTO.  We have requested time on the
>> ALTO agenda at IETF 73 to present this.
>> 
>> Regards
>> Jason
>> _______________________________________________
>> p2pi mailing list
>> p2pi@ietf.org
>> https://www.ietf.org/mailman/listinfo/p2pi
>> 
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi
_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi
_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Wed Nov  5 15:12:09 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 21D2D3A688C;
	Wed,  5 Nov 2008 15:12:09 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 4B8BB3A6832
	for <p2pi@core3.amsl.com>; Wed,  5 Nov 2008 15:12:07 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -10.264
X-Spam-Level: 
X-Spam-Status: No, score=-10.264 tagged_above=-999 required=5
	tests=[AWL=-0.001, BAYES_00=-2.599, HABEAS_ACCREDITED_COI=-8,
	HTML_MESSAGE=0.001, IP_NOT_FRIENDLY=0.334]
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 w6i+67x28h3G for <p2pi@core3.amsl.com>;
	Wed,  5 Nov 2008 15:12:05 -0800 (PST)
Received: from dkny.pando.com (dkny.pando.com [67.99.55.163])
	by core3.amsl.com (Postfix) with ESMTP id 1D9873A687B
	for <p2pi@ietf.org>; Wed,  5 Nov 2008 15:12:04 -0800 (PST)
Received: from localhost (localhost.localdomain [127.0.0.1])
	by dkny.pando.com (Postfix) with ESMTP id 2E150E10B90;
	Wed,  5 Nov 2008 18:11:40 -0500 (EST)
X-Virus-Scanned: amavisd-new at 
Received: from dkny.pando.com ([127.0.0.1])
	by localhost (dkny.pando.com [127.0.0.1]) (amavisd-new, port 10024)
	with ESMTP id dQyglmFvQ8uU; Wed,  5 Nov 2008 18:11:30 -0500 (EST)
Received: from dkny.pando.com (dkny.pando.com [10.10.60.11])
	by dkny.pando.com (Postfix) with ESMTP id E3A8AE10B6D;
	Wed,  5 Nov 2008 18:11:30 -0500 (EST)
Date: Wed, 5 Nov 2008 18:11:30 -0500 (EST)
From: Laird Popkin <laird@pando.com>
To: Robb Topolski <robb@funchords.com>
Message-ID: <1105108207.76991225926690886.JavaMail.root@dkny.pando.com>
In-Reply-To: <387057524.76851225926501103.JavaMail.root@dkny.pando.com>
MIME-Version: 1.0
X-Originating-IP: [10.10.20.77]
Cc: p2pi@ietf.org, Jason Livingood <Jason_Livingood@cable.comcast.com>,
	Richard Woundy <Richard_Woundy@cable.comcast.com>
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: multipart/mixed; boundary="===============1476751583=="
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

--===============1476751583==
Content-Type: multipart/alternative; 
	boundary="----=_Part_3556_1817511305.1225926690885"

------=_Part_3556_1817511305.1225926690885
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit

That's a good question, and Richard and I spoke about this yesterday. I'll be looking into the data to see what the cause is. 

- Laird Popkin, CTO, Pando Networks 
mobile: 646/465-0570 

----- Original Message ----- 
From: "Robb Topolski" <robb@funchords.com> 
To: "Richard Woundy" <Richard_Woundy@cable.comcast.com> 
Cc: "Jason Livingood" <Jason_Livingood@cable.comcast.com>, p2pi@ietf.org 
Sent: Wednesday, November 5, 2008 5:42:51 PM (GMT-0500) America/New_York 
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted 

I don't get the part where access network download consumption increased as a result of using P4P (section 4.2). Can someone explain how that could happen? 

Robb 


On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard < Richard_Woundy@cable.comcast.com > wrote: 


Reinaldo, 

I can answer the easy questions. We will need some assistance from Pando 
(and Yale) for some of the other ones. 


>What was the file size in those experiments? 

21 megabytes. From section 2: "Pando distributed a special 21 MB 
licensed video file as in order to measure the effectiveness of P4P 
iTrackers." 


>How long would it take to download the file in the three different 
scenarios? I know that more consumed bandwidth in access might lead one 
to conclude that file was downloaded faster... 

To clarify, most of the raw data (download speed and Internet 
peering/transit traffic volumes) were collected by Pando Networks from 
their P2P clients, not collected by Comcast across its links. So my 
assumption is that the Pando client used the content size (21 MB), and 
divided by the download time to get the speed. 


>Was the file already seeded in Comcast's network? More specifically, 
how 
was file propagation done? 

Any seeding happened outside of Comcast's network, and outside of 
Comcast's control. That's really a question for Pando. 


>Was PEX, DHT and others enabled in the clients? 

Pando would know whether PEX was enabled. It would be safe to assume 
that with respect to this trial, DHT was NOT enabled, since Pando 
supplied the tracker. (The pTracker in the draft is a tracker operated 
by Pando.) 


>Was local peer discovery enabled in the clients? 

Pando would know. 


>BTW, can broadcast/multicast peer discovery work in Cable networks? 

Do you mean something like this: 
http://bittorrent.org/beps/bep_0026.html ? 

If so, peer discovery probably would not work over the typical last mile 
cable network. Maybe I'm wrong, but I see this protocol as intended for 
peer discovery within one's home network / LAN / WiFi network, not over 
a cable network. 


>So, were clients allowed to become seeders to the outside of Comcast's 
network? 

Yes, they were. 

As a related item, look closely at section 4.2. The amount of aggregate 
uploaded data from Comcast clients (per swarm) was about 140,000 MB. The 
amount of aggregate downloaded data from Comcast clients (per swarm) was 
about 60,000 MB or so. So the typical Comcast client uploaded more than 
twice the amount of data that it downloaded. 


>How much of the swarm was within Comcast and outside? 

Most of the swarm was outside of Comcast. Unfortunately I don't have 
access to the size of the global swarm, but I would guess that Comcast 
clients represented no more than 15% of the swarm, and maybe as little 
as 5%. Those guesses are based on the behavior of the random swarm, e.g. 
Comcast clients uploaded to non-Comcast clients 94% of the time in the 
random swarm. 

-- Rich 


-----Original Message----- 
From: p2pi-bounces@ietf.org [mailto: p2pi-bounces@ietf.org ] On Behalf Of 



Reinaldo Penno 
Sent: Wednesday, November 05, 2008 11:23 AM 
To: Livingood, Jason; p2pi@ietf.org 
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted 

Hello Jason/Rich, 

This is such an interesting draft. I'm surprised there are no questions 
about it. Maybe everybody else is part of P4P one way or another and I'm 
not 
in the 'in' crowd (;-) so I have questions. 

* What was the file size in those experiments? Some post long ago said 
the 
file size in some P4P experiments was really small, as opposed to the 
top 
100 torrents where the file size is ~1Gb. I was curious what is the 
optimization payback in terms of download time for large files as 
opposed 
small files. 

* How long would it take to download the file in the three different 
scenarios? I know that more consumed bandwidth in access might lead one 
to 
conclude that file was downloaded faster but I'm not sure this is a 
straightforward conclusion. 

* Was the file already seeded in Comcast's network? More specifically, 
how 
was file propagation done? All clients started from scratch and had to 
start 
pulling the file from some other side of the world and then exchanging 
pieces? This is mainly due to the discussion in 4.2. 

* Was PEX, DHT and others enabled in the clients? 

* Was local peer discovery enabled in the clients? BTW, can 
broadcast/multicast peer discovery work in Cable networks? 

* If more clients finish downloading faster and become seeders you would 
think that for popular content Comcast's upstream bandwidth would 
increase 
due to the number of seeder in its network. So, were clients allowed to 
become seeders to the outside of Comcast's network? How much of the 
swarm 
was within Comcast and outside? 

Thanks, 

Reinaldo 

On 11/3/08 12:49 PM, "Livingood, Jason" 
< Jason_Livingood@cable.comcast.com > 
wrote: 

> For some reason the URL was cut to two lines - trying again: 
> 
> 
http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc 
> es-02.txt 
> 
> 
> 
>> -----Original Message----- 
>> From: p2pi-bounces@ietf.org [mailto: p2pi-bounces@ietf.org ] On 
>> Behalf Of Livingood, Jason 
>> Sent: Monday, November 03, 2008 3:35 PM 
>> To: p2pi@ietf.org 
>> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted 
>> 
>> A draft at 
>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p 
>> -experienc 
>> es-02.txt may be of interest to folks that have been 
>> interested in P2Pi and ALTO. We have requested time on the 
>> ALTO agenda at IETF 73 to present this. 
>> 
>> Regards 
>> Jason 
>> _______________________________________________ 
>> p2pi mailing list 
>> p2pi@ietf.org 
>> https://www.ietf.org/mailman/listinfo/p2pi 
>> 
> _______________________________________________ 
> p2pi mailing list 
> p2pi@ietf.org 
> https://www.ietf.org/mailman/listinfo/p2pi 

_______________________________________________ 
p2pi mailing list 
p2pi@ietf.org 
https://www.ietf.org/mailman/listinfo/p2pi 
_______________________________________________ 
p2pi mailing list 
p2pi@ietf.org 
https://www.ietf.org/mailman/listinfo/p2pi 



-- 
Robb Topolski ( robb@funchords.com ) 
Hillsboro, Oregon USA 
http://www.funchords.com/ 

_______________________________________________ p2pi mailing list p2pi@ietf.org https://www.ietf.org/mailman/listinfo/p2pi 
------=_Part_3556_1817511305.1225926690885
Content-Type: text/html; charset=utf-8
Content-Transfer-Encoding: quoted-printable

<html><head><style type=3D'text/css'>p { margin: 0; }</style><style type=3D=
'text/css'>body { font-family: 'Times New Roman'; font-size: 12pt; color: #=
000000}</style></head><body>That's a good question, and Richard and I spoke=
 about this yesterday. I'll be looking into the data to see what the cause =
is.<br><br>-&nbsp;Laird&nbsp;Popkin,&nbsp;CTO,&nbsp;Pando&nbsp;Networks<br>=
&nbsp;&nbsp;mobile:&nbsp;646/465-0570<br><br>----- Original Message -----<b=
r>From: "Robb Topolski" &lt;robb@funchords.com&gt;<br>To: "Richard Woundy" =
&lt;Richard_Woundy@cable.comcast.com&gt;<br>Cc: "Jason Livingood" &lt;Jason=
_Livingood@cable.comcast.com&gt;, p2pi@ietf.org<br>Sent: Wednesday, Novembe=
r 5, 2008 5:42:51 PM (GMT-0500) America/New_York<br>Subject: Re: [p2pi] dra=
ft-livingood-woundy-p4p-experiences-02 posted<br><br>I don't get the part w=
here access network download consumption increased as a result of using P4P=
 (section 4.2).&nbsp; Can someone explain how that could happen?&nbsp; <br>=
<br>Robb<br><br><div class=3D"gmail_quote">On Wed, Nov 5, 2008 at 2:29 PM, =
Woundy, Richard <span dir=3D"ltr">&lt;<a href=3D"mailto:Richard_Woundy@cabl=
e.comcast.com" target=3D"_blank">Richard_Woundy@cable.comcast.com</a>&gt;</=
span> wrote:<br>
<blockquote class=3D"gmail_quote" style=3D"border-left: 1px solid rgb(204, =
204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">Reinaldo,<br>
<br>
I can answer the easy questions. We will need some assistance from Pando<br=
>
(and Yale) for some of the other ones.<br>
<div class=3D"Ih2E3d"><br>
&gt;What was the file size in those experiments?<br>
<br>
</div>21 megabytes. From section 2: "Pando distributed a special 21 MB<br>
licensed video file as in order to measure the effectiveness of P4P<br>
iTrackers."<br>
<div class=3D"Ih2E3d"><br>
&gt;How long would it take to download the file in the three different<br>
scenarios? I know that more consumed bandwidth in access might lead one<br>
</div>to conclude that file was downloaded faster...<br>
<br>
To clarify, most of the raw data (download speed and Internet<br>
peering/transit traffic volumes) were collected by Pando Networks from<br>
their P2P clients, not collected by Comcast across its links. So my<br>
assumption is that the Pando client used the content size (21 MB), and<br>
divided by the download time to get the speed.<br>
<div class=3D"Ih2E3d"><br>
&gt;Was the file already seeded in Comcast's network? More specifically,<br=
>
how<br>
was file propagation done?<br>
<br>
</div>Any seeding happened outside of Comcast's network, and outside of<br>
Comcast's control. That's really a question for Pando.<br>
<div class=3D"Ih2E3d"><br>
&gt;Was PEX, DHT and others enabled in the clients?<br>
<br>
</div>Pando would know whether PEX was enabled. It would be safe to assume<=
br>
that with respect to this trial, DHT was NOT enabled, since Pando<br>
supplied the tracker. (The pTracker in the draft is a tracker operated<br>
by Pando.)<br>
<div class=3D"Ih2E3d"><br>
&gt;Was local peer discovery enabled in the clients?<br>
<br>
</div>Pando would know.<br>
<div class=3D"Ih2E3d"><br>
&gt;BTW, can broadcast/multicast peer discovery work in Cable networks?<br>
<br>
</div>Do you mean something like this:<br>
<a href=3D"http://bittorrent.org/beps/bep_0026.html" target=3D"_blank">http=
://bittorrent.org/beps/bep_0026.html</a>?<br>
<br>
If so, peer discovery probably would not work over the typical last mile<br=
>
cable network. Maybe I'm wrong, but I see this protocol as intended for<br>
peer discovery within one's home network / LAN / WiFi network, not over<br>
a cable network.<br>
<div class=3D"Ih2E3d"><br>
&gt;So, were clients allowed to become seeders to the outside of Comcast's<=
br>
network?<br>
<br>
</div>Yes, they were.<br>
<br>
As a related item, look closely at section 4.2. The amount of aggregate<br>
uploaded data from Comcast clients (per swarm) was about 140,000 MB. The<br=
>
amount of aggregate downloaded data from Comcast clients (per swarm) was<br=
>
about 60,000 MB or so. So the typical Comcast client uploaded more than<br>
twice the amount of data that it downloaded.<br>
<div class=3D"Ih2E3d"><br>
&gt;How much of the swarm was within Comcast and outside?<br>
<br>
</div>Most of the swarm was outside of Comcast. Unfortunately I don't have<=
br>
access to the size of the global swarm, but I would guess that Comcast<br>
clients represented no more than 15% of the swarm, and maybe as little<br>
as 5%. Those guesses are based on the behavior of the random swarm, e.g.<br=
>
Comcast clients uploaded to non-Comcast clients 94% of the time in the<br>
random swarm.<br>
<br>
-- Rich<br>
<div class=3D"Ih2E3d"><br>
-----Original Message-----<br>
From: <a href=3D"mailto:p2pi-bounces@ietf.org" target=3D"_blank">p2pi-bounc=
es@ietf.org</a> [mailto:<a href=3D"mailto:p2pi-bounces@ietf.org" target=3D"=
_blank">p2pi-bounces@ietf.org</a>] On Behalf Of<br>
</div><div><div></div><div class=3D"Wj3C7c">Reinaldo Penno<br>
Sent: Wednesday, November 05, 2008 11:23 AM<br>
To: Livingood, Jason; <a href=3D"mailto:p2pi@ietf.org" target=3D"_blank">p2=
pi@ietf.org</a><br>
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted<br>
<br>
Hello Jason/Rich,<br>
<br>
This is such an interesting draft. I'm surprised there are no questions<br>
about it. Maybe everybody else is part of P4P one way or another and I'm<br=
>
not<br>
in the 'in' crowd (;-) so I have questions.<br>
<br>
* What was the file size in those experiments? Some post long ago said<br>
the<br>
file size in some P4P experiments was really small, as opposed to the<br>
top<br>
100 torrents where the file size is ~1Gb. I was curious what is the<br>
optimization payback in terms of download time for large files as<br>
opposed<br>
small files.<br>
<br>
* How long would it take to download the file in the three different<br>
scenarios? I know that more consumed bandwidth in access might lead one<br>
to<br>
conclude that file was downloaded faster but I'm not sure this is a<br>
straightforward conclusion.<br>
<br>
* Was the file already seeded in Comcast's network? More specifically,<br>
how<br>
was file propagation done? All clients started from scratch and had to<br>
start<br>
pulling the file from some other side of the world and then exchanging<br>
pieces? This is mainly due to the discussion in 4.2.<br>
<br>
* Was PEX, DHT and others enabled in the clients?<br>
<br>
* Was local peer discovery enabled in the clients? BTW, can<br>
broadcast/multicast peer discovery work in Cable networks?<br>
<br>
* If more clients finish downloading faster and become seeders you would<br=
>
think that for popular content Comcast's upstream bandwidth would<br>
increase<br>
due to the number of seeder in its network. So, were clients allowed to<br>
become seeders to the outside of Comcast's network? How much of the<br>
swarm<br>
was within Comcast and outside?<br>
<br>
Thanks,<br>
<br>
Reinaldo<br>
<br>
On 11/3/08 12:49 PM, "Livingood, Jason"<br>
&lt;<a href=3D"mailto:Jason_Livingood@cable.comcast.com" target=3D"_blank">=
Jason_Livingood@cable.comcast.com</a>&gt;<br>
wrote:<br>
<br>
&gt; For some reason the URL was cut to two lines - trying again:<br>
&gt;<br>
&gt;<br>
<a href=3D"http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-e=
xperienc" target=3D"_blank">http://www.ietf.org/internet-drafts/draft-livin=
good-woundy-p4p-experienc</a><br>
&gt; es-02.txt<br>
&gt;<br>
&gt;<br>
&gt;<br>
&gt;&gt; -----Original Message-----<br>
&gt;&gt; From: <a href=3D"mailto:p2pi-bounces@ietf.org" target=3D"_blank">p=
2pi-bounces@ietf.org</a> [mailto:<a href=3D"mailto:p2pi-bounces@ietf.org" t=
arget=3D"_blank">p2pi-bounces@ietf.org</a>] On<br>
&gt;&gt; Behalf Of Livingood, Jason<br>
&gt;&gt; Sent: Monday, November 03, 2008 3:35 PM<br>
&gt;&gt; To: <a href=3D"mailto:p2pi@ietf.org" target=3D"_blank">p2pi@ietf.o=
rg</a><br>
&gt;&gt; Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted<b=
r>
&gt;&gt;<br>
&gt;&gt; A draft at<br>
&gt;&gt; <a href=3D"http://www.ietf.org/internet-drafts/draft-livingood-wou=
ndy-p4p" target=3D"_blank">http://www.ietf.org/internet-drafts/draft-living=
ood-woundy-p4p</a><br>
&gt;&gt; -experienc<br>
&gt;&gt; es-02.txt may be of interest to folks that have been<br>
&gt;&gt; interested in P2Pi and ALTO. &nbsp;We have requested time on the<b=
r>
&gt;&gt; ALTO agenda at IETF 73 to present this.<br>
&gt;&gt;<br>
&gt;&gt; Regards<br>
&gt;&gt; Jason<br>
&gt;&gt; _______________________________________________<br>
&gt;&gt; p2pi mailing list<br>
&gt;&gt; <a href=3D"mailto:p2pi@ietf.org" target=3D"_blank">p2pi@ietf.org</=
a><br>
&gt;&gt; <a href=3D"https://www.ietf.org/mailman/listinfo/p2pi" target=3D"_=
blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
&gt;&gt;<br>
&gt; _______________________________________________<br>
&gt; p2pi mailing list<br>
&gt; <a href=3D"mailto:p2pi@ietf.org" target=3D"_blank">p2pi@ietf.org</a><b=
r>
&gt; <a href=3D"https://www.ietf.org/mailman/listinfo/p2pi" target=3D"_blan=
k">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
<br>
_______________________________________________<br>
p2pi mailing list<br>
<a href=3D"mailto:p2pi@ietf.org" target=3D"_blank">p2pi@ietf.org</a><br>
<a href=3D"https://www.ietf.org/mailman/listinfo/p2pi" target=3D"_blank">ht=
tps://www.ietf.org/mailman/listinfo/p2pi</a><br>
_______________________________________________<br>
p2pi mailing list<br>
<a href=3D"mailto:p2pi@ietf.org" target=3D"_blank">p2pi@ietf.org</a><br>
<a href=3D"https://www.ietf.org/mailman/listinfo/p2pi" target=3D"_blank">ht=
tps://www.ietf.org/mailman/listinfo/p2pi</a><br>
</div></div></blockquote></div><br><br clear=3D"all"><br>-- <br>Robb Topols=
ki (<a href=3D"mailto:robb@funchords.com" target=3D"_blank">robb@funchords.=
com</a>)<br>Hillsboro, Oregon USA<br><a href=3D"http://www.funchords.com/" =
target=3D"_blank">http://www.funchords.com/</a><br>

<br>_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi
</body></html>
------=_Part_3556_1817511305.1225926690885--

--===============1476751583==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi

--===============1476751583==--


From p2pi-bounces@ietf.org  Wed Nov  5 15:26:59 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 0DDF53A68BC;
	Wed,  5 Nov 2008 15:26:59 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id AC0023A6879
	for <p2pi@core3.amsl.com>; Wed,  5 Nov 2008 15:26:57 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -0.463
X-Spam-Level: 
X-Spam-Status: No, score=-0.463 tagged_above=-999 required=5
	tests=[AWL=-0.001, BAYES_00=-2.599, HELO_EQ_MODEMCABLE=0.768,
	HOST_EQ_MODEMCABLE=1.368, HTML_MESSAGE=0.001]
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 3gfoTaML8gNi for <p2pi@core3.amsl.com>;
	Wed,  5 Nov 2008 15:26:55 -0800 (PST)
Received: from pacdcimo01.cable.comcast.com (PacdcIMO01.cable.comcast.com
	[24.40.8.145]) by core3.amsl.com (Postfix) with ESMTP id 86F853A689C
	for <p2pi@ietf.org>; Wed,  5 Nov 2008 15:26:55 -0800 (PST)
Received: from ([10.52.116.30])
	by pacdcimo01.cable.comcast.com with ESMTP  id 5503620.18695294;
	Wed, 05 Nov 2008 18:26:21 -0500
Received: from PACDCEXCMB06.cable.comcast.com ([24.40.15.22]) by
	PAOAKEXCSMTP01.cable.comcast.com with Microsoft
	SMTPSVC(6.0.3790.3959); Wed, 5 Nov 2008 18:26:21 -0500
X-MimeOLE: Produced By Microsoft Exchange V6.5
Content-class: urn:content-classes:message
MIME-Version: 1.0
Date: Wed, 5 Nov 2008 18:26:18 -0500
Message-ID: <74CCBBDF76102846AFA7B29F3A98D3F60289648E@PACDCEXCMB06.cable.comcast.com>
In-Reply-To: <1105108207.76991225926690886.JavaMail.root@dkny.pando.com>
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Thread-Topic: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
Thread-Index: Ack/m+rqP9PLqj6vSQiDyHf8nRrZzwAAMotg
References: <387057524.76851225926501103.JavaMail.root@dkny.pando.com>
	<1105108207.76991225926690886.JavaMail.root@dkny.pando.com>
From: "Woundy, Richard" <Richard_Woundy@cable.comcast.com>
To: "Laird Popkin" <laird@pando.com>,
	"Robb Topolski" <robb@funchords.com>
X-OriginalArrivalTime: 05 Nov 2008 23:26:21.0544 (UTC)
	FILETIME=[E96D4E80:01C93F9D]
Cc: p2pi@ietf.org, "Livingood, Jason" <Jason_Livingood@cable.comcast.com>
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: multipart/mixed; boundary="===============0450058540=="
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

This is a multi-part message in MIME format.

--===============0450058540==
Content-class: urn:content-classes:message
Content-Type: multipart/alternative;
	boundary="----_=_NextPart_001_01C93F9D.E7805558"

This is a multi-part message in MIME format.

------_=_NextPart_001_01C93F9D.E7805558
Content-Type: text/plain;
	charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

My current theory/guess is that some users may terminated the download
prematurely, eg due to user impatience. So faster downloads (e.g. thanks
to P4P) may result in fewer user terminations.

=20

Laird is checking the data to see if we can confirm that, or find
another explanation.

=20

-- Rich

=20

________________________________

From: Laird Popkin [mailto:laird@pando.com]=20
Sent: Wednesday, November 05, 2008 6:12 PM
To: Robb Topolski
Cc: Livingood, Jason; p2pi@ietf.org; Woundy, Richard
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted

=20

That's a good question, and Richard and I spoke about this yesterday.
I'll be looking into the data to see what the cause is.

- Laird Popkin, CTO, Pando Networks
  mobile: 646/465-0570

----- Original Message -----
From: "Robb Topolski" <robb@funchords.com>
To: "Richard Woundy" <Richard_Woundy@cable.comcast.com>
Cc: "Jason Livingood" <Jason_Livingood@cable.comcast.com>, p2pi@ietf.org
Sent: Wednesday, November 5, 2008 5:42:51 PM (GMT-0500) America/New_York
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted

I don't get the part where access network download consumption increased
as a result of using P4P (section 4.2).  Can someone explain how that
could happen? =20

Robb

On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard
<Richard_Woundy@cable.comcast.com> wrote:

Reinaldo,

I can answer the easy questions. We will need some assistance from Pando
(and Yale) for some of the other ones.


>What was the file size in those experiments?

21 megabytes. From section 2: "Pando distributed a special 21 MB
licensed video file as in order to measure the effectiveness of P4P
iTrackers."


>How long would it take to download the file in the three different
scenarios? I know that more consumed bandwidth in access might lead one

to conclude that file was downloaded faster...

To clarify, most of the raw data (download speed and Internet
peering/transit traffic volumes) were collected by Pando Networks from
their P2P clients, not collected by Comcast across its links. So my
assumption is that the Pando client used the content size (21 MB), and
divided by the download time to get the speed.


>Was the file already seeded in Comcast's network? More specifically,
how
was file propagation done?

Any seeding happened outside of Comcast's network, and outside of
Comcast's control. That's really a question for Pando.


>Was PEX, DHT and others enabled in the clients?

Pando would know whether PEX was enabled. It would be safe to assume
that with respect to this trial, DHT was NOT enabled, since Pando
supplied the tracker. (The pTracker in the draft is a tracker operated
by Pando.)


>Was local peer discovery enabled in the clients?

Pando would know.


>BTW, can broadcast/multicast peer discovery work in Cable networks?

Do you mean something like this:
http://bittorrent.org/beps/bep_0026.html?

If so, peer discovery probably would not work over the typical last mile
cable network. Maybe I'm wrong, but I see this protocol as intended for
peer discovery within one's home network / LAN / WiFi network, not over
a cable network.


>So, were clients allowed to become seeders to the outside of Comcast's
network?

Yes, they were.

As a related item, look closely at section 4.2. The amount of aggregate
uploaded data from Comcast clients (per swarm) was about 140,000 MB. The
amount of aggregate downloaded data from Comcast clients (per swarm) was
about 60,000 MB or so. So the typical Comcast client uploaded more than
twice the amount of data that it downloaded.


>How much of the swarm was within Comcast and outside?

Most of the swarm was outside of Comcast. Unfortunately I don't have
access to the size of the global swarm, but I would guess that Comcast
clients represented no more than 15% of the swarm, and maybe as little
as 5%. Those guesses are based on the behavior of the random swarm, e.g.
Comcast clients uploaded to non-Comcast clients 94% of the time in the
random swarm.

-- Rich


-----Original Message-----
From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of

Reinaldo Penno
Sent: Wednesday, November 05, 2008 11:23 AM
To: Livingood, Jason; p2pi@ietf.org
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted

Hello Jason/Rich,

This is such an interesting draft. I'm surprised there are no questions
about it. Maybe everybody else is part of P4P one way or another and I'm
not
in the 'in' crowd (;-) so I have questions.

* What was the file size in those experiments? Some post long ago said
the
file size in some P4P experiments was really small, as opposed to the
top
100 torrents where the file size is ~1Gb. I was curious what is the
optimization payback in terms of download time for large files as
opposed
small files.

* How long would it take to download the file in the three different
scenarios? I know that more consumed bandwidth in access might lead one
to
conclude that file was downloaded faster but I'm not sure this is a
straightforward conclusion.

* Was the file already seeded in Comcast's network? More specifically,
how
was file propagation done? All clients started from scratch and had to
start
pulling the file from some other side of the world and then exchanging
pieces? This is mainly due to the discussion in 4.2.

* Was PEX, DHT and others enabled in the clients?

* Was local peer discovery enabled in the clients? BTW, can
broadcast/multicast peer discovery work in Cable networks?

* If more clients finish downloading faster and become seeders you would
think that for popular content Comcast's upstream bandwidth would
increase
due to the number of seeder in its network. So, were clients allowed to
become seeders to the outside of Comcast's network? How much of the
swarm
was within Comcast and outside?

Thanks,

Reinaldo

On 11/3/08 12:49 PM, "Livingood, Jason"
<Jason_Livingood@cable.comcast.com>
wrote:

> For some reason the URL was cut to two lines - trying again:
>
>
http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
> es-02.txt
>
>
>
>> -----Original Message-----
>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
>> Behalf Of Livingood, Jason
>> Sent: Monday, November 03, 2008 3:35 PM
>> To: p2pi@ietf.org
>> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>
>> A draft at
>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
>> -experienc
>> es-02.txt may be of interest to folks that have been
>> interested in P2Pi and ALTO.  We have requested time on the
>> ALTO agenda at IETF 73 to present this.
>>
>> Regards
>> Jason
>> _______________________________________________
>> p2pi mailing list
>> p2pi@ietf.org
>> https://www.ietf.org/mailman/listinfo/p2pi
>>
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi
_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi




--=20
Robb Topolski (robb@funchords.com)
Hillsboro, Oregon USA
http://www.funchords.com/

_______________________________________________ p2pi mailing list
p2pi@ietf.org https://www.ietf.org/mailman/listinfo/p2pi=20


------_=_NextPart_001_01C93F9D.E7805558
Content-Type: text/html;
	charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

<html xmlns:v=3D"urn:schemas-microsoft-com:vml" =
xmlns:o=3D"urn:schemas-microsoft-com:office:office" =
xmlns:w=3D"urn:schemas-microsoft-com:office:word" =
xmlns:st1=3D"urn:schemas-microsoft-com:office:smarttags" =
xmlns=3D"http://www.w3.org/TR/REC-html40">

<head>
<meta http-equiv=3DContent-Type content=3D"text/html; =
charset=3Dus-ascii">
<meta name=3DGenerator content=3D"Microsoft Word 11 (filtered medium)">
<!--[if !mso]>
<style>
v\:* {behavior:url(#default#VML);}
o\:* {behavior:url(#default#VML);}
w\:* {behavior:url(#default#VML);}
.shape {behavior:url(#default#VML);}
</style>
<![endif]--><o:SmartTagType
 namespaceuri=3D"urn:schemas-microsoft-com:office:smarttags" =
name=3D"country-region"/>
<o:SmartTagType =
namespaceuri=3D"urn:schemas-microsoft-com:office:smarttags"
 name=3D"State"/>
<o:SmartTagType =
namespaceuri=3D"urn:schemas-microsoft-com:office:smarttags"
 name=3D"City"/>
<o:SmartTagType =
namespaceuri=3D"urn:schemas-microsoft-com:office:smarttags"
 name=3D"place"/>
<o:SmartTagType =
namespaceuri=3D"urn:schemas-microsoft-com:office:smarttags"
 name=3D"PersonName"/>
<!--[if !mso]>
<style>
st1\:*{behavior:url(#default#ieooui) }
</style>
<![endif]-->
<style>
<!--
 /* Font Definitions */
 @font-face
	{font-family:Tahoma;
	panose-1:2 11 6 4 3 5 4 4 2 4;}
 /* Style Definitions */
 p.MsoNormal, li.MsoNormal, div.MsoNormal
	{margin:0in;
	margin-bottom:.0001pt;
	font-size:12.0pt;
	font-family:"Times New Roman";}
a:link, span.MsoHyperlink
	{color:blue;
	text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
	{color:blue;
	text-decoration:underline;}
p
	{margin:0in;
	margin-bottom:.0001pt;
	font-size:12.0pt;
	font-family:"Times New Roman";}
span.EmailStyle18
	{mso-style-type:personal-reply;
	font-family:Arial;
	color:navy;}
@page Section1
	{size:8.5in 11.0in;
	margin:1.0in 1.25in 1.0in 1.25in;}
div.Section1
	{page:Section1;}
-->
</style>

</head>

<body lang=3DEN-US link=3Dblue vlink=3Dblue>

<div class=3DSection1>

<p class=3DMsoNormal><font size=3D2 color=3Dnavy face=3DArial><span =
style=3D'font-size:
10.0pt;font-family:Arial;color:navy'>My current theory/guess is that =
some users
may terminated the download prematurely, eg due to user impatience. So =
faster downloads
(e.g. thanks to P4P) may result in fewer user =
terminations.<o:p></o:p></span></font></p>

<p class=3DMsoNormal><font size=3D2 color=3Dnavy face=3DArial><span =
style=3D'font-size:
10.0pt;font-family:Arial;color:navy'><o:p>&nbsp;</o:p></span></font></p>

<p class=3DMsoNormal><font size=3D2 color=3Dnavy face=3DArial><span =
style=3D'font-size:
10.0pt;font-family:Arial;color:navy'>Laird is checking the data to see =
if we
can confirm that, or find another =
explanation.<o:p></o:p></span></font></p>

<p class=3DMsoNormal><font size=3D2 color=3Dnavy face=3DArial><span =
style=3D'font-size:
10.0pt;font-family:Arial;color:navy'><o:p>&nbsp;</o:p></span></font></p>

<p class=3DMsoNormal><font size=3D2 color=3Dnavy face=3DArial><span =
style=3D'font-size:
10.0pt;font-family:Arial;color:navy'>-- =
Rich<o:p></o:p></span></font></p>

<p class=3DMsoNormal><font size=3D2 color=3Dnavy face=3DArial><span =
style=3D'font-size:
10.0pt;font-family:Arial;color:navy'><o:p>&nbsp;</o:p></span></font></p>

<div>

<div class=3DMsoNormal align=3Dcenter style=3D'text-align:center'><font =
size=3D3
face=3D"Times New Roman"><span style=3D'font-size:12.0pt'>

<hr size=3D2 width=3D"100%" align=3Dcenter tabindex=3D-1>

</span></font></div>

<p class=3DMsoNormal><b><font size=3D2 face=3DTahoma><span =
style=3D'font-size:10.0pt;
font-family:Tahoma;font-weight:bold'>From:</span></font></b><font =
size=3D2
face=3DTahoma><span style=3D'font-size:10.0pt;font-family:Tahoma'> Laird =
Popkin
[mailto:laird@pando.com] <br>
<b><span style=3D'font-weight:bold'>Sent:</span></b> Wednesday, November =
05, 2008
6:12 PM<br>
<b><span style=3D'font-weight:bold'>To:</span></b> Robb Topolski<br>
<b><span style=3D'font-weight:bold'>Cc:</span></b> <st1:PersonName =
w:st=3D"on">Livingood,
 Jason</st1:PersonName>; p2pi@ietf.org; Woundy, Richard<br>
<b><span style=3D'font-weight:bold'>Subject:</span></b> Re: [p2pi]
draft-livingood-woundy-p4p-experiences-02 =
posted</span></font><o:p></o:p></p>

</div>

<p class=3DMsoNormal><font size=3D3 face=3D"Times New Roman"><span =
style=3D'font-size:
12.0pt'><o:p>&nbsp;</o:p></span></font></p>

<p class=3DMsoNormal style=3D'margin-bottom:12.0pt'><font size=3D3 =
color=3Dblack
face=3D"Times New Roman"><span =
style=3D'font-size:12.0pt;color:black'>That's a good
question, and Richard and I spoke about this yesterday. I'll be looking =
into
the data to see what the cause is.<br>
<br>
-&nbsp;Laird&nbsp;Popkin,&nbsp;CTO,&nbsp;Pando&nbsp;Networks<br>
&nbsp;&nbsp;mobile:&nbsp;646/465-0570<br>
<br>
----- Original Message -----<br>
From: &quot;Robb Topolski&quot; &lt;robb@funchords.com&gt;<br>
To: &quot;Richard Woundy&quot; =
&lt;Richard_Woundy@cable.comcast.com&gt;<br>
Cc: &quot;Jason Livingood&quot; =
&lt;Jason_Livingood@cable.comcast.com&gt;,
p2pi@ietf.org<br>
Sent: Wednesday, November 5, 2008 5:42:51 PM (GMT-0500) =
America/New_York<br>
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted<br>
<br>
I don't get the part where access network download consumption increased =
as a
result of using P4P (section 4.2).&nbsp; Can someone explain how that =
could
happen?&nbsp; <br>
<br>
Robb<o:p></o:p></span></font></p>

<div>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'>On Wed, Nov 5, 2008 at 2:29 PM, =
Woundy,
Richard &lt;<a href=3D"mailto:Richard_Woundy@cable.comcast.com" =
target=3D"_blank">Richard_Woundy@cable.comcast.com</a>&gt;
wrote:<o:p></o:p></span></font></p>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'>Reinaldo,<br>
<br>
I can answer the easy questions. We will need some assistance from =
Pando<br>
(and Yale) for some of the other ones.<o:p></o:p></span></font></p>

