From matta at cs.bu.edu  Mon May  2 10:36:38 2005
From: matta at cs.bu.edu (Ibrahim Matta)
Date: Mon, 2 May 2005 13:36:38 -0400
Subject: [e2e] ICNP'05 deadlines (clarification)
Message-ID: <0511C607B17F804EBE96FFECD1FD9859319EDF@cs-exs2.cs-nt.bu.edu>

Dear Colleague,

Please note that May 6, 5pm PST is the deadline for registering the
title and the abstract of papers. Authors of already registered papers
can submit the actual paper by May 12, 11:59pm PST. These deadlines are
hard to keep up with a tight schedule. Please visit the web site
http://csr.bu.edu/icnp2005/ for detailed submission instructions.

Best regards,
Ibrahim

===
Ibrahim Matta, Associate Professor
Computer Science Department
Boston University, Boston, MA 02215, USA
Tel: (617) 358-1062, Fax: (617) 353-6457
matta at cs.bu.edu
http://www.cs.bu.edu/~matta 

From aaa at cs.stanford.edu  Wed May  4 18:54:17 2005
From: aaa at cs.stanford.edu (Amr A. Awadallah)
Date: Wed, 04 May 2005 18:54:17 -0700
Subject: [e2e] Google Web Accelerator ....
In-Reply-To: <0511C607B17F804EBE96FFECD1FD9859319EDF@cs-exs2.cs-nt.bu.edu>
References: <0511C607B17F804EBE96FFECD1FD9859319EDF@cs-exs2.cs-nt.bu.edu>
Message-ID: <42797CC9.40101@cs.stanford.edu>


Very interested to hear what folks think about this product from Google. 
As the network becomes faster, and most web servers support compression, 
is there still value in doing this ? I mean, there is Akamai for 
embedded objects, etc, but do we need it for the html pages too ?

http://webaccelerator.google.com/
http://webaccelerator.google.com/support.html

Google Web Accelerator uses various strategies to make your web pages 
load faster, including:

Sending your page requests through Google machines dedicated to handling
Google Web Accelerator traffic.

Storing copies of frequently looked at pages to make them quickly 
accessible.

Downloading only the updates if a web page has changed slightly since 
you last viewed it.

Prefetching certain pages onto your computer in advance.

Managing your Internet connection to reduce delays.

Compressing data before sending it to your computer.



From vikrantsk at gmail.com  Wed May  4 21:06:54 2005
From: vikrantsk at gmail.com (Vikrant Kaulgud)
Date: Thu, 5 May 2005 09:36:54 +0530
Subject: [e2e] Google Web Accelerator ....
In-Reply-To: <42797CC9.40101@cs.stanford.edu>
References: <0511C607B17F804EBE96FFECD1FD9859319EDF@cs-exs2.cs-nt.bu.edu>
	<42797CC9.40101@cs.stanford.edu>
Message-ID: <2cbceb1605050421062b3c9058@mail.gmail.com>

Hi,
I had checked this few days back. Prima facie, it seems to offer a
higher degree of personalization with intelligent caching etc. Another
question that always pops up in mind is: Google started as a search
company, why is it diversifying in to seemingly non-core areas like
email, web acceleration etc. Is Google becoming a monopoly?...

Rgds
Vikrant


On 5/5/05, Amr A. Awadallah <aaa at cs.stanford.edu> wrote:
> 
> Very interested to hear what folks think about this product from Google.
> As the network becomes faster, and most web servers support compression,
> is there still value in doing this ? I mean, there is Akamai for
> embedded objects, etc, but do we need it for the html pages too ?
> 
> http://webaccelerator.google.com/
> http://webaccelerator.google.com/support.html
> 
> Google Web Accelerator uses various strategies to make your web pages
> load faster, including:
> 
> Sending your page requests through Google machines dedicated to handling
> Google Web Accelerator traffic.
> 
> Storing copies of frequently looked at pages to make them quickly
> accessible.
> 
> Downloading only the updates if a web page has changed slightly since
> you last viewed it.
> 
> Prefetching certain pages onto your computer in advance.
> 
> Managing your Internet connection to reduce delays.
> 
> Compressing data before sending it to your computer.
> 
> 


-- 
-----------------
Regards,
Vikrant

From digitalove at gmail.com  Wed May  4 22:00:50 2005
From: digitalove at gmail.com (Ritesh Kumar)
Date: Thu, 5 May 2005 01:00:50 -0400
Subject: [e2e] Google Web Accelerator ....
In-Reply-To: <2cbceb1605050421062b3c9058@mail.gmail.com>
References: <0511C607B17F804EBE96FFECD1FD9859319EDF@cs-exs2.cs-nt.bu.edu>
	<42797CC9.40101@cs.stanford.edu>
	<2cbceb1605050421062b3c9058@mail.gmail.com>
Message-ID: <fc67f8b7050504220023609e92@mail.gmail.com>

    Actually, routing all your web requests through google will give
them a very good dataset for web page popularity. Infact giving a
web-caching service seems to be good service in exchange of that
"private" data.

