From owner-ecm@wyvern.aciri.org Tue May 9 10:57:51 2000 Received: from wyvern.aciri.org (wyvern.aciri.org [192.150.187.14]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id KAA21924 for ; Tue, 9 May 2000 10:57:50 -0400 (EDT) Received: (from majordomo@localhost) by wyvern.aciri.org (8.9.3/8.9.3) id HAA87360 for ecm-outgoing; Tue, 9 May 2000 07:54:36 -0700 (PDT) (envelope-from owner-ecm@smtp.aciri.org) X-Authentication-Warning: wyvern.aciri.org: majordomo set sender to owner-ecm@smtp.aciri.org using -f Received: from scooby.lineone.net ([194.75.152.224]) by wyvern.aciri.org (8.9.3/8.9.3) with ESMTP id HAA87349; Tue, 9 May 2000 07:54:30 -0700 (PDT) (envelope-from charlie@ukdata.com) Received: from ukd ([195.171.177.9]) by scooby.lineone.net (8.9.3/8.9.3) with SMTP id PAA27470; Tue, 9 May 2000 15:45:47 +0100 (BST) Message-ID: <011f01bfb9c6$cc650960$09b1abc3@ukd> From: "Charlie Fletcher - www.ukdata.com" To: "Finance Director" Subject: Instant Credit Reports on all UK Businesses www.ukdata.com Date: Tue, 9 May 2000 15:52:05 +0100 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.00.2615.200 X-MimeOLE: Produced By Microsoft MimeOLE V5.00.2615.200 Sender: owner-ecm@aciri.org Precedence: bulk Content-Transfer-Encoding: 7bit Do you need fast accurate information to assist you when appraising potential customers, and suppliers? The UK Data internet website www.ukdata.com contains 28 million pages of data with full information on every UK company! Credit Reports-Director Searches-Accounts-Annual Returns All of these products and many more are available to you immediately, and can be downloaded to and printed from your personal computer. Free samples of all reports are available at www.ukdata.com. Please also visit www.formacompany.co.uk the on-line company formation website Thank You Charles Fletcher www.ukdata.com an instant report on every UK business www.formacompany.co.uk the on-line company formation site www.irishdata.ie - instant reports on all Irish companies From owner-ecm@wyvern.aciri.org Mon May 29 10:30:15 2000 Received: from wyvern.aciri.org (wyvern.aciri.org [192.150.187.14]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id KAA00654 for ; Mon, 29 May 2000 10:30:14 -0400 (EDT) Received: (from majordomo@localhost) by wyvern.aciri.org (8.9.3/8.9.3) id HAA36992 for ecm-outgoing; Mon, 29 May 2000 07:25:28 -0700 (PDT) (envelope-from owner-ecm@smtp.aciri.org) X-Authentication-Warning: wyvern.aciri.org: majordomo set sender to owner-ecm@smtp.aciri.org using -f Received: from rolex.csc.ncsu.edu (rolex.csc.ncsu.edu [152.1.213.197]) by wyvern.aciri.org (8.9.3/8.9.3) with ESMTP id HAA36987 for ; Mon, 29 May 2000 07:25:26 -0700 (PDT) (envelope-from rhee@eos.ncsu.edu) Received: (from rhee@localhost) by rolex.csc.ncsu.edu (8.8.4/UC02Jan97) id KAA05231; Mon, 29 May 2000 10:25:22 -0400 (EDT) From: "Dr. Injong Rhee" Message-Id: <10005291025.ZM5229@unity.ncsu.edu> Date: Mon, 29 May 2000 10:25:22 -0400 In-Reply-To: Hari Balakrishnan "A family of TCP-friendly congestion control algorithms" (May 28, 8:02pm) References: <200005290002.UAA22502@breeze.lcs.mit.edu> X-Mailer: Z-Mail (3.2.1 10oct95) To: Hari Balakrishnan , end2end-interest@isi.edu, ecm@aciri.org Subject: Re: A family of TCP-friendly congestion control algorithms Cc: bansal@lcs.mit.edu, hari@breeze.lcs.mit.edu Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: owner-ecm@aciri.org Precedence: bulk Hari, I would also like to direct your attention to our tcp-friendly paper which was announced a few weeks ago on end-to-end mailing list (it seems you might have missed it :-). The paper can be found in http://www.csc.ncsu.edu/faculty/rhee/export/tear_page It describes a scheme called TEAR (TCP emulation at receiver). By emulating TCP AIMD at the receiver, the receiver finds an equilibrium operating point without actually modulating tcp sending rates, and asks the sender to set its transmission rate to this point. Since the equilibrium point does not fluctuate as much as the actual cwnd values of TCP, TEAR smoothes the transmission rate very effectively while achieving tcp-friendliness. Some detailed comparison with TFRC can be found from the paper. Some bug fixes are reported from TFRC folks recently and we are testing the new version and conducting some more extensive simulation experiments suggested by TFRC folks as well. We will report the result in a couple of days. Stay tuned... Injong On May 28, 8:02pm, Hari Balakrishnan wrote: > Subject: A family of TCP-friendly congestion control algorithms > > We are pleased to announce the availability of a new paper on a family > of TCP-friendly congestion control algorithms that generalize > TCP-style additive-increase/multiplicative-decrease and have some > interesting properties, including their potential suitability for > streaming apps where drastic reductions in rates due to congestion > control may be unsuitable. In addition, the paper makes some general > observations about the behavior of increase/decrease mechanisms for > bandwidth-probing/congestion-reaction. > > This paper, titled "TCP-friendly Congestion Control for Real-time > Streaming Applications" is available as a technical report, > MIT-LCS-TR-806, from http://nms.lcs.mit.edu/papers/cm-binomial.html > (abstract attached below). > > Comments and suggestions are welcome. Thanks, > > Deepak Bansal & Hari Balakrishnan > {bansal,hari}@lcs.mit.edu > > --------------------------------------------------------------------- > > TCP-friendly Congestion Control for Real-time Streaming Applications > Deepak Bansal and Hari Balakrishnan > MIT Technical Report, MIT-LCS-TR-806. > > This paper introduces and analyzes a class of nonlinear congestion > control algorithms called "binomial algorithms," motivated in part by > the needs of streaming audio and video applications for which a > drastic reduction in transmission rate upon congestion is problematic. > Binomial algorithms generalize TCP-style additive-increase by > increasing inversely proportional to a power $k$ of the current window > (for TCP, $k=0$) ; they generalize TCP-style multiplicative-decrease > by decreasing proportional to a power $l$ of the current window (for > TCP, $l=1$). We show that there are an infinite number of deployable > TCP-friendly binomial algorithms, all of which satisfy $k+l=1$, and > that all binomial algorithms converge to fairness under a > synchronized-feedback assumption provided $k+l > 0; k,l >= 0$. Our > simulation results show that binomial algorithms interact well with > TCP across a RED bottleneck gateway. We focus on two particular > algorithms, IIAD (inverse-increase/additive-decrease, $k=1, l=0$) and > SQRT ($k=l=0.5$), showing that they are well-suited to applications > that do not react well to large TCP-style window reductions. We also > find that TCP-friendliness in terms of the relationship between > throughput and loss rate of an algorithm does not necessarily imply > fairness relative to TCP performance, especially for drop-tail > bottleneck gateways. >-- End of excerpt from Hari Balakrishnan -- Injong Rhee, Department of Computer Science North Carolina State University, Raleigh, NC 27695 Home page: http://www.csc.ncsu.edu/faculty/rhee Email: rhee@csc.ncsu.edu, Phone: 919-515-3305, Fax: 919-515-7925 From owner-ecm@wyvern.aciri.org Tue May 30 03:43:53 2000 Received: from wyvern.aciri.org (wyvern.aciri.org [192.150.187.14]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id DAA21848 for ; Tue, 30 May 2000 03:43:51 -0400 (EDT) Received: (from majordomo@localhost) by wyvern.aciri.org (8.9.3/8.9.3) id AAA42012 for ecm-outgoing; Tue, 30 May 2000 00:42:25 -0700 (PDT) (envelope-from owner-ecm@smtp.aciri.org) X-Authentication-Warning: wyvern.aciri.org: majordomo set sender to owner-ecm@smtp.aciri.org using -f Received: from hotmail.com (f169.law8.hotmail.com [216.33.241.169]) by wyvern.aciri.org (8.9.3/8.9.3) with SMTP id AAA42007 for ; Tue, 30 May 2000 00:42:24 -0700 (PDT) (envelope-from revirieg@hotmail.com) Received: (qmail 91870 invoked by uid 0); 30 May 2000 07:42:23 -0000 Message-ID: <20000530074223.91869.qmail@hotmail.com> Received: from 212.95.193.166 by www.hotmail.com with HTTP; Tue, 30 May 2000 00:42:23 PDT X-Originating-IP: [212.95.193.166] From: "Pedro Revriego" To: rhee@unity.ncsu.edu, hari@lcs.mit.edu, end2end-interest@isi.edu, ecm@aciri.org Cc: bansal@lcs.mit.edu, hari@breeze.lcs.mit.edu Subject: Re: A family of TCP-friendly congestion control algorithms Date: Tue, 30 May 2000 00:42:23 PDT Mime-Version: 1.0 Content-Type: text/plain; format=flowed Sender: owner-ecm@aciri.org Precedence: bulk Hi All, Yet another Technical report on TCP-Friendly Congestion Control. The abstract is included and the report is available at : http://www.icsi.berkeley.edu/techreports/index.html Any comments are most welcomed... Best Regards, Pedro Reviriego Variable Packet Size Equation Based Congestion Control Pedro Reviriego Vasallo tr-00-008.ps.gz April 2000 Abstract This report, extends previous work in equation-based congestion control for unicast traffic. Most best effort traffic on the internet is appropriately served by TCP which is the dominant transport protocol on the internet. However, there is a growing number of multimedia application for which TCP is not well suited. For those applications, several congestion control mechanisms have been proposed in order to avoid congestion collapse on the internet. One of them is the recently proposed TCP Friendly Rate Control Protocol (TFRC). It can be only used by flows that have a constant packet size. In this paper, we propose an extension to the TFRC protocol in order to support variable packet size flows. Variable packet size has been used for the transmission of video over the internet and is also used in voice applications. So it is important for a congestion control protocol to support variable packet size flows. We also explore the concept of fairness among flows when some of the flows send small packets. Currently, these flows are penalized by TFRC because it imitates TCP's behavior giving less throughput to flows that use small packets. We argue that if a flow is sending small packets because the application requires it to do so (for example to minimize delay in a voice over IP conversation) it should get the same amount of bandwidth as a TCP session using large packets. This results in a modified concept of TCP friendliness that we introduce in this paper. Finally we analyze some shortcomings of the equation used by TFRC to model TCP behavior and show that the impact of TCP timeouts are not completely modeled by the current TFRC equation. -------------------------------------------------------------------------------- ________________________________________________________________________ Get Your Private, Free E-mail from MSN Hotmail at http://www.hotmail.com