<div>

<p class=3DMsoNormal style=3D'margin-bottom:12.0pt'><font size=3D3 =
color=3Dblack
face=3D"Times New Roman"><span =
style=3D'font-size:12.0pt;color:black'><br>
&gt;What was the file size in those =
experiments?<o:p></o:p></span></font></p>

</div>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'>21 megabytes. From section 2: =
&quot;Pando
distributed a special 21 MB<br>
licensed video file as in order to measure the effectiveness of P4P<br>
iTrackers.&quot;<o:p></o:p></span></font></p>

<div>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'><br>
&gt;How long would it take to download the file in the three =
different<br>
scenarios? I know that more consumed bandwidth in access might lead =
one<o:p></o:p></span></font></p>

</div>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'>to conclude that file was =
downloaded
faster...<br>
<br>
To clarify, most of the raw data (download speed and Internet<br>
peering/transit traffic volumes) were collected by Pando Networks =
from<br>
their P2P clients, not collected by Comcast across its links. So my<br>
assumption is that the Pando client used the content size (21 MB), =
and<br>
divided by the download time to get the =
speed.<o:p></o:p></span></font></p>

<div>

<p class=3DMsoNormal style=3D'margin-bottom:12.0pt'><font size=3D3 =
color=3Dblack
face=3D"Times New Roman"><span =
style=3D'font-size:12.0pt;color:black'><br>
&gt;Was the file already seeded in Comcast's network? More =
specifically,<br>
how<br>
was file propagation done?<o:p></o:p></span></font></p>

</div>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'>Any seeding happened outside of =
Comcast's
network, and outside of<br>
Comcast's control. That's really a question for =
Pando.<o:p></o:p></span></font></p>

<div>

<p class=3DMsoNormal style=3D'margin-bottom:12.0pt'><font size=3D3 =
color=3Dblack
face=3D"Times New Roman"><span =
style=3D'font-size:12.0pt;color:black'><br>
&gt;Was PEX, DHT and others enabled in the =
clients?<o:p></o:p></span></font></p>

</div>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'>Pando would know whether PEX was =
enabled.
It would be safe to assume<br>
that with respect to this trial, DHT was NOT enabled, since Pando<br>
supplied the tracker. (The pTracker in the draft is a tracker =
operated<br>
by Pando.)<o:p></o:p></span></font></p>

<div>

<p class=3DMsoNormal style=3D'margin-bottom:12.0pt'><font size=3D3 =
color=3Dblack
face=3D"Times New Roman"><span =
style=3D'font-size:12.0pt;color:black'><br>
&gt;Was local peer discovery enabled in the =
clients?<o:p></o:p></span></font></p>

</div>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'>Pando would =
know.<o:p></o:p></span></font></p>

<div>

<p class=3DMsoNormal style=3D'margin-bottom:12.0pt'><font size=3D3 =
color=3Dblack
face=3D"Times New Roman"><span =
style=3D'font-size:12.0pt;color:black'><br>
&gt;BTW, can broadcast/multicast peer discovery work in Cable =
networks?<o:p></o:p></span></font></p>

</div>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'>Do you mean something like =
this:<br>
<a href=3D"http://bittorrent.org/beps/bep_0026.html" =
target=3D"_blank">http://bittorrent.org/beps/bep_0026.html</a>?<br>
<br>
If so, peer discovery probably would not work over the typical last =
mile<br>
cable network. Maybe I'm wrong, but I see this protocol as intended =
for<br>
peer discovery within one's home network / LAN / WiFi network, not =
over<br>
a cable network.<o:p></o:p></span></font></p>

<div>

<p class=3DMsoNormal style=3D'margin-bottom:12.0pt'><font size=3D3 =
color=3Dblack
face=3D"Times New Roman"><span =
style=3D'font-size:12.0pt;color:black'><br>
&gt;So, were clients allowed to become seeders to the outside of =
Comcast's<br>
network?<o:p></o:p></span></font></p>

</div>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'>Yes, they were.<br>
<br>
As a related item, look closely at section 4.2. The amount of =
aggregate<br>
uploaded data from Comcast clients (per swarm) was about 140,000 MB. =
The<br>
amount of aggregate downloaded data from Comcast clients (per swarm) =
was<br>
about 60,000 MB or so. So the typical Comcast client uploaded more =
than<br>
twice the amount of data that it =
downloaded.<o:p></o:p></span></font></p>

<div>

<p class=3DMsoNormal style=3D'margin-bottom:12.0pt'><font size=3D3 =
color=3Dblack
face=3D"Times New Roman"><span =
style=3D'font-size:12.0pt;color:black'><br>
&gt;How much of the swarm was within Comcast and =
outside?<o:p></o:p></span></font></p>

</div>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'>Most of the swarm was outside of =
Comcast.
Unfortunately I don't have<br>
access to the size of the global swarm, but I would guess that =
Comcast<br>
clients represented no more than 15% of the swarm, and maybe as =
little<br>
as 5%. Those guesses are based on the behavior of the random swarm, =
e.g.<br>
Comcast clients uploaded to non-Comcast clients 94% of the time in =
the<br>
random swarm.<br>
<br>
-- Rich<o:p></o:p></span></font></p>

<div>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'><br>
-----Original Message-----<br>
From: <a href=3D"mailto:p2pi-bounces@ietf.org" =
target=3D"_blank">p2pi-bounces@ietf.org</a>
[mailto:<a href=3D"mailto:p2pi-bounces@ietf.org" =
target=3D"_blank">p2pi-bounces@ietf.org</a>]
On Behalf Of<o:p></o:p></span></font></p>

</div>

<div>

<div>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'>Reinaldo Penno<br>
Sent: Wednesday, November 05, 2008 11:23 AM<br>
To: <st1:PersonName w:st=3D"on">Livingood, Jason</st1:PersonName>; <a
href=3D"mailto:p2pi@ietf.org" target=3D"_blank">p2pi@ietf.org</a><br>
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted<br>
<br>
Hello Jason/Rich,<br>
<br>
This is such an interesting draft. I'm surprised there are no =
questions<br>
about it. Maybe everybody else is part of P4P one way or another and =
I'm<br>
not<br>
in the 'in' crowd (;-) so I have questions.<br>
<br>
* What was the file size in those experiments? Some post long ago =
said<br>
the<br>
file size in some P4P experiments was really small, as opposed to =
the<br>
top<br>
100 torrents where the file size is ~1Gb. I was curious what is the<br>
optimization payback in terms of download time for large files as<br>
opposed<br>
small files.<br>
<br>
* How long would it take to download the file in the three different<br>
scenarios? I know that more consumed bandwidth in access might lead =
one<br>
to<br>
conclude that file was downloaded faster but I'm not sure this is a<br>
straightforward conclusion.<br>
<br>
* Was the file already seeded in Comcast's network? More =
specifically,<br>
how<br>
was file propagation done? All clients started from scratch and had =
to<br>
start<br>
pulling the file from some other side of the world and then =
exchanging<br>
pieces? This is mainly due to the discussion in 4.2.<br>
<br>
* Was PEX, DHT and others enabled in the clients?<br>
<br>
* Was local peer discovery enabled in the clients? BTW, can<br>
broadcast/multicast peer discovery work in Cable networks?<br>
<br>
* If more clients finish downloading faster and become seeders you =
would<br>
think that for popular content Comcast's upstream bandwidth would<br>
increase<br>
due to the number of seeder in its network. So, were clients allowed =
to<br>
become seeders to the outside of Comcast's network? How much of the<br>
swarm<br>
was within Comcast and outside?<br>
<br>
Thanks,<br>
<br>
Reinaldo<br>
<br>
On 11/3/08 12:49 PM, &quot;<st1:PersonName w:st=3D"on">Livingood, =
Jason</st1:PersonName>&quot;<br>
&lt;<a href=3D"mailto:Jason_Livingood@cable.comcast.com" =
target=3D"_blank">Jason_Livingood@cable.comcast.com</a>&gt;<br>
wrote:<br>
<br>
&gt; For some reason the URL was cut to two lines - trying again:<br>
&gt;<br>
&gt;<br>
<a
href=3D"http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-ex=
perienc"
target=3D"_blank">http://www.ietf.org/internet-drafts/draft-livingood-wou=
ndy-p4p-experienc</a><br>
&gt; es-02.txt<br>
&gt;<br>
&gt;<br>
&gt;<br>
&gt;&gt; -----Original Message-----<br>
&gt;&gt; From: <a href=3D"mailto:p2pi-bounces@ietf.org" =
target=3D"_blank">p2pi-bounces@ietf.org</a>
[mailto:<a href=3D"mailto:p2pi-bounces@ietf.org" =
target=3D"_blank">p2pi-bounces@ietf.org</a>]
On<br>
&gt;&gt; Behalf Of <st1:PersonName w:st=3D"on">Livingood, =
Jason</st1:PersonName><br>
&gt;&gt; Sent: Monday, November 03, 2008 3:35 PM<br>
&gt;&gt; To: <a href=3D"mailto:p2pi@ietf.org" =
target=3D"_blank">p2pi@ietf.org</a><br>
&gt;&gt; Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 =
posted<br>
&gt;&gt;<br>
&gt;&gt; A draft at<br>
&gt;&gt; <a
href=3D"http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p"
target=3D"_blank">http://www.ietf.org/internet-drafts/draft-livingood-wou=
ndy-p4p</a><br>
&gt;&gt; -experienc<br>
&gt;&gt; es-02.txt may be of interest to folks that have been<br>
&gt;&gt; interested in P2Pi and ALTO. &nbsp;We have requested time on =
the<br>
&gt;&gt; ALTO agenda at IETF 73 to present this.<br>
&gt;&gt;<br>
&gt;&gt; Regards<br>
&gt;&gt; Jason<br>
&gt;&gt; _______________________________________________<br>
&gt;&gt; p2pi mailing list<br>
&gt;&gt; <a href=3D"mailto:p2pi@ietf.org" =
target=3D"_blank">p2pi@ietf.org</a><br>
&gt;&gt; <a href=3D"https://www.ietf.org/mailman/listinfo/p2pi" =
target=3D"_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
&gt;&gt;<br>
&gt; _______________________________________________<br>
&gt; p2pi mailing list<br>
&gt; <a href=3D"mailto:p2pi@ietf.org" =
target=3D"_blank">p2pi@ietf.org</a><br>
&gt; <a href=3D"https://www.ietf.org/mailman/listinfo/p2pi" =
target=3D"_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
<br>
_______________________________________________<br>
p2pi mailing list<br>
<a href=3D"mailto:p2pi@ietf.org" target=3D"_blank">p2pi@ietf.org</a><br>
<a href=3D"https://www.ietf.org/mailman/listinfo/p2pi" =
target=3D"_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
_______________________________________________<br>
p2pi mailing list<br>
<a href=3D"mailto:p2pi@ietf.org" target=3D"_blank">p2pi@ietf.org</a><br>
<a href=3D"https://www.ietf.org/mailman/listinfo/p2pi" =
target=3D"_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><o:p></o:=
p></span></font></p>

</div>

</div>

</div>

<p class=3DMsoNormal><font size=3D3 color=3Dblack face=3D"Times New =
Roman"><span
style=3D'font-size:12.0pt;color:black'><br>
<br clear=3Dall>
<br>
-- <br>
Robb Topolski (<a href=3D"mailto:robb@funchords.com" =
target=3D"_blank">robb@funchords.com</a>)<br>
<st1:place w:st=3D"on"><st1:City w:st=3D"on">Hillsboro</st1:City>, =
<st1:State
 w:st=3D"on">Oregon</st1:State> <st1:country-region =
w:st=3D"on">USA</st1:country-region></st1:place><br>
<a href=3D"http://www.funchords.com/" =
target=3D"_blank">http://www.funchords.com/</a><br>
<br>
_______________________________________________ p2pi mailing list =
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi <o:p></o:p></span></font></p>

</div>

</body>

</html>

------_=_NextPart_001_01C93F9D.E7805558--

--===============0450058540==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi

--===============0450058540==--


From p2pi-bounces@ietf.org  Wed Nov  5 18:40:22 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 2725E3A6878;
	Wed,  5 Nov 2008 18:40:22 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 593303A6838
	for <p2pi@core3.amsl.com>; Wed,  5 Nov 2008 18:40:20 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -6.599
X-Spam-Level: 
X-Spam-Status: No, score=-6.599 tagged_above=-999 required=5
	tests=[BAYES_00=-2.599, RCVD_IN_DNSWL_MED=-4]
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 KVwYbQjrNN6b for <p2pi@core3.amsl.com>;
	Wed,  5 Nov 2008 18:40:18 -0800 (PST)
Received: from netra.cs.yale.edu (netra.cs.yale.edu [128.36.229.21])
	by core3.amsl.com (Postfix) with ESMTP id 8EE353A6784
	for <p2pi@ietf.org>; Wed,  5 Nov 2008 18:40:17 -0800 (PST)
Received: from cyndra.cs.yale.edu (cyndra.cs.yale.edu [128.36.229.87])
	by netra.cs.yale.edu (Postfix) with ESMTP id 33D2E4094B6;
	Wed,  5 Nov 2008 21:40:15 -0500 (EST)
Date: Wed, 5 Nov 2008 21:40:15 -0500 (EST)
From: "Y. R. Yang" <yry@cs.yale.edu>
To: "Woundy, Richard" <Richard_Woundy@cable.comcast.com>
In-Reply-To: <74CCBBDF76102846AFA7B29F3A98D3F60289648E@PACDCEXCMB06.cable.comcast.com>
Message-ID: <Pine.LNX.4.64.0811052100570.13140@cyndra.cs.yale.edu>
References: <387057524.76851225926501103.JavaMail.root@dkny.pando.com>
	<1105108207.76991225926690886.JavaMail.root@dkny.pando.com>
	<74CCBBDF76102846AFA7B29F3A98D3F60289648E@PACDCEXCMB06.cable.comcast.com>
MIME-Version: 1.0
Cc: p2pi@ietf.org, "Livingood, Jason" <Jason_Livingood@cable.comcast.com>
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org


Hi Rich and others,

The access download of each swarm should be equal to the sum of those 
downloaded by the clients in each swarm. So if the number of downloads in 
each swarm is the same and the amount downloaded is the same, then each 
swarm should have the same access download.

First look at the amount downloaded. There are can be some differences due 
to duplicated chunks and the way we detected data chunks (there are also 
control data in the logs), but the difference appears to be small.

Now let's look at the number of downloads. During the test, each client is 
uniformly assigned to a swarm. Given the large number of clients, each 
swarm should have about the same number of clients. But there can be two 
factors for us to see different numbers of *reported* downloads: (1) some 
clients are old and may not report or the reporting of logs was not 
successful; and (2) different # of clients finished downloading (if a 
client does not finish downloading, it does not report. Laird, please 
correct me if I am wrong). I belive the first factor should be small due 
to uniform random assignment of peers to swarms.

I just looked at the data available. We did detect a smaller number of 
finished download with Random than with the P4P swarms. For example, from 
July 3 to July 10, detected # of finished download of Generic is about 5% 
more than than Random, and Coarse is 7% more than Random. From July 10 to 
July 17, Generic is 10.5% more than Random, and Coarse is 4.7% more. 
Looking at the traffic volume at Section 4.2, I see that Generic is about 
7% higher, and Coarse is about 8.5% higher. Note that # of finished 
download and volume are different due to duplicated chunks and missing 
logs.

So I would like to support the theory/guess of Rich that some users 
terminated the download prematurally and faster downloads may result in 
fewer such terminations. But it may also include factors in (1) 
differences in initial assignment due to random numbers; and (2) # of 
finished but non-reporting clients.

If you have any other suggestions, we will be more than happy to look into 
the available data more.

Richard

On Wed, 5 Nov 2008, 6:26pm -0500, Woundy, Richard wrote:

> My current theory/guess is that some users may terminated the download
> prematurely, eg due to user impatience. So faster downloads (e.g. thanks
> to P4P) may result in fewer user terminations.
> 
>  
> 
> Laird is checking the data to see if we can confirm that, or find
> another explanation.
> 
>  
> 
> -- Rich
> 
>  
> 
> ________________________________
> 
> From: Laird Popkin [mailto:laird@pando.com] 
> Sent: Wednesday, November 05, 2008 6:12 PM
> To: Robb Topolski
> Cc: Livingood, Jason; p2pi@ietf.org; Woundy, Richard
> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> 
>  
> 
> That's a good question, and Richard and I spoke about this yesterday.
> I'll be looking into the data to see what the cause is.
> 
> - Laird Popkin, CTO, Pando Networks
>   mobile: 646/465-0570
> 
> ----- Original Message -----
> From: "Robb Topolski" <robb@funchords.com>
> To: "Richard Woundy" <Richard_Woundy@cable.comcast.com>
> Cc: "Jason Livingood" <Jason_Livingood@cable.comcast.com>, p2pi@ietf.org
> Sent: Wednesday, November 5, 2008 5:42:51 PM (GMT-0500) America/New_York
> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> 
> I don't get the part where access network download consumption increased
> as a result of using P4P (section 4.2).  Can someone explain how that
> could happen?  
> 
> Robb
> 
> On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard
> <Richard_Woundy@cable.comcast.com> wrote:
> 
> Reinaldo,
> 
> I can answer the easy questions. We will need some assistance from Pando
> (and Yale) for some of the other ones.
> 
> 
> >What was the file size in those experiments?
> 
> 21 megabytes. From section 2: "Pando distributed a special 21 MB
> licensed video file as in order to measure the effectiveness of P4P
> iTrackers."
> 
> 
> >How long would it take to download the file in the three different
> scenarios? I know that more consumed bandwidth in access might lead one
> 
> to conclude that file was downloaded faster...
> 
> To clarify, most of the raw data (download speed and Internet
> peering/transit traffic volumes) were collected by Pando Networks from
> their P2P clients, not collected by Comcast across its links. So my
> assumption is that the Pando client used the content size (21 MB), and
> divided by the download time to get the speed.
> 
> 
> >Was the file already seeded in Comcast's network? More specifically,
> how
> was file propagation done?
> 
> Any seeding happened outside of Comcast's network, and outside of
> Comcast's control. That's really a question for Pando.
> 
> 
> >Was PEX, DHT and others enabled in the clients?
> 
> Pando would know whether PEX was enabled. It would be safe to assume
> that with respect to this trial, DHT was NOT enabled, since Pando
> supplied the tracker. (The pTracker in the draft is a tracker operated
> by Pando.)
> 
> 
> >Was local peer discovery enabled in the clients?
> 
> Pando would know.
> 
> 
> >BTW, can broadcast/multicast peer discovery work in Cable networks?
> 
> Do you mean something like this:
> http://bittorrent.org/beps/bep_0026.html?
> 
> If so, peer discovery probably would not work over the typical last mile
> cable network. Maybe I'm wrong, but I see this protocol as intended for
> peer discovery within one's home network / LAN / WiFi network, not over
> a cable network.
> 
> 
> >So, were clients allowed to become seeders to the outside of Comcast's
> network?
> 
> Yes, they were.
> 
> As a related item, look closely at section 4.2. The amount of aggregate
> uploaded data from Comcast clients (per swarm) was about 140,000 MB. The
> amount of aggregate downloaded data from Comcast clients (per swarm) was
> about 60,000 MB or so. So the typical Comcast client uploaded more than
> twice the amount of data that it downloaded.
> 
> 
> >How much of the swarm was within Comcast and outside?
> 
> Most of the swarm was outside of Comcast. Unfortunately I don't have
> access to the size of the global swarm, but I would guess that Comcast
> clients represented no more than 15% of the swarm, and maybe as little
> as 5%. Those guesses are based on the behavior of the random swarm, e.g.
> Comcast clients uploaded to non-Comcast clients 94% of the time in the
> random swarm.
> 
> -- Rich
> 
> 
> -----Original Message-----
> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
> 
> Reinaldo Penno
> Sent: Wednesday, November 05, 2008 11:23 AM
> To: Livingood, Jason; p2pi@ietf.org
> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> 
> Hello Jason/Rich,
> 
> This is such an interesting draft. I'm surprised there are no questions
> about it. Maybe everybody else is part of P4P one way or another and I'm
> not
> in the 'in' crowd (;-) so I have questions.
> 
> * What was the file size in those experiments? Some post long ago said
> the
> file size in some P4P experiments was really small, as opposed to the
> top
> 100 torrents where the file size is ~1Gb. I was curious what is the
> optimization payback in terms of download time for large files as
> opposed
> small files.
> 
> * How long would it take to download the file in the three different
> scenarios? I know that more consumed bandwidth in access might lead one
> to
> conclude that file was downloaded faster but I'm not sure this is a
> straightforward conclusion.
> 
> * Was the file already seeded in Comcast's network? More specifically,
> how
> was file propagation done? All clients started from scratch and had to
> start
> pulling the file from some other side of the world and then exchanging
> pieces? This is mainly due to the discussion in 4.2.
> 
> * Was PEX, DHT and others enabled in the clients?
> 
> * Was local peer discovery enabled in the clients? BTW, can
> broadcast/multicast peer discovery work in Cable networks?
> 
> * If more clients finish downloading faster and become seeders you would
> think that for popular content Comcast's upstream bandwidth would
> increase
> due to the number of seeder in its network. So, were clients allowed to
> become seeders to the outside of Comcast's network? How much of the
> swarm
> was within Comcast and outside?
> 
> Thanks,
> 
> Reinaldo
> 
> On 11/3/08 12:49 PM, "Livingood, Jason"
> <Jason_Livingood@cable.comcast.com>
> wrote:
> 
> > For some reason the URL was cut to two lines - trying again:
> >
> >
> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
> > es-02.txt
> >
> >
> >
> >> -----Original Message-----
> >> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
> >> Behalf Of Livingood, Jason
> >> Sent: Monday, November 03, 2008 3:35 PM
> >> To: p2pi@ietf.org
> >> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> >>
> >> A draft at
> >> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
> >> -experienc
> >> es-02.txt may be of interest to folks that have been
> >> interested in P2Pi and ALTO.  We have requested time on the
> >> ALTO agenda at IETF 73 to present this.
> >>
> >> Regards
> >> Jason
> >> _______________________________________________
> >> p2pi mailing list
> >> p2pi@ietf.org
> >> https://www.ietf.org/mailman/listinfo/p2pi
> >>
> > _______________________________________________
> > p2pi mailing list
> > p2pi@ietf.org
> > https://www.ietf.org/mailman/listinfo/p2pi
> 
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi
> 
> 
> 
> 
> -- 
> Robb Topolski (robb@funchords.com)
> Hillsboro, Oregon USA
> http://www.funchords.com/
> 
> _______________________________________________ p2pi mailing list
> p2pi@ietf.org https://www.ietf.org/mailman/listinfo/p2pi 
> 
> 
_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Thu Nov  6 01:09:33 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 42DFE3A69D7;
	Thu,  6 Nov 2008 01:09:33 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 221EA3A6989
	for <p2pi@core3.amsl.com>; Thu,  6 Nov 2008 01:09:32 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.122
X-Spam-Level: 
X-Spam-Status: No, score=-1.122 tagged_above=-999 required=5
	tests=[AWL=-0.627, BAYES_00=-2.599, FH_RELAY_NODNS=1.451,
	HELO_MISMATCH_COM=0.553, RDNS_NONE=0.1]
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 u7Gz8fFa7xmr for <p2pi@core3.amsl.com>;
	Thu,  6 Nov 2008 01:09:30 -0800 (PST)
Received: from szxga03-in.huawei.com (unknown [119.145.14.66])
	by core3.amsl.com (Postfix) with ESMTP id 024D53A697B
	for <p2pi@ietf.org>; Thu,  6 Nov 2008 01:09:30 -0800 (PST)
Received: from huawei.com (szxga03-in [172.24.2.9])
	by szxga03-in.huawei.com (iPlanet Messaging Server 5.2 HotFix 2.14
	(built Aug
	8 2006)) with ESMTP id <0K9W00KLTMRH45@szxga03-in.huawei.com> for
	p2pi@ietf.org; Thu, 06 Nov 2008 17:09:17 +0800 (CST)
Received: from huawei.com ([172.24.1.18])
	by szxga03-in.huawei.com (iPlanet Messaging Server 5.2 HotFix 2.14
	(built Aug
	8 2006)) with ESMTP id <0K9W004FHMRH1G@szxga03-in.huawei.com> for
	p2pi@ietf.org; Thu, 06 Nov 2008 17:09:17 +0800 (CST)
Received: from s64081 ([10.164.12.12])
	by szxml03-in.huawei.com (iPlanet Messaging Server 5.2 HotFix 2.14
	(built Aug
	8 2006)) with ESMTPA id <0K9W009RJMRG6A@szxml03-in.huawei.com> for
	p2pi@ietf.org; Thu, 06 Nov 2008 17:09:17 +0800 (CST)
Date: Thu, 06 Nov 2008 17:09:16 +0800
From: Song Haibin <melodysong@huawei.com>
In-reply-to: <Pine.LNX.4.64.0811052100570.13140@cyndra.cs.yale.edu>
To: "'Y. R. Yang'" <yry@cs.yale.edu>,
	"'Woundy, Richard'" <Richard_Woundy@cable.comcast.com>
Message-id: <005601c93fef$586864e0$0c0ca40a@china.huawei.com>
MIME-version: 1.0
X-MIMEOLE: Produced By Microsoft MimeOLE V6.00.2900.3350
X-Mailer: Microsoft Office Outlook 11
Thread-index: Ack/uPokoPA31KFDTvC6+K9BcdC9uwANC3gA
Cc: "'Livingood, Jason'" <Jason_Livingood@cable.comcast.com>, p2pi@ietf.org
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

Hi Richard and all,

>The access download of each swarm should be equal to the sum of those
>downloaded by the clients in each swarm. So if the number of downloads in
>each swarm is the same and the amount downloaded is the same, then each
>swarm should have the same access download.

Song Haibin: From section 4.1, we can see that "The results of the trial
indicated that P4P can improve the speed of downloads to P2P clients", so if
the statistics data is collected during a certain period (from July 2 to
July 17, 2008), then the download will be increased than the random swarm. I
don't think each swarm has downloaded the same amount of chunk files during
the statistic period.


Best Regards,
Song Haibin
Email: melodysong@huawei.com
Skype: alexsonghw



>-----Original Message-----
>From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of Y.
R.
>Yang
>Sent: Thursday, November 06, 2008 10:40 AM
>To: Woundy, Richard
>Cc: p2pi@ietf.org; Livingood, Jason
>Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>
>
>Hi Rich and others,
>
>The access download of each swarm should be equal to the sum of those
>downloaded by the clients in each swarm. So if the number of downloads in
>each swarm is the same and the amount downloaded is the same, then each
>swarm should have the same access download.
>
>First look at the amount downloaded. There are can be some differences due
>to duplicated chunks and the way we detected data chunks (there are also
>control data in the logs), but the difference appears to be small.
>
>Now let's look at the number of downloads. During the test, each client is
>uniformly assigned to a swarm. Given the large number of clients, each
>swarm should have about the same number of clients. But there can be two
>factors for us to see different numbers of *reported* downloads: (1) some
>clients are old and may not report or the reporting of logs was not
>successful; and (2) different # of clients finished downloading (if a
>client does not finish downloading, it does not report. Laird, please
>correct me if I am wrong). I belive the first factor should be small due
>to uniform random assignment of peers to swarms.
>
>I just looked at the data available. We did detect a smaller number of
>finished download with Random than with the P4P swarms. For example, from
>July 3 to July 10, detected # of finished download of Generic is about 5%
>more than than Random, and Coarse is 7% more than Random. From July 10 to
>July 17, Generic is 10.5% more than Random, and Coarse is 4.7% more.
>Looking at the traffic volume at Section 4.2, I see that Generic is about
>7% higher, and Coarse is about 8.5% higher. Note that # of finished
>download and volume are different due to duplicated chunks and missing
>logs.
>
>So I would like to support the theory/guess of Rich that some users
>terminated the download prematurally and faster downloads may result in
>fewer such terminations. But it may also include factors in (1)
>differences in initial assignment due to random numbers; and (2) # of
>finished but non-reporting clients.
>
>If you have any other suggestions, we will be more than happy to look into
>the available data more.
>
>Richard
>
>On Wed, 5 Nov 2008, 6:26pm -0500, Woundy, Richard wrote:
>
>> My current theory/guess is that some users may terminated the download
>> prematurely, eg due to user impatience. So faster downloads (e.g. thanks
>> to P4P) may result in fewer user terminations.
>>
>>
>>
>> Laird is checking the data to see if we can confirm that, or find
>> another explanation.
>>
>>
>>
>> -- Rich
>>
>>
>>
>> ________________________________
>>
>> From: Laird Popkin [mailto:laird@pando.com]
>> Sent: Wednesday, November 05, 2008 6:12 PM
>> To: Robb Topolski
>> Cc: Livingood, Jason; p2pi@ietf.org; Woundy, Richard
>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>
>>
>>
>> That's a good question, and Richard and I spoke about this yesterday.
>> I'll be looking into the data to see what the cause is.
>>
>> - Laird Popkin, CTO, Pando Networks
>>   mobile: 646/465-0570
>>
>> ----- Original Message -----
>> From: "Robb Topolski" <robb@funchords.com>
>> To: "Richard Woundy" <Richard_Woundy@cable.comcast.com>
>> Cc: "Jason Livingood" <Jason_Livingood@cable.comcast.com>, p2pi@ietf.org
>> Sent: Wednesday, November 5, 2008 5:42:51 PM (GMT-0500) America/New_York
>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>
>> I don't get the part where access network download consumption increased
>> as a result of using P4P (section 4.2).  Can someone explain how that
>> could happen?
>>
>> Robb
>>
>> On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard
>> <Richard_Woundy@cable.comcast.com> wrote:
>>
>> Reinaldo,
>>
>> I can answer the easy questions. We will need some assistance from Pando
>> (and Yale) for some of the other ones.
>>
>>
>> >What was the file size in those experiments?
>>
>> 21 megabytes. From section 2: "Pando distributed a special 21 MB
>> licensed video file as in order to measure the effectiveness of P4P
>> iTrackers."
>>
>>
>> >How long would it take to download the file in the three different
>> scenarios? I know that more consumed bandwidth in access might lead one
>>
>> to conclude that file was downloaded faster...
>>
>> To clarify, most of the raw data (download speed and Internet
>> peering/transit traffic volumes) were collected by Pando Networks from
>> their P2P clients, not collected by Comcast across its links. So my
>> assumption is that the Pando client used the content size (21 MB), and
>> divided by the download time to get the speed.
>>
>>
>> >Was the file already seeded in Comcast's network? More specifically,
>> how
>> was file propagation done?
>>
>> Any seeding happened outside of Comcast's network, and outside of
>> Comcast's control. That's really a question for Pando.
>>
>>
>> >Was PEX, DHT and others enabled in the clients?
>>
>> Pando would know whether PEX was enabled. It would be safe to assume
>> that with respect to this trial, DHT was NOT enabled, since Pando
>> supplied the tracker. (The pTracker in the draft is a tracker operated
>> by Pando.)
>>
>>
>> >Was local peer discovery enabled in the clients?
>>
>> Pando would know.
>>
>>
>> >BTW, can broadcast/multicast peer discovery work in Cable networks?
>>
>> Do you mean something like this:
>> http://bittorrent.org/beps/bep_0026.html?
>>
>> If so, peer discovery probably would not work over the typical last mile
>> cable network. Maybe I'm wrong, but I see this protocol as intended for
>> peer discovery within one's home network / LAN / WiFi network, not over
>> a cable network.
>>
>>
>> >So, were clients allowed to become seeders to the outside of Comcast's
>> network?
>>
>> Yes, they were.
>>
>> As a related item, look closely at section 4.2. The amount of aggregate
>> uploaded data from Comcast clients (per swarm) was about 140,000 MB. The
>> amount of aggregate downloaded data from Comcast clients (per swarm) was
>> about 60,000 MB or so. So the typical Comcast client uploaded more than
>> twice the amount of data that it downloaded.
>>
>>
>> >How much of the swarm was within Comcast and outside?
>>
>> Most of the swarm was outside of Comcast. Unfortunately I don't have
>> access to the size of the global swarm, but I would guess that Comcast
>> clients represented no more than 15% of the swarm, and maybe as little
>> as 5%. Those guesses are based on the behavior of the random swarm, e.g.
>> Comcast clients uploaded to non-Comcast clients 94% of the time in the
>> random swarm.
>>
>> -- Rich
>>
>>
>> -----Original Message-----
>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
>>
>> Reinaldo Penno
>> Sent: Wednesday, November 05, 2008 11:23 AM
>> To: Livingood, Jason; p2pi@ietf.org
>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>
>> Hello Jason/Rich,
>>
>> This is such an interesting draft. I'm surprised there are no questions
>> about it. Maybe everybody else is part of P4P one way or another and I'm
>> not
>> in the 'in' crowd (;-) so I have questions.
>>
>> * What was the file size in those experiments? Some post long ago said
>> the
>> file size in some P4P experiments was really small, as opposed to the
>> top
>> 100 torrents where the file size is ~1Gb. I was curious what is the
>> optimization payback in terms of download time for large files as
>> opposed
>> small files.
>>
>> * How long would it take to download the file in the three different
>> scenarios? I know that more consumed bandwidth in access might lead one
>> to
>> conclude that file was downloaded faster but I'm not sure this is a
>> straightforward conclusion.
>>
>> * Was the file already seeded in Comcast's network? More specifically,
>> how
>> was file propagation done? All clients started from scratch and had to
>> start
>> pulling the file from some other side of the world and then exchanging
>> pieces? This is mainly due to the discussion in 4.2.
>>
>> * Was PEX, DHT and others enabled in the clients?
>>
>> * Was local peer discovery enabled in the clients? BTW, can
>> broadcast/multicast peer discovery work in Cable networks?
>>
>> * If more clients finish downloading faster and become seeders you would
>> think that for popular content Comcast's upstream bandwidth would
>> increase
>> due to the number of seeder in its network. So, were clients allowed to
>> become seeders to the outside of Comcast's network? How much of the
>> swarm
>> was within Comcast and outside?
>>
>> Thanks,
>>
>> Reinaldo
>>
>> On 11/3/08 12:49 PM, "Livingood, Jason"
>> <Jason_Livingood@cable.comcast.com>
>> wrote:
>>
>> > For some reason the URL was cut to two lines - trying again:
>> >
>> >
>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
>> > es-02.txt
>> >
>> >
>> >
>> >> -----Original Message-----
>> >> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
>> >> Behalf Of Livingood, Jason
>> >> Sent: Monday, November 03, 2008 3:35 PM
>> >> To: p2pi@ietf.org
>> >> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>> >>
>> >> A draft at
>> >> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
>> >> -experienc
>> >> es-02.txt may be of interest to folks that have been
>> >> interested in P2Pi and ALTO.  We have requested time on the
>> >> ALTO agenda at IETF 73 to present this.
>> >>
>> >> Regards
>> >> Jason
>> >> _______________________________________________
>> >> p2pi mailing list
>> >> p2pi@ietf.org
>> >> https://www.ietf.org/mailman/listinfo/p2pi
>> >>
>> > _______________________________________________
>> > p2pi mailing list
>> > p2pi@ietf.org
>> > https://www.ietf.org/mailman/listinfo/p2pi
>>
>> _______________________________________________
>> p2pi mailing list
>> p2pi@ietf.org
>> https://www.ietf.org/mailman/listinfo/p2pi
>> _______________________________________________
>> p2pi mailing list
>> p2pi@ietf.org
>> https://www.ietf.org/mailman/listinfo/p2pi
>>
>>
>>
>>
>> --
>> Robb Topolski (robb@funchords.com)
>> Hillsboro, Oregon USA
>> http://www.funchords.com/
>>
>> _______________________________________________ p2pi mailing list
>> p2pi@ietf.org https://www.ietf.org/mailman/listinfo/p2pi
>>
>>
>_______________________________________________
>p2pi mailing list
>p2pi@ietf.org
>https://www.ietf.org/mailman/listinfo/p2pi

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Thu Nov  6 08:34:47 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 1C6CF3A68D1;
	Thu,  6 Nov 2008 08:34:47 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 059C93A68D1
	for <p2pi@core3.amsl.com>; Thu,  6 Nov 2008 08:34:46 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.598
X-Spam-Level: 
X-Spam-Status: No, score=-2.598 tagged_above=-999 required=5
	tests=[BAYES_00=-2.599, HTML_MESSAGE=0.001]
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 OoPF3VO0o917 for <p2pi@core3.amsl.com>;
	Thu,  6 Nov 2008 08:34:43 -0800 (PST)
Received: from nf-out-0910.google.com (nf-out-0910.google.com [64.233.182.189])
	by core3.amsl.com (Postfix) with ESMTP id AAA1E3A6834
	for <p2pi@ietf.org>; Thu,  6 Nov 2008 08:34:42 -0800 (PST)
Received: by nf-out-0910.google.com with SMTP id b11so383048nfh.39
	for <p2pi@ietf.org>; Thu, 06 Nov 2008 08:34:03 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma;
	h=domainkey-signature:received:received:message-id:date:from:to
	:subject:cc:in-reply-to:mime-version:content-type:references;
	bh=5c5EUBRn8gB2tpPm3wMbzASuQSDoU7A3YMVtWHblDM0=;
	b=xRKS7wSwvoeAs0r4EekCicp52aLOyqEIK9ieS3RB6m/OGl4N/XURD/zPYM3tcuL0XY
	3psuk1lOdriWr+4i8gM2Fc9qmsnwcgnL+LktW0Tz7mta9IDwnkh3Zgcu4uD9X4vBMroQ
	5yv8EcrAIOjxZcT0DcZ3yRyP0J1XVwjVtD/t4=
DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma;
	h=message-id:date:from:to:subject:cc:in-reply-to:mime-version
	:content-type:references;
	b=U2zRIE/CzzNLRkwKyEfsVs0qiPveuEXbQqNUB+73KwVLNAJjC0uCRW3fBW6aXjhQBt
	eAseAaDkfJSMFUxHVqulQkUWtog4lYn958nnA5EOB5Kh0UtGxu9tiMdWMe9gA4+ZUbhb
	KQ5kj6k6DKoq6BJMAEfGifXtapddUA0lQfmLY=
Received: by 10.103.218.9 with SMTP id v9mr1192181muq.78.1225989243593;
	Thu, 06 Nov 2008 08:34:03 -0800 (PST)
Received: by 10.103.52.9 with HTTP; Thu, 6 Nov 2008 08:34:03 -0800 (PST)
Message-ID: <2574b1d30811060834n71f43ca1q6c6c227d9479a1cf@mail.gmail.com>
Date: Thu, 6 Nov 2008 11:34:03 -0500
From: "Ye WANG" <wangye.thu@gmail.com>
To: "Song Haibin" <melodysong@huawei.com>
In-Reply-To: <005601c93fef$586864e0$0c0ca40a@china.huawei.com>
MIME-Version: 1.0
References: <Pine.LNX.4.64.0811052100570.13140@cyndra.cs.yale.edu>
	<005601c93fef$586864e0$0c0ca40a@china.huawei.com>
Cc: p2pi@ietf.org, "Woundy, Richard" <Richard_Woundy@cable.comcast.com>,
	"Livingood, Jason" <Jason_Livingood@cable.comcast.com>
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: multipart/mixed; boundary="===============2073853111=="
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

--===============2073853111==
Content-Type: multipart/alternative; 
	boundary="----=_Part_23943_25712443.1225989243583"

------=_Part_23943_25712443.1225989243583
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

Hi Haibin,

Yes, the Random swarm has notable smaller finished downloads than Generic or
Coarse Grained during the period.

Since the swarm sizes (# downloading peers) are roughly equal across all
five swarms (Richard explained this in details), we suspect that a portion
of slow peers terminate/discard their downloads.  This is almost the same
hypothesis pointed out by Rich Woundy.

Another evidence is we do notice significantly slower peers in Random swarm,
e.g., the slowest Random peer took 7268s (>2hours) to download the video,
but the slowest Generic took 2725s (<1hour), the slowest Corase Grained took
3114s (<1hour).   Hours of downloading may make users impatient.  If the
"tail" peers in Random swarm could suffer much lower download rates,
presumably, the number of "terminated" peers may be larger in Random swarm.

On Thu, Nov 6, 2008 at 4:09 AM, Song Haibin <melodysong@huawei.com> wrote:

> Hi Richard and all,
>
> >The access download of each swarm should be equal to the sum of those
> >downloaded by the clients in each swarm. So if the number of downloads in
> >each swarm is the same and the amount downloaded is the same, then each
> >swarm should have the same access download.
>
> Song Haibin: From section 4.1, we can see that "The results of the trial
> indicated that P4P can improve the speed of downloads to P2P clients", so
> if
> the statistics data is collected during a certain period (from July 2 to
> July 17, 2008), then the download will be increased than the random swarm.
> I
> don't think each swarm has downloaded the same amount of chunk files during
> the statistic period.



>
>
>
> Best Regards,
> Song Haibin
> Email: melodysong@huawei.com
> Skype: alexsonghw
>
>
>
> >-----Original Message-----
> >From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
> Y.
> R.
> >Yang
> >Sent: Thursday, November 06, 2008 10:40 AM
> >To: Woundy, Richard
> >Cc: p2pi@ietf.org; Livingood, Jason
> >Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> >
> >
> >Hi Rich and others,
> >
> >The access download of each swarm should be equal to the sum of those
> >downloaded by the clients in each swarm. So if the number of downloads in
> >each swarm is the same and the amount downloaded is the same, then each
> >swarm should have the same access download.
> >
> >First look at the amount downloaded. There are can be some differences due
> >to duplicated chunks and the way we detected data chunks (there are also
> >control data in the logs), but the difference appears to be small.
> >
> >Now let's look at the number of downloads. During the test, each client is
> >uniformly assigned to a swarm. Given the large number of clients, each
> >swarm should have about the same number of clients. But there can be two
> >factors for us to see different numbers of *reported* downloads: (1) some
> >clients are old and may not report or the reporting of logs was not
> >successful; and (2) different # of clients finished downloading (if a
> >client does not finish downloading, it does not report. Laird, please
> >correct me if I am wrong). I belive the first factor should be small due
> >to uniform random assignment of peers to swarms.
> >
> >I just looked at the data available. We did detect a smaller number of
> >finished download with Random than with the P4P swarms. For example, from
> >July 3 to July 10, detected # of finished download of Generic is about 5%
> >more than than Random, and Coarse is 7% more than Random. From July 10 to
> >July 17, Generic is 10.5% more than Random, and Coarse is 4.7% more.
> >Looking at the traffic volume at Section 4.2, I see that Generic is about
> >7% higher, and Coarse is about 8.5% higher. Note that # of finished
> >download and volume are different due to duplicated chunks and missing
> >logs.
> >
> >So I would like to support the theory/guess of Rich that some users
> >terminated the download prematurally and faster downloads may result in
> >fewer such terminations. But it may also include factors in (1)
> >differences in initial assignment due to random numbers; and (2) # of
> >finished but non-reporting clients.
> >
> >If you have any other suggestions, we will be more than happy to look into
> >the available data more.
> >
> >Richard
> >
> >On Wed, 5 Nov 2008, 6:26pm -0500, Woundy, Richard wrote:
> >
> >> My current theory/guess is that some users may terminated the download
> >> prematurely, eg due to user impatience. So faster downloads (e.g. thanks
> >> to P4P) may result in fewer user terminations.
> >>
> >>
> >>
> >> Laird is checking the data to see if we can confirm that, or find
> >> another explanation.
> >>
> >>
> >>
> >> -- Rich
> >>
> >>
> >>
> >> ________________________________
> >>
> >> From: Laird Popkin [mailto:laird@pando.com]
> >> Sent: Wednesday, November 05, 2008 6:12 PM
> >> To: Robb Topolski
> >> Cc: Livingood, Jason; p2pi@ietf.org; Woundy, Richard
> >> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> >>
> >>
> >>
> >> That's a good question, and Richard and I spoke about this yesterday.
> >> I'll be looking into the data to see what the cause is.
> >>
> >> - Laird Popkin, CTO, Pando Networks
> >>   mobile: 646/465-0570
> >>
> >> ----- Original Message -----
> >> From: "Robb Topolski" <robb@funchords.com>
> >> To: "Richard Woundy" <Richard_Woundy@cable.comcast.com>
> >> Cc: "Jason Livingood" <Jason_Livingood@cable.comcast.com>,
> p2pi@ietf.org
> >> Sent: Wednesday, November 5, 2008 5:42:51 PM (GMT-0500) America/New_York
> >> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> >>
> >> I don't get the part where access network download consumption increased
> >> as a result of using P4P (section 4.2).  Can someone explain how that
> >> could happen?
> >>
> >> Robb
> >>
> >> On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard
> >> <Richard_Woundy@cable.comcast.com> wrote:
> >>
> >> Reinaldo,
> >>
> >> I can answer the easy questions. We will need some assistance from Pando
> >> (and Yale) for some of the other ones.
> >>
> >>
> >> >What was the file size in those experiments?
> >>
> >> 21 megabytes. From section 2: "Pando distributed a special 21 MB
> >> licensed video file as in order to measure the effectiveness of P4P
> >> iTrackers."
> >>
> >>
> >> >How long would it take to download the file in the three different
> >> scenarios? I know that more consumed bandwidth in access might lead one
> >>
> >> to conclude that file was downloaded faster...
> >>
> >> To clarify, most of the raw data (download speed and Internet
> >> peering/transit traffic volumes) were collected by Pando Networks from
> >> their P2P clients, not collected by Comcast across its links. So my
> >> assumption is that the Pando client used the content size (21 MB), and
> >> divided by the download time to get the speed.
> >>
> >>
> >> >Was the file already seeded in Comcast's network? More specifically,
> >> how
> >> was file propagation done?
> >>
> >> Any seeding happened outside of Comcast's network, and outside of
> >> Comcast's control. That's really a question for Pando.
> >>
> >>
> >> >Was PEX, DHT and others enabled in the clients?
> >>
> >> Pando would know whether PEX was enabled. It would be safe to assume
> >> that with respect to this trial, DHT was NOT enabled, since Pando
> >> supplied the tracker. (The pTracker in the draft is a tracker operated
> >> by Pando.)
> >>
> >>
> >> >Was local peer discovery enabled in the clients?
> >>
> >> Pando would know.
> >>
> >>
> >> >BTW, can broadcast/multicast peer discovery work in Cable networks?
> >>
> >> Do you mean something like this:
> >> http://bittorrent.org/beps/bep_0026.html?
> >>
> >> If so, peer discovery probably would not work over the typical last mile
> >> cable network. Maybe I'm wrong, but I see this protocol as intended for
> >> peer discovery within one's home network / LAN / WiFi network, not over
> >> a cable network.
> >>
> >>
> >> >So, were clients allowed to become seeders to the outside of Comcast's
> >> network?
> >>
> >> Yes, they were.
> >>
> >> As a related item, look closely at section 4.2. The amount of aggregate
> >> uploaded data from Comcast clients (per swarm) was about 140,000 MB. The
> >> amount of aggregate downloaded data from Comcast clients (per swarm) was
> >> about 60,000 MB or so. So the typical Comcast client uploaded more than
> >> twice the amount of data that it downloaded.
> >>
> >>
> >> >How much of the swarm was within Comcast and outside?
> >>
> >> Most of the swarm was outside of Comcast. Unfortunately I don't have
> >> access to the size of the global swarm, but I would guess that Comcast
> >> clients represented no more than 15% of the swarm, and maybe as little
> >> as 5%. Those guesses are based on the behavior of the random swarm, e.g.
> >> Comcast clients uploaded to non-Comcast clients 94% of the time in the
> >> random swarm.
> >>
> >> -- Rich
> >>
> >>
> >> -----Original Message-----
> >> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
> >>
> >> Reinaldo Penno
> >> Sent: Wednesday, November 05, 2008 11:23 AM
> >> To: Livingood, Jason; p2pi@ietf.org
> >> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> >>
> >> Hello Jason/Rich,
> >>
> >> This is such an interesting draft. I'm surprised there are no questions
> >> about it. Maybe everybody else is part of P4P one way or another and I'm
> >> not
> >> in the 'in' crowd (;-) so I have questions.
> >>
> >> * What was the file size in those experiments? Some post long ago said
> >> the
> >> file size in some P4P experiments was really small, as opposed to the
> >> top
> >> 100 torrents where the file size is ~1Gb. I was curious what is the
> >> optimization payback in terms of download time for large files as
> >> opposed
> >> small files.
> >>
> >> * How long would it take to download the file in the three different
> >> scenarios? I know that more consumed bandwidth in access might lead one
> >> to
> >> conclude that file was downloaded faster but I'm not sure this is a
> >> straightforward conclusion.
> >>
> >> * Was the file already seeded in Comcast's network? More specifically,
> >> how
> >> was file propagation done? All clients started from scratch and had to
> >> start
> >> pulling the file from some other side of the world and then exchanging
> >> pieces? This is mainly due to the discussion in 4.2.
> >>
> >> * Was PEX, DHT and others enabled in the clients?
> >>
> >> * Was local peer discovery enabled in the clients? BTW, can
> >> broadcast/multicast peer discovery work in Cable networks?
> >>
> >> * If more clients finish downloading faster and become seeders you would
> >> think that for popular content Comcast's upstream bandwidth would
> >> increase
> >> due to the number of seeder in its network. So, were clients allowed to
> >> become seeders to the outside of Comcast's network? How much of the
> >> swarm
> >> was within Comcast and outside?
> >>
> >> Thanks,
> >>
> >> Reinaldo
> >>
> >> On 11/3/08 12:49 PM, "Livingood, Jason"
> >> <Jason_Livingood@cable.comcast.com>
> >> wrote:
> >>
> >> > For some reason the URL was cut to two lines - trying again:
> >> >
> >> >
> >>
> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
> >> > es-02.txt
> >> >
> >> >
> >> >
> >> >> -----Original Message-----
> >> >> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
> >> >> Behalf Of Livingood, Jason
> >> >> Sent: Monday, November 03, 2008 3:35 PM
> >> >> To: p2pi@ietf.org
> >> >> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> >> >>
> >> >> A draft at
> >> >> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
> >> >> -experienc
> >> >> es-02.txt may be of interest to folks that have been
> >> >> interested in P2Pi and ALTO.  We have requested time on the
> >> >> ALTO agenda at IETF 73 to present this.
> >> >>
> >> >> Regards
> >> >> Jason
> >> >> _______________________________________________
> >> >> p2pi mailing list
> >> >> p2pi@ietf.org
> >> >> https://www.ietf.org/mailman/listinfo/p2pi
> >> >>
> >> > _______________________________________________
> >> > p2pi mailing list
> >> > p2pi@ietf.org
> >> > https://www.ietf.org/mailman/listinfo/p2pi
> >>
> >> _______________________________________________
> >> p2pi mailing list
> >> p2pi@ietf.org
> >> https://www.ietf.org/mailman/listinfo/p2pi
> >> _______________________________________________
> >> p2pi mailing list
> >> p2pi@ietf.org
> >> https://www.ietf.org/mailman/listinfo/p2pi
> >>
> >>
> >>
> >>
> >> --
> >> Robb Topolski (robb@funchords.com)
> >> Hillsboro, Oregon USA
> >> http://www.funchords.com/
> >>
> >> _______________________________________________ p2pi mailing list
> >> p2pi@ietf.org https://www.ietf.org/mailman/listinfo/p2pi
> >>
> >>
> >_______________________________________________
> >p2pi mailing list
> >p2pi@ietf.org
> >https://www.ietf.org/mailman/listinfo/p2pi
>
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi
>

------=_Part_23943_25712443.1225989243583
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

Hi Haibin,<br><br>Yes, the Random swarm has notable smaller finished downloads than Generic or Coarse Grained during the period.&nbsp; <br><br>Since the swarm sizes (# downloading peers) are roughly equal across all five swarms (Richard explained this in details), we suspect that a portion of slow peers terminate/discard their downloads.&nbsp; This is almost the same hypothesis pointed out by Rich Woundy.<br>
<br>Another evidence is we do notice significantly slower peers in Random swarm, e.g., the slowest Random peer took 7268s (&gt;2hours) to download the video, but the slowest Generic took 2725s (&lt;1hour), the slowest Corase Grained took 3114s (&lt;1hour).&nbsp;&nbsp; Hours of downloading may make users impatient.&nbsp; If the &quot;tail&quot; peers in Random swarm could suffer much lower download rates, presumably, the number of &quot;terminated&quot; peers may be larger in Random swarm.<br>
<br><div class="gmail_quote">On Thu, Nov 6, 2008 at 4:09 AM, Song Haibin <span dir="ltr">&lt;<a href="mailto:melodysong@huawei.com" target="_blank">melodysong@huawei.com</a>&gt;</span> wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">Hi Richard and all,<br>
<div><br>
&gt;The access download of each swarm should be equal to the sum of those<br>
&gt;downloaded by the clients in each swarm. So if the number of downloads in<br>
&gt;each swarm is the same and the amount downloaded is the same, then each<br>
&gt;swarm should have the same access download.<br>
<br>
</div>Song Haibin: From section 4.1, we can see that &quot;The results of the trial<br>
indicated that P4P can improve the speed of downloads to P2P clients&quot;, so if<br>
the statistics data is collected during a certain period (from July 2 to<br>
July 17, 2008), then the download will be increased than the random swarm. I<br>
don&#39;t think each swarm has downloaded the same amount of chunk files during<br>
the statistic period.</blockquote><div>&nbsp;</div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><br>
<br>
<br>
Best Regards,<br>
<font color="#888888">Song Haibin<br>
Email: <a href="mailto:melodysong@huawei.com" target="_blank">melodysong@huawei.com</a><br>
Skype: alexsonghw<br>
</font><div><div></div><div><br>
<br>
<br>
&gt;-----Original Message-----<br>
&gt;From: <a href="mailto:p2pi-bounces@ietf.org" target="_blank">p2pi-bounces@ietf.org</a> [mailto:<a href="mailto:p2pi-bounces@ietf.org" target="_blank">p2pi-bounces@ietf.org</a>] On Behalf Of Y.<br>
R.<br>
&gt;Yang<br>
&gt;Sent: Thursday, November 06, 2008 10:40 AM<br>
&gt;To: Woundy, Richard<br>
&gt;Cc: <a href="mailto:p2pi@ietf.org" target="_blank">p2pi@ietf.org</a>; Livingood, Jason<br>
&gt;Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted<br>
&gt;<br>
&gt;<br>
&gt;Hi Rich and others,<br>
&gt;<br>
&gt;The access download of each swarm should be equal to the sum of those<br>
&gt;downloaded by the clients in each swarm. So if the number of downloads in<br>
&gt;each swarm is the same and the amount downloaded is the same, then each<br>
&gt;swarm should have the same access download.<br>
&gt;<br>
&gt;First look at the amount downloaded. There are can be some differences due<br>
&gt;to duplicated chunks and the way we detected data chunks (there are also<br>
&gt;control data in the logs), but the difference appears to be small.<br>
&gt;<br>
&gt;Now let&#39;s look at the number of downloads. During the test, each client is<br>
&gt;uniformly assigned to a swarm. Given the large number of clients, each<br>
&gt;swarm should have about the same number of clients. But there can be two<br>
&gt;factors for us to see different numbers of *reported* downloads: (1) some<br>
&gt;clients are old and may not report or the reporting of logs was not<br>
&gt;successful; and (2) different # of clients finished downloading (if a<br>
&gt;client does not finish downloading, it does not report. Laird, please<br>
&gt;correct me if I am wrong). I belive the first factor should be small due<br>
&gt;to uniform random assignment of peers to swarms.<br>
&gt;<br>
&gt;I just looked at the data available. We did detect a smaller number of<br>
&gt;finished download with Random than with the P4P swarms. For example, from<br>
&gt;July 3 to July 10, detected # of finished download of Generic is about 5%<br>
&gt;more than than Random, and Coarse is 7% more than Random. From July 10 to<br>
&gt;July 17, Generic is 10.5% more than Random, and Coarse is 4.7% more.<br>
&gt;Looking at the traffic volume at Section 4.2, I see that Generic is about<br>
&gt;7% higher, and Coarse is about 8.5% higher. Note that # of finished<br>
&gt;download and volume are different due to duplicated chunks and missing<br>
&gt;logs.<br>
&gt;<br>
&gt;So I would like to support the theory/guess of Rich that some users<br>
&gt;terminated the download prematurally and faster downloads may result in<br>
&gt;fewer such terminations. But it may also include factors in (1)<br>
&gt;differences in initial assignment due to random numbers; and (2) # of<br>
&gt;finished but non-reporting clients.<br>
&gt;<br>
&gt;If you have any other suggestions, we will be more than happy to look into<br>
&gt;the available data more.<br>
&gt;<br>
&gt;Richard<br>
&gt;<br>
&gt;On Wed, 5 Nov 2008, 6:26pm -0500, Woundy, Richard wrote:<br>
&gt;<br>
&gt;&gt; My current theory/guess is that some users may terminated the download<br>
&gt;&gt; prematurely, eg due to user impatience. So faster downloads (e.g. thanks<br>
&gt;&gt; to P4P) may result in fewer user terminations.<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; Laird is checking the data to see if we can confirm that, or find<br>
&gt;&gt; another explanation.<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; -- Rich<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; ________________________________<br>
&gt;&gt;<br>
&gt;&gt; From: Laird Popkin [mailto:<a href="mailto:laird@pando.com" target="_blank">laird@pando.com</a>]<br>
&gt;&gt; Sent: Wednesday, November 05, 2008 6:12 PM<br>
&gt;&gt; To: Robb Topolski<br>
&gt;&gt; Cc: Livingood, Jason; <a href="mailto:p2pi@ietf.org" target="_blank">p2pi@ietf.org</a>; Woundy, Richard<br>
&gt;&gt; Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; That&#39;s a good question, and Richard and I spoke about this yesterday.<br>
&gt;&gt; I&#39;ll be looking into the data to see what the cause is.<br>
&gt;&gt;<br>
&gt;&gt; - Laird Popkin, CTO, Pando Networks<br>
&gt;&gt; &nbsp; mobile: 646/465-0570<br>
&gt;&gt;<br>
&gt;&gt; ----- Original Message -----<br>
&gt;&gt; From: &quot;Robb Topolski&quot; &lt;<a href="mailto:robb@funchords.com" target="_blank">robb@funchords.com</a>&gt;<br>
&gt;&gt; To: &quot;Richard Woundy&quot; &lt;<a href="mailto:Richard_Woundy@cable.comcast.com" target="_blank">Richard_Woundy@cable.comcast.com</a>&gt;<br>
&gt;&gt; Cc: &quot;Jason Livingood&quot; &lt;<a href="mailto:Jason_Livingood@cable.comcast.com" target="_blank">Jason_Livingood@cable.comcast.com</a>&gt;, <a href="mailto:p2pi@ietf.org" target="_blank">p2pi@ietf.org</a><br>

&gt;&gt; Sent: Wednesday, November 5, 2008 5:42:51 PM (GMT-0500) America/New_York<br>
&gt;&gt; Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted<br>
&gt;&gt;<br>
&gt;&gt; I don&#39;t get the part where access network download consumption increased<br>
&gt;&gt; as a result of using P4P (section 4.2). &nbsp;Can someone explain how that<br>
&gt;&gt; could happen?<br>
&gt;&gt;<br>
&gt;&gt; Robb<br>
&gt;&gt;<br>
&gt;&gt; On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard<br>
&gt;&gt; &lt;<a href="mailto:Richard_Woundy@cable.comcast.com" target="_blank">Richard_Woundy@cable.comcast.com</a>&gt; wrote:<br>
&gt;&gt;<br>
&gt;&gt; Reinaldo,<br>
&gt;&gt;<br>
&gt;&gt; I can answer the easy questions. We will need some assistance from Pando<br>
&gt;&gt; (and Yale) for some of the other ones.<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; &gt;What was the file size in those experiments?<br>
&gt;&gt;<br>
&gt;&gt; 21 megabytes. From section 2: &quot;Pando distributed a special 21 MB<br>
&gt;&gt; licensed video file as in order to measure the effectiveness of P4P<br>
&gt;&gt; iTrackers.&quot;<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; &gt;How long would it take to download the file in the three different<br>
&gt;&gt; scenarios? I know that more consumed bandwidth in access might lead one<br>
&gt;&gt;<br>
&gt;&gt; to conclude that file was downloaded faster...<br>
&gt;&gt;<br>
&gt;&gt; To clarify, most of the raw data (download speed and Internet<br>
&gt;&gt; peering/transit traffic volumes) were collected by Pando Networks from<br>
&gt;&gt; their P2P clients, not collected by Comcast across its links. So my<br>
&gt;&gt; assumption is that the Pando client used the content size (21 MB), and<br>
&gt;&gt; divided by the download time to get the speed.<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; &gt;Was the file already seeded in Comcast&#39;s network? More specifically,<br>
&gt;&gt; how<br>
&gt;&gt; was file propagation done?<br>
&gt;&gt;<br>
&gt;&gt; Any seeding happened outside of Comcast&#39;s network, and outside of<br>
&gt;&gt; Comcast&#39;s control. That&#39;s really a question for Pando.<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; &gt;Was PEX, DHT and others enabled in the clients?<br>
&gt;&gt;<br>
&gt;&gt; Pando would know whether PEX was enabled. It would be safe to assume<br>
&gt;&gt; that with respect to this trial, DHT was NOT enabled, since Pando<br>
&gt;&gt; supplied the tracker. (The pTracker in the draft is a tracker operated<br>
&gt;&gt; by Pando.)<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; &gt;Was local peer discovery enabled in the clients?<br>
&gt;&gt;<br>
&gt;&gt; Pando would know.<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; &gt;BTW, can broadcast/multicast peer discovery work in Cable networks?<br>
&gt;&gt;<br>
&gt;&gt; Do you mean something like this:<br>
&gt;&gt; <a href="http://bittorrent.org/beps/bep_0026.html" target="_blank">http://bittorrent.org/beps/bep_0026.html</a>?<br>
&gt;&gt;<br>
&gt;&gt; If so, peer discovery probably would not work over the typical last mile<br>
&gt;&gt; cable network. Maybe I&#39;m wrong, but I see this protocol as intended for<br>
&gt;&gt; peer discovery within one&#39;s home network / LAN / WiFi network, not over<br>
&gt;&gt; a cable network.<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; &gt;So, were clients allowed to become seeders to the outside of Comcast&#39;s<br>
&gt;&gt; network?<br>
&gt;&gt;<br>
&gt;&gt; Yes, they were.<br>
&gt;&gt;<br>
&gt;&gt; As a related item, look closely at section 4.2. The amount of aggregate<br>
&gt;&gt; uploaded data from Comcast clients (per swarm) was about 140,000 MB. The<br>
&gt;&gt; amount of aggregate downloaded data from Comcast clients (per swarm) was<br>
&gt;&gt; about 60,000 MB or so. So the typical Comcast client uploaded more than<br>
&gt;&gt; twice the amount of data that it downloaded.<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; &gt;How much of the swarm was within Comcast and outside?<br>
&gt;&gt;<br>
&gt;&gt; Most of the swarm was outside of Comcast. Unfortunately I don&#39;t have<br>
&gt;&gt; access to the size of the global swarm, but I would guess that Comcast<br>
&gt;&gt; clients represented no more than 15% of the swarm, and maybe as little<br>
&gt;&gt; as 5%. Those guesses are based on the behavior of the random swarm, e.g.<br>
&gt;&gt; Comcast clients uploaded to non-Comcast clients 94% of the time in the<br>
&gt;&gt; random swarm.<br>
&gt;&gt;<br>
&gt;&gt; -- Rich<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; -----Original Message-----<br>
&gt;&gt; From: <a href="mailto:p2pi-bounces@ietf.org" target="_blank">p2pi-bounces@ietf.org</a> [mailto:<a href="mailto:p2pi-bounces@ietf.org" target="_blank">p2pi-bounces@ietf.org</a>] On Behalf Of<br>
&gt;&gt;<br>
&gt;&gt; Reinaldo Penno<br>
&gt;&gt; Sent: Wednesday, November 05, 2008 11:23 AM<br>
&gt;&gt; To: Livingood, Jason; <a href="mailto:p2pi@ietf.org" target="_blank">p2pi@ietf.org</a><br>
&gt;&gt; Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted<br>
&gt;&gt;<br>
&gt;&gt; Hello Jason/Rich,<br>
&gt;&gt;<br>
&gt;&gt; This is such an interesting draft. I&#39;m surprised there are no questions<br>
&gt;&gt; about it. Maybe everybody else is part of P4P one way or another and I&#39;m<br>
&gt;&gt; not<br>
&gt;&gt; in the &#39;in&#39; crowd (;-) so I have questions.<br>
&gt;&gt;<br>
&gt;&gt; * What was the file size in those experiments? Some post long ago said<br>
&gt;&gt; the<br>
&gt;&gt; file size in some P4P experiments was really small, as opposed to the<br>
&gt;&gt; top<br>
&gt;&gt; 100 torrents where the file size is ~1Gb. I was curious what is the<br>
&gt;&gt; optimization payback in terms of download time for large files as<br>
&gt;&gt; opposed<br>
&gt;&gt; small files.<br>
&gt;&gt;<br>
&gt;&gt; * How long would it take to download the file in the three different<br>
&gt;&gt; scenarios? I know that more consumed bandwidth in access might lead one<br>
&gt;&gt; to<br>
&gt;&gt; conclude that file was downloaded faster but I&#39;m not sure this is a<br>
&gt;&gt; straightforward conclusion.<br>
&gt;&gt;<br>
&gt;&gt; * Was the file already seeded in Comcast&#39;s network? More specifically,<br>
&gt;&gt; how<br>
&gt;&gt; was file propagation done? All clients started from scratch and had to<br>
&gt;&gt; start<br>
&gt;&gt; pulling the file from some other side of the world and then exchanging<br>
&gt;&gt; pieces? This is mainly due to the discussion in 4.2.<br>
&gt;&gt;<br>
&gt;&gt; * Was PEX, DHT and others enabled in the clients?<br>
&gt;&gt;<br>
&gt;&gt; * Was local peer discovery enabled in the clients? BTW, can<br>
&gt;&gt; broadcast/multicast peer discovery work in Cable networks?<br>
&gt;&gt;<br>
&gt;&gt; * If more clients finish downloading faster and become seeders you would<br>
&gt;&gt; think that for popular content Comcast&#39;s upstream bandwidth would<br>
&gt;&gt; increase<br>
&gt;&gt; due to the number of seeder in its network. So, were clients allowed to<br>
&gt;&gt; become seeders to the outside of Comcast&#39;s network? How much of the<br>
&gt;&gt; swarm<br>
&gt;&gt; was within Comcast and outside?<br>
&gt;&gt;<br>
&gt;&gt; Thanks,<br>
&gt;&gt;<br>
&gt;&gt; Reinaldo<br>
&gt;&gt;<br>
&gt;&gt; On 11/3/08 12:49 PM, &quot;Livingood, Jason&quot;<br>
&gt;&gt; &lt;<a href="mailto:Jason_Livingood@cable.comcast.com" target="_blank">Jason_Livingood@cable.comcast.com</a>&gt;<br>
&gt;&gt; wrote:<br>
&gt;&gt;<br>
&gt;&gt; &gt; For some reason the URL was cut to two lines - trying again:<br>
&gt;&gt; &gt;<br>
&gt;&gt; &gt;<br>
&gt;&gt; <a href="http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc" target="_blank">http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc</a><br>
&gt;&gt; &gt; es-02.txt<br>
&gt;&gt; &gt;<br>
&gt;&gt; &gt;<br>
&gt;&gt; &gt;<br>
&gt;&gt; &gt;&gt; -----Original Message-----<br>
&gt;&gt; &gt;&gt; From: <a href="mailto:p2pi-bounces@ietf.org" target="_blank">p2pi-bounces@ietf.org</a> [mailto:<a href="mailto:p2pi-bounces@ietf.org" target="_blank">p2pi-bounces@ietf.org</a>] On<br>
&gt;&gt; &gt;&gt; Behalf Of Livingood, Jason<br>
&gt;&gt; &gt;&gt; Sent: Monday, November 03, 2008 3:35 PM<br>
&gt;&gt; &gt;&gt; To: <a href="mailto:p2pi@ietf.org" target="_blank">p2pi@ietf.org</a><br>
&gt;&gt; &gt;&gt; Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted<br>
&gt;&gt; &gt;&gt;<br>
&gt;&gt; &gt;&gt; A draft at<br>
&gt;&gt; &gt;&gt; <a href="http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p" target="_blank">http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p</a><br>
&gt;&gt; &gt;&gt; -experienc<br>
&gt;&gt; &gt;&gt; es-02.txt may be of interest to folks that have been<br>
&gt;&gt; &gt;&gt; interested in P2Pi and ALTO. &nbsp;We have requested time on the<br>
&gt;&gt; &gt;&gt; ALTO agenda at IETF 73 to present this.<br>
&gt;&gt; &gt;&gt;<br>
&gt;&gt; &gt;&gt; Regards<br>
&gt;&gt; &gt;&gt; Jason<br>
&gt;&gt; &gt;&gt; _______________________________________________<br>
&gt;&gt; &gt;&gt; p2pi mailing list<br>
&gt;&gt; &gt;&gt; <a href="mailto:p2pi@ietf.org" target="_blank">p2pi@ietf.org</a><br>
&gt;&gt; &gt;&gt; <a href="https://www.ietf.org/mailman/listinfo/p2pi" target="_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
&gt;&gt; &gt;&gt;<br>
&gt;&gt; &gt; _______________________________________________<br>
&gt;&gt; &gt; p2pi mailing list<br>
&gt;&gt; &gt; <a href="mailto:p2pi@ietf.org" target="_blank">p2pi@ietf.org</a><br>
&gt;&gt; &gt; <a href="https://www.ietf.org/mailman/listinfo/p2pi" target="_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
&gt;&gt;<br>
&gt;&gt; _______________________________________________<br>
&gt;&gt; p2pi mailing list<br>
&gt;&gt; <a href="mailto:p2pi@ietf.org" target="_blank">p2pi@ietf.org</a><br>
&gt;&gt; <a href="https://www.ietf.org/mailman/listinfo/p2pi" target="_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
&gt;&gt; _______________________________________________<br>
&gt;&gt; p2pi mailing list<br>
&gt;&gt; <a href="mailto:p2pi@ietf.org" target="_blank">p2pi@ietf.org</a><br>
&gt;&gt; <a href="https://www.ietf.org/mailman/listinfo/p2pi" target="_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;&gt; --<br>
&gt;&gt; Robb Topolski (<a href="mailto:robb@funchords.com" target="_blank">robb@funchords.com</a>)<br>
&gt;&gt; Hillsboro, Oregon USA<br>
&gt;&gt; <a href="http://www.funchords.com/" target="_blank">http://www.funchords.com/</a><br>
&gt;&gt;<br>
&gt;&gt; _______________________________________________ p2pi mailing list<br>
&gt;&gt; <a href="mailto:p2pi@ietf.org" target="_blank">p2pi@ietf.org</a> <a href="https://www.ietf.org/mailman/listinfo/p2pi" target="_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
&gt;&gt;<br>
&gt;&gt;<br>
&gt;_______________________________________________<br>
&gt;p2pi mailing list<br>
&gt;<a href="mailto:p2pi@ietf.org" target="_blank">p2pi@ietf.org</a><br>
&gt;<a href="https://www.ietf.org/mailman/listinfo/p2pi" target="_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
<br>
_______________________________________________<br>
p2pi mailing list<br>
<a href="mailto:p2pi@ietf.org" target="_blank">p2pi@ietf.org</a><br>
<a href="https://www.ietf.org/mailman/listinfo/p2pi" target="_blank">https://www.ietf.org/mailman/listinfo/p2pi</a><br>
</div></div></blockquote></div><br>

------=_Part_23943_25712443.1225989243583--

--===============2073853111==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi

--===============2073853111==--


From p2pi-bounces@ietf.org  Thu Nov  6 15:38:05 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 7088D3A69FC;
	Thu,  6 Nov 2008 15:38:05 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 014F03A69FC
	for <p2pi@core3.amsl.com>; Thu,  6 Nov 2008 15:38:05 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.599
X-Spam-Level: 
X-Spam-Status: No, score=-2.599 tagged_above=-999 required=5 tests=[AWL=0.000, 
	BAYES_00=-2.599]
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 V2zz9IQxLTgy for <p2pi@core3.amsl.com>;
	Thu,  6 Nov 2008 15:38:04 -0800 (PST)
Received: from ihemail4.lucent.com (ihemail4.lucent.com [135.245.0.39])
	by core3.amsl.com (Postfix) with ESMTP id 2B8C13A6813
	for <p2pi@ietf.org>; Thu,  6 Nov 2008 15:38:03 -0800 (PST)
Received: from umail.lucent.com (h135-3-40-61.lucent.com [135.3.40.61])
	by ihemail4.lucent.com (8.13.8/IER-o) with ESMTP id mA6Nbwin007971
	(version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO)
	for <p2pi@ietf.org>; Thu, 6 Nov 2008 17:37:58 -0600 (CST)
Received: from [135.185.236.17] (il0015vkg1.ih.lucent.com [135.185.236.17])
	by umail.lucent.com (8.13.8/TPES) with ESMTP id mA6NbvOG004606
	for <p2pi@ietf.org>; Thu, 6 Nov 2008 17:37:58 -0600 (CST)
Message-ID: <49137FD4.100@alcatel-lucent.com>
Date: Thu, 06 Nov 2008 17:37:56 -0600
From: "Vijay K. Gurbani" <vkg@alcatel-lucent.com>
Organization: Bell Labs Security Technology Research Group
User-Agent: Thunderbird 2.0.0.6 (Windows/20070728)
MIME-Version: 1.0
To: "p2pi@ietf.org" <p2pi@ietf.org>
X-Scanned-By: MIMEDefang 2.57 on 135.245.2.39
Subject: [p2pi] alto approved as WG
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset="us-ascii"; Format="flowed"
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

Folks: We heard from the AD; alto has been approved as a WG
in the Applications area.  Thank you all for helping refine
the charter to get us to this point.

The official IETF announcement will be coming out soon; in
the meantime the agenda Enrico sent out earlier (please see
http://www.ietf.org/proceedings/08nov/agenda/alto.html)
stands; although as usual it may incur minor changes.

See you in Minneapolis.

- vijay
-- 
Vijay K. Gurbani, Bell Laboratories, Alcatel-Lucent
1960 Lucent Lane, Rm. 9C-533, Naperville, Illinois 60566 (USA)
Email: vkg@{alcatel-lucent.com,bell-labs.com,acm.org}
Web:   http://ect.bell-labs.com/who/vkg/

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Sun Nov  9 13:06:43 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 4289D3A6891;
	Sun,  9 Nov 2008 13:06:43 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 097F63A6891
	for <p2pi@core3.amsl.com>; Sun,  9 Nov 2008 13:06:42 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.531
X-Spam-Level: 
X-Spam-Status: No, score=-1.531 tagged_above=-999 required=5 tests=[AWL=0.446, 
	BAYES_00=-2.599, FM_FORGED_GMAIL=0.622]
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 RvnDGQxTGCIs for <p2pi@core3.amsl.com>;
	Sun,  9 Nov 2008 13:06:40 -0800 (PST)
Received: from rv-out-0506.google.com (rv-out-0506.google.com [209.85.198.234])
	by core3.amsl.com (Postfix) with ESMTP id 4E4033A67DD
	for <p2pi@ietf.org>; Sun,  9 Nov 2008 13:06:39 -0800 (PST)
Received: by rv-out-0506.google.com with SMTP id b25so2099641rvf.49
	for <p2pi@ietf.org>; Sun, 09 Nov 2008 13:06:35 -0800 (PST)
Received: by 10.140.178.17 with SMTP id a17mr3158103rvf.186.1226264795839;
	Sun, 09 Nov 2008 13:06:35 -0800 (PST)
Received: by 10.141.69.3 with HTTP; Sun, 9 Nov 2008 13:06:35 -0800 (PST)
Message-ID: <3efc39a60811091306r5e76a90et1b4ae2cbddfd3f29@mail.gmail.com>
Date: Sun, 9 Nov 2008 13:06:35 -0800
From: "Robb Topolski" <robb@funchords.com>
To: "p2pi@ietf.org" <p2pi@ietf.org>
In-Reply-To: <2574b1d30811060834n71f43ca1q6c6c227d9479a1cf@mail.gmail.com>
MIME-Version: 1.0
Content-Disposition: inline
References: <Pine.LNX.4.64.0811052100570.13140@cyndra.cs.yale.edu>
	<005601c93fef$586864e0$0c0ca40a@china.huawei.com>
	<2574b1d30811060834n71f43ca1q6c6c227d9479a1cf@mail.gmail.com>
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

It seems like a broken statistic given this experiment.

If it were tightly controlled (and thus less Internet-like), all of
the downloads would have completed and the download byte amounts would
be virtually the same.

One might argue that there is virtue to these observations because a
downloader who cancels a slow download is a bad thing, because they
ultimately did not get what they attempted to download.

But is there virtue in an aborted download?  If they canceled the
download in frustration or because they simply couldn't stay connected
to the swarm long enough before being forced to quit by some other
personal oe obligation, then one could say that an aborted download is
a band thing. OTOH, an incomplete download is a good thing when a
downloader may have changed his mind (wanted to hear/see/do something
else) with less bandwidth wasted. There's just no way to know why the
user aborted the download.

Even if we did know, this experiment doesn't deal with other possible
P4P-advantaged uses such as streaming-P2P video delivery (a mode more
prone to user "taste-testing" before completing a download than
traditional file-transfer models).

Robb

2008/11/6 Ye WANG <wangye.thu@gmail.com>:
> Hi Haibin,
>
> Yes, the Random swarm has notable smaller finished downloads than Generic or
> Coarse Grained during the period.
>
> Since the swarm sizes (# downloading peers) are roughly equal across all
> five swarms (Richard explained this in details), we suspect that a portion
> of slow peers terminate/discard their downloads.  This is almost the same
> hypothesis pointed out by Rich Woundy.
>
> Another evidence is we do notice significantly slower peers in Random swarm,
> e.g., the slowest Random peer took 7268s (>2hours) to download the video,
> but the slowest Generic took 2725s (<1hour), the slowest Corase Grained took
> 3114s (<1hour).   Hours of downloading may make users impatient.  If the
> "tail" peers in Random swarm could suffer much lower download rates,
> presumably, the number of "terminated" peers may be larger in Random swarm.
>
> On Thu, Nov 6, 2008 at 4:09 AM, Song Haibin <melodysong@huawei.com> wrote:
>>
>> Hi Richard and all,
>>
>> >The access download of each swarm should be equal to the sum of those
>> >downloaded by the clients in each swarm. So if the number of downloads in
>> >each swarm is the same and the amount downloaded is the same, then each
>> >swarm should have the same access download.
>>
>> Song Haibin: From section 4.1, we can see that "The results of the trial
>> indicated that P4P can improve the speed of downloads to P2P clients", so
>> if
>> the statistics data is collected during a certain period (from July 2 to
>> July 17, 2008), then the download will be increased than the random swarm.
>> I
>> don't think each swarm has downloaded the same amount of chunk files
>> during
>> the statistic period.
>
>
>>
>>
>> Best Regards,
>> Song Haibin
>> Email: melodysong@huawei.com
>> Skype: alexsonghw
>>
>>
>>
>> >-----Original Message-----
>> >From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
>> > Y.
>> R.
>> >Yang
>> >Sent: Thursday, November 06, 2008 10:40 AM
>> >To: Woundy, Richard
>> >Cc: p2pi@ietf.org; Livingood, Jason
>> >Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>> >
>> >
>> >Hi Rich and others,
>> >
>> >The access download of each swarm should be equal to the sum of those
>> >downloaded by the clients in each swarm. So if the number of downloads in
>> >each swarm is the same and the amount downloaded is the same, then each
>> >swarm should have the same access download.
>> >
>> >First look at the amount downloaded. There are can be some differences
>> > due
>> >to duplicated chunks and the way we detected data chunks (there are also
>> >control data in the logs), but the difference appears to be small.
>> >
>> >Now let's look at the number of downloads. During the test, each client
>> > is
>> >uniformly assigned to a swarm. Given the large number of clients, each
>> >swarm should have about the same number of clients. But there can be two
>> >factors for us to see different numbers of *reported* downloads: (1) some
>> >clients are old and may not report or the reporting of logs was not
>> >successful; and (2) different # of clients finished downloading (if a
>> >client does not finish downloading, it does not report. Laird, please
>> >correct me if I am wrong). I belive the first factor should be small due
>> >to uniform random assignment of peers to swarms.
>> >
>> >I just looked at the data available. We did detect a smaller number of
>> >finished download with Random than with the P4P swarms. For example, from
>> >July 3 to July 10, detected # of finished download of Generic is about 5%
>> >more than than Random, and Coarse is 7% more than Random. From July 10 to
>> >July 17, Generic is 10.5% more than Random, and Coarse is 4.7% more.
>> >Looking at the traffic volume at Section 4.2, I see that Generic is about
>> >7% higher, and Coarse is about 8.5% higher. Note that # of finished
>> >download and volume are different due to duplicated chunks and missing
>> >logs.
>> >
>> >So I would like to support the theory/guess of Rich that some users
>> >terminated the download prematurally and faster downloads may result in
>> >fewer such terminations. But it may also include factors in (1)
>> >differences in initial assignment due to random numbers; and (2) # of
>> >finished but non-reporting clients.
>> >
>> >If you have any other suggestions, we will be more than happy to look
>> > into
>> >the available data more.
>> >
>> >Richard
>> >
>> >On Wed, 5 Nov 2008, 6:26pm -0500, Woundy, Richard wrote:
>> >
>> >> My current theory/guess is that some users may terminated the download
>> >> prematurely, eg due to user impatience. So faster downloads (e.g.
>> >> thanks
>> >> to P4P) may result in fewer user terminations.
>> >>
>> >>
>> >>
>> >> Laird is checking the data to see if we can confirm that, or find
>> >> another explanation.
>> >>
>> >>
>> >>
>> >> -- Rich
>> >>
>> >>
>> >>
>> >> ________________________________
>> >>
>> >> From: Laird Popkin [mailto:laird@pando.com]
>> >> Sent: Wednesday, November 05, 2008 6:12 PM
>> >> To: Robb Topolski
>> >> Cc: Livingood, Jason; p2pi@ietf.org; Woundy, Richard
>> >> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>> >>
>> >>
>> >>
>> >> That's a good question, and Richard and I spoke about this yesterday.
>> >> I'll be looking into the data to see what the cause is.
>> >>
>> >> - Laird Popkin, CTO, Pando Networks
>> >>   mobile: 646/465-0570
>> >>
>> >> ----- Original Message -----
>> >> From: "Robb Topolski" <robb@funchords.com>
>> >> To: "Richard Woundy" <Richard_Woundy@cable.comcast.com>
>> >> Cc: "Jason Livingood" <Jason_Livingood@cable.comcast.com>,
>> >> p2pi@ietf.org
>> >> Sent: Wednesday, November 5, 2008 5:42:51 PM (GMT-0500)
>> >> America/New_York
>> >> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>> >>
>> >> I don't get the part where access network download consumption
>> >> increased
>> >> as a result of using P4P (section 4.2).  Can someone explain how that
>> >> could happen?
>> >>
>> >> Robb
>> >>
>> >> On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard
>> >> <Richard_Woundy@cable.comcast.com> wrote:
>> >>
>> >> Reinaldo,
>> >>
>> >> I can answer the easy questions. We will need some assistance from
>> >> Pando
>> >> (and Yale) for some of the other ones.
>> >>
>> >>
>> >> >What was the file size in those experiments?
>> >>
>> >> 21 megabytes. From section 2: "Pando distributed a special 21 MB
>> >> licensed video file as in order to measure the effectiveness of P4P
>> >> iTrackers."
>> >>
>> >>
>> >> >How long would it take to download the file in the three different
>> >> scenarios? I know that more consumed bandwidth in access might lead one
>> >>
>> >> to conclude that file was downloaded faster...
>> >>
>> >> To clarify, most of the raw data (download speed and Internet
>> >> peering/transit traffic volumes) were collected by Pando Networks from
>> >> their P2P clients, not collected by Comcast across its links. So my
>> >> assumption is that the Pando client used the content size (21 MB), and
>> >> divided by the download time to get the speed.
>> >>
>> >>
>> >> >Was the file already seeded in Comcast's network? More specifically,
>> >> how
>> >> was file propagation done?
>> >>
>> >> Any seeding happened outside of Comcast's network, and outside of
>> >> Comcast's control. That's really a question for Pando.
>> >>
>> >>
>> >> >Was PEX, DHT and others enabled in the clients?
>> >>
>> >> Pando would know whether PEX was enabled. It would be safe to assume
>> >> that with respect to this trial, DHT was NOT enabled, since Pando
>> >> supplied the tracker. (The pTracker in the draft is a tracker operated
>> >> by Pando.)
>> >>
>> >>
>> >> >Was local peer discovery enabled in the clients?
>> >>
>> >> Pando would know.
>> >>
>> >>
>> >> >BTW, can broadcast/multicast peer discovery work in Cable networks?
>> >>
>> >> Do you mean something like this:
>> >> http://bittorrent.org/beps/bep_0026.html?
>> >>
>> >> If so, peer discovery probably would not work over the typical last
>> >> mile
>> >> cable network. Maybe I'm wrong, but I see this protocol as intended for
>> >> peer discovery within one's home network / LAN / WiFi network, not over
>> >> a cable network.
>> >>
>> >>
>> >> >So, were clients allowed to become seeders to the outside of Comcast's
>> >> network?
>> >>
>> >> Yes, they were.
>> >>
>> >> As a related item, look closely at section 4.2. The amount of aggregate
>> >> uploaded data from Comcast clients (per swarm) was about 140,000 MB.
>> >> The
>> >> amount of aggregate downloaded data from Comcast clients (per swarm)
>> >> was
>> >> about 60,000 MB or so. So the typical Comcast client uploaded more than
>> >> twice the amount of data that it downloaded.
>> >>
>> >>
>> >> >How much of the swarm was within Comcast and outside?
>> >>
>> >> Most of the swarm was outside of Comcast. Unfortunately I don't have
>> >> access to the size of the global swarm, but I would guess that Comcast
>> >> clients represented no more than 15% of the swarm, and maybe as little
>> >> as 5%. Those guesses are based on the behavior of the random swarm,
>> >> e.g.
>> >> Comcast clients uploaded to non-Comcast clients 94% of the time in the
>> >> random swarm.
>> >>
>> >> -- Rich
>> >>
>> >>
>> >> -----Original Message-----
>> >> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
>> >>
>> >> Reinaldo Penno
>> >> Sent: Wednesday, November 05, 2008 11:23 AM
>> >> To: Livingood, Jason; p2pi@ietf.org
>> >> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>> >>
>> >> Hello Jason/Rich,
>> >>
>> >> This is such an interesting draft. I'm surprised there are no questions
>> >> about it. Maybe everybody else is part of P4P one way or another and
>> >> I'm
>> >> not
>> >> in the 'in' crowd (;-) so I have questions.
>> >>
>> >> * What was the file size in those experiments? Some post long ago said
>> >> the
>> >> file size in some P4P experiments was really small, as opposed to the
>> >> top
>> >> 100 torrents where the file size is ~1Gb. I was curious what is the
>> >> optimization payback in terms of download time for large files as
>> >> opposed
>> >> small files.
>> >>
>> >> * How long would it take to download the file in the three different
>> >> scenarios? I know that more consumed bandwidth in access might lead one
>> >> to
>> >> conclude that file was downloaded faster but I'm not sure this is a
>> >> straightforward conclusion.
>> >>
>> >> * Was the file already seeded in Comcast's network? More specifically,
>> >> how
>> >> was file propagation done? All clients started from scratch and had to
>> >> start
>> >> pulling the file from some other side of the world and then exchanging
>> >> pieces? This is mainly due to the discussion in 4.2.
>> >>
>> >> * Was PEX, DHT and others enabled in the clients?
>> >>
>> >> * Was local peer discovery enabled in the clients? BTW, can
>> >> broadcast/multicast peer discovery work in Cable networks?
>> >>
>> >> * If more clients finish downloading faster and become seeders you
>> >> would
>> >> think that for popular content Comcast's upstream bandwidth would
>> >> increase
>> >> due to the number of seeder in its network. So, were clients allowed to
>> >> become seeders to the outside of Comcast's network? How much of the
>> >> swarm
>> >> was within Comcast and outside?
>> >>
>> >> Thanks,
>> >>
>> >> Reinaldo
>> >>
>> >> On 11/3/08 12:49 PM, "Livingood, Jason"
>> >> <Jason_Livingood@cable.comcast.com>
>> >> wrote:
>> >>
>> >> > For some reason the URL was cut to two lines - trying again:
>> >> >
>> >> >
>> >>
>> >> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
>> >> > es-02.txt
>> >> >
>> >> >
>> >> >
>> >> >> -----Original Message-----
>> >> >> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
>> >> >> Behalf Of Livingood, Jason
>> >> >> Sent: Monday, November 03, 2008 3:35 PM
>> >> >> To: p2pi@ietf.org
>> >> >> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>> >> >>
>> >> >> A draft at
>> >> >> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
>> >> >> -experienc
>> >> >> es-02.txt may be of interest to folks that have been
>> >> >> interested in P2Pi and ALTO.  We have requested time on the
>> >> >> ALTO agenda at IETF 73 to present this.
>> >> >>
>> >> >> Regards
>> >> >> Jason
>> >> >> _______________________________________________
>> >> >> p2pi mailing list
>> >> >> p2pi@ietf.org
>> >> >> https://www.ietf.org/mailman/listinfo/p2pi
>> >> >>
>> >> > _______________________________________________
>> >> > p2pi mailing list
>> >> > p2pi@ietf.org
>> >> > https://www.ietf.org/mailman/listinfo/p2pi
>> >>
>> >> _______________________________________________
>> >> p2pi mailing list
>> >> p2pi@ietf.org
>> >> https://www.ietf.org/mailman/listinfo/p2pi
>> >> _______________________________________________
>> >> p2pi mailing list
>> >> p2pi@ietf.org
>> >> https://www.ietf.org/mailman/listinfo/p2pi
>> >>
>> >>
>> >>
>> >>
>> >> --
>> >> Robb Topolski (robb@funchords.com)
>> >> Hillsboro, Oregon USA
>> >> http://www.funchords.com/
>> >>
>> >> _______________________________________________ p2pi mailing list
>> >> p2pi@ietf.org https://www.ietf.org/mailman/listinfo/p2pi
>> >>
>> >>
>> >_______________________________________________
>> >p2pi mailing list
>> >p2pi@ietf.org
>> >https://www.ietf.org/mailman/listinfo/p2pi
>>
>> _______________________________________________
>> p2pi mailing list
>> p2pi@ietf.org
>> https://www.ietf.org/mailman/listinfo/p2pi
>
>
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi
>
>



-- 
Robb Topolski (robb@funchords.com)
Hillsboro, Oregon USA
http://www.funchords.com/
_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Sun Nov  9 13:58:09 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 3CBDA3A6891;
	Sun,  9 Nov 2008 13:58:09 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 622363A6891
	for <p2pi@core3.amsl.com>; Sun,  9 Nov 2008 13:58:07 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -4.185
X-Spam-Level: 
X-Spam-Status: No, score=-4.185 tagged_above=-999 required=5
	tests=[BAYES_40=-0.185, RCVD_IN_DNSWL_MED=-4]
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 L6+3fn0hPT6z for <p2pi@core3.amsl.com>;
	Sun,  9 Nov 2008 13:58:05 -0800 (PST)
Received: from netra.cs.yale.edu (netra.cs.yale.edu [128.36.229.21])
	by core3.amsl.com (Postfix) with ESMTP id 22E513A6778
	for <p2pi@ietf.org>; Sun,  9 Nov 2008 13:58:05 -0800 (PST)
Received: from [127.0.0.1] (dhcp130132249171.its.yale.edu [130.132.249.171])
	by netra.cs.yale.edu (Postfix) with ESMTP id 10506409471;
	Sun,  9 Nov 2008 16:58:02 -0500 (EST)
Message-ID: <49175CCC.1010500@cs.yale.edu>
Date: Sun, 09 Nov 2008 16:57:32 -0500
From: "Y. Richard Yang" <yry@cs.yale.edu>
User-Agent: Thunderbird 2.0.0.17 (Windows/20080914)
MIME-Version: 1.0
To: Robb Topolski <robb@funchords.com>
References: <Pine.LNX.4.64.0811052100570.13140@cyndra.cs.yale.edu>	<005601c93fef$586864e0$0c0ca40a@china.huawei.com>	<2574b1d30811060834n71f43ca1q6c6c227d9479a1cf@mail.gmail.com>
	<3efc39a60811091306r5e76a90et1b4ae2cbddfd3f29@mail.gmail.com>
In-Reply-To: <3efc39a60811091306r5e76a90et1b4ae2cbddfd3f29@mail.gmail.com>
Cc: "p2pi@ietf.org" <p2pi@ietf.org>
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset="us-ascii"; Format="flowed"
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

Hi Robb,

Thanks for the excellent comments. Please see below.

Robb Topolski wrote:
> It seems like a broken statistic given this experiment.
>
> If it were tightly controlled (and thus less Internet-like), all of
> the downloads would have completed and the download byte amounts would
> be virtually the same.
>
>   
Welcome to the real world :-) Large-scale and yet tightly controlled 
experiments are hard to
conduct (if you have an idea or are interested in more discussion, it 
will be fantastic). We did
quite a few controlled experiments using clients on PlanetLab, but we 
could get a couple
hundred users if we were lucky. Neither may tightly controlled 
experiments be highly desirable,
because we would not know what we were missing then (your example of p2p 
streaming is
an excellent example). One objective of real experiments is unexpected 
discovery. Sometime
they are pleasant, and sometime they are not. Download abort was one 
unexpected. But given
the small fraction, I think it does not changes the reported results. 
For full disclosure, another
unexpected user behavior we discovered during our log processing was 
that users sometime paused
their download process (e.g. put the machines to sleep). We spent quite 
a lot of time on this issue.
Unfortunately the logs we had did not capture such events. We were 
careful to use statistically
more robust metrics (e.g., the download rates at different percentiles 
instead of the average). We
tried to check the impacts of such events. For example, we also computed 
statistics after filtering
to make sure our statistics did not change much. One filtering we did 
was that if a user had no
activity for too long (we tried two minutes and some other numbers), we 
flagged that the user
might have paused, and we ignored  that user's data. We did not see 
large change of the
statistics we computed before and after such filtering.

Of course, we learn from such experiences. In our current experiments, 
we are designing a new log
format to try to capture more events. We might be surprised again and go 
back to log more.
We will be happy to share and work with others on robust experiment 
design and statistics collection.
> One might argue that there is virtue to these observations because a
> downloader who cancels a slow download is a bad thing, because they
> ultimately did not get what they attempted to download.
>
> But is there virtue in an aborted download?  If they canceled the
> download in frustration or because they simply couldn't stay connected
> to the swarm long enough before being forced to quit by some other
> personal oe obligation, then one could say that an aborted download is
> a band thing. OTOH, an incomplete download is a good thing when a
> downloader may have changed his mind (wanted to hear/see/do something
> else) with less bandwidth wasted. There's just no way to know why the
> user aborted the download.
>
>   
I agree it will be fantastic if we can know the reason for an aborted 
download. One thought came to
mind immediately is a pop-up window after a download abort to ask the 
user for reason(s). I do not
know any P2P clients doing this right now and I am not sure how many 
users will respond (e.g. not click
cancel). But it is an excellent suggestion! We sure will talk to the P2P 
developers we are working with
to see if we can add such an option in one of our log plug-in.
> Even if we did know, this experiment doesn't deal with other possible
> P4P-advantaged uses such as streaming-P2P video delivery (a mode more
> prone to user "taste-testing" before completing a download than
> traditional file-transfer models).
>
>   
Absolutely good comment. This is why we are focusing on P2P streaming, 
where channel hopping is
a common user behavior (http://ccr.sigcomm.org/online/?q=node/404), and 
startup delay is a major
performance metric.

Hope to hear more such good comments!

Richard
> Robb
>
> 2008/11/6 Ye WANG <wangye.thu@gmail.com>:
>   
>> Hi Haibin,
>>
>> Yes, the Random swarm has notable smaller finished downloads than Generic or
>> Coarse Grained during the period.
>>
>> Since the swarm sizes (# downloading peers) are roughly equal across all
>> five swarms (Richard explained this in details), we suspect that a portion
>> of slow peers terminate/discard their downloads.  This is almost the same
>> hypothesis pointed out by Rich Woundy.
>>
>> Another evidence is we do notice significantly slower peers in Random swarm,
>> e.g., the slowest Random peer took 7268s (>2hours) to download the video,
>> but the slowest Generic took 2725s (<1hour), the slowest Corase Grained took
>> 3114s (<1hour).   Hours of downloading may make users impatient.  If the
>> "tail" peers in Random swarm could suffer much lower download rates,
>> presumably, the number of "terminated" peers may be larger in Random swarm.
>>
>> On Thu, Nov 6, 2008 at 4:09 AM, Song Haibin <melodysong@huawei.com> wrote:
>>     
>>> Hi Richard and all,
>>>
>>>       
>>>> The access download of each swarm should be equal to the sum of those
>>>> downloaded by the clients in each swarm. So if the number of downloads in
>>>> each swarm is the same and the amount downloaded is the same, then each
>>>> swarm should have the same access download.
>>>>         
>>> Song Haibin: From section 4.1, we can see that "The results of the trial
>>> indicated that P4P can improve the speed of downloads to P2P clients", so
>>> if
>>> the statistics data is collected during a certain period (from July 2 to
>>> July 17, 2008), then the download will be increased than the random swarm.
>>> I
>>> don't think each swarm has downloaded the same amount of chunk files
>>> during
>>> the statistic period.
>>>       
>>     
>>> Best Regards,
>>> Song Haibin
>>> Email: melodysong@huawei.com
>>> Skype: alexsonghw
>>>
>>>
>>>
>>>       
>>>> -----Original Message-----
>>>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
>>>> Y.
>>>>         
>>> R.
>>>       
>>>> Yang
>>>> Sent: Thursday, November 06, 2008 10:40 AM
>>>> To: Woundy, Richard
>>>> Cc: p2pi@ietf.org; Livingood, Jason
>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>
>>>>
>>>> Hi Rich and others,
>>>>
>>>> The access download of each swarm should be equal to the sum of those
>>>> downloaded by the clients in each swarm. So if the number of downloads in
>>>> each swarm is the same and the amount downloaded is the same, then each
>>>> swarm should have the same access download.
>>>>
>>>> First look at the amount downloaded. There are can be some differences
>>>> due
>>>> to duplicated chunks and the way we detected data chunks (there are also
>>>> control data in the logs), but the difference appears to be small.
>>>>
>>>> Now let's look at the number of downloads. During the test, each client
>>>> is
>>>> uniformly assigned to a swarm. Given the large number of clients, each
>>>> swarm should have about the same number of clients. But there can be two
>>>> factors for us to see different numbers of *reported* downloads: (1) some
>>>> clients are old and may not report or the reporting of logs was not
>>>> successful; and (2) different # of clients finished downloading (if a
>>>> client does not finish downloading, it does not report. Laird, please
>>>> correct me if I am wrong). I belive the first factor should be small due
>>>> to uniform random assignment of peers to swarms.
>>>>
>>>> I just looked at the data available. We did detect a smaller number of
>>>> finished download with Random than with the P4P swarms. For example, from
>>>> July 3 to July 10, detected # of finished download of Generic is about 5%
>>>> more than than Random, and Coarse is 7% more than Random. From July 10 to
>>>> July 17, Generic is 10.5% more than Random, and Coarse is 4.7% more.
>>>> Looking at the traffic volume at Section 4.2, I see that Generic is about
>>>> 7% higher, and Coarse is about 8.5% higher. Note that # of finished
>>>> download and volume are different due to duplicated chunks and missing
>>>> logs.
>>>>
>>>> So I would like to support the theory/guess of Rich that some users
>>>> terminated the download prematurally and faster downloads may result in
>>>> fewer such terminations. But it may also include factors in (1)
>>>> differences in initial assignment due to random numbers; and (2) # of
>>>> finished but non-reporting clients.
>>>>
>>>> If you have any other suggestions, we will be more than happy to look
>>>> into
>>>> the available data more.
>>>>
>>>> Richard
>>>>
>>>> On Wed, 5 Nov 2008, 6:26pm -0500, Woundy, Richard wrote:
>>>>
>>>>         
>>>>> My current theory/guess is that some users may terminated the download
>>>>> prematurely, eg due to user impatience. So faster downloads (e.g.
>>>>> thanks
>>>>> to P4P) may result in fewer user terminations.
>>>>>
>>>>>
>>>>>
>>>>> Laird is checking the data to see if we can confirm that, or find
>>>>> another explanation.
>>>>>
>>>>>
>>>>>
>>>>> -- Rich
>>>>>
>>>>>
>>>>>
>>>>> ________________________________
>>>>>
>>>>> From: Laird Popkin [mailto:laird@pando.com]
>>>>> Sent: Wednesday, November 05, 2008 6:12 PM
>>>>> To: Robb Topolski
>>>>> Cc: Livingood, Jason; p2pi@ietf.org; Woundy, Richard
>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>
>>>>>
>>>>>
>>>>> That's a good question, and Richard and I spoke about this yesterday.
>>>>> I'll be looking into the data to see what the cause is.
>>>>>
>>>>> - Laird Popkin, CTO, Pando Networks
>>>>>   mobile: 646/465-0570
>>>>>
>>>>> ----- Original Message -----
>>>>> From: "Robb Topolski" <robb@funchords.com>
>>>>> To: "Richard Woundy" <Richard_Woundy@cable.comcast.com>
>>>>> Cc: "Jason Livingood" <Jason_Livingood@cable.comcast.com>,
>>>>> p2pi@ietf.org
>>>>> Sent: Wednesday, November 5, 2008 5:42:51 PM (GMT-0500)
>>>>> America/New_York
>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>
>>>>> I don't get the part where access network download consumption
>>>>> increased
>>>>> as a result of using P4P (section 4.2).  Can someone explain how that
>>>>> could happen?
>>>>>
>>>>> Robb
>>>>>
>>>>> On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard
>>>>> <Richard_Woundy@cable.comcast.com> wrote:
>>>>>
>>>>> Reinaldo,
>>>>>
>>>>> I can answer the easy questions. We will need some assistance from
>>>>> Pando
>>>>> (and Yale) for some of the other ones.
>>>>>
>>>>>
>>>>>           
>>>>>> What was the file size in those experiments?
>>>>>>             
>>>>> 21 megabytes. From section 2: "Pando distributed a special 21 MB
>>>>> licensed video file as in order to measure the effectiveness of P4P
>>>>> iTrackers."
>>>>>
>>>>>
>>>>>           
>>>>>> How long would it take to download the file in the three different
>>>>>>             
>>>>> scenarios? I know that more consumed bandwidth in access might lead one
>>>>>
>>>>> to conclude that file was downloaded faster...
>>>>>
>>>>> To clarify, most of the raw data (download speed and Internet
>>>>> peering/transit traffic volumes) were collected by Pando Networks from
>>>>> their P2P clients, not collected by Comcast across its links. So my
>>>>> assumption is that the Pando client used the content size (21 MB), and
>>>>> divided by the download time to get the speed.
>>>>>
>>>>>
>>>>>           
>>>>>> Was the file already seeded in Comcast's network? More specifically,
>>>>>>             
>>>>> how
>>>>> was file propagation done?
>>>>>
>>>>> Any seeding happened outside of Comcast's network, and outside of
>>>>> Comcast's control. That's really a question for Pando.
>>>>>
>>>>>
>>>>>           
>>>>>> Was PEX, DHT and others enabled in the clients?
>>>>>>             
>>>>> Pando would know whether PEX was enabled. It would be safe to assume
>>>>> that with respect to this trial, DHT was NOT enabled, since Pando
>>>>> supplied the tracker. (The pTracker in the draft is a tracker operated
>>>>> by Pando.)
>>>>>
>>>>>
>>>>>           
>>>>>> Was local peer discovery enabled in the clients?
>>>>>>             
>>>>> Pando would know.
>>>>>
>>>>>
>>>>>           
>>>>>> BTW, can broadcast/multicast peer discovery work in Cable networks?
>>>>>>             
>>>>> Do you mean something like this:
>>>>> http://bittorrent.org/beps/bep_0026.html?
>>>>>
>>>>> If so, peer discovery probably would not work over the typical last
>>>>> mile
>>>>> cable network. Maybe I'm wrong, but I see this protocol as intended for
>>>>> peer discovery within one's home network / LAN / WiFi network, not over
>>>>> a cable network.
>>>>>
>>>>>
>>>>>           
>>>>>> So, were clients allowed to become seeders to the outside of Comcast's
>>>>>>             
>>>>> network?
>>>>>
>>>>> Yes, they were.
>>>>>
>>>>> As a related item, look closely at section 4.2. The amount of aggregate
>>>>> uploaded data from Comcast clients (per swarm) was about 140,000 MB.
>>>>> The
>>>>> amount of aggregate downloaded data from Comcast clients (per swarm)
>>>>> was
>>>>> about 60,000 MB or so. So the typical Comcast client uploaded more than
>>>>> twice the amount of data that it downloaded.
>>>>>
>>>>>
>>>>>           
>>>>>> How much of the swarm was within Comcast and outside?
>>>>>>             
>>>>> Most of the swarm was outside of Comcast. Unfortunately I don't have
>>>>> access to the size of the global swarm, but I would guess that Comcast
>>>>> clients represented no more than 15% of the swarm, and maybe as little
>>>>> as 5%. Those guesses are based on the behavior of the random swarm,
>>>>> e.g.
>>>>> Comcast clients uploaded to non-Comcast clients 94% of the time in the
>>>>> random swarm.
>>>>>
>>>>> -- Rich
>>>>>
>>>>>
>>>>> -----Original Message-----
>>>>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
>>>>>
>>>>> Reinaldo Penno
>>>>> Sent: Wednesday, November 05, 2008 11:23 AM
>>>>> To: Livingood, Jason; p2pi@ietf.org
>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>
>>>>> Hello Jason/Rich,
>>>>>
>>>>> This is such an interesting draft. I'm surprised there are no questions
>>>>> about it. Maybe everybody else is part of P4P one way or another and
>>>>> I'm
>>>>> not
>>>>> in the 'in' crowd (;-) so I have questions.
>>>>>
>>>>> * What was the file size in those experiments? Some post long ago said
>>>>> the
>>>>> file size in some P4P experiments was really small, as opposed to the
>>>>> top
>>>>> 100 torrents where the file size is ~1Gb. I was curious what is the
>>>>> optimization payback in terms of download time for large files as
>>>>> opposed
>>>>> small files.
>>>>>
>>>>> * How long would it take to download the file in the three different
>>>>> scenarios? I know that more consumed bandwidth in access might lead one
>>>>> to
>>>>> conclude that file was downloaded faster but I'm not sure this is a
>>>>> straightforward conclusion.
>>>>>
>>>>> * Was the file already seeded in Comcast's network? More specifically,
>>>>> how
>>>>> was file propagation done? All clients started from scratch and had to
>>>>> start
>>>>> pulling the file from some other side of the world and then exchanging
>>>>> pieces? This is mainly due to the discussion in 4.2.
>>>>>
>>>>> * Was PEX, DHT and others enabled in the clients?
>>>>>
>>>>> * Was local peer discovery enabled in the clients? BTW, can
>>>>> broadcast/multicast peer discovery work in Cable networks?
>>>>>
>>>>> * If more clients finish downloading faster and become seeders you
>>>>> would
>>>>> think that for popular content Comcast's upstream bandwidth would
>>>>> increase
>>>>> due to the number of seeder in its network. So, were clients allowed to
>>>>> become seeders to the outside of Comcast's network? How much of the
>>>>> swarm
>>>>> was within Comcast and outside?
>>>>>
>>>>> Thanks,
>>>>>
>>>>> Reinaldo
>>>>>
>>>>> On 11/3/08 12:49 PM, "Livingood, Jason"
>>>>> <Jason_Livingood@cable.comcast.com>
>>>>> wrote:
>>>>>
>>>>>           
>>>>>> For some reason the URL was cut to two lines - trying again:
>>>>>>
>>>>>>
>>>>>>             
>>>>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
>>>>>           
>>>>>> es-02.txt
>>>>>>
>>>>>>
>>>>>>
>>>>>>             
>>>>>>> -----Original Message-----
>>>>>>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
>>>>>>> Behalf Of Livingood, Jason
>>>>>>> Sent: Monday, November 03, 2008 3:35 PM
>>>>>>> To: p2pi@ietf.org
>>>>>>> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>>>
>>>>>>> A draft at
>>>>>>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
>>>>>>> -experienc
>>>>>>> es-02.txt may be of interest to folks that have been
>>>>>>> interested in P2Pi and ALTO.  We have requested time on the
>>>>>>> ALTO agenda at IETF 73 to present this.
>>>>>>>
>>>>>>> Regards
>>>>>>> Jason
>>>>>>> _______________________________________________
>>>>>>> p2pi mailing list
>>>>>>> p2pi@ietf.org
>>>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>>>
>>>>>>>               
>>>>>> _______________________________________________
>>>>>> p2pi mailing list
>>>>>> p2pi@ietf.org
>>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>>             
>>>>> _______________________________________________
>>>>> p2pi mailing list
>>>>> p2pi@ietf.org
>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>> _______________________________________________
>>>>> p2pi mailing list
>>>>> p2pi@ietf.org
>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>
>>>>>
>>>>>
>>>>>
>>>>> --
>>>>> Robb Topolski (robb@funchords.com)
>>>>> Hillsboro, Oregon USA
>>>>> http://www.funchords.com/
>>>>>
>>>>> _______________________________________________ p2pi mailing list
>>>>> p2pi@ietf.org https://www.ietf.org/mailman/listinfo/p2pi
>>>>>
>>>>>
>>>>>           
>>>> _______________________________________________
>>>> p2pi mailing list
>>>> p2pi@ietf.org
>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>         
>>> _______________________________________________
>>> p2pi mailing list
>>> p2pi@ietf.org
>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>       
>> _______________________________________________
>> p2pi mailing list
>> p2pi@ietf.org
>> https://www.ietf.org/mailman/listinfo/p2pi
>>
>>
>>     
>
>
>
>   


_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Sun Nov  9 19:40:27 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 4D6343A689F;
	Sun,  9 Nov 2008 19:40:27 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 5FCF23A6803
	for <p2pi@core3.amsl.com>; Sun,  9 Nov 2008 19:40:26 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -10.265
X-Spam-Level: 
X-Spam-Status: No, score=-10.265 tagged_above=-999 required=5
	tests=[AWL=0.000, BAYES_00=-2.599, HABEAS_ACCREDITED_COI=-8,
	IP_NOT_FRIENDLY=0.334]
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 oiNM46Szkk6D for <p2pi@core3.amsl.com>;
	Sun,  9 Nov 2008 19:40:24 -0800 (PST)
Received: from dkny.pando.com (dkny.pando.com [67.99.55.163])
	by core3.amsl.com (Postfix) with ESMTP id DC7703A689F
	for <p2pi@ietf.org>; Sun,  9 Nov 2008 19:40:23 -0800 (PST)
Received: from localhost (localhost.localdomain [127.0.0.1])
	by dkny.pando.com (Postfix) with ESMTP id 32C86E10AA5;
	Sun,  9 Nov 2008 22:40:16 -0500 (EST)
X-Virus-Scanned: amavisd-new at 
Received: from dkny.pando.com ([127.0.0.1])
	by localhost (dkny.pando.com [127.0.0.1]) (amavisd-new, port 10024)
	with ESMTP id 1EoV+-Biljsg; Sun,  9 Nov 2008 22:39:58 -0500 (EST)
Received: from dkny.pando.com (dkny.pando.com [10.10.60.11])
	by dkny.pando.com (Postfix) with ESMTP id F1741E10CFD;
	Sun,  9 Nov 2008 22:39:57 -0500 (EST)
Date: Sun, 9 Nov 2008 22:39:57 -0500 (EST)
From: Laird Popkin <laird@pando.com>
To: "Y. Richard Yang" <yry@cs.yale.edu>
Message-ID: <131331900.83471226288397931.JavaMail.root@dkny.pando.com>
In-Reply-To: <1967859877.83451226287789308.JavaMail.root@dkny.pando.com>
MIME-Version: 1.0
X-Originating-IP: [71.187.59.213]
Cc: p2pi@ietf.org
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

To explain a bit of the test methodology, downloaders were globally distributed, and every downloader was assigned randomly to one of the five swarms at the time that they started the download. The result of this is that while there were quite comparable numbers of downloaders in each swarm globally, the number of downloaders within a given ISP for each swarm has random variation. For example, one ISP might have a few percent more downloaders of the 'random' swarm while another ISP might have a few percent more downloaders of the 'P4P generic weight matrix' swarm. As with any statistical analysis of real world data, you should expect some random variation based on sample size. In particular, within Comcast there happened to be a few percent more 'random' downloaders than for the guided swarms.

Looking at the numbers of downloads and their completion rates, all of the swarms had completion rates that were extremely high, with the guided (P4P and PNA) having a higher completion rate (about 98%) and the unguided (random) downloads having a slightly lower completion rate (about 97%).

The standard technique for addressing random samples is to look at percentages rather than absolute values. That is, instead of looking at the number of bytes downloaded for each swarm from external sources (for example), it's better to compare the percentage of data downloaded that came from external sources. It's not particularly meaningful that one swarm was downloaded with one ISP a few percent more than another, but comparing cancellation rates, or ratio of internal to external data download volumes, is rather illuminating.

- Laird Popkin, CTO, Pando Networks
  mobile: 646/465-0570

----- Original Message -----
From: "Y. Richard Yang" <yry@cs.yale.edu>
To: "Robb Topolski" <robb@funchords.com>
Cc: p2pi@ietf.org
Sent: Sunday, November 9, 2008 4:57:32 PM (GMT-0500) America/New_York
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted

Hi Robb,

Thanks for the excellent comments. Please see below.

Robb Topolski wrote:
> It seems like a broken statistic given this experiment.
>
> If it were tightly controlled (and thus less Internet-like), all of
> the downloads would have completed and the download byte amounts would
> be virtually the same.
>
>   
Welcome to the real world :-) Large-scale and yet tightly controlled 
experiments are hard to
conduct (if you have an idea or are interested in more discussion, it 
will be fantastic). We did
quite a few controlled experiments using clients on PlanetLab, but we 
could get a couple
hundred users if we were lucky. Neither may tightly controlled 
experiments be highly desirable,
because we would not know what we were missing then (your example of p2p 
streaming is
an excellent example). One objective of real experiments is unexpected 
discovery. Sometime
they are pleasant, and sometime they are not. Download abort was one 
unexpected. But given
the small fraction, I think it does not changes the reported results. 
For full disclosure, another
unexpected user behavior we discovered during our log processing was 
that users sometime paused
their download process (e.g. put the machines to sleep). We spent quite 
a lot of time on this issue.
Unfortunately the logs we had did not capture such events. We were 
careful to use statistically
more robust metrics (e.g., the download rates at different percentiles 
instead of the average). We
tried to check the impacts of such events. For example, we also computed 
statistics after filtering
to make sure our statistics did not change much. One filtering we did 
was that if a user had no
activity for too long (we tried two minutes and some other numbers), we 
flagged that the user
might have paused, and we ignored  that user's data. We did not see 
large change of the
statistics we computed before and after such filtering.

Of course, we learn from such experiences. In our current experiments, 
we are designing a new log
format to try to capture more events. We might be surprised again and go 
back to log more.
We will be happy to share and work with others on robust experiment 
design and statistics collection.
> One might argue that there is virtue to these observations because a
> downloader who cancels a slow download is a bad thing, because they
> ultimately did not get what they attempted to download.
>
> But is there virtue in an aborted download?  If they canceled the
> download in frustration or because they simply couldn't stay connected
> to the swarm long enough before being forced to quit by some other
> personal oe obligation, then one could say that an aborted download is
> a band thing. OTOH, an incomplete download is a good thing when a
> downloader may have changed his mind (wanted to hear/see/do something
> else) with less bandwidth wasted. There's just no way to know why the
> user aborted the download.
>
>   
I agree it will be fantastic if we can know the reason for an aborted 
download. One thought came to
mind immediately is a pop-up window after a download abort to ask the 
user for reason(s). I do not
know any P2P clients doing this right now and I am not sure how many 
users will respond (e.g. not click
cancel). But it is an excellent suggestion! We sure will talk to the P2P 
developers we are working with
to see if we can add such an option in one of our log plug-in.
> Even if we did know, this experiment doesn't deal with other possible
> P4P-advantaged uses such as streaming-P2P video delivery (a mode more
> prone to user "taste-testing" before completing a download than
> traditional file-transfer models).
>
>   
Absolutely good comment. This is why we are focusing on P2P streaming, 
where channel hopping is
a common user behavior (http://ccr.sigcomm.org/online/?q=node/404), and 
startup delay is a major
performance metric.

Hope to hear more such good comments!

Richard
> Robb
>
> 2008/11/6 Ye WANG <wangye.thu@gmail.com>:
>   
>> Hi Haibin,
>>
>> Yes, the Random swarm has notable smaller finished downloads than Generic or
>> Coarse Grained during the period.
>>
>> Since the swarm sizes (# downloading peers) are roughly equal across all
>> five swarms (Richard explained this in details), we suspect that a portion
>> of slow peers terminate/discard their downloads.  This is almost the same
>> hypothesis pointed out by Rich Woundy.
>>
>> Another evidence is we do notice significantly slower peers in Random swarm,
>> e.g., the slowest Random peer took 7268s (>2hours) to download the video,
>> but the slowest Generic took 2725s (<1hour), the slowest Corase Grained took
>> 3114s (<1hour).   Hours of downloading may make users impatient.  If the
>> "tail" peers in Random swarm could suffer much lower download rates,
>> presumably, the number of "terminated" peers may be larger in Random swarm.
>>
>> On Thu, Nov 6, 2008 at 4:09 AM, Song Haibin <melodysong@huawei.com> wrote:
>>     
>>> Hi Richard and all,
>>>
>>>       
>>>> The access download of each swarm should be equal to the sum of those
>>>> downloaded by the clients in each swarm. So if the number of downloads in
>>>> each swarm is the same and the amount downloaded is the same, then each
>>>> swarm should have the same access download.
>>>>         
>>> Song Haibin: From section 4.1, we can see that "The results of the trial
>>> indicated that P4P can improve the speed of downloads to P2P clients", so
>>> if
>>> the statistics data is collected during a certain period (from July 2 to
>>> July 17, 2008), then the download will be increased than the random swarm.
>>> I
>>> don't think each swarm has downloaded the same amount of chunk files
>>> during
>>> the statistic period.
>>>       
>>     
>>> Best Regards,
>>> Song Haibin
>>> Email: melodysong@huawei.com
>>> Skype: alexsonghw
>>>
>>>
>>>
>>>       
>>>> -----Original Message-----
>>>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
>>>> Y.
>>>>         
>>> R.
>>>       
>>>> Yang
>>>> Sent: Thursday, November 06, 2008 10:40 AM
>>>> To: Woundy, Richard
>>>> Cc: p2pi@ietf.org; Livingood, Jason
>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>
>>>>
>>>> Hi Rich and others,
>>>>
>>>> The access download of each swarm should be equal to the sum of those
>>>> downloaded by the clients in each swarm. So if the number of downloads in
>>>> each swarm is the same and the amount downloaded is the same, then each
>>>> swarm should have the same access download.
>>>>
>>>> First look at the amount downloaded. There are can be some differences
>>>> due
>>>> to duplicated chunks and the way we detected data chunks (there are also
>>>> control data in the logs), but the difference appears to be small.
>>>>
>>>> Now let's look at the number of downloads. During the test, each client
>>>> is
>>>> uniformly assigned to a swarm. Given the large number of clients, each
>>>> swarm should have about the same number of clients. But there can be two
>>>> factors for us to see different numbers of *reported* downloads: (1) some
>>>> clients are old and may not report or the reporting of logs was not
>>>> successful; and (2) different # of clients finished downloading (if a
>>>> client does not finish downloading, it does not report. Laird, please
>>>> correct me if I am wrong). I belive the first factor should be small due
>>>> to uniform random assignment of peers to swarms.
>>>>
>>>> I just looked at the data available. We did detect a smaller number of
>>>> finished download with Random than with the P4P swarms. For example, from
>>>> July 3 to July 10, detected # of finished download of Generic is about 5%
>>>> more than than Random, and Coarse is 7% more than Random. From July 10 to
>>>> July 17, Generic is 10.5% more than Random, and Coarse is 4.7% more.
>>>> Looking at the traffic volume at Section 4.2, I see that Generic is about
>>>> 7% higher, and Coarse is about 8.5% higher. Note that # of finished
>>>> download and volume are different due to duplicated chunks and missing
>>>> logs.
>>>>
>>>> So I would like to support the theory/guess of Rich that some users
>>>> terminated the download prematurally and faster downloads may result in
>>>> fewer such terminations. But it may also include factors in (1)
>>>> differences in initial assignment due to random numbers; and (2) # of
>>>> finished but non-reporting clients.
>>>>
>>>> If you have any other suggestions, we will be more than happy to look
>>>> into
>>>> the available data more.
>>>>
>>>> Richard
>>>>
>>>> On Wed, 5 Nov 2008, 6:26pm -0500, Woundy, Richard wrote:
>>>>
>>>>         
>>>>> My current theory/guess is that some users may terminated the download
>>>>> prematurely, eg due to user impatience. So faster downloads (e.g.
>>>>> thanks
>>>>> to P4P) may result in fewer user terminations.
>>>>>
>>>>>
>>>>>
>>>>> Laird is checking the data to see if we can confirm that, or find
>>>>> another explanation.
>>>>>
>>>>>
>>>>>
>>>>> -- Rich
>>>>>
>>>>>
>>>>>
>>>>> ________________________________
>>>>>
>>>>> From: Laird Popkin [mailto:laird@pando.com]
>>>>> Sent: Wednesday, November 05, 2008 6:12 PM
>>>>> To: Robb Topolski
>>>>> Cc: Livingood, Jason; p2pi@ietf.org; Woundy, Richard
>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>
>>>>>
>>>>>
>>>>> That's a good question, and Richard and I spoke about this yesterday.
>>>>> I'll be looking into the data to see what the cause is.
>>>>>
>>>>> - Laird Popkin, CTO, Pando Networks
>>>>>   mobile: 646/465-0570
>>>>>
>>>>> ----- Original Message -----
>>>>> From: "Robb Topolski" <robb@funchords.com>
>>>>> To: "Richard Woundy" <Richard_Woundy@cable.comcast.com>
>>>>> Cc: "Jason Livingood" <Jason_Livingood@cable.comcast.com>,
>>>>> p2pi@ietf.org
>>>>> Sent: Wednesday, November 5, 2008 5:42:51 PM (GMT-0500)
>>>>> America/New_York
>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>
>>>>> I don't get the part where access network download consumption
>>>>> increased
>>>>> as a result of using P4P (section 4.2).  Can someone explain how that
>>>>> could happen?
>>>>>
>>>>> Robb
>>>>>
>>>>> On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard
>>>>> <Richard_Woundy@cable.comcast.com> wrote:
>>>>>
>>>>> Reinaldo,
>>>>>
>>>>> I can answer the easy questions. We will need some assistance from
>>>>> Pando
>>>>> (and Yale) for some of the other ones.
>>>>>
>>>>>
>>>>>           
>>>>>> What was the file size in those experiments?
>>>>>>             
>>>>> 21 megabytes. From section 2: "Pando distributed a special 21 MB
>>>>> licensed video file as in order to measure the effectiveness of P4P
>>>>> iTrackers."
>>>>>
>>>>>
>>>>>           
>>>>>> How long would it take to download the file in the three different
>>>>>>             
>>>>> scenarios? I know that more consumed bandwidth in access might lead one
>>>>>
>>>>> to conclude that file was downloaded faster...
>>>>>
>>>>> To clarify, most of the raw data (download speed and Internet
>>>>> peering/transit traffic volumes) were collected by Pando Networks from
>>>>> their P2P clients, not collected by Comcast across its links. So my
>>>>> assumption is that the Pando client used the content size (21 MB), and
>>>>> divided by the download time to get the speed.
>>>>>
>>>>>
>>>>>           
>>>>>> Was the file already seeded in Comcast's network? More specifically,
>>>>>>             
>>>>> how
>>>>> was file propagation done?
>>>>>
>>>>> Any seeding happened outside of Comcast's network, and outside of
>>>>> Comcast's control. That's really a question for Pando.
>>>>>
>>>>>
>>>>>           
>>>>>> Was PEX, DHT and others enabled in the clients?
>>>>>>             
>>>>> Pando would know whether PEX was enabled. It would be safe to assume
>>>>> that with respect to this trial, DHT was NOT enabled, since Pando
>>>>> supplied the tracker. (The pTracker in the draft is a tracker operated
>>>>> by Pando.)
>>>>>
>>>>>
>>>>>           
>>>>>> Was local peer discovery enabled in the clients?
>>>>>>             
>>>>> Pando would know.
>>>>>
>>>>>
>>>>>           
>>>>>> BTW, can broadcast/multicast peer discovery work in Cable networks?
>>>>>>             
>>>>> Do you mean something like this:
>>>>> http://bittorrent.org/beps/bep_0026.html?
>>>>>
>>>>> If so, peer discovery probably would not work over the typical last
>>>>> mile
>>>>> cable network. Maybe I'm wrong, but I see this protocol as intended for
>>>>> peer discovery within one's home network / LAN / WiFi network, not over
>>>>> a cable network.
>>>>>
>>>>>
>>>>>           
>>>>>> So, were clients allowed to become seeders to the outside of Comcast's
>>>>>>             
>>>>> network?
>>>>>
>>>>> Yes, they were.
>>>>>
>>>>> As a related item, look closely at section 4.2. The amount of aggregate
>>>>> uploaded data from Comcast clients (per swarm) was about 140,000 MB.
>>>>> The
>>>>> amount of aggregate downloaded data from Comcast clients (per swarm)
>>>>> was
>>>>> about 60,000 MB or so. So the typical Comcast client uploaded more than
>>>>> twice the amount of data that it downloaded.
>>>>>
>>>>>
>>>>>           
>>>>>> How much of the swarm was within Comcast and outside?
>>>>>>             
>>>>> Most of the swarm was outside of Comcast. Unfortunately I don't have
>>>>> access to the size of the global swarm, but I would guess that Comcast
>>>>> clients represented no more than 15% of the swarm, and maybe as little
>>>>> as 5%. Those guesses are based on the behavior of the random swarm,
>>>>> e.g.
>>>>> Comcast clients uploaded to non-Comcast clients 94% of the time in the
>>>>> random swarm.
>>>>>
>>>>> -- Rich
>>>>>
>>>>>
>>>>> -----Original Message-----
>>>>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
>>>>>
>>>>> Reinaldo Penno
>>>>> Sent: Wednesday, November 05, 2008 11:23 AM
>>>>> To: Livingood, Jason; p2pi@ietf.org
>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>
>>>>> Hello Jason/Rich,
>>>>>
>>>>> This is such an interesting draft. I'm surprised there are no questions
>>>>> about it. Maybe everybody else is part of P4P one way or another and
>>>>> I'm
>>>>> not
>>>>> in the 'in' crowd (;-) so I have questions.
>>>>>
>>>>> * What was the file size in those experiments? Some post long ago said
>>>>> the
>>>>> file size in some P4P experiments was really small, as opposed to the
>>>>> top
>>>>> 100 torrents where the file size is ~1Gb. I was curious what is the
>>>>> optimization payback in terms of download time for large files as
>>>>> opposed
>>>>> small files.
>>>>>
>>>>> * How long would it take to download the file in the three different
>>>>> scenarios? I know that more consumed bandwidth in access might lead one
>>>>> to
>>>>> conclude that file was downloaded faster but I'm not sure this is a
>>>>> straightforward conclusion.
>>>>>
>>>>> * Was the file already seeded in Comcast's network? More specifically,
>>>>> how
>>>>> was file propagation done? All clients started from scratch and had to
>>>>> start
>>>>> pulling the file from some other side of the world and then exchanging
>>>>> pieces? This is mainly due to the discussion in 4.2.
>>>>>
>>>>> * Was PEX, DHT and others enabled in the clients?
>>>>>
>>>>> * Was local peer discovery enabled in the clients? BTW, can
>>>>> broadcast/multicast peer discovery work in Cable networks?
>>>>>
>>>>> * If more clients finish downloading faster and become seeders you
>>>>> would
>>>>> think that for popular content Comcast's upstream bandwidth would
>>>>> increase
>>>>> due to the number of seeder in its network. So, were clients allowed to
>>>>> become seeders to the outside of Comcast's network? How much of the
>>>>> swarm
>>>>> was within Comcast and outside?
>>>>>
>>>>> Thanks,
>>>>>
>>>>> Reinaldo
>>>>>
>>>>> On 11/3/08 12:49 PM, "Livingood, Jason"
>>>>> <Jason_Livingood@cable.comcast.com>
>>>>> wrote:
>>>>>
>>>>>           
>>>>>> For some reason the URL was cut to two lines - trying again:
>>>>>>
>>>>>>
>>>>>>             
>>>>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
>>>>>           
>>>>>> es-02.txt
>>>>>>
>>>>>>
>>>>>>
>>>>>>             
>>>>>>> -----Original Message-----
>>>>>>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
>>>>>>> Behalf Of Livingood, Jason
>>>>>>> Sent: Monday, November 03, 2008 3:35 PM
>>>>>>> To: p2pi@ietf.org
>>>>>>> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>>>
>>>>>>> A draft at
>>>>>>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
>>>>>>> -experienc
>>>>>>> es-02.txt may be of interest to folks that have been
>>>>>>> interested in P2Pi and ALTO.  We have requested time on the
>>>>>>> ALTO agenda at IETF 73 to present this.
>>>>>>>
>>>>>>> Regards
>>>>>>> Jason
>>>>>>> _______________________________________________
>>>>>>> p2pi mailing list
>>>>>>> p2pi@ietf.org
>>>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>>>
>>>>>>>               
>>>>>> _______________________________________________
>>>>>> p2pi mailing list
>>>>>> p2pi@ietf.org
>>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>>             
>>>>> _______________________________________________
>>>>> p2pi mailing list
>>>>> p2pi@ietf.org
>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>> _______________________________________________
>>>>> p2pi mailing list
>>>>> p2pi@ietf.org
>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>
>>>>>
>>>>>
>>>>>
>>>>> --
>>>>> Robb Topolski (robb@funchords.com)
>>>>> Hillsboro, Oregon USA
>>>>> http://www.funchords.com/
>>>>>
>>>>> _______________________________________________ p2pi mailing list
>>>>> p2pi@ietf.org https://www.ietf.org/mailman/listinfo/p2pi
>>>>>
>>>>>
>>>>>           
>>>> _______________________________________________
>>>> p2pi mailing list
>>>> p2pi@ietf.org
>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>         
>>> _______________________________________________
>>> p2pi mailing list
>>> p2pi@ietf.org
>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>       
>> _______________________________________________
>> p2pi mailing list
>> p2pi@ietf.org
>> https://www.ietf.org/mailman/listinfo/p2pi
>>
>>
>>     
>
>
>
>   


_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi
_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Sun Nov  9 19:47:16 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 9C1723A682E;
	Sun,  9 Nov 2008 19:47:16 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 556933A682E
	for <p2pi@core3.amsl.com>; Sun,  9 Nov 2008 19:47:15 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -10.265
X-Spam-Level: 
X-Spam-Status: No, score=-10.265 tagged_above=-999 required=5
	tests=[AWL=0.000, BAYES_00=-2.599, HABEAS_ACCREDITED_COI=-8,
	IP_NOT_FRIENDLY=0.334]
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 MZ3rUhnaYOdf for <p2pi@core3.amsl.com>;
	Sun,  9 Nov 2008 19:47:14 -0800 (PST)
Received: from dkny.pando.com (dkny.pando.com [67.99.55.163])
	by core3.amsl.com (Postfix) with ESMTP id 27E6A3A6803
	for <p2pi@ietf.org>; Sun,  9 Nov 2008 19:47:13 -0800 (PST)
Received: from localhost (localhost.localdomain [127.0.0.1])
	by dkny.pando.com (Postfix) with ESMTP id B3BCFE10DF0;
	Sun,  9 Nov 2008 22:47:09 -0500 (EST)
X-Virus-Scanned: amavisd-new at 
Received: from dkny.pando.com ([127.0.0.1])
	by localhost (dkny.pando.com [127.0.0.1]) (amavisd-new, port 10024)
	with ESMTP id vapHQPDTQ-3c; Sun,  9 Nov 2008 22:46:59 -0500 (EST)
Received: from dkny.pando.com (dkny.pando.com [10.10.60.11])
	by dkny.pando.com (Postfix) with ESMTP id 7A0B6E10BC4;
	Sun,  9 Nov 2008 22:46:59 -0500 (EST)
Date: Sun, 9 Nov 2008 22:46:59 -0500 (EST)
From: Laird Popkin <laird@pando.com>
To: "Y. R. Yang" <yry@cs.yale.edu>
Message-ID: <1809573662.83531226288819425.JavaMail.root@dkny.pando.com>
In-Reply-To: <Pine.LNX.4.64.0811052100570.13140@cyndra.cs.yale.edu>
MIME-Version: 1.0
X-Originating-IP: [71.187.59.213]
Cc: p2pi@ietf.org, Jason Livingood <Jason_Livingood@cable.comcast.com>,
	Richard Woundy <Richard_Woundy@cable.comcast.com>
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

To address one point "(if a client does not finish downloading, it does not report. Laird, please 
correct me if I am wrong)"

All downloads are reported, whether cancelled, paused, or completed. The three swarms had very high completion rates (97% for random, about 98% for the guided swarms).

- Laird Popkin, CTO, Pando Networks
  mobile: 646/465-0570

----- Original Message -----
From: "Y. R. Yang" <yry@cs.yale.edu>
To: "Richard Woundy" <Richard_Woundy@cable.comcast.com>
Cc: "Laird Popkin" <laird@pando.com>, "Robb Topolski" <robb@funchords.com>, p2pi@ietf.org, "Jason Livingood" <Jason_Livingood@cable.comcast.com>
Sent: Wednesday, November 5, 2008 9:40:15 PM (GMT-0500) America/New_York
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted


Hi Rich and others,

The access download of each swarm should be equal to the sum of those 
downloaded by the clients in each swarm. So if the number of downloads in 
each swarm is the same and the amount downloaded is the same, then each 
swarm should have the same access download.

First look at the amount downloaded. There are can be some differences due 
to duplicated chunks and the way we detected data chunks (there are also 
control data in the logs), but the difference appears to be small.

Now let's look at the number of downloads. During the test, each client is 
uniformly assigned to a swarm. Given the large number of clients, each 
swarm should have about the same number of clients. But there can be two 
factors for us to see different numbers of *reported* downloads: (1) some 
clients are old and may not report or the reporting of logs was not 
successful; and (2) different # of clients finished downloading (if a 
client does not finish downloading, it does not report. Laird, please 
correct me if I am wrong). I belive the first factor should be small due 
to uniform random assignment of peers to swarms.

I just looked at the data available. We did detect a smaller number of 
finished download with Random than with the P4P swarms. For example, from 
July 3 to July 10, detected # of finished download of Generic is about 5% 
more than than Random, and Coarse is 7% more than Random. From July 10 to 
July 17, Generic is 10.5% more than Random, and Coarse is 4.7% more. 
Looking at the traffic volume at Section 4.2, I see that Generic is about 
7% higher, and Coarse is about 8.5% higher. Note that # of finished 
download and volume are different due to duplicated chunks and missing 
logs.

So I would like to support the theory/guess of Rich that some users 
terminated the download prematurally and faster downloads may result in 
fewer such terminations. But it may also include factors in (1) 
differences in initial assignment due to random numbers; and (2) # of 
finished but non-reporting clients.

If you have any other suggestions, we will be more than happy to look into 
the available data more.

Richard

On Wed, 5 Nov 2008, 6:26pm -0500, Woundy, Richard wrote:

> My current theory/guess is that some users may terminated the download
> prematurely, eg due to user impatience. So faster downloads (e.g. thanks
> to P4P) may result in fewer user terminations.
> 
>  
> 
> Laird is checking the data to see if we can confirm that, or find
> another explanation.
> 
>  
> 
> -- Rich
> 
>  
> 
> ________________________________
> 
> From: Laird Popkin [mailto:laird@pando.com] 
> Sent: Wednesday, November 05, 2008 6:12 PM
> To: Robb Topolski
> Cc: Livingood, Jason; p2pi@ietf.org; Woundy, Richard
> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> 
>  
> 
> That's a good question, and Richard and I spoke about this yesterday.
> I'll be looking into the data to see what the cause is.
> 
> - Laird Popkin, CTO, Pando Networks
>   mobile: 646/465-0570
> 
> ----- Original Message -----
> From: "Robb Topolski" <robb@funchords.com>
> To: "Richard Woundy" <Richard_Woundy@cable.comcast.com>
> Cc: "Jason Livingood" <Jason_Livingood@cable.comcast.com>, p2pi@ietf.org
> Sent: Wednesday, November 5, 2008 5:42:51 PM (GMT-0500) America/New_York
> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> 
> I don't get the part where access network download consumption increased
> as a result of using P4P (section 4.2).  Can someone explain how that
> could happen?  
> 
> Robb
> 
> On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard
> <Richard_Woundy@cable.comcast.com> wrote:
> 
> Reinaldo,
> 
> I can answer the easy questions. We will need some assistance from Pando
> (and Yale) for some of the other ones.
> 
> 
> >What was the file size in those experiments?
> 
> 21 megabytes. From section 2: "Pando distributed a special 21 MB
> licensed video file as in order to measure the effectiveness of P4P
> iTrackers."
> 
> 
> >How long would it take to download the file in the three different
> scenarios? I know that more consumed bandwidth in access might lead one
> 
> to conclude that file was downloaded faster...
> 
> To clarify, most of the raw data (download speed and Internet
> peering/transit traffic volumes) were collected by Pando Networks from
> their P2P clients, not collected by Comcast across its links. So my
> assumption is that the Pando client used the content size (21 MB), and
> divided by the download time to get the speed.
> 
> 
> >Was the file already seeded in Comcast's network? More specifically,
> how
> was file propagation done?
> 
> Any seeding happened outside of Comcast's network, and outside of
> Comcast's control. That's really a question for Pando.
> 
> 
> >Was PEX, DHT and others enabled in the clients?
> 
> Pando would know whether PEX was enabled. It would be safe to assume
> that with respect to this trial, DHT was NOT enabled, since Pando
> supplied the tracker. (The pTracker in the draft is a tracker operated
> by Pando.)
> 
> 
> >Was local peer discovery enabled in the clients?
> 
> Pando would know.
> 
> 
> >BTW, can broadcast/multicast peer discovery work in Cable networks?
> 
> Do you mean something like this:
> http://bittorrent.org/beps/bep_0026.html?
> 
> If so, peer discovery probably would not work over the typical last mile
> cable network. Maybe I'm wrong, but I see this protocol as intended for
> peer discovery within one's home network / LAN / WiFi network, not over
> a cable network.
> 
> 
> >So, were clients allowed to become seeders to the outside of Comcast's
> network?
> 
> Yes, they were.
> 
> As a related item, look closely at section 4.2. The amount of aggregate
> uploaded data from Comcast clients (per swarm) was about 140,000 MB. The
> amount of aggregate downloaded data from Comcast clients (per swarm) was
> about 60,000 MB or so. So the typical Comcast client uploaded more than
> twice the amount of data that it downloaded.
> 
> 
> >How much of the swarm was within Comcast and outside?
> 
> Most of the swarm was outside of Comcast. Unfortunately I don't have
> access to the size of the global swarm, but I would guess that Comcast
> clients represented no more than 15% of the swarm, and maybe as little
> as 5%. Those guesses are based on the behavior of the random swarm, e.g.
> Comcast clients uploaded to non-Comcast clients 94% of the time in the
> random swarm.
> 
> -- Rich
> 
> 
> -----Original Message-----
> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
> 
> Reinaldo Penno
> Sent: Wednesday, November 05, 2008 11:23 AM
> To: Livingood, Jason; p2pi@ietf.org
> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> 
> Hello Jason/Rich,
> 
> This is such an interesting draft. I'm surprised there are no questions
> about it. Maybe everybody else is part of P4P one way or another and I'm
> not
> in the 'in' crowd (;-) so I have questions.
> 
> * What was the file size in those experiments? Some post long ago said
> the
> file size in some P4P experiments was really small, as opposed to the
> top
> 100 torrents where the file size is ~1Gb. I was curious what is the
> optimization payback in terms of download time for large files as
> opposed
> small files.
> 
> * How long would it take to download the file in the three different
> scenarios? I know that more consumed bandwidth in access might lead one
> to
> conclude that file was downloaded faster but I'm not sure this is a
> straightforward conclusion.
> 
> * Was the file already seeded in Comcast's network? More specifically,
> how
> was file propagation done? All clients started from scratch and had to
> start
> pulling the file from some other side of the world and then exchanging
> pieces? This is mainly due to the discussion in 4.2.
> 
> * Was PEX, DHT and others enabled in the clients?
> 
> * Was local peer discovery enabled in the clients? BTW, can
> broadcast/multicast peer discovery work in Cable networks?
> 
> * If more clients finish downloading faster and become seeders you would
> think that for popular content Comcast's upstream bandwidth would
> increase
> due to the number of seeder in its network. So, were clients allowed to
> become seeders to the outside of Comcast's network? How much of the
> swarm
> was within Comcast and outside?
> 
> Thanks,
> 
> Reinaldo
> 
> On 11/3/08 12:49 PM, "Livingood, Jason"
> <Jason_Livingood@cable.comcast.com>
> wrote:
> 
> > For some reason the URL was cut to two lines - trying again:
> >
> >
> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
> > es-02.txt
> >
> >
> >
> >> -----Original Message-----
> >> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
> >> Behalf Of Livingood, Jason
> >> Sent: Monday, November 03, 2008 3:35 PM
> >> To: p2pi@ietf.org
> >> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
> >>
> >> A draft at
> >> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
> >> -experienc
> >> es-02.txt may be of interest to folks that have been
> >> interested in P2Pi and ALTO.  We have requested time on the
> >> ALTO agenda at IETF 73 to present this.
> >>
> >> Regards
> >> Jason
> >> _______________________________________________
> >> p2pi mailing list
> >> p2pi@ietf.org
> >> https://www.ietf.org/mailman/listinfo/p2pi
> >>
> > _______________________________________________
> > p2pi mailing list
> > p2pi@ietf.org
> > https://www.ietf.org/mailman/listinfo/p2pi
> 
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi
> 
> 
> 
> 
> -- 
> Robb Topolski (robb@funchords.com)
> Hillsboro, Oregon USA
> http://www.funchords.com/
> 
> _______________________________________________ p2pi mailing list
> p2pi@ietf.org https://www.ietf.org/mailman/listinfo/p2pi 
> 
> 
_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Sun Nov  9 21:58:17 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id A9E8A3A6A19;
	Sun,  9 Nov 2008 21:58:17 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id D32583A6A19
	for <p2pi@core3.amsl.com>; Sun,  9 Nov 2008 21:58:15 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -5.392
X-Spam-Level: 
X-Spam-Status: No, score=-5.392 tagged_above=-999 required=5 tests=[AWL=1.207, 
	BAYES_00=-2.599, RCVD_IN_DNSWL_MED=-4]
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 8KO3NABUiMfb for <p2pi@core3.amsl.com>;
	Sun,  9 Nov 2008 21:58:13 -0800 (PST)
Received: from netra.cs.yale.edu (netra.cs.yale.edu [128.36.229.21])
	by core3.amsl.com (Postfix) with ESMTP id 9F26F3A694D
	for <p2pi@ietf.org>; Sun,  9 Nov 2008 21:58:12 -0800 (PST)
Received: from [127.0.0.1] (dhcp130132249176.its.yale.edu [130.132.249.176])
	by netra.cs.yale.edu (Postfix) with ESMTP id 7ACDF409525;
	Mon, 10 Nov 2008 00:58:08 -0500 (EST)
Message-ID: <4917CD55.1000906@cs.yale.edu>
Date: Mon, 10 Nov 2008 00:57:41 -0500
From: "Y. Richard Yang" <yry@cs.yale.edu>
User-Agent: Thunderbird 2.0.0.17 (Windows/20080914)
MIME-Version: 1.0
To: Laird Popkin <laird@pando.com>
References: <131331900.83471226288397931.JavaMail.root@dkny.pando.com>
In-Reply-To: <131331900.83471226288397931.JavaMail.root@dkny.pando.com>
Cc: p2pi@ietf.org
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset="us-ascii"; Format="flowed"
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

Hi All,
> To explain a bit of the test methodology, downloaders were globally distributed, and every downloader was assigned randomly to one of the five swarms at the time that they started the download. The result of this is that while there were quite comparable numbers of downloaders in each swarm globally, the number of downloaders within a given ISP for each swarm has random variation. For example, one ISP might have a few percent more downloaders of the 'random' swarm while another ISP might have a few percent more downloaders of the 'P4P generic weight matrix' swarm. As with any statistical analysis of real world data, you should expect some random variation based on sample size. In particular, within Comcast there happened to be a few percent more 'random' downloaders than for the guided swarms.
>
>   
To be more precise, I just did some analysis on if the random number 
generator did a good job in assigning downloaders to swarms. Consider 
the assignment of Comcast downloaders to different swarms. Let's focus 
on one particular swarm, say Generic. If uniform random assignment, a 
downloader from Comcast is assigned to Generic with probability 1/5. 
Define random variable X1 as an indicator that the first downloader from 
Comcast is assigned to Generic; X2 the second Comcast downloader is 
assigned to Generic, ...  Then:

Xi = 1 with prob. 1/5; 0 with prob. 4/5.

Define SN = X1 + X2 + ... + XN, where N is the number of downloaders 
from Comcast. Then SN is the number of Comcast downloaders assigned to 
Generic.

Applying Central Limit Theorem,

      SN - 1/5*N
z = ------------
      \sqrt(N) * 0.4

should follow Standard Normal Distribution.

I calculated the z scores for fine, coarse, generic, and random:

Z_fine = 0.69
Z_coarse = 1.27
Z_generic = -0.81
Z_random = -1.43

It looks that the assignment algorithm did a decent job in assigning 
downloaders from Comcast to the different swarms (the 95% confidence 
interval of Z is -1.96 to 1.96). Of course, the preceding is to give 
intuition, and we can write more rigorous statistical hypothesis 
testing. (BTW, there is a typo in the previous email, Random had the 
smallest number of downloaders from Comcast assigned to it.). We did 
observe higher cancellation rate by Random (3.17%) vs others 
(1.77%-2.22%), but this is just one sample. We can derive more samples 
by reprocessing the testing logs by days, calculating the cancellation 
rate during each day to obtain a series, and then conducting statistical 
testing to test if guided swarms have lower cancellation rate against 
the series of Random. But if the cancellation rate is of true interest, 
we may want to conduct more experiments to evaluate it.

Richard
> Looking at the numbers of downloads and their completion rates, all of the swarms had completion rates that were extremely high, with the guided (P4P and PNA) having a higher completion rate (about 98%) and the unguided (random) downloads having a slightly lower completion rate (about 97%).
>
> The standard technique for addressing random samples is to look at percentages rather than absolute values. That is, instead of looking at the number of bytes downloaded for each swarm from external sources (for example), it's better to compare the percentage of data downloaded that came from external sources. It's not particularly meaningful that one swarm was downloaded with one ISP a few percent more than another, but comparing cancellation rates, or ratio of internal to external data download volumes, is rather illuminating.
>
> - Laird Popkin, CTO, Pando Networks
>   mobile: 646/465-0570
>
> ----- Original Message -----
> From: "Y. Richard Yang" <yry@cs.yale.edu>
> To: "Robb Topolski" <robb@funchords.com>
> Cc: p2pi@ietf.org
> Sent: Sunday, November 9, 2008 4:57:32 PM (GMT-0500) America/New_York
> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>
> Hi Robb,
>
> Thanks for the excellent comments. Please see below.
>
> Robb Topolski wrote:
>   
>> It seems like a broken statistic given this experiment.
>>
>> If it were tightly controlled (and thus less Internet-like), all of
>> the downloads would have completed and the download byte amounts would
>> be virtually the same.
>>
>>   
>>     
> Welcome to the real world :-) Large-scale and yet tightly controlled 
> experiments are hard to
> conduct (if you have an idea or are interested in more discussion, it 
> will be fantastic). We did
> quite a few controlled experiments using clients on PlanetLab, but we 
> could get a couple
> hundred users if we were lucky. Neither may tightly controlled 
> experiments be highly desirable,
> because we would not know what we were missing then (your example of p2p 
> streaming is
> an excellent example). One objective of real experiments is unexpected 
> discovery. Sometime
> they are pleasant, and sometime they are not. Download abort was one 
> unexpected. But given
> the small fraction, I think it does not changes the reported results. 
> For full disclosure, another
> unexpected user behavior we discovered during our log processing was 
> that users sometime paused
> their download process (e.g. put the machines to sleep). We spent quite 
> a lot of time on this issue.
> Unfortunately the logs we had did not capture such events. We were 
> careful to use statistically
> more robust metrics (e.g., the download rates at different percentiles 
> instead of the average). We
> tried to check the impacts of such events. For example, we also computed 
> statistics after filtering
> to make sure our statistics did not change much. One filtering we did 
> was that if a user had no
> activity for too long (we tried two minutes and some other numbers), we 
> flagged that the user
> might have paused, and we ignored  that user's data. We did not see 
> large change of the
> statistics we computed before and after such filtering.
>
> Of course, we learn from such experiences. In our current experiments, 
> we are designing a new log
> format to try to capture more events. We might be surprised again and go 
> back to log more.
> We will be happy to share and work with others on robust experiment 
> design and statistics collection.
>   
>> One might argue that there is virtue to these observations because a
>> downloader who cancels a slow download is a bad thing, because they
>> ultimately did not get what they attempted to download.
>>
>> But is there virtue in an aborted download?  If they canceled the
>> download in frustration or because they simply couldn't stay connected
>> to the swarm long enough before being forced to quit by some other
>> personal oe obligation, then one could say that an aborted download is
>> a band thing. OTOH, an incomplete download is a good thing when a
>> downloader may have changed his mind (wanted to hear/see/do something
>> else) with less bandwidth wasted. There's just no way to know why the
>> user aborted the download.
>>
>>   
>>     
> I agree it will be fantastic if we can know the reason for an aborted 
> download. One thought came to
> mind immediately is a pop-up window after a download abort to ask the 
> user for reason(s). I do not
> know any P2P clients doing this right now and I am not sure how many 
> users will respond (e.g. not click
> cancel). But it is an excellent suggestion! We sure will talk to the P2P 
> developers we are working with
> to see if we can add such an option in one of our log plug-in.
>   
>> Even if we did know, this experiment doesn't deal with other possible
>> P4P-advantaged uses such as streaming-P2P video delivery (a mode more
>> prone to user "taste-testing" before completing a download than
>> traditional file-transfer models).
>>
>>   
>>     
> Absolutely good comment. This is why we are focusing on P2P streaming, 
> where channel hopping is
> a common user behavior (http://ccr.sigcomm.org/online/?q=node/404), and 
> startup delay is a major
> performance metric.
>
> Hope to hear more such good comments!
>
> Richard
>   
>> Robb
>>
>> 2008/11/6 Ye WANG <wangye.thu@gmail.com>:
>>   
>>     
>>> Hi Haibin,
>>>
>>> Yes, the Random swarm has notable smaller finished downloads than Generic or
>>> Coarse Grained during the period.
>>>
>>> Since the swarm sizes (# downloading peers) are roughly equal across all
>>> five swarms (Richard explained this in details), we suspect that a portion
>>> of slow peers terminate/discard their downloads.  This is almost the same
>>> hypothesis pointed out by Rich Woundy.
>>>
>>> Another evidence is we do notice significantly slower peers in Random swarm,
>>> e.g., the slowest Random peer took 7268s (>2hours) to download the video,
>>> but the slowest Generic took 2725s (<1hour), the slowest Corase Grained took
>>> 3114s (<1hour).   Hours of downloading may make users impatient.  If the
>>> "tail" peers in Random swarm could suffer much lower download rates,
>>> presumably, the number of "terminated" peers may be larger in Random swarm.
>>>
>>> On Thu, Nov 6, 2008 at 4:09 AM, Song Haibin <melodysong@huawei.com> wrote:
>>>     
>>>       
>>>> Hi Richard and all,
>>>>
>>>>       
>>>>         
>>>>> The access download of each swarm should be equal to the sum of those
>>>>> downloaded by the clients in each swarm. So if the number of downloads in
>>>>> each swarm is the same and the amount downloaded is the same, then each
>>>>> swarm should have the same access download.
>>>>>         
>>>>>           
>>>> Song Haibin: From section 4.1, we can see that "The results of the trial
>>>> indicated that P4P can improve the speed of downloads to P2P clients", so
>>>> if
>>>> the statistics data is collected during a certain period (from July 2 to
>>>> July 17, 2008), then the download will be increased than the random swarm.
>>>> I
>>>> don't think each swarm has downloaded the same amount of chunk files
>>>> during
>>>> the statistic period.
>>>>       
>>>>         
>>>     
>>>       
>>>> Best Regards,
>>>> Song Haibin
>>>> Email: melodysong@huawei.com
>>>> Skype: alexsonghw
>>>>
>>>>
>>>>
>>>>       
>>>>         
>>>>> -----Original Message-----
>>>>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
>>>>> Y.
>>>>>         
>>>>>           
>>>> R.
>>>>       
>>>>         
>>>>> Yang
>>>>> Sent: Thursday, November 06, 2008 10:40 AM
>>>>> To: Woundy, Richard
>>>>> Cc: p2pi@ietf.org; Livingood, Jason
>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>
>>>>>
>>>>> Hi Rich and others,
>>>>>
>>>>> The access download of each swarm should be equal to the sum of those
>>>>> downloaded by the clients in each swarm. So if the number of downloads in
>>>>> each swarm is the same and the amount downloaded is the same, then each
>>>>> swarm should have the same access download.
>>>>>
>>>>> First look at the amount downloaded. There are can be some differences
>>>>> due
>>>>> to duplicated chunks and the way we detected data chunks (there are also
>>>>> control data in the logs), but the difference appears to be small.
>>>>>
>>>>> Now let's look at the number of downloads. During the test, each client
>>>>> is
>>>>> uniformly assigned to a swarm. Given the large number of clients, each
>>>>> swarm should have about the same number of clients. But there can be two
>>>>> factors for us to see different numbers of *reported* downloads: (1) some
>>>>> clients are old and may not report or the reporting of logs was not
>>>>> successful; and (2) different # of clients finished downloading (if a
>>>>> client does not finish downloading, it does not report. Laird, please
>>>>> correct me if I am wrong). I belive the first factor should be small due
>>>>> to uniform random assignment of peers to swarms.
>>>>>
>>>>> I just looked at the data available. We did detect a smaller number of
>>>>> finished download with Random than with the P4P swarms. For example, from
>>>>> July 3 to July 10, detected # of finished download of Generic is about 5%
>>>>> more than than Random, and Coarse is 7% more than Random. From July 10 to
>>>>> July 17, Generic is 10.5% more than Random, and Coarse is 4.7% more.
>>>>> Looking at the traffic volume at Section 4.2, I see that Generic is about
>>>>> 7% higher, and Coarse is about 8.5% higher. Note that # of finished
>>>>> download and volume are different due to duplicated chunks and missing
>>>>> logs.
>>>>>
>>>>> So I would like to support the theory/guess of Rich that some users
>>>>> terminated the download prematurally and faster downloads may result in
>>>>> fewer such terminations. But it may also include factors in (1)
>>>>> differences in initial assignment due to random numbers; and (2) # of
>>>>> finished but non-reporting clients.
>>>>>
>>>>> If you have any other suggestions, we will be more than happy to look
>>>>> into
>>>>> the available data more.
>>>>>
>>>>> Richard
>>>>>
>>>>> On Wed, 5 Nov 2008, 6:26pm -0500, Woundy, Richard wrote:
>>>>>
>>>>>         
>>>>>           
>>>>>> My current theory/guess is that some users may terminated the download
>>>>>> prematurely, eg due to user impatience. So faster downloads (e.g.
>>>>>> thanks
>>>>>> to P4P) may result in fewer user terminations.
>>>>>>
>>>>>>
>>>>>>
>>>>>> Laird is checking the data to see if we can confirm that, or find
>>>>>> another explanation.
>>>>>>
>>>>>>
>>>>>>
>>>>>> -- Rich
>>>>>>
>>>>>>
>>>>>>
>>>>>> ________________________________
>>>>>>
>>>>>> From: Laird Popkin [mailto:laird@pando.com]
>>>>>> Sent: Wednesday, November 05, 2008 6:12 PM
>>>>>> To: Robb Topolski
>>>>>> Cc: Livingood, Jason; p2pi@ietf.org; Woundy, Richard
>>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>>
>>>>>>
>>>>>>
>>>>>> That's a good question, and Richard and I spoke about this yesterday.
>>>>>> I'll be looking into the data to see what the cause is.
>>>>>>
>>>>>> - Laird Popkin, CTO, Pando Networks
>>>>>>   mobile: 646/465-0570
>>>>>>
>>>>>> ----- Original Message -----
>>>>>> From: "Robb Topolski" <robb@funchords.com>
>>>>>> To: "Richard Woundy" <Richard_Woundy@cable.comcast.com>
>>>>>> Cc: "Jason Livingood" <Jason_Livingood@cable.comcast.com>,
>>>>>> p2pi@ietf.org
>>>>>> Sent: Wednesday, November 5, 2008 5:42:51 PM (GMT-0500)
>>>>>> America/New_York
>>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>>
>>>>>> I don't get the part where access network download consumption
>>>>>> increased
>>>>>> as a result of using P4P (section 4.2).  Can someone explain how that
>>>>>> could happen?
>>>>>>
>>>>>> Robb
>>>>>>
>>>>>> On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard
>>>>>> <Richard_Woundy@cable.comcast.com> wrote:
>>>>>>
>>>>>> Reinaldo,
>>>>>>
>>>>>> I can answer the easy questions. We will need some assistance from
>>>>>> Pando
>>>>>> (and Yale) for some of the other ones.
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> What was the file size in those experiments?
>>>>>>>             
>>>>>>>               
>>>>>> 21 megabytes. From section 2: "Pando distributed a special 21 MB
>>>>>> licensed video file as in order to measure the effectiveness of P4P
>>>>>> iTrackers."
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> How long would it take to download the file in the three different
>>>>>>>             
>>>>>>>               
>>>>>> scenarios? I know that more consumed bandwidth in access might lead one
>>>>>>
>>>>>> to conclude that file was downloaded faster...
>>>>>>
>>>>>> To clarify, most of the raw data (download speed and Internet
>>>>>> peering/transit traffic volumes) were collected by Pando Networks from
>>>>>> their P2P clients, not collected by Comcast across its links. So my
>>>>>> assumption is that the Pando client used the content size (21 MB), and
>>>>>> divided by the download time to get the speed.
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> Was the file already seeded in Comcast's network? More specifically,
>>>>>>>             
>>>>>>>               
>>>>>> how
>>>>>> was file propagation done?
>>>>>>
>>>>>> Any seeding happened outside of Comcast's network, and outside of
>>>>>> Comcast's control. That's really a question for Pando.
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> Was PEX, DHT and others enabled in the clients?
>>>>>>>             
>>>>>>>               
>>>>>> Pando would know whether PEX was enabled. It would be safe to assume
>>>>>> that with respect to this trial, DHT was NOT enabled, since Pando
>>>>>> supplied the tracker. (The pTracker in the draft is a tracker operated
>>>>>> by Pando.)
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> Was local peer discovery enabled in the clients?
>>>>>>>             
>>>>>>>               
>>>>>> Pando would know.
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> BTW, can broadcast/multicast peer discovery work in Cable networks?
>>>>>>>             
>>>>>>>               
>>>>>> Do you mean something like this:
>>>>>> http://bittorrent.org/beps/bep_0026.html?
>>>>>>
>>>>>> If so, peer discovery probably would not work over the typical last
>>>>>> mile
>>>>>> cable network. Maybe I'm wrong, but I see this protocol as intended for
>>>>>> peer discovery within one's home network / LAN / WiFi network, not over
>>>>>> a cable network.
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> So, were clients allowed to become seeders to the outside of Comcast's
>>>>>>>             
>>>>>>>               
>>>>>> network?
>>>>>>
>>>>>> Yes, they were.
>>>>>>
>>>>>> As a related item, look closely at section 4.2. The amount of aggregate
>>>>>> uploaded data from Comcast clients (per swarm) was about 140,000 MB.
>>>>>> The
>>>>>> amount of aggregate downloaded data from Comcast clients (per swarm)
>>>>>> was
>>>>>> about 60,000 MB or so. So the typical Comcast client uploaded more than
>>>>>> twice the amount of data that it downloaded.
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> How much of the swarm was within Comcast and outside?
>>>>>>>             
>>>>>>>               
>>>>>> Most of the swarm was outside of Comcast. Unfortunately I don't have
>>>>>> access to the size of the global swarm, but I would guess that Comcast
>>>>>> clients represented no more than 15% of the swarm, and maybe as little
>>>>>> as 5%. Those guesses are based on the behavior of the random swarm,
>>>>>> e.g.
>>>>>> Comcast clients uploaded to non-Comcast clients 94% of the time in the
>>>>>> random swarm.
>>>>>>
>>>>>> -- Rich
>>>>>>
>>>>>>
>>>>>> -----Original Message-----
>>>>>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
>>>>>>
>>>>>> Reinaldo Penno
>>>>>> Sent: Wednesday, November 05, 2008 11:23 AM
>>>>>> To: Livingood, Jason; p2pi@ietf.org
>>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>>
>>>>>> Hello Jason/Rich,
>>>>>>
>>>>>> This is such an interesting draft. I'm surprised there are no questions
>>>>>> about it. Maybe everybody else is part of P4P one way or another and
>>>>>> I'm
>>>>>> not
>>>>>> in the 'in' crowd (;-) so I have questions.
>>>>>>
>>>>>> * What was the file size in those experiments? Some post long ago said
>>>>>> the
>>>>>> file size in some P4P experiments was really small, as opposed to the
>>>>>> top
>>>>>> 100 torrents where the file size is ~1Gb. I was curious what is the
>>>>>> optimization payback in terms of download time for large files as
>>>>>> opposed
>>>>>> small files.
>>>>>>
>>>>>> * How long would it take to download the file in the three different
>>>>>> scenarios? I know that more consumed bandwidth in access might lead one
>>>>>> to
>>>>>> conclude that file was downloaded faster but I'm not sure this is a
>>>>>> straightforward conclusion.
>>>>>>
>>>>>> * Was the file already seeded in Comcast's network? More specifically,
>>>>>> how
>>>>>> was file propagation done? All clients started from scratch and had to
>>>>>> start
>>>>>> pulling the file from some other side of the world and then exchanging
>>>>>> pieces? This is mainly due to the discussion in 4.2.
>>>>>>
>>>>>> * Was PEX, DHT and others enabled in the clients?
>>>>>>
>>>>>> * Was local peer discovery enabled in the clients? BTW, can
>>>>>> broadcast/multicast peer discovery work in Cable networks?
>>>>>>
>>>>>> * If more clients finish downloading faster and become seeders you
>>>>>> would
>>>>>> think that for popular content Comcast's upstream bandwidth would
>>>>>> increase
>>>>>> due to the number of seeder in its network. So, were clients allowed to
>>>>>> become seeders to the outside of Comcast's network? How much of the
>>>>>> swarm
>>>>>> was within Comcast and outside?
>>>>>>
>>>>>> Thanks,
>>>>>>
>>>>>> Reinaldo
>>>>>>
>>>>>> On 11/3/08 12:49 PM, "Livingood, Jason"
>>>>>> <Jason_Livingood@cable.comcast.com>
>>>>>> wrote:
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> For some reason the URL was cut to two lines - trying again:
>>>>>>>
>>>>>>>
>>>>>>>             
>>>>>>>               
>>>>>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
>>>>>>           
>>>>>>             
>>>>>>> es-02.txt
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>>             
>>>>>>>               
>>>>>>>> -----Original Message-----
>>>>>>>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
>>>>>>>> Behalf Of Livingood, Jason
>>>>>>>> Sent: Monday, November 03, 2008 3:35 PM
>>>>>>>> To: p2pi@ietf.org
>>>>>>>> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>>>>
>>>>>>>> A draft at
>>>>>>>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
>>>>>>>> -experienc
>>>>>>>> es-02.txt may be of interest to folks that have been
>>>>>>>> interested in P2Pi and ALTO.  We have requested time on the
>>>>>>>> ALTO agenda at IETF 73 to present this.
>>>>>>>>
>>>>>>>> Regards
>>>>>>>> Jason
>>>>>>>> _______________________________________________
>>>>>>>> p2pi mailing list
>>>>>>>> p2pi@ietf.org
>>>>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>>>>
>>>>>>>>               
>>>>>>>>                 
>>>>>>> _______________________________________________
>>>>>>> p2pi mailing list
>>>>>>> p2pi@ietf.org
>>>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>>>             
>>>>>>>               
>>>>>> _______________________________________________
>>>>>> p2pi mailing list
>>>>>> p2pi@ietf.org
>>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>> _______________________________________________
>>>>>> p2pi mailing list
>>>>>> p2pi@ietf.org
>>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>> --
>>>>>> Robb Topolski (robb@funchords.com)
>>>>>> Hillsboro, Oregon USA
>>>>>> http://www.funchords.com/
>>>>>>
>>>>>> _______________________________________________ p2pi mailing list
>>>>>> p2pi@ietf.org https://www.ietf.org/mailman/listinfo/p2pi
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>> _______________________________________________
>>>>> p2pi mailing list
>>>>> p2pi@ietf.org
>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>         
>>>>>           
>>>> _______________________________________________
>>>> p2pi mailing list
>>>> p2pi@ietf.org
>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>       
>>>>         
>>> _______________________________________________
>>> p2pi mailing list
>>> p2pi@ietf.org
>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>
>>>
>>>     
>>>       
>>
>>   
>>     
>
>
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi
>   


_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Sun Nov  9 23:12:40 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 3FF993A68FC;
	Sun,  9 Nov 2008 23:12:40 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 557D53A683D
	for <p2pi@core3.amsl.com>; Sun,  9 Nov 2008 23:12:39 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -10.265
X-Spam-Level: 
X-Spam-Status: No, score=-10.265 tagged_above=-999 required=5
	tests=[AWL=0.000, BAYES_00=-2.599, HABEAS_ACCREDITED_COI=-8,
	IP_NOT_FRIENDLY=0.334]
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 Y9ppDNTblQRi for <p2pi@core3.amsl.com>;
	Sun,  9 Nov 2008 23:12:36 -0800 (PST)
Received: from dkny.pando.com (dkny.pando.com [67.99.55.163])
	by core3.amsl.com (Postfix) with ESMTP id 91EFD3A6843
	for <p2pi@ietf.org>; Sun,  9 Nov 2008 23:12:36 -0800 (PST)
Received: from localhost (localhost.localdomain [127.0.0.1])
	by dkny.pando.com (Postfix) with ESMTP id 618AEE10B38;
	Mon, 10 Nov 2008 02:12:29 -0500 (EST)
X-Virus-Scanned: amavisd-new at 
Received: from dkny.pando.com ([127.0.0.1])
	by localhost (dkny.pando.com [127.0.0.1]) (amavisd-new, port 10024)
	with ESMTP id Dg4PfkCDYPjT; Mon, 10 Nov 2008 02:12:13 -0500 (EST)
Received: from dkny.pando.com (dkny.pando.com [10.10.60.11])
	by dkny.pando.com (Postfix) with ESMTP id C1BF2E10B26;
	Mon, 10 Nov 2008 02:12:13 -0500 (EST)
Date: Mon, 10 Nov 2008 02:12:13 -0500 (EST)
From: Laird Popkin <laird@pando.com>
To: "Y. Richard Yang" <yry@cs.yale.edu>
Message-ID: <1499909111.83701226301133712.JavaMail.root@dkny.pando.com>
In-Reply-To: <4917CD55.1000906@cs.yale.edu>
MIME-Version: 1.0
X-Originating-IP: [71.187.59.213]
Cc: p2pi@ietf.org
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

Nice analysis.

- Laird Popkin, CTO, Pando Networks
  mobile: 646/465-0570

----- Original Message -----
From: "Y. Richard Yang" <yry@cs.yale.edu>
To: "Laird Popkin" <laird@pando.com>
Cc: p2pi@ietf.org, "Robb Topolski" <robb@funchords.com>
Sent: Monday, November 10, 2008 12:57:41 AM (GMT-0500) America/New_York
Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted

Hi All,
> To explain a bit of the test methodology, downloaders were globally distributed, and every downloader was assigned randomly to one of the five swarms at the time that they started the download. The result of this is that while there were quite comparable numbers of downloaders in each swarm globally, the number of downloaders within a given ISP for each swarm has random variation. For example, one ISP might have a few percent more downloaders of the 'random' swarm while another ISP might have a few percent more downloaders of the 'P4P generic weight matrix' swarm. As with any statistical analysis of real world data, you should expect some random variation based on sample size. In particular, within Comcast there happened to be a few percent more 'random' downloaders than for the guided swarms.
>
>   
To be more precise, I just did some analysis on if the random number 
generator did a good job in assigning downloaders to swarms. Consider 
the assignment of Comcast downloaders to different swarms. Let's focus 
on one particular swarm, say Generic. If uniform random assignment, a 
downloader from Comcast is assigned to Generic with probability 1/5. 
Define random variable X1 as an indicator that the first downloader from 
Comcast is assigned to Generic; X2 the second Comcast downloader is 
assigned to Generic, ...  Then:

Xi = 1 with prob. 1/5; 0 with prob. 4/5.

Define SN = X1 + X2 + ... + XN, where N is the number of downloaders 
from Comcast. Then SN is the number of Comcast downloaders assigned to 
Generic.

Applying Central Limit Theorem,

      SN - 1/5*N
z = ------------
      \sqrt(N) * 0.4

should follow Standard Normal Distribution.

I calculated the z scores for fine, coarse, generic, and random:

Z_fine = 0.69
Z_coarse = 1.27
Z_generic = -0.81
Z_random = -1.43

It looks that the assignment algorithm did a decent job in assigning 
downloaders from Comcast to the different swarms (the 95% confidence 
interval of Z is -1.96 to 1.96). Of course, the preceding is to give 
intuition, and we can write more rigorous statistical hypothesis 
testing. (BTW, there is a typo in the previous email, Random had the 
smallest number of downloaders from Comcast assigned to it.). We did 
observe higher cancellation rate by Random (3.17%) vs others 
(1.77%-2.22%), but this is just one sample. We can derive more samples 
by reprocessing the testing logs by days, calculating the cancellation 
rate during each day to obtain a series, and then conducting statistical 
testing to test if guided swarms have lower cancellation rate against 
the series of Random. But if the cancellation rate is of true interest, 
we may want to conduct more experiments to evaluate it.

Richard
> Looking at the numbers of downloads and their completion rates, all of the swarms had completion rates that were extremely high, with the guided (P4P and PNA) having a higher completion rate (about 98%) and the unguided (random) downloads having a slightly lower completion rate (about 97%).
>
> The standard technique for addressing random samples is to look at percentages rather than absolute values. That is, instead of looking at the number of bytes downloaded for each swarm from external sources (for example), it's better to compare the percentage of data downloaded that came from external sources. It's not particularly meaningful that one swarm was downloaded with one ISP a few percent more than another, but comparing cancellation rates, or ratio of internal to external data download volumes, is rather illuminating.
>
> - Laird Popkin, CTO, Pando Networks
>   mobile: 646/465-0570
>
> ----- Original Message -----
> From: "Y. Richard Yang" <yry@cs.yale.edu>
> To: "Robb Topolski" <robb@funchords.com>
> Cc: p2pi@ietf.org
> Sent: Sunday, November 9, 2008 4:57:32 PM (GMT-0500) America/New_York
> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>
> Hi Robb,
>
> Thanks for the excellent comments. Please see below.
>
> Robb Topolski wrote:
>   
>> It seems like a broken statistic given this experiment.
>>
>> If it were tightly controlled (and thus less Internet-like), all of
>> the downloads would have completed and the download byte amounts would
>> be virtually the same.
>>
>>   
>>     
> Welcome to the real world :-) Large-scale and yet tightly controlled 
> experiments are hard to
> conduct (if you have an idea or are interested in more discussion, it 
> will be fantastic). We did
> quite a few controlled experiments using clients on PlanetLab, but we 
> could get a couple
> hundred users if we were lucky. Neither may tightly controlled 
> experiments be highly desirable,
> because we would not know what we were missing then (your example of p2p 
> streaming is
> an excellent example). One objective of real experiments is unexpected 
> discovery. Sometime
> they are pleasant, and sometime they are not. Download abort was one 
> unexpected. But given
> the small fraction, I think it does not changes the reported results. 
> For full disclosure, another
> unexpected user behavior we discovered during our log processing was 
> that users sometime paused
> their download process (e.g. put the machines to sleep). We spent quite 
> a lot of time on this issue.
> Unfortunately the logs we had did not capture such events. We were 
> careful to use statistically
> more robust metrics (e.g., the download rates at different percentiles 
> instead of the average). We
> tried to check the impacts of such events. For example, we also computed 
> statistics after filtering
> to make sure our statistics did not change much. One filtering we did 
> was that if a user had no
> activity for too long (we tried two minutes and some other numbers), we 
> flagged that the user
> might have paused, and we ignored  that user's data. We did not see 
> large change of the
> statistics we computed before and after such filtering.
>
> Of course, we learn from such experiences. In our current experiments, 
> we are designing a new log
> format to try to capture more events. We might be surprised again and go 
> back to log more.
> We will be happy to share and work with others on robust experiment 
> design and statistics collection.
>   
>> One might argue that there is virtue to these observations because a
>> downloader who cancels a slow download is a bad thing, because they
>> ultimately did not get what they attempted to download.
>>
>> But is there virtue in an aborted download?  If they canceled the
>> download in frustration or because they simply couldn't stay connected
>> to the swarm long enough before being forced to quit by some other
>> personal oe obligation, then one could say that an aborted download is
>> a band thing. OTOH, an incomplete download is a good thing when a
>> downloader may have changed his mind (wanted to hear/see/do something
>> else) with less bandwidth wasted. There's just no way to know why the
>> user aborted the download.
>>
>>   
>>     
> I agree it will be fantastic if we can know the reason for an aborted 
> download. One thought came to
> mind immediately is a pop-up window after a download abort to ask the 
> user for reason(s). I do not
> know any P2P clients doing this right now and I am not sure how many 
> users will respond (e.g. not click
> cancel). But it is an excellent suggestion! We sure will talk to the P2P 
> developers we are working with
> to see if we can add such an option in one of our log plug-in.
>   
>> Even if we did know, this experiment doesn't deal with other possible
>> P4P-advantaged uses such as streaming-P2P video delivery (a mode more
>> prone to user "taste-testing" before completing a download than
>> traditional file-transfer models).
>>
>>   
>>     
> Absolutely good comment. This is why we are focusing on P2P streaming, 
> where channel hopping is
> a common user behavior (http://ccr.sigcomm.org/online/?q=node/404), and 
> startup delay is a major
> performance metric.
>
> Hope to hear more such good comments!
>
> Richard
>   
>> Robb
>>
>> 2008/11/6 Ye WANG <wangye.thu@gmail.com>:
>>   
>>     
>>> Hi Haibin,
>>>
>>> Yes, the Random swarm has notable smaller finished downloads than Generic or
>>> Coarse Grained during the period.
>>>
>>> Since the swarm sizes (# downloading peers) are roughly equal across all
>>> five swarms (Richard explained this in details), we suspect that a portion
>>> of slow peers terminate/discard their downloads.  This is almost the same
>>> hypothesis pointed out by Rich Woundy.
>>>
>>> Another evidence is we do notice significantly slower peers in Random swarm,
>>> e.g., the slowest Random peer took 7268s (>2hours) to download the video,
>>> but the slowest Generic took 2725s (<1hour), the slowest Corase Grained took
>>> 3114s (<1hour).   Hours of downloading may make users impatient.  If the
>>> "tail" peers in Random swarm could suffer much lower download rates,
>>> presumably, the number of "terminated" peers may be larger in Random swarm.
>>>
>>> On Thu, Nov 6, 2008 at 4:09 AM, Song Haibin <melodysong@huawei.com> wrote:
>>>     
>>>       
>>>> Hi Richard and all,
>>>>
>>>>       
>>>>         
>>>>> The access download of each swarm should be equal to the sum of those
>>>>> downloaded by the clients in each swarm. So if the number of downloads in
>>>>> each swarm is the same and the amount downloaded is the same, then each
>>>>> swarm should have the same access download.
>>>>>         
>>>>>           
>>>> Song Haibin: From section 4.1, we can see that "The results of the trial
>>>> indicated that P4P can improve the speed of downloads to P2P clients", so
>>>> if
>>>> the statistics data is collected during a certain period (from July 2 to
>>>> July 17, 2008), then the download will be increased than the random swarm.
>>>> I
>>>> don't think each swarm has downloaded the same amount of chunk files
>>>> during
>>>> the statistic period.
>>>>       
>>>>         
>>>     
>>>       
>>>> Best Regards,
>>>> Song Haibin
>>>> Email: melodysong@huawei.com
>>>> Skype: alexsonghw
>>>>
>>>>
>>>>
>>>>       
>>>>         
>>>>> -----Original Message-----
>>>>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
>>>>> Y.
>>>>>         
>>>>>           
>>>> R.
>>>>       
>>>>         
>>>>> Yang
>>>>> Sent: Thursday, November 06, 2008 10:40 AM
>>>>> To: Woundy, Richard
>>>>> Cc: p2pi@ietf.org; Livingood, Jason
>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>
>>>>>
>>>>> Hi Rich and others,
>>>>>
>>>>> The access download of each swarm should be equal to the sum of those
>>>>> downloaded by the clients in each swarm. So if the number of downloads in
>>>>> each swarm is the same and the amount downloaded is the same, then each
>>>>> swarm should have the same access download.
>>>>>
>>>>> First look at the amount downloaded. There are can be some differences
>>>>> due
>>>>> to duplicated chunks and the way we detected data chunks (there are also
>>>>> control data in the logs), but the difference appears to be small.
>>>>>
>>>>> Now let's look at the number of downloads. During the test, each client
>>>>> is
>>>>> uniformly assigned to a swarm. Given the large number of clients, each
>>>>> swarm should have about the same number of clients. But there can be two
>>>>> factors for us to see different numbers of *reported* downloads: (1) some
>>>>> clients are old and may not report or the reporting of logs was not
>>>>> successful; and (2) different # of clients finished downloading (if a
>>>>> client does not finish downloading, it does not report. Laird, please
>>>>> correct me if I am wrong). I belive the first factor should be small due
>>>>> to uniform random assignment of peers to swarms.
>>>>>
>>>>> I just looked at the data available. We did detect a smaller number of
>>>>> finished download with Random than with the P4P swarms. For example, from
>>>>> July 3 to July 10, detected # of finished download of Generic is about 5%
>>>>> more than than Random, and Coarse is 7% more than Random. From July 10 to
>>>>> July 17, Generic is 10.5% more than Random, and Coarse is 4.7% more.
>>>>> Looking at the traffic volume at Section 4.2, I see that Generic is about
>>>>> 7% higher, and Coarse is about 8.5% higher. Note that # of finished
>>>>> download and volume are different due to duplicated chunks and missing
>>>>> logs.
>>>>>
>>>>> So I would like to support the theory/guess of Rich that some users
>>>>> terminated the download prematurally and faster downloads may result in
>>>>> fewer such terminations. But it may also include factors in (1)
>>>>> differences in initial assignment due to random numbers; and (2) # of
>>>>> finished but non-reporting clients.
>>>>>
>>>>> If you have any other suggestions, we will be more than happy to look
>>>>> into
>>>>> the available data more.
>>>>>
>>>>> Richard
>>>>>
>>>>> On Wed, 5 Nov 2008, 6:26pm -0500, Woundy, Richard wrote:
>>>>>
>>>>>         
>>>>>           
>>>>>> My current theory/guess is that some users may terminated the download
>>>>>> prematurely, eg due to user impatience. So faster downloads (e.g.
>>>>>> thanks
>>>>>> to P4P) may result in fewer user terminations.
>>>>>>
>>>>>>
>>>>>>
>>>>>> Laird is checking the data to see if we can confirm that, or find
>>>>>> another explanation.
>>>>>>
>>>>>>
>>>>>>
>>>>>> -- Rich
>>>>>>
>>>>>>
>>>>>>
>>>>>> ________________________________
>>>>>>
>>>>>> From: Laird Popkin [mailto:laird@pando.com]
>>>>>> Sent: Wednesday, November 05, 2008 6:12 PM
>>>>>> To: Robb Topolski
>>>>>> Cc: Livingood, Jason; p2pi@ietf.org; Woundy, Richard
>>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>>
>>>>>>
>>>>>>
>>>>>> That's a good question, and Richard and I spoke about this yesterday.
>>>>>> I'll be looking into the data to see what the cause is.
>>>>>>
>>>>>> - Laird Popkin, CTO, Pando Networks
>>>>>>   mobile: 646/465-0570
>>>>>>
>>>>>> ----- Original Message -----
>>>>>> From: "Robb Topolski" <robb@funchords.com>
>>>>>> To: "Richard Woundy" <Richard_Woundy@cable.comcast.com>
>>>>>> Cc: "Jason Livingood" <Jason_Livingood@cable.comcast.com>,
>>>>>> p2pi@ietf.org
>>>>>> Sent: Wednesday, November 5, 2008 5:42:51 PM (GMT-0500)
>>>>>> America/New_York
>>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>>
>>>>>> I don't get the part where access network download consumption
>>>>>> increased
>>>>>> as a result of using P4P (section 4.2).  Can someone explain how that
>>>>>> could happen?
>>>>>>
>>>>>> Robb
>>>>>>
>>>>>> On Wed, Nov 5, 2008 at 2:29 PM, Woundy, Richard
>>>>>> <Richard_Woundy@cable.comcast.com> wrote:
>>>>>>
>>>>>> Reinaldo,
>>>>>>
>>>>>> I can answer the easy questions. We will need some assistance from
>>>>>> Pando
>>>>>> (and Yale) for some of the other ones.
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> What was the file size in those experiments?
>>>>>>>             
>>>>>>>               
>>>>>> 21 megabytes. From section 2: "Pando distributed a special 21 MB
>>>>>> licensed video file as in order to measure the effectiveness of P4P
>>>>>> iTrackers."
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> How long would it take to download the file in the three different
>>>>>>>             
>>>>>>>               
>>>>>> scenarios? I know that more consumed bandwidth in access might lead one
>>>>>>
>>>>>> to conclude that file was downloaded faster...
>>>>>>
>>>>>> To clarify, most of the raw data (download speed and Internet
>>>>>> peering/transit traffic volumes) were collected by Pando Networks from
>>>>>> their P2P clients, not collected by Comcast across its links. So my
>>>>>> assumption is that the Pando client used the content size (21 MB), and
>>>>>> divided by the download time to get the speed.
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> Was the file already seeded in Comcast's network? More specifically,
>>>>>>>             
>>>>>>>               
>>>>>> how
>>>>>> was file propagation done?
>>>>>>
>>>>>> Any seeding happened outside of Comcast's network, and outside of
>>>>>> Comcast's control. That's really a question for Pando.
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> Was PEX, DHT and others enabled in the clients?
>>>>>>>             
>>>>>>>               
>>>>>> Pando would know whether PEX was enabled. It would be safe to assume
>>>>>> that with respect to this trial, DHT was NOT enabled, since Pando
>>>>>> supplied the tracker. (The pTracker in the draft is a tracker operated
>>>>>> by Pando.)
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> Was local peer discovery enabled in the clients?
>>>>>>>             
>>>>>>>               
>>>>>> Pando would know.
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> BTW, can broadcast/multicast peer discovery work in Cable networks?
>>>>>>>             
>>>>>>>               
>>>>>> Do you mean something like this:
>>>>>> http://bittorrent.org/beps/bep_0026.html?
>>>>>>
>>>>>> If so, peer discovery probably would not work over the typical last
>>>>>> mile
>>>>>> cable network. Maybe I'm wrong, but I see this protocol as intended for
>>>>>> peer discovery within one's home network / LAN / WiFi network, not over
>>>>>> a cable network.
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> So, were clients allowed to become seeders to the outside of Comcast's
>>>>>>>             
>>>>>>>               
>>>>>> network?
>>>>>>
>>>>>> Yes, they were.
>>>>>>
>>>>>> As a related item, look closely at section 4.2. The amount of aggregate
>>>>>> uploaded data from Comcast clients (per swarm) was about 140,000 MB.
>>>>>> The
>>>>>> amount of aggregate downloaded data from Comcast clients (per swarm)
>>>>>> was
>>>>>> about 60,000 MB or so. So the typical Comcast client uploaded more than
>>>>>> twice the amount of data that it downloaded.
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> How much of the swarm was within Comcast and outside?
>>>>>>>             
>>>>>>>               
>>>>>> Most of the swarm was outside of Comcast. Unfortunately I don't have
>>>>>> access to the size of the global swarm, but I would guess that Comcast
>>>>>> clients represented no more than 15% of the swarm, and maybe as little
>>>>>> as 5%. Those guesses are based on the behavior of the random swarm,
>>>>>> e.g.
>>>>>> Comcast clients uploaded to non-Comcast clients 94% of the time in the
>>>>>> random swarm.
>>>>>>
>>>>>> -- Rich
>>>>>>
>>>>>>
>>>>>> -----Original Message-----
>>>>>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On Behalf Of
>>>>>>
>>>>>> Reinaldo Penno
>>>>>> Sent: Wednesday, November 05, 2008 11:23 AM
>>>>>> To: Livingood, Jason; p2pi@ietf.org
>>>>>> Subject: Re: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>>
>>>>>> Hello Jason/Rich,
>>>>>>
>>>>>> This is such an interesting draft. I'm surprised there are no questions
>>>>>> about it. Maybe everybody else is part of P4P one way or another and
>>>>>> I'm
>>>>>> not
>>>>>> in the 'in' crowd (;-) so I have questions.
>>>>>>
>>>>>> * What was the file size in those experiments? Some post long ago said
>>>>>> the
>>>>>> file size in some P4P experiments was really small, as opposed to the
>>>>>> top
>>>>>> 100 torrents where the file size is ~1Gb. I was curious what is the
>>>>>> optimization payback in terms of download time for large files as
>>>>>> opposed
>>>>>> small files.
>>>>>>
>>>>>> * How long would it take to download the file in the three different
>>>>>> scenarios? I know that more consumed bandwidth in access might lead one
>>>>>> to
>>>>>> conclude that file was downloaded faster but I'm not sure this is a
>>>>>> straightforward conclusion.
>>>>>>
>>>>>> * Was the file already seeded in Comcast's network? More specifically,
>>>>>> how
>>>>>> was file propagation done? All clients started from scratch and had to
>>>>>> start
>>>>>> pulling the file from some other side of the world and then exchanging
>>>>>> pieces? This is mainly due to the discussion in 4.2.
>>>>>>
>>>>>> * Was PEX, DHT and others enabled in the clients?
>>>>>>
>>>>>> * Was local peer discovery enabled in the clients? BTW, can
>>>>>> broadcast/multicast peer discovery work in Cable networks?
>>>>>>
>>>>>> * If more clients finish downloading faster and become seeders you
>>>>>> would
>>>>>> think that for popular content Comcast's upstream bandwidth would
>>>>>> increase
>>>>>> due to the number of seeder in its network. So, were clients allowed to
>>>>>> become seeders to the outside of Comcast's network? How much of the
>>>>>> swarm
>>>>>> was within Comcast and outside?
>>>>>>
>>>>>> Thanks,
>>>>>>
>>>>>> Reinaldo
>>>>>>
>>>>>> On 11/3/08 12:49 PM, "Livingood, Jason"
>>>>>> <Jason_Livingood@cable.comcast.com>
>>>>>> wrote:
>>>>>>
>>>>>>           
>>>>>>             
>>>>>>> For some reason the URL was cut to two lines - trying again:
>>>>>>>
>>>>>>>
>>>>>>>             
>>>>>>>               
>>>>>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p-experienc
>>>>>>           
>>>>>>             
>>>>>>> es-02.txt
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>>             
>>>>>>>               
>>>>>>>> -----Original Message-----
>>>>>>>> From: p2pi-bounces@ietf.org [mailto:p2pi-bounces@ietf.org] On
>>>>>>>> Behalf Of Livingood, Jason
>>>>>>>> Sent: Monday, November 03, 2008 3:35 PM
>>>>>>>> To: p2pi@ietf.org
>>>>>>>> Subject: [p2pi] draft-livingood-woundy-p4p-experiences-02 posted
>>>>>>>>
>>>>>>>> A draft at
>>>>>>>> http://www.ietf.org/internet-drafts/draft-livingood-woundy-p4p
>>>>>>>> -experienc
>>>>>>>> es-02.txt may be of interest to folks that have been
>>>>>>>> interested in P2Pi and ALTO.  We have requested time on the
>>>>>>>> ALTO agenda at IETF 73 to present this.
>>>>>>>>
>>>>>>>> Regards
>>>>>>>> Jason
>>>>>>>> _______________________________________________
>>>>>>>> p2pi mailing list
>>>>>>>> p2pi@ietf.org
>>>>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>>>>
>>>>>>>>               
>>>>>>>>                 
>>>>>>> _______________________________________________
>>>>>>> p2pi mailing list
>>>>>>> p2pi@ietf.org
>>>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>>>             
>>>>>>>               
>>>>>> _______________________________________________
>>>>>> p2pi mailing list
>>>>>> p2pi@ietf.org
>>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>> _______________________________________________
>>>>>> p2pi mailing list
>>>>>> p2pi@ietf.org
>>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>> --
>>>>>> Robb Topolski (robb@funchords.com)
>>>>>> Hillsboro, Oregon USA
>>>>>> http://www.funchords.com/
>>>>>>
>>>>>> _______________________________________________ p2pi mailing list
>>>>>> p2pi@ietf.org https://www.ietf.org/mailman/listinfo/p2pi
>>>>>>
>>>>>>
>>>>>>           
>>>>>>             
>>>>> _______________________________________________
>>>>> p2pi mailing list
>>>>> p2pi@ietf.org
>>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>>         
>>>>>           
>>>> _______________________________________________
>>>> p2pi mailing list
>>>> p2pi@ietf.org
>>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>>       
>>>>         
>>> _______________________________________________
>>> p2pi mailing list
>>> p2pi@ietf.org
>>> https://www.ietf.org/mailman/listinfo/p2pi
>>>
>>>
>>>     
>>>       
>>
>>   
>>     
>
>
> _______________________________________________
> p2pi mailing list
> p2pi@ietf.org
> https://www.ietf.org/mailman/listinfo/p2pi
>   



_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Mon Nov 10 07:21:24 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 7373F3A69AB;
	Mon, 10 Nov 2008 07:21:24 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id CD8283A69AB
	for <p2pi@core3.amsl.com>; Mon, 10 Nov 2008 07:21:22 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -0.13
X-Spam-Level: 
X-Spam-Status: No, score=-0.13 tagged_above=-999 required=5 tests=[AWL=1.300, 
	BAYES_00=-2.599, HELO_EQ_AT=0.424, HOST_EQ_AT=0.745]
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 cqiFge-Nzq2h for <p2pi@core3.amsl.com>;
	Mon, 10 Nov 2008 07:21:21 -0800 (PST)
Received: from grace.univie.ac.at (grace.univie.ac.at
	[IPv6:2001:62a:4:25::25:115])
	by core3.amsl.com (Postfix) with ESMTP id 20D0B3A68D7
	for <p2pi@ietf.org>; Mon, 10 Nov 2008 07:21:21 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
	d=univie.ac.at; s=rev1; h=Message-ID:Date:Subject:From:To:
	MIME-Version:Content-Type:Content-Transfer-Encoding; bh=9b+5uZ5w
	JBeVWeyyHlp1TwfsIZe6TSvzsSJ3Gc/ahvs=; b=p2E/lsG4uQrpPne1/5nK68e0
	7pzahgcJhEzoMSVr80NVDQ01f/NmK2lQcHojvcx/VDwQvkd0gbmJcxqVDI7Yepuv
	p13EGldc/98zb/KgsJGzlpUMsuLFg9sKOyVUzWdv0WeH9fe90+WKrTJ2e4xwV34f
	jVJMiaIgNhUJwmnLW/Y=
Received: from justin.univie.ac.at ([131.130.3.111] helo=justin.univie.ac.at)
	by grace.univie.ac.at with esmtp (Exim 4.69)
	(envelope-from <kurt.tutschku@univie.ac.at>) id 1KzYZo-0000Ib-Mb
	for p2pi@ietf.org; Mon, 10 Nov 2008 16:21:16 +0100
Received: from webmail.univie.ac.at ([131.130.1.47] helo=webmail.univie.ac.at)
	by justin.univie.ac.at with esmtp (Exim 4.69)
	(envelope-from <kurt.tutschku@univie.ac.at>) id 1KzYZo-00015I-Js
	for p2pi@ietf.org; Mon, 10 Nov 2008 16:21:16 +0100
Received: from 131.130.37.129 (SquirrelMail authenticated user tutschk6)
	by webmail.univie.ac.at with HTTP;
	Mon, 10 Nov 2008 16:21:16 +0100 (CET)
Message-ID: <55835.131.130.37.129.1226330476.squirrel@webmail.univie.ac.at>
Date: Mon, 10 Nov 2008 16:21:16 +0100 (CET)
From: "Kurt Tutschku" <kurt.tutschku@univie.ac.at>
To: p2pi@ietf.org
User-Agent: SquirrelMail/1.4.10a
MIME-Version: 1.0
Subject: [p2pi] 2nd CFP: 20th ITC Specialist Seminar on Network
	Virtualization
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: base64
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org
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=


From p2pi-bounces@ietf.org  Wed Nov 12 11:19:34 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 1184E28C174;
	Wed, 12 Nov 2008 11:19:34 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 315A328C179
	for <p2pi@core3.amsl.com>; Wed, 12 Nov 2008 11:19:32 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.599
X-Spam-Level: 
X-Spam-Status: No, score=-2.599 tagged_above=-999 required=5 tests=[AWL=0.000, 
	BAYES_00=-2.599]
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 c6YUjsR2LWWo for <p2pi@core3.amsl.com>;
	Wed, 12 Nov 2008 11:19:30 -0800 (PST)
Received: from ihemail1.lucent.com (ihemail1.lucent.com [135.245.0.33])
	by core3.amsl.com (Postfix) with ESMTP id 8BBB028C165
	for <p2pi@ietf.org>; Wed, 12 Nov 2008 11:19:30 -0800 (PST)
Received: from umail.lucent.com (h135-3-40-61.lucent.com [135.3.40.61])
	by ihemail1.lucent.com (8.13.8/IER-o) with ESMTP id mACJKo6x007724
	(version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO)
	for <p2pi@ietf.org>; Wed, 12 Nov 2008 13:20:52 -0600 (CST)
Received: from [135.185.236.17] (il0015vkg1.ih.lucent.com [135.185.236.17])
	by umail.lucent.com (8.13.8/TPES) with ESMTP id mACJJSZb005510
	for <p2pi@ietf.org>; Wed, 12 Nov 2008 13:19:28 -0600 (CST)
Message-ID: <491B2C40.5080106@alcatel-lucent.com>
Date: Wed, 12 Nov 2008 13:19:28 -0600
From: "Vijay K. Gurbani" <vkg@alcatel-lucent.com>
Organization: Bell Labs Security Technology Research Group
User-Agent: Thunderbird 2.0.0.6 (Windows/20070728)
MIME-Version: 1.0
To: "p2pi@ietf.org" <p2pi@ietf.org>
Content-Type: multipart/mixed; boundary="------------030809050904050603030102"
X-Scanned-By: MIMEDefang 2.57 on 135.245.2.33
Subject: [p2pi] [Fwd: WG Action: Application-Layer Traffic Optimization
	(alto)]
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

This is a multi-part message in MIME format.
--------------030809050904050603030102
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit

Folks: Attached is the official ALTO WG announcement from
the IESG Secretary.

On an important logistical point, please take note that we
have a *new* mailing list for ALTO:

General Discussion: alto@ietf.org
To Subscribe: https://www.ietf.org/mailman/listinfo/alto
Archive: http://www.ietf.org/pipermail/alto/

Can you please subscribe to the new ALTO WG list.  We are
moving away from the p2pi mailing list that was set up for the
IETF/MIT Workshop earlier this year.

The charter, chairs and deliverable information that went out
as part of the official announcement is attached to this email.

Welcome to the ALTO WG!  And once again, thanks to all of
those that participated since the IETF/MIT Workshop in May
to get us here.

So, once again, please subscribe yourself to the new email
list so subsequent work can continue there.

See you all in Minneapolis.

Thank you.

- vijay
-- 
Vijay K. Gurbani, Bell Laboratories, Alcatel-Lucent
1960 Lucent Lane, Rm. 9C-533, Naperville, Illinois 60566 (USA)
Email: vkg@{alcatel-lucent.com,bell-labs.com,acm.org}
Web:   http://ect.bell-labs.com/who/vkg/

--------------030809050904050603030102
Content-Type: message/rfc822;
 name="WG Action: Application-Layer Traffic Optimization (alto).eml"
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename*0="WG Action: Application-Layer Traffic Optimization (alto).eml"

Return-Path: <root@core3.amsl.com>
Received: from hoemail1.alcatel.com (hoemail1.usa.alcatel.com [172.22.12.27])
	by umail.lucent.com (8.13.8/TPES) with ESMTP id mACJ03YO013674
	for <vkg@umail.lucent.com>; Wed, 12 Nov 2008 13:00:05 -0600 (CST)
Received: from mail.ietf.org (mail.ietf.org [64.170.98.32])
	by hoemail1.alcatel.com (8.13.8/IER-i) with ESMTP id mACJ0300009261
	for <vkg@alcatel-lucent.com>; Wed, 12 Nov 2008 13:00:03 -0600 (CST)
Received: by core3.amsl.com (Postfix, from userid 0)
	id 0BFD03A6A25; Wed, 12 Nov 2008 11:00:01 -0800 (PST)
From: IESG Secretary <iesg-secretary@ietf.org>
To: ietf-announce@ietf.org
Cc: jon.peterson@neustar.biz, enrico.marocco@telecomitalia.it,
        vkg@alcatel-lucent.com, alto@ietf.org
Subject: WG Action: Application-Layer Traffic Optimization (alto) 
Content-Type: text/plain; charset="utf-8"
Mime-Version: 1.0
Message-Id: <20081112190002.0BFD03A6A25@core3.amsl.com>
Date: Wed, 12 Nov 2008 11:00:02 -0800 (PST)
X-Scanned-By: MIMEDefang 2.57 on 192.160.6.148

A new IETF working group has been formed in the Applications Area.  For
additional information, please contact the Area Directors or the WG
Chairs.

Application-Layer Traffic Optimization (alto)
=============================================
Last Modified: 2008-11-03

Current Status: Active Working Group

Chair(s):

Jon Peterson [jon.peterson@neustar.biz]
Enrico Marocco [enrico.marocco@telecomitalia.it]
Vijay K. Gurbani [vkg@alcatel-lucent.com]

Applications Area Director(s):

Lisa Dusseault [lisa at osafoundation.org]
Chris Newman [Chris.Newman at sun.com]

Applications Area Advisor:

Lisa Dusseault [lisa at osafoundation.org]

Mailing List:

General Discussion: alto@ietf.org
To Subscribe: https://www.ietf.org/mailman/listinfo/alto
Archive: http://www.ietf.org/pipermail/alto/

Description of Working Group:

A significant part of the Internet traffic today is generated by
peer-to-peer (P2P) applications used for file sharing, real-time
communications, and live media streaming.  P2P applications exchange
large amounts of data, often uploading as much as downloading.  In
contrast to client/server architectures, P2P applications often must
choose one or more suitable candidates from a selection of peers
offering the same resource or service.

One of the advantages of P2P systems comes from redundancy in resource
availability.  This requires choosing among a list of peers, yet
applications have at best incomplete information to help the selection,
e.g., topology of the network.

Applications can sometimes obtain network information dynamically
or measure link performance with respect to particular peers, but
even when this is an option it takes time. The application cannot
always start out with an optimal arrangement of peers, thus risking
at least temporary poor performance and
excessive cross-domain traffic.  Providing more information for use in
peer selection can improve P2P performance and lower ISP costs.

The Working Group will design and specify an Application-Layer Traffic
Optimization (ALTO) service that will provide applications with
information to perform better-than-random initial peer selection.
ALTO services may take different approaches at balancing factors
such as maximum bandwidth, minimum cross-domain traffic, lowest cost to
the user, etc.  The WG will consider the needs of BitTorrent, tracker-less
P2P, and other applications, such as content delivery networks (CDN)
and mirror selection.

The WG will focus on the following items:

- A "problem statement" document providing a description of the
problem and a common terminology.

- A requirements document.  This document will list requirements for
the ALTO service, identifying, for example, types of information
P2P applications may need for optimizing their choices.

- A request/response protocol for querying the ALTO service to obtain
information useful for peer selection, and a format for requests and
responses
If the requirements analysis identifies the need to allow clients to
delegate third-parties to query the ALTO service on their behalf, the
WG will ensure that the protocol provides a mechanism to assert the
consent of the delegating client.

- A document defining core request and response formats and semantics
to communicate network preferences to applications.  Since ALTO
services may be run by entities with different level of knowledge
about the underlying network, such preferences may have different
representations. Initially the WG will consider: IP ranges to prefer
and to avoid, ranked lists of the peers requested by the client,
information about topological proximity and approximate geographic
locations.  Other usages will be considered as charter additions
once the work for the initial services has been completed.

- In order to query the ALTO server, clients must first know one or
more ALTO servers that might provide useful information.  The WG
will look at service discovery mechanisms that are in use, or
defined elsewhere (e.g. based on DNS SRV records or DHCP options).
If such discovery mechanisms can be reused, the WG will produce a
document to specify how they may be adopted for locating such
servers.  However, a new, general-purpose service discovery
mechanism is not in scope.

When the WG considers standardizing information that the ALTO server
could provide, the following criteria are important to ensure real
feasibility.

- Can the ALTO service realistically discover that information?

- Is the distribution of that information allowed by the operators of
that service?

- Is it information that a client will find useful?

- Can a client get that information without excessive privacy concerns
(e.g. by sending large lists of peers)?

- Is it information that a client cannot find easily some other way?

After these criteria are met, the importance of the data will be
considered for prioritizing standardization work, for example the
number of operators and clients that are likely to be able to provide
or use that particular data.  In any case, this WG will not propose
standards on how congestion is signaled, remediated, or avoided, and
will not deal with information representing instantaneous network
state.  Such issues belong to other IETF areas and will be treated
accordingly by the specific area.

This WG will focus solely on the communication protocol between
applications and ALTO servers.  Note that ALTO services may be useful
in client-server environments as well as P2P environments, although
P2P environments are the first focus.  If, in the future, the IETF
considers changes to other protocols for actually implementing ALTO
services (e.g. application-layer protocols for Internet coordinate
systems, routing protocol extensions for ISP-based solutions), such
work will be done in strict coordination with the appropriate WGs.

Issues related to the content exchanged in P2P systems are also
excluded from the WG's scope, as is the issue dealing with enforcing
the legality of the content.

Goals and Milestones (very tentative dates):

Apr 2009: Working Group Last Call for problem statement
Jun 2009: Submit problem statement to IESG as Informational
Aug 2009: Working Group Last Call for requirements document
Oct 2009: Submit requirements document to IESG as Informational
Jan 2010: Working Group Last Call for request/response protocol
Jan 2010: Working Group Last Call for usage document for communicating
network preferences
Mar 2010: Submit request/response protocol to IESG as Proposed Standard
Mar 2010: Submit usage document to IESG as Proposed Standard
May 2010: Working Group Last Call of discovery mechanism
Jul 2010: Submit discovery mechanism to IESG as Proposed Standard
Aug 2010: Dissolve or re-charter

Initial Drafts for Consideration

- draft-marocco-alto-problem-statement-02 -- Application-Layer Traffic
Optimization (ALTO) Problem Statement

- draft-kiesel-alto-reqs-00 -- Application-Layer Traffic Optimization
(ALTO) Requirements

--------------030809050904050603030102
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi

--------------030809050904050603030102--


From p2pi-bounces@ietf.org  Thu Nov 13 02:53:05 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 0CA733A6868;
	Thu, 13 Nov 2008 02:53:05 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 388443A6868
	for <p2pi@core3.amsl.com>; Thu, 13 Nov 2008 02:53:04 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.598
X-Spam-Level: 
X-Spam-Status: No, score=-2.598 tagged_above=-999 required=5
	tests=[BAYES_00=-2.599, HTML_MESSAGE=0.001]
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 7hksJ5bDfTig for <p2pi@core3.amsl.com>;
	Thu, 13 Nov 2008 02:53:02 -0800 (PST)
Received: from rv-out-0506.google.com (rv-out-0506.google.com [209.85.198.228])
	by core3.amsl.com (Postfix) with ESMTP id 728973A6807
	for <p2pi@ietf.org>; Thu, 13 Nov 2008 02:53:02 -0800 (PST)
Received: by rv-out-0506.google.com with SMTP id b25so811770rvf.49
	for <p2pi@ietf.org>; Thu, 13 Nov 2008 02:53:01 -0800 (PST)
Received: by 10.140.169.4 with SMTP id r4mr5431374rve.242.1226573581843;
	Thu, 13 Nov 2008 02:53:01 -0800 (PST)
Received: from ?192.168.1.103? (c-67-188-243-194.hsd1.ca.comcast.net
	[67.188.243.194])
	by mx.google.com with ESMTPS id k2sm31100171rvb.1.2008.11.13.02.53.00
	(version=TLSv1/SSLv3 cipher=RC4-MD5);
	Thu, 13 Nov 2008 02:53:01 -0800 (PST)
Message-Id: <51EB0268-A743-4D58-A268-0B8CFA56ECBD@shlang.com>
From: Stanislav Shalunov <shalunov@shlang.com>
To: p2pi@ietf.org,
 "tsv-area@ietf.org Area" <tsv-area@ietf.org>
Mime-Version: 1.0 (Apple Message framework v929.2)
Date: Thu, 13 Nov 2008 02:52:58 -0800
References: <20081111183001.3D9CF28C18D@core3.amsl.com>
X-Mailer: Apple Mail (2.929.2)
Subject: [p2pi] Fwd: WG Action: Low Extra Delay Background Transport (ledbat)
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: multipart/mixed; boundary="===============1441628924=="
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org


--===============1441628924==
Content-Type: multipart/alternative; boundary=Apple-Mail-1078--841724403


--Apple-Mail-1078--841724403
Content-Type: text/plain;
	charset=US-ASCII;
	format=flowed;
	delsp=yes
Content-Transfer-Encoding: 7bit

LEDBAT was formerly known as TANA.  If you were subscribed, your  
subscription should have been migrated.  If you were not and are  
interested, please consider subscribing to ledbat@ietf.org.

Thank you,  -- Stas



Begin forwarded message:

> From: IESG Secretary <iesg-secretary@ietf.org>
> Date: November 11, 2008 10:30:01 AM PST
> To: ietf-announce@ietf.org
> Cc: shalunov@shlang.com, muraris@microsoft.com, ledbat@ietf.org
> Subject: WG Action: Low Extra Delay Background Transport (ledbat)
>
> A new IETF working group has been formed in the Transport Area.  For
> additional information, please contact the Area Directors or the WG
> Chairs.
>
> Low Extra Delay Background Transport (ledbat)
> --------------------------------------------------------------
> Current Status: Active Working Group
>
> Last Modified: 2008-11-06
>
> Chair(s):
> * Stanislav Shalunov [shalunov@shlang.com]
> * Murari Sridhavan [muraris@microsoft.com]
>
> Transport Area Director(s):
> * Magnus Westerlund [magnus.westerlund@ericsson.com]
> * Lars Eggert [lars.eggert@nokia.com]
>
> Transport Area Advisor:
> * Lars Eggert [lars.eggert@nokia.com]
>
> Mailing Lists:
>
> General Discussion: ledbat@ietf.org
> To Subscribe: https://www.ietf.org/mailman/listinfo/ledbat
> In Body: (un)subscribe
> Archive: http://www.ietf.org/mail-archive/web/ledbat/
>
> Description of Working Group:
>
> The LEDBAT WG is chartered to standardize a congestion
> control mechanism that should saturate the bottleneck,
> maintain low delay, and yield to standard TCP.
>
> Applications that transmit large amounts of data for a long
> time with congestion-limited TCP, but without AQM, fill the
> buffer at the head of the bottleneck link. With FIFO queue,
> this increases the delay experienced by other applications.
> With buffer of one RTT, the delay doubles. In some cases,
> the extra delay may be much larger. This is a particularly
> acute and common case is when P2P applications upload over
> thin home uplinks: delays in these cases can sometimes be of
> the order of seconds.
>
> The IETF's standard end-to-end transport protocols have not
> been designed to minimize the extra delay introduced by them
> into the network. TCP, as a side effect of filling the
> buffer until it experiences drop-tail loss, effectively
> maximizes the delay. While this works well for applications
> that are not delay-sensitive, it harms interactive
> applications that share the same bottleneck. VoIP and games
> are particularly affected, but even web browsing may become
> problematic.
>
> LEDBAT is a transport-area WG that will focus on broadly
> applicable techniques that allow large amounts of data to be
> consistently transmitted without substantially affecting the
> delays experienced by other users and applications.
>
> The WG will work on the following:
>
> (1) An experimental congestion control algorithm for
> less-than-best-effort "background" transmissions, i.e., an
> algorithm that attempts to scavenge otherwise idle bandwidth
> for its transmissions in a way that minimizes interference
> with regular best-effort traffic.
>
> Desired features of such an algorithm are:
>
> * saturate the bottleneck
>
> * eliminate long standing queues and thus keep
> delay low when no other traffic is present
>
> * quickly yield to traffic sharing the same bottleneck queue
> that uses standard TCP congestion control
>
> * add little to the queueing delays induced by TCP traffic
>
> * operate well in networks with FIFO queueing with drop-tail
> discipline
>
> * be deployable for popular applications that currently
> comprise noticeable fractions of Internet traffic
>
> * where available, use explicit congestion notification (ECN),
> active queue management (AQM), and/or end-to-end
> differentiated services (DiffServ).
>
> Application of this algorithm to existing transport
> protocols (TCP, SCTP, DCCP) is expected to occur in the
> working groups that maintain those protocols.
>
> Once experience is gained with this congestion control
> algorithm on the Internet, the WG will consider if it is
> appropriate to ask the IESG to advance the document as a
> Proposed Standard.
>
> (2) A document that clarifies the current practices of
> application design and reasons behind them and discusses the
> tradeoffs surrounding the use of many concurrent TCP
> connections to one destination and/or to different
> destinations.
>
> Applications routinely open multiple TCP connections. For
> example, P2P applications maintain connections to a number
> of different peers while web browsers perform concurrent
> downloads from the same web server. Application designers
> pursue different goals when doing so: P2P apps need to
> maintain a well-connected mesh in the swarm while web
> browsers mainly use multiple connections to parallelize
> requests that involve application latency on the web server
> side. The IETF transport area community is concerned about
> this practice, because standard Internet congestion control
> results in different transport connections sharing
> bottleneck capacity. When an application uses several
> non-rate-limited transport connections to transfer through a
> bottleneck, it may obtain a larger fraction of the
> bottleneck than if it had used fewer connections. Although
> capacity is the most commonly considered bottleneck
> resource, middlebox state table entries are also an
> important resource for an end system communication. Other
> resource types may exist, and the guidelines are expected to
> comprehensively discuss them.
>
> Applications use a variety of techniques to mitigate these
> concerns. These techniques have not always been reviewed by
> the IETF and their interaction with TCP dynamics is poorly
> understood. The WG will document the known techniques,
> discussing the consequences and, where appropriate, provide
> guidance to application designers.
>
> Goals and Milestones:
>
> Oct 2009 Submit "Multiple Transport Connections in Applications  
> Design"
> to the IESG for consideration as an Informational RFC
>
> Oct 2009 Submit "Low Extra Delay Background Transport (LEDBAT)"
> to the IESG for consideration as an Experimental RFC

--
Stanislav Shalunov




--Apple-Mail-1078--841724403
Content-Type: text/html;
	charset=US-ASCII
Content-Transfer-Encoding: quoted-printable

<html><body style=3D"word-wrap: break-word; -webkit-nbsp-mode: space; =
-webkit-line-break: after-white-space; "><div>LEDBAT was formerly known =
as TANA. &nbsp;If you were subscribed, your subscription should have =
been migrated. &nbsp;If you were not and are interested, please consider =
subscribing to <a =
href=3D"mailto:ledbat@ietf.org">ledbat@ietf.org</a>.</div><div><br></div><=
div>Thank you, &nbsp;-- =
Stas</div><div><br></div><div><br></div><div><br><div>Begin forwarded =
message:</div><br class=3D"Apple-interchange-newline"><blockquote =
type=3D"cite"><div><div style=3D"margin-top: 0px; margin-right: 0px; =
margin-bottom: 0px; margin-left: 0px; "><font face=3D"Helvetica" =
size=3D"4" color=3D"#000000" style=3D"font: 14.0px Helvetica; color: =
#000000"><b>From: </b></font><font face=3D"Helvetica" size=3D"4" =
style=3D"font: 14.0px Helvetica">IESG Secretary &lt;<a =
href=3D"mailto:iesg-secretary@ietf.org">iesg-secretary@ietf.org</a>></font=
></div><div style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: =
0px; margin-left: 0px; "><font face=3D"Helvetica" size=3D"4" =
color=3D"#000000" style=3D"font: 14.0px Helvetica; color: =
#000000"><b>Date: </b></font><font face=3D"Helvetica" size=3D"4" =
style=3D"font: 14.0px Helvetica">November 11, 2008 10:30:01 AM =
PST</font></div><div style=3D"margin-top: 0px; margin-right: 0px; =
margin-bottom: 0px; margin-left: 0px; "><font face=3D"Helvetica" =
size=3D"4" color=3D"#000000" style=3D"font: 14.0px Helvetica; color: =
#000000"><b>To: </b></font><font face=3D"Helvetica" size=3D"4" =
style=3D"font: 14.0px Helvetica"><a =
href=3D"mailto:ietf-announce@ietf.org">ietf-announce@ietf.org</a></font></=
div><div style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: =
0px; margin-left: 0px; "><font face=3D"Helvetica" size=3D"4" =
color=3D"#000000" style=3D"font: 14.0px Helvetica; color: =
#000000"><b>Cc: </b></font><font face=3D"Helvetica" size=3D"4" =
style=3D"font: 14.0px Helvetica"><a =
href=3D"mailto:shalunov@shlang.com">shalunov@shlang.com</a>, <a =
href=3D"mailto:muraris@microsoft.com">muraris@microsoft.com</a>, <a =
href=3D"mailto:ledbat@ietf.org">ledbat@ietf.org</a></font></div><div =
style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; =
margin-left: 0px; "><font face=3D"Helvetica" size=3D"4" color=3D"#000000" =
style=3D"font: 14.0px Helvetica; color: #000000"><b>Subject: =
</b></font><font face=3D"Helvetica" size=3D"4" style=3D"font: 14.0px =
Helvetica"><b>WG Action: Low Extra Delay Background Transport =
(ledbat)<span =
class=3D"Apple-converted-space">&nbsp;</span></b></font></div><div =
style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; =
margin-left: 0px; min-height: 14px; "><br></div> </div><div>A new IETF =
working group has been formed in the Transport Area. =
&nbsp;For<br>additional information, please contact the Area Directors =
or the WG<br>Chairs.<br><br>Low Extra Delay Background Transport =
(ledbat) =
<br>--------------------------------------------------------------<br>Curr=
ent Status: Active Working Group<br><br>Last Modified: =
2008-11-06<br><br>Chair(s):<br>* Stanislav Shalunov [<a =
href=3D"mailto:shalunov@shlang.com">shalunov@shlang.com</a>]<br>* Murari =
Sridhavan [<a =
href=3D"mailto:muraris@microsoft.com">muraris@microsoft.com</a>]<br><br>Tr=
ansport Area Director(s):<br>* Magnus Westerlund [<a =
href=3D"mailto:magnus.westerlund@ericsson.com">magnus.westerlund@ericsson.=
com</a>]<br>* Lars Eggert [<a =
href=3D"mailto:lars.eggert@nokia.com">lars.eggert@nokia.com</a>]<br><br>Tr=
ansport Area Advisor:<br>* Lars Eggert [<a =
href=3D"mailto:lars.eggert@nokia.com">lars.eggert@nokia.com</a>]<br><br>Ma=
iling Lists:<br><br>General Discussion: <a =
href=3D"mailto:ledbat@ietf.org">ledbat@ietf.org</a><br>To Subscribe: <a =
href=3D"https://www.ietf.org/mailman/listinfo/ledbat">https://www.ietf.org=
/mailman/listinfo/ledbat</a><br>In Body: (un)subscribe<br>Archive: <a =
href=3D"http://www.ietf.org/mail-archive/web/ledbat/">http://www.ietf.org/=
mail-archive/web/ledbat/</a><br><br>Description of Working =
Group:<br><br>The LEDBAT WG is chartered to standardize a =
congestion<br>control mechanism that should saturate the =
bottleneck,<br>maintain low delay, and yield to standard =
TCP.<br><br>Applications that transmit large amounts of data for a =
long<br>time with congestion-limited TCP, but without AQM, fill =
the<br>buffer at the head of the bottleneck link. With FIFO =
queue,<br>this increases the delay experienced by other =
applications.<br>With buffer of one RTT, the delay doubles. In some =
cases,<br>the extra delay may be much larger. This is a =
particularly<br>acute and common case is when P2P applications upload =
over<br>thin home uplinks: delays in these cases can sometimes be =
of<br>the order of seconds.<br><br>The IETF's standard end-to-end =
transport protocols have not<br>been designed to minimize the extra =
delay introduced by them<br>into the network. TCP, as a side effect of =
filling the<br>buffer until it experiences drop-tail loss, =
effectively<br>maximizes the delay. While this works well for =
applications<br>that are not delay-sensitive, it harms =
interactive<br>applications that share the same bottleneck. VoIP and =
games<br>are particularly affected, but even web browsing may =
become<br>problematic.<br><br>LEDBAT is a transport-area WG that will =
focus on broadly<br>applicable techniques that allow large amounts of =
data to be<br>consistently transmitted without substantially affecting =
the<br>delays experienced by other users and applications.<br><br>The WG =
will work on the following:<br><br>(1) An experimental congestion =
control algorithm for<br>less-than-best-effort "background" =
transmissions, i.e., an<br>algorithm that attempts to scavenge otherwise =
idle bandwidth<br>for its transmissions in a way that minimizes =
interference<br>with regular best-effort traffic.<br><br>Desired =
features of such an algorithm are:<br><br>* saturate the =
bottleneck<br><br>* eliminate long standing queues and thus =
keep<br>delay low when no other traffic is present<br><br>* quickly =
yield to traffic sharing the same bottleneck queue<br>that uses standard =
TCP congestion control<br><br>* add little to the queueing delays =
induced by TCP traffic<br><br>* operate well in networks with FIFO =
queueing with drop-tail<br>discipline<br><br>* be deployable for popular =
applications that currently<br>comprise noticeable fractions of Internet =
traffic<br><br>* where available, use explicit congestion notification =
(ECN),<br>active queue management (AQM), and/or =
end-to-end<br>differentiated services (DiffServ).<br><br>Application of =
this algorithm to existing transport<br>protocols (TCP, SCTP, DCCP) is =
expected to occur in the<br>working groups that maintain those =
protocols.<br><br>Once experience is gained with this congestion =
control<br>algorithm on the Internet, the WG will consider if it =
is<br>appropriate to ask the IESG to advance the document as =
a<br>Proposed Standard.<br><br>(2) A document that clarifies the current =
practices of<br>application design and reasons behind them and discusses =
the<br>tradeoffs surrounding the use of many concurrent =
TCP<br>connections to one destination and/or to =
different<br>destinations.<br><br>Applications routinely open multiple =
TCP connections. For<br>example, P2P applications maintain connections =
to a number<br>of different peers while web browsers perform =
concurrent<br>downloads from the same web server. Application =
designers<br>pursue different goals when doing so: P2P apps need =
to<br>maintain a well-connected mesh in the swarm while web<br>browsers =
mainly use multiple connections to parallelize<br>requests that involve =
application latency on the web server<br>side. The IETF transport area =
community is concerned about<br>this practice, because standard Internet =
congestion control<br>results in different transport connections =
sharing<br>bottleneck capacity. When an application uses =
several<br>non-rate-limited transport connections to transfer through =
a<br>bottleneck, it may obtain a larger fraction of the<br>bottleneck =
than if it had used fewer connections. Although<br>capacity is the most =
commonly considered bottleneck<br>resource, middlebox state table =
entries are also an<br>important resource for an end system =
communication. Other<br>resource types may exist, and the guidelines are =
expected to<br>comprehensively discuss them.<br><br>Applications use a =
variety of techniques to mitigate these<br>concerns. These techniques =
have not always been reviewed by<br>the IETF and their interaction with =
TCP dynamics is poorly<br>understood. The WG will document the known =
techniques,<br>discussing the consequences and, where appropriate, =
provide<br>guidance to application designers.<br><br>Goals and =
Milestones:<br><br>Oct 2009 Submit "Multiple Transport Connections in =
Applications Design"<br>to the IESG for consideration as an =
Informational RFC<br><br>Oct 2009 Submit "Low Extra Delay Background =
Transport (LEDBAT)"<br>to the IESG for consideration as an Experimental =
RFC<br></div></blockquote></div><br><div> <div>--<br> <font =
face=3D"Garamond"><a href=3D"http://shlang.com/">Stanislav =
Shalunov</a></font><br><br> <a =
href=3D"http://feeds.feedburner.com/~r/shlang/~6/1"><img =
src=3D"http://feeds.feedburner.com/shlang.1.gif" alt=3D"Hacking =
Startups" style=3D"border:0"></a></div> </div><br></body></html>=

--Apple-Mail-1078--841724403--

--===============1441628924==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi

--===============1441628924==--


From p2pi-bounces@ietf.org  Thu Nov 13 03:03:32 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 938143A6905;
	Thu, 13 Nov 2008 03:03:32 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 444E93A687E;
	Thu, 13 Nov 2008 03:03:31 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.8
X-Spam-Level: 
X-Spam-Status: No, score=-1.8 tagged_above=-999 required=5
	tests=[BAYES_00=-2.599, SARE_SUB_RAND_LETTRS4=0.799]
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 Ub07RUq6qx8y; Thu, 13 Nov 2008 03:03:30 -0800 (PST)
Received: from av-tac-bru.cisco.com (odd-brew.cisco.com [144.254.15.119])
	by core3.amsl.com (Postfix) with ESMTP id 2C0BC3A6856;
	Thu, 13 Nov 2008 03:03:29 -0800 (PST)
X-TACSUNS: Virus Scanned
Received: from strange-brew.cisco.com (localhost [127.0.0.1])
	by av-tac-bru.cisco.com (8.11.7p3+Sun/8.11.7) with ESMTP id
	mADB3Dk13506; Thu, 13 Nov 2008 12:03:13 +0100 (CET)
Received: from [192.168.0.100] (ams3-vpn-dhcp5378.cisco.com [10.61.85.1])
	by strange-brew.cisco.com (8.11.7p3+Sun/8.11.7) with ESMTP id
	mADB34G13306; Thu, 13 Nov 2008 12:03:06 +0100 (CET)
User-Agent: Microsoft-Entourage/11.4.0.080122
Date: Thu, 13 Nov 2008 12:02:46 +0100
From: stefano previdi <sprevidi@cisco.com>
To: <p2prg@irtf.org>, <p2psip@ietf.org>, <p2pi@ietf.org>, <alto@ietf.org>,
	<ledbat@ietf.org>
Message-ID: <C541C7E6.7CB53%sprevidi@cisco.com>
Thread-Topic: IRTF - P2P Research Group
Thread-Index: AclFf1vLmi5mtLFyEd24OAAX8vOM8g==
Mime-version: 1.0
Cc: Volker Hilt <volkerh@alcatel-lucent.com>, Aaron Falk <falk@bbn.com>
Subject: [p2pi] IRTF - P2P Research Group
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org


Following the new creation of IETF WGs scoped around issues of
peer-to-peer applications (ALTO and LEDBAT) and considering the
interest into a forum where research topics related to p2p can
be discussed, we started an effort in order to re-activate the
IRTF Peer-to-peer Research Group with the proposed (updated)
charter below. The p2prg will of course interact with the IETF
P2P WGs (P2PSIP, ALTO, LEDBAT).

Any comments, feedback and suggestions are welcome.


Thanks.
s.

---------------------------------------------------------------------
IRTF
Peer-to-Peer Research Group (P2PRG)
-----------------------------------
Chair(s):
---------
TBD

Mailing Lists:
--------------
The email list is p2prg@irtf.org. You need not be a list member to send
mail to the list. To subscribe, visit the P2PRG mail page
(https://www.ietf.org/mailman/listinfo/p2prg) or send an email to
p2prg-request@irtf.org.

Website
-------
Documents and members only discussion mailing list can be found at the
P2Prg web site: 
http://trac.tools.ietf.org/group/irtf/trac/wiki/PeerToPeerResearchGroup

Charter
-------
Peer-to-Peer (P2P) is a way of structuring distributed applications such
that the individual nodes have symmetric roles. Rather than being
divided into clients and servers each with quite distinct roles (such as
Web clients vs. Web servers), in P2P applications each node can act as
both a client and a server. A key concept for P2P systems is therefore
to permit any two peers to communicate with one another in such a way
that either ought to be able to initiate the contact. P2P systems in
general are highly distributed, highly scalable to large numbers of
nodes and users, highly autonomous, and can lend themselves to anonymity.

Some historical examples of P2P systems are USENET servers, built on top
of NNTP, and inter-domain routing, built on top of BGP. More recent P2P
systems are file sharing networks such as Gnutella, BitTorrent,
eDonkey/eMule and voice-over-IP applications such as Skype.

While P2P systems are deployed and used on a large scale, many research
questions in the field of P2P remain open. For example, current P2P
systems often form their overlay networks based on application layer
information and ignore the structure and policies of the underlying
network infrastructure. As a result, peers often connect to peers in a
remote network even though an equivalent peer would be available in the
local network. This can lead to the inefficient use of network resources
and to conflicts between application- and network-level routing. Another
problem arises from the fact that many different P2P systems are defined
and deployed. It is desirable for users on one system to be able to
reach users on other P2P systems without requiring applications to
implement the mechanisms and protocols of all systems available.
Mechanisms for interconnecting and interoperability between P2P systems
are needed. Many P2P systems are based on distributed hash tables
(DHTs), which implement a distributed storage for key-value pairs. While
DHTs are effective in looking up a specific key, search and information
retrieval in DHTs remain challenging problems. Peer nodes in a P2P
network perform services for other peers. A challenge is therefore to
protect a P2P network against malicious nodes which may try to alter the
service or disable it. Finally, it is interesting to evaluate P2P
systems that are deployed to better understand the performance of
algorithms deployed and the behavior of user. Performance and usage data
is an important foundation for the development of new P2P mechanisms and
architectures. Mechanisms and tools that collect this information from
existing p2p systems are highly desirable.

Overall, the field of P2P technologies presents a number of interesting
challenges which includes new methods for forming P2P application
overlays, interconnecting distinct P2P application overlays, performing
routing and peer selection decisions, managing traffic and discovering
resources. Other challenges are related to storage, reliability, and
information retrieval in P2P systems. Yet another challenging area for
P2P is security, privacy, anonymity and trust. Finally, it is
challenging to examine P2P systems that are deployed, for example, to
measure, monitor and characterize P2P applications. The P2P RG will
collaborate with academia and industry on making progress addressing
these challenges.

The IETF has formed working groups to address specific issues of P2P
networking. During the development of standards for P2P networks in
these working groups, new research topics may arise that exceed the
working group charter and require a separate forum for discussion. The
P2P RG will provide such a forum. The IETF has chartered working groups
related to the following topics:
        - Peer-to-Peer SIP signaling (P2PSIP)
        - Application-Layer Traffic Optimization (ALTO)
        - Low Extra Delay Background Transport (LEDBAT)

Organization
------------
The P2PRG will maintain a list of prioritized topics in order to organize
the activity of the research group according to agreed importance and
priority.

The P2PRG will use an open mailing list (p2prg@irtf.org) as the main
communication vehicle for the group.

The P2PRG will encourage the organization of the work in smaller design
teams focused on specific areas of research. The design teams will use
the general mailing list in order to allow the broader community to
follow the evolution of their topics.

Most of the communication inside the P2PRG will be done through use of
mailing lists, however, the group will hold regular physical meetings
at least once a year in conjunction with IETF meetings.  Additional
meetings  may be held at IETF or other venues, such as in conjunction
with related academic conferences.

The P2PRG will produce Informational and Experimental RFCs in order to
document the activity of the group and to formalize the outcome of the
research topics carried by the group. In addition, such documentation
could become input to IETF working groups.

Membership
----------
The RG operates in an open fashion (meetings & mailing list).


_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Thu Nov 13 03:20:33 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 430CE3A690F;
	Thu, 13 Nov 2008 03:20:33 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 223323A6905
	for <p2pi@core3.amsl.com>; Thu, 13 Nov 2008 03:20:31 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.598
X-Spam-Level: 
X-Spam-Status: No, score=-2.598 tagged_above=-999 required=5
	tests=[BAYES_00=-2.599, HTML_MESSAGE=0.001]
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 MhYd+E5U6NiX for <p2pi@core3.amsl.com>;
	Thu, 13 Nov 2008 03:20:26 -0800 (PST)
Received: from rv-out-0506.google.com (rv-out-0506.google.com [209.85.198.235])
	by core3.amsl.com (Postfix) with ESMTP id 6D08E3A68C6
	for <p2pi@ietf.org>; Thu, 13 Nov 2008 03:20:26 -0800 (PST)
Received: by rv-out-0506.google.com with SMTP id g9so1612238rvb.2
	for <p2pi@ietf.org>; Thu, 13 Nov 2008 03:20:26 -0800 (PST)
Received: by 10.141.48.6 with SMTP id a6mr5434017rvk.36.1226575226253;
	Thu, 13 Nov 2008 03:20:26 -0800 (PST)
Received: from ?192.168.1.103? (c-67-188-243-194.hsd1.ca.comcast.net
	[67.188.243.194])
	by mx.google.com with ESMTPS id k41sm16857061rvb.4.2008.11.13.03.20.24
	(version=TLSv1/SSLv3 cipher=RC4-MD5);
	Thu, 13 Nov 2008 03:20:25 -0800 (PST)
Message-Id: <300C8924-619D-4462-AF47-000070C9C85F@shlang.com>
From: Stanislav Shalunov <shalunov@shlang.com>
To: p2pi@ietf.org,
 "tsv-area@ietf.org Area" <tsv-area@ietf.org>
In-Reply-To: <51EB0268-A743-4D58-A268-0B8CFA56ECBD@shlang.com>
Mime-Version: 1.0 (Apple Message framework v929.2)
Date: Thu, 13 Nov 2008 03:20:22 -0800
References: <20081111183001.3D9CF28C18D@core3.amsl.com>
	<51EB0268-A743-4D58-A268-0B8CFA56ECBD@shlang.com>
X-Mailer: Apple Mail (2.929.2)
Subject: Re: [p2pi] WG Action: Low Extra Delay Background Transport (ledbat)
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: multipart/mixed; boundary="===============1801309988=="
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org


--===============1801309988==
Content-Type: multipart/alternative; boundary=Apple-Mail-1170--840080234


--Apple-Mail-1170--840080234
Content-Type: text/plain;
	charset=US-ASCII;
	format=flowed;
	delsp=yes
Content-Transfer-Encoding: 7bit

P.S. The URL to subscribe is https://www.ietf.org/mailman/listinfo/ledbat

On Nov 13, 2008, at 2:52 AM, Stanislav Shalunov wrote:

> LEDBAT was formerly known as TANA.  If you were subscribed, your  
> subscription should have been migrated.  If you were not and are  
> interested, please consider subscribing to ledbat@ietf.org.
>
> Thank you,  -- Stas
>
>
>
> Begin forwarded message:
>
>> From: IESG Secretary <iesg-secretary@ietf.org>
>> Date: November 11, 2008 10:30:01 AM PST
>> To: ietf-announce@ietf.org
>> Cc: shalunov@shlang.com, muraris@microsoft.com, ledbat@ietf.org
>> Subject: WG Action: Low Extra Delay Background Transport (ledbat)
>>
>> A new IETF working group has been formed in the Transport Area.  For
>> additional information, please contact the Area Directors or the WG
>> Chairs.
>>
>> Low Extra Delay Background Transport (ledbat)
>> --------------------------------------------------------------
>> Current Status: Active Working Group
>>
>> Last Modified: 2008-11-06
>>
>> Chair(s):
>> * Stanislav Shalunov [shalunov@shlang.com]
>> * Murari Sridhavan [muraris@microsoft.com]
>>
>> Transport Area Director(s):
>> * Magnus Westerlund [magnus.westerlund@ericsson.com]
>> * Lars Eggert [lars.eggert@nokia.com]
>>
>> Transport Area Advisor:
>> * Lars Eggert [lars.eggert@nokia.com]
>>
>> Mailing Lists:
>>
>> General Discussion: ledbat@ietf.org
>> To Subscribe: https://www.ietf.org/mailman/listinfo/ledbat
>> In Body: (un)subscribe
>> Archive: http://www.ietf.org/mail-archive/web/ledbat/
>>
>> Description of Working Group:
>>
>> The LEDBAT WG is chartered to standardize a congestion
>> control mechanism that should saturate the bottleneck,
>> maintain low delay, and yield to standard TCP.
>>
>> Applications that transmit large amounts of data for a long
>> time with congestion-limited TCP, but without AQM, fill the
>> buffer at the head of the bottleneck link. With FIFO queue,
>> this increases the delay experienced by other applications.
>> With buffer of one RTT, the delay doubles. In some cases,
>> the extra delay may be much larger. This is a particularly
>> acute and common case is when P2P applications upload over
>> thin home uplinks: delays in these cases can sometimes be of
>> the order of seconds.
>>
>> The IETF's standard end-to-end transport protocols have not
>> been designed to minimize the extra delay introduced by them
>> into the network. TCP, as a side effect of filling the
>> buffer until it experiences drop-tail loss, effectively
>> maximizes the delay. While this works well for applications
>> that are not delay-sensitive, it harms interactive
>> applications that share the same bottleneck. VoIP and games
>> are particularly affected, but even web browsing may become
>> problematic.
>>
>> LEDBAT is a transport-area WG that will focus on broadly
>> applicable techniques that allow large amounts of data to be
>> consistently transmitted without substantially affecting the
>> delays experienced by other users and applications.
>>
>> The WG will work on the following:
>>
>> (1) An experimental congestion control algorithm for
>> less-than-best-effort "background" transmissions, i.e., an
>> algorithm that attempts to scavenge otherwise idle bandwidth
>> for its transmissions in a way that minimizes interference
>> with regular best-effort traffic.
>>
>> Desired features of such an algorithm are:
>>
>> * saturate the bottleneck
>>
>> * eliminate long standing queues and thus keep
>> delay low when no other traffic is present
>>
>> * quickly yield to traffic sharing the same bottleneck queue
>> that uses standard TCP congestion control
>>
>> * add little to the queueing delays induced by TCP traffic
>>
>> * operate well in networks with FIFO queueing with drop-tail
>> discipline
>>
>> * be deployable for popular applications that currently
>> comprise noticeable fractions of Internet traffic
>>
>> * where available, use explicit congestion notification (ECN),
>> active queue management (AQM), and/or end-to-end
>> differentiated services (DiffServ).
>>
>> Application of this algorithm to existing transport
>> protocols (TCP, SCTP, DCCP) is expected to occur in the
>> working groups that maintain those protocols.
>>
>> Once experience is gained with this congestion control
>> algorithm on the Internet, the WG will consider if it is
>> appropriate to ask the IESG to advance the document as a
>> Proposed Standard.
>>
>> (2) A document that clarifies the current practices of
>> application design and reasons behind them and discusses the
>> tradeoffs surrounding the use of many concurrent TCP
>> connections to one destination and/or to different
>> destinations.
>>
>> Applications routinely open multiple TCP connections. For
>> example, P2P applications maintain connections to a number
>> of different peers while web browsers perform concurrent
>> downloads from the same web server. Application designers
>> pursue different goals when doing so: P2P apps need to
>> maintain a well-connected mesh in the swarm while web
>> browsers mainly use multiple connections to parallelize
>> requests that involve application latency on the web server
>> side. The IETF transport area community is concerned about
>> this practice, because standard Internet congestion control
>> results in different transport connections sharing
>> bottleneck capacity. When an application uses several
>> non-rate-limited transport connections to transfer through a
>> bottleneck, it may obtain a larger fraction of the
>> bottleneck than if it had used fewer connections. Although
>> capacity is the most commonly considered bottleneck
>> resource, middlebox state table entries are also an
>> important resource for an end system communication. Other
>> resource types may exist, and the guidelines are expected to
>> comprehensively discuss them.
>>
>> Applications use a variety of techniques to mitigate these
>> concerns. These techniques have not always been reviewed by
>> the IETF and their interaction with TCP dynamics is poorly
>> understood. The WG will document the known techniques,
>> discussing the consequences and, where appropriate, provide
>> guidance to application designers.
>>
>> Goals and Milestones:
>>
>> Oct 2009 Submit "Multiple Transport Connections in Applications  
>> Design"
>> to the IESG for consideration as an Informational RFC
>>
>> Oct 2009 Submit "Low Extra Delay Background Transport (LEDBAT)"
>> to the IESG for consideration as an Experimental RFC
>
> --
> Stanislav Shalunov
>
>
>

--
Stanislav Shalunov




--Apple-Mail-1170--840080234
Content-Type: text/html;
	charset=US-ASCII
Content-Transfer-Encoding: quoted-printable

<html><body style=3D"word-wrap: break-word; -webkit-nbsp-mode: space; =
-webkit-line-break: after-white-space; "><div><div>P.S. The URL to =
subscribe is&nbsp;<a =
href=3D"https://www.ietf.org/mailman/listinfo/ledbat">https://www.ietf.org=
/mailman/listinfo/ledbat</a></div><div><br></div><div>On Nov 13, 2008, =
at 2:52 AM, Stanislav Shalunov wrote:</div><br =
class=3D"Apple-interchange-newline"><blockquote type=3D"cite"><div =
style=3D"word-wrap: break-word; -webkit-nbsp-mode: space; =
-webkit-line-break: after-white-space; "><div>LEDBAT was formerly known =
as TANA. &nbsp;If you were subscribed, your subscription should have =
been migrated. &nbsp;If you were not and are interested, please consider =
subscribing to <a =
href=3D"mailto:ledbat@ietf.org">ledbat@ietf.org</a>.</div><div><br></div><=
div>Thank you, &nbsp;-- =
Stas</div><div><br></div><div><br></div><div><br><div>Begin forwarded =
message:</div><br class=3D"Apple-interchange-newline"><blockquote =
type=3D"cite"><div><div style=3D"margin-top: 0px; margin-right: 0px; =
margin-bottom: 0px; margin-left: 0px; "><font face=3D"Helvetica" =
size=3D"4" color=3D"#000000" style=3D"font: 14.0px Helvetica; color: =
#000000"><b>From: </b></font><font face=3D"Helvetica" size=3D"4" =
style=3D"font: 14.0px Helvetica">IESG Secretary &lt;<a =
href=3D"mailto:iesg-secretary@ietf.org">iesg-secretary@ietf.org</a>></font=
></div><div style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: =
0px; margin-left: 0px; "><font face=3D"Helvetica" size=3D"4" =
color=3D"#000000" style=3D"font: 14.0px Helvetica; color: =
#000000"><b>Date: </b></font><font face=3D"Helvetica" size=3D"4" =
style=3D"font: 14.0px Helvetica">November 11, 2008 10:30:01 AM =
PST</font></div><div style=3D"margin-top: 0px; margin-right: 0px; =
margin-bottom: 0px; margin-left: 0px; "><font face=3D"Helvetica" =
size=3D"4" color=3D"#000000" style=3D"font: 14.0px Helvetica; color: =
#000000"><b>To: </b></font><font face=3D"Helvetica" size=3D"4" =
style=3D"font: 14.0px Helvetica"><a =
href=3D"mailto:ietf-announce@ietf.org">ietf-announce@ietf.org</a></font></=
div><div style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: =
0px; margin-left: 0px; "><font face=3D"Helvetica" size=3D"4" =
color=3D"#000000" style=3D"font: 14.0px Helvetica; color: =
#000000"><b>Cc: </b></font><font face=3D"Helvetica" size=3D"4" =
style=3D"font: 14.0px Helvetica"><a =
href=3D"mailto:shalunov@shlang.com">shalunov@shlang.com</a>, <a =
href=3D"mailto:muraris@microsoft.com">muraris@microsoft.com</a>, <a =
href=3D"mailto:ledbat@ietf.org">ledbat@ietf.org</a></font></div><div =
style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; =
margin-left: 0px; "><font face=3D"Helvetica" size=3D"4" color=3D"#000000" =
style=3D"font: 14.0px Helvetica; color: #000000"><b>Subject: =
</b></font><font face=3D"Helvetica" size=3D"4" style=3D"font: 14.0px =
Helvetica"><b>WG Action: Low Extra Delay Background Transport =
(ledbat)<span =
class=3D"Apple-converted-space">&nbsp;</span></b></font></div><div =
style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; =
margin-left: 0px; min-height: 14px; "><br></div> </div><div>A new IETF =
working group has been formed in the Transport Area. =
&nbsp;For<br>additional information, please contact the Area Directors =
or the WG<br>Chairs.<br><br>Low Extra Delay Background Transport =
(ledbat) =
<br>--------------------------------------------------------------<br>Curr=
ent Status: Active Working Group<br><br>Last Modified: =
2008-11-06<br><br>Chair(s):<br>* Stanislav Shalunov [<a =
href=3D"mailto:shalunov@shlang.com">shalunov@shlang.com</a>]<br>* Murari =
Sridhavan [<a =
href=3D"mailto:muraris@microsoft.com">muraris@microsoft.com</a>]<br><br>Tr=
ansport Area Director(s):<br>* Magnus Westerlund [<a =
href=3D"mailto:magnus.westerlund@ericsson.com">magnus.westerlund@ericsson.=
com</a>]<br>* Lars Eggert [<a =
href=3D"mailto:lars.eggert@nokia.com">lars.eggert@nokia.com</a>]<br><br>Tr=
ansport Area Advisor:<br>* Lars Eggert [<a =
href=3D"mailto:lars.eggert@nokia.com">lars.eggert@nokia.com</a>]<br><br>Ma=
iling Lists:<br><br>General Discussion: <a =
href=3D"mailto:ledbat@ietf.org">ledbat@ietf.org</a><br>To Subscribe: <a =
href=3D"https://www.ietf.org/mailman/listinfo/ledbat">https://www.ietf.org=
/mailman/listinfo/ledbat</a><br>In Body: (un)subscribe<br>Archive: <a =
href=3D"http://www.ietf.org/mail-archive/web/ledbat/">http://www.ietf.org/=
mail-archive/web/ledbat/</a><br><br>Description of Working =
Group:<br><br>The LEDBAT WG is chartered to standardize a =
congestion<br>control mechanism that should saturate the =
bottleneck,<br>maintain low delay, and yield to standard =
TCP.<br><br>Applications that transmit large amounts of data for a =
long<br>time with congestion-limited TCP, but without AQM, fill =
the<br>buffer at the head of the bottleneck link. With FIFO =
queue,<br>this increases the delay experienced by other =
applications.<br>With buffer of one RTT, the delay doubles. In some =
cases,<br>the extra delay may be much larger. This is a =
particularly<br>acute and common case is when P2P applications upload =
over<br>thin home uplinks: delays in these cases can sometimes be =
of<br>the order of seconds.<br><br>The IETF's standard end-to-end =
transport protocols have not<br>been designed to minimize the extra =
delay introduced by them<br>into the network. TCP, as a side effect of =
filling the<br>buffer until it experiences drop-tail loss, =
effectively<br>maximizes the delay. While this works well for =
applications<br>that are not delay-sensitive, it harms =
interactive<br>applications that share the same bottleneck. VoIP and =
games<br>are particularly affected, but even web browsing may =
become<br>problematic.<br><br>LEDBAT is a transport-area WG that will =
focus on broadly<br>applicable techniques that allow large amounts of =
data to be<br>consistently transmitted without substantially affecting =
the<br>delays experienced by other users and applications.<br><br>The WG =
will work on the following:<br><br>(1) An experimental congestion =
control algorithm for<br>less-than-best-effort "background" =
transmissions, i.e., an<br>algorithm that attempts to scavenge otherwise =
idle bandwidth<br>for its transmissions in a way that minimizes =
interference<br>with regular best-effort traffic.<br><br>Desired =
features of such an algorithm are:<br><br>* saturate the =
bottleneck<br><br>* eliminate long standing queues and thus =
keep<br>delay low when no other traffic is present<br><br>* quickly =
yield to traffic sharing the same bottleneck queue<br>that uses standard =
TCP congestion control<br><br>* add little to the queueing delays =
induced by TCP traffic<br><br>* operate well in networks with FIFO =
queueing with drop-tail<br>discipline<br><br>* be deployable for popular =
applications that currently<br>comprise noticeable fractions of Internet =
traffic<br><br>* where available, use explicit congestion notification =
(ECN),<br>active queue management (AQM), and/or =
end-to-end<br>differentiated services (DiffServ).<br><br>Application of =
this algorithm to existing transport<br>protocols (TCP, SCTP, DCCP) is =
expected to occur in the<br>working groups that maintain those =
protocols.<br><br>Once experience is gained with this congestion =
control<br>algorithm on the Internet, the WG will consider if it =
is<br>appropriate to ask the IESG to advance the document as =
a<br>Proposed Standard.<br><br>(2) A document that clarifies the current =
practices of<br>application design and reasons behind them and discusses =
the<br>tradeoffs surrounding the use of many concurrent =
TCP<br>connections to one destination and/or to =
different<br>destinations.<br><br>Applications routinely open multiple =
TCP connections. For<br>example, P2P applications maintain connections =
to a number<br>of different peers while web browsers perform =
concurrent<br>downloads from the same web server. Application =
designers<br>pursue different goals when doing so: P2P apps need =
to<br>maintain a well-connected mesh in the swarm while web<br>browsers =
mainly use multiple connections to parallelize<br>requests that involve =
application latency on the web server<br>side. The IETF transport area =
community is concerned about<br>this practice, because standard Internet =
congestion control<br>results in different transport connections =
sharing<br>bottleneck capacity. When an application uses =
several<br>non-rate-limited transport connections to transfer through =
a<br>bottleneck, it may obtain a larger fraction of the<br>bottleneck =
than if it had used fewer connections. Although<br>capacity is the most =
commonly considered bottleneck<br>resource, middlebox state table =
entries are also an<br>important resource for an end system =
communication. Other<br>resource types may exist, and the guidelines are =
expected to<br>comprehensively discuss them.<br><br>Applications use a =
variety of techniques to mitigate these<br>concerns. These techniques =
have not always been reviewed by<br>the IETF and their interaction with =
TCP dynamics is poorly<br>understood. The WG will document the known =
techniques,<br>discussing the consequences and, where appropriate, =
provide<br>guidance to application designers.<br><br>Goals and =
Milestones:<br><br>Oct 2009 Submit "Multiple Transport Connections in =
Applications Design"<br>to the IESG for consideration as an =
Informational RFC<br><br>Oct 2009 Submit "Low Extra Delay Background =
Transport (LEDBAT)"<br>to the IESG for consideration as an Experimental =
RFC<br></div></blockquote></div><br><div> <div>--<br> <font =
face=3D"Garamond"><a href=3D"http://shlang.com/">Stanislav =
Shalunov</a></font><br><br> <a =
href=3D"http://feeds.feedburner.com/~r/shlang/~6/1"><img =
src=3D"http://feeds.feedburner.com/shlang.1.gif" alt=3D"Hacking =
Startups" style=3D"border:0"></a></div> =
</div><br></div></blockquote></div><br><div> <div>--<br> <font =
face=3D"Garamond"><a href=3D"http://shlang.com/">Stanislav =
Shalunov</a></font><br><br> <a =
href=3D"http://feeds.feedburner.com/~r/shlang/~6/1"><img =
src=3D"http://feeds.feedburner.com/shlang.1.gif" alt=3D"Hacking =
Startups" style=3D"border:0"></a></div> </div><br></body></html>=

--Apple-Mail-1170--840080234--

--===============1801309988==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi

--===============1801309988==--


From p2pi-bounces@ietf.org  Thu Nov 13 08:08:46 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 3A6DE28C194;
	Thu, 13 Nov 2008 08:08:46 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 4200D3A698B;
	Thu, 13 Nov 2008 08:08:44 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -6.599
X-Spam-Level: 
X-Spam-Status: No, score=-6.599 tagged_above=-999 required=5
	tests=[BAYES_00=-2.599, RCVD_IN_DNSWL_MED=-4]
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 lHxM8BQr8jyT; Thu, 13 Nov 2008 08:08:43 -0800 (PST)
Received: from netra.cs.yale.edu (netra.cs.yale.edu [128.36.229.21])
	by core3.amsl.com (Postfix) with ESMTP id 5B7FD3A6826;
	Thu, 13 Nov 2008 08:08:43 -0800 (PST)
Received: from [127.0.0.1] (dhcp130132249228.its.yale.edu [130.132.249.228])
	by netra.cs.yale.edu (Postfix) with ESMTP id A88BE40948B;
	Thu, 13 Nov 2008 11:08:43 -0500 (EST)
Message-ID: <491C50ED.8080906@cs.yale.edu>
Date: Thu, 13 Nov 2008 11:08:13 -0500
From: "Y. Richard Yang" <yry@cs.yale.edu>
User-Agent: Thunderbird 2.0.0.17 (Windows/20080914)
MIME-Version: 1.0
To: alto@ietf.org, "p2pi@ietf.org" <p2pi@ietf.org>
Subject: [p2pi] P4P framework doc
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset="us-ascii"; Format="flowed"
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

Dear All,

We would like to point you to a document related with P4P that we are 
working on:
http://www-net.cs.yale.edu/projects/p4p/draft-p4p-framework.txt

It is not a spec but rather a key concepts/framework document.

The document is formated as an Internet Draft as we intend to submit it 
after IETF reopens
Internet draft submission. To reduce confusion, we labeled the document as
"**To Be Submitted Internet-Draft**". Since it is related with ALTO, we 
feel that
it is beneficial to make it available as soon as possible.

Any comments, questions, or suggestions are highly appreciated!

Looking forward to seeing many of you at IETF.

Best,
Richard Yang
http://www.cs.yale.edu/~yry/


_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


From p2pi-bounces@ietf.org  Tue Nov 18 11:42:00 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 5D5EA3A6885;
	Tue, 18 Nov 2008 11:42:00 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 17CB03A6885
	for <p2pi@core3.amsl.com>; Tue, 18 Nov 2008 11:42:00 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.998
X-Spam-Level: 
X-Spam-Status: No, score=-1.998 tagged_above=-999 required=5 tests=[AWL=0.600, 
	BAYES_00=-2.599, HTML_MESSAGE=0.001]
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 swx68iWVVU8B for <p2pi@core3.amsl.com>;
	Tue, 18 Nov 2008 11:41:59 -0800 (PST)
Received: from gv-out-0910.google.com (gv-out-0910.google.com [216.239.58.190])
	by core3.amsl.com (Postfix) with ESMTP id 1E0A63A677C
	for <p2pi@ietf.org>; Tue, 18 Nov 2008 11:41:57 -0800 (PST)
Received: by gv-out-0910.google.com with SMTP id e6so573505gvc.15
	for <p2pi@ietf.org>; Tue, 18 Nov 2008 11:41:56 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma;
	h=domainkey-signature:received:received:message-id:date:from:to
	:subject:mime-version:content-type;
	bh=FPhDcdVuipbGayb41amCeiB+Ig0sYnT8pk7NOppaHhg=;
	b=AezdEx/m6hPmBRgiW1WuuKjjhhrLIPNMSBSyJJQ1PlPJsd8o5xrrS8ptNVJ5aXlWGk
	QcXIRCW0oT7+mJqdVdK3KJ4EkdWRxToMropx2OQLSTDteaWu6EHu4EY74zM2/sjodAGQ
	iHDHA8SCQ9545cd5zUwrznfbns+0AD2/pj9lw=
DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma;
	h=message-id:date:from:to:subject:mime-version:content-type;
	b=EINkN/JDeyLaVXV7thm3MFJSDYhLtswJeN/wcaZQ5ouEeUwvWU7pqpqqPPpCMgNuAP
	1n61AERvq2QhG5UwSIKKiM7a0ytNXNUgGI/8p7DYsyFJhEHErKCxvoN89k1dnbb2y1sB
	JxJu5AEekDxTA654AP4r/xD57yz7lYN++UT/c=
Received: by 10.103.226.20 with SMTP id d20mr98872mur.8.1227037315634;
	Tue, 18 Nov 2008 11:41:55 -0800 (PST)
Received: by 10.103.94.12 with HTTP; Tue, 18 Nov 2008 11:41:55 -0800 (PST)
Message-ID: <8bd755250811181141r7e61ff32i2280c2cc244fcf1f@mail.gmail.com>
Date: Wed, 19 Nov 2008 03:41:55 +0800
From: "yunfei zhang" <hishigh@gmail.com>
To: p2pi@ietf.org
MIME-Version: 1.0
Subject: [p2pi] two solution drafts of alto
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Type: multipart/mixed; boundary="===============0892327472=="
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

--===============0892327472==
Content-Type: multipart/alternative; 
	boundary="----=_Part_76408_21531597.1227037315630"

------=_Part_76408_21531597.1227037315630
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

Dear all,
   This is yunfei from china mobile.I think the new problem statement is
much more clear. According to the problem statement, I've submitted two
drafts regarding the specific solutions,namely attp and traceroute.You can
find it in http://www.ietf.org/internet-drafts/draft-zhang-alto-attp-02.txtand
http://www.ietf.org/internet-drafts/draft-zhang-alto-traceroute-02.txt.
Comments and suggestions are highly appreciated.

                                                     Yunfei

------=_Part_76408_21531597.1227037315630
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

<div>Dear all,</div>
<div>&nbsp;&nbsp; This is yunfei from china mobile.I think the new problem statement is much more clear. According to the problem statement, I&#39;ve submitted two drafts regarding the specific solutions,namely attp and traceroute.You can find it in <a href="http://www.ietf.org/internet-drafts/draft-zhang-alto-attp-02.txt">http://www.ietf.org/internet-drafts/draft-zhang-alto-attp-02.txt</a> and <a href="http://www.ietf.org/internet-drafts/draft-zhang-alto-traceroute-02.txt">http://www.ietf.org/internet-drafts/draft-zhang-alto-traceroute-02.txt</a>. Comments and suggestions are highly appreciated.</div>

<div>&nbsp;</div>
<div>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Yunfei</div>

------=_Part_76408_21531597.1227037315630--

--===============0892327472==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi

--===============0892327472==--


From p2pi-bounces@ietf.org  Tue Nov 25 14:34:01 2008
Return-Path: <p2pi-bounces@ietf.org>
X-Original-To: p2pi-archive@ietf.org
Delivered-To: ietfarch-p2pi-archive@core3.amsl.com
Received: from [127.0.0.1] (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 72A9F3A6C6F;
	Tue, 25 Nov 2008 14:34:01 -0800 (PST)
X-Original-To: p2pi@core3.amsl.com
Delivered-To: p2pi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1])
	by core3.amsl.com (Postfix) with ESMTP id 33BBC28C1C7
	for <p2pi@core3.amsl.com>; Tue, 25 Nov 2008 14:34:00 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.599
X-Spam-Level: 
X-Spam-Status: No, score=-2.599 tagged_above=-999 required=5
	tests=[BAYES_00=-2.599]
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 j1ZKsyTrUCFz for <p2pi@core3.amsl.com>;
	Tue, 25 Nov 2008 14:33:59 -0800 (PST)
Received: from ihemail3.lucent.com (ihemail3.lucent.com [135.245.0.37])
	by core3.amsl.com (Postfix) with ESMTP id 2E7523A6C6F
	for <p2pi@ietf.org>; Tue, 25 Nov 2008 14:33:59 -0800 (PST)
Received: from umail.lucent.com (h135-3-40-61.lucent.com [135.3.40.61])
	by ihemail3.lucent.com (8.13.8/IER-o) with ESMTP id mAPMXt5u007238
	(version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO)
	for <p2pi@ietf.org>; Tue, 25 Nov 2008 16:33:55 -0600 (CST)
Received: from [135.185.236.17] (il0015vkg1.ih.lucent.com [135.185.236.17])
	by umail.lucent.com (8.13.8/TPES) with ESMTP id mAPMXt6u006057
	for <p2pi@ietf.org>; Tue, 25 Nov 2008 16:33:55 -0600 (CST)
Message-ID: <492C7D53.6000205@alcatel-lucent.com>
Date: Tue, 25 Nov 2008 16:33:55 -0600
From: "Vijay K. Gurbani" <vkg@alcatel-lucent.com>
Organization: Bell Labs Security Technology Research Group
User-Agent: Thunderbird 2.0.0.6 (Windows/20070728)
MIME-Version: 1.0
To: "p2pi@ietf.org" <p2pi@ietf.org>
X-Scanned-By: MIMEDefang 2.57 on 135.245.2.37
Subject: [p2pi] P2Pi list closing down
X-BeenThere: p2pi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <p2pi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/pipermail/p2pi>
List-Post: <mailto:p2pi@ietf.org>
List-Help: <mailto:p2pi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/p2pi>,
	<mailto:p2pi-request@ietf.org?subject=subscribe>
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset="us-ascii"; Format="flowed"
Sender: p2pi-bounces@ietf.org
Errors-To: p2pi-bounces@ietf.org

Folks: Just a reminder that this list will be closing down.

This list was established as a precursor to the alto and ledbat
mailing lists; now that these two are WGs in their own right,
all discussion should be moved there.

For those of you on the p2pi list that have not yet subscribed
to either alto or ledbat, here is the information to do so:

ALTO: https://www.ietf.org/mailman/listinfo/alto
LEDBAT: https://www.ietf.org/mailman/listinfo/ledbat

Thank,

- vijay
-- 
Vijay K. Gurbani, Bell Laboratories, Alcatel-Lucent
1960 Lucent Lane, Rm. 9C-533, Naperville, Illinois 60566 (USA)
Email: vkg@{alcatel-lucent.com,bell-labs.com,acm.org}
Web:   http://ect.bell-labs.com/who/vkg/
_______________________________________________
p2pi mailing list
p2pi@ietf.org
https://www.ietf.org/mailman/listinfo/p2pi