Ritesh

On 5/5/05, Vikrant Kaulgud <vikrantsk at gmail.com> wrote:
> Hi,
> I had checked this few days back. Prima facie, it seems to offer a
> higher degree of personalization with intelligent caching etc. Another
> question that always pops up in mind is: Google started as a search
> company, why is it diversifying in to seemingly non-core areas like
> email, web acceleration etc. Is Google becoming a monopoly?...
> 
> Rgds
> Vikrant
> 
> 
> On 5/5/05, Amr A. Awadallah <aaa at cs.stanford.edu> wrote:
> >
> > Very interested to hear what folks think about this product from Google.
> > As the network becomes faster, and most web servers support compression,
> > is there still value in doing this ? I mean, there is Akamai for
> > embedded objects, etc, but do we need it for the html pages too ?
> >
> > http://webaccelerator.google.com/
> > http://webaccelerator.google.com/support.html
> >
> > Google Web Accelerator uses various strategies to make your web pages
> > load faster, including:
> >
> > Sending your page requests through Google machines dedicated to handling
> > Google Web Accelerator traffic.
> >
> > Storing copies of frequently looked at pages to make them quickly
> > accessible.
> >
> > Downloading only the updates if a web page has changed slightly since
> > you last viewed it.
> >
> > Prefetching certain pages onto your computer in advance.
> >
> > Managing your Internet connection to reduce delays.
> >
> > Compressing data before sending it to your computer.
> >
> >
> 
> --
> -----------------
> Regards,
> Vikrant
> 


-- 
http://www.cs.unc.edu/~ritesh/

From vikrantsk at gmail.com  Wed May  4 22:12:24 2005
From: vikrantsk at gmail.com (Vikrant)
Date: Thu, 5 May 2005 10:42:24 +0530
Subject: [e2e] e2e QoS
Message-ID: <2cbceb160505042212466b95f7@mail.gmail.com>

Hi,
Is e2e QoS or seamless QoS across heterogeneous networks a necessity?
Is there research going on currently in this space?

-- 
-----------------
Regards,
Vikrant

From vikrantsk at gmail.com  Wed May  4 22:19:48 2005
From: vikrantsk at gmail.com (Vikrant)
Date: Thu, 5 May 2005 10:49:48 +0530
Subject: [e2e] Google Web Accelerator ....
In-Reply-To: <fc67f8b7050504220023609e92@mail.gmail.com>
References: <0511C607B17F804EBE96FFECD1FD9859319EDF@cs-exs2.cs-nt.bu.edu>
	<42797CC9.40101@cs.stanford.edu>
	<2cbceb1605050421062b3c9058@mail.gmail.com>
	<fc67f8b7050504220023609e92@mail.gmail.com>
Message-ID: <2cbceb160505042219674bcdea@mail.gmail.com>

Yes, but that raises the spectre of privacy infringements now or in the future.


On 5/5/05, Ritesh Kumar <digitalove at gmail.com> wrote:
>    Actually, routing all your web requests through google will give
> them a very good dataset for web page popularity. Infact giving a
> web-caching service seems to be good service in exchange of that
> "private" data.
> 
> Ritesh
> 
> On 5/5/05, Vikrant Kaulgud <vikrantsk at gmail.com> wrote:
> > Hi,
> > I had checked this few days back. Prima facie, it seems to offer a
> > higher degree of personalization with intelligent caching etc. Another
> > question that always pops up in mind is: Google started as a search
> > company, why is it diversifying in to seemingly non-core areas like
> > email, web acceleration etc. Is Google becoming a monopoly?...
> >
> > Rgds
> > Vikrant
> >
> >
> > On 5/5/05, Amr A. Awadallah <aaa at cs.stanford.edu> wrote:
> > >
> > > Very interested to hear what folks think about this product from Google.
> > > As the network becomes faster, and most web servers support compression,
> > > is there still value in doing this ? I mean, there is Akamai for
> > > embedded objects, etc, but do we need it for the html pages too ?
> > >
> > > http://webaccelerator.google.com/
> > > http://webaccelerator.google.com/support.html
> > >
> > > Google Web Accelerator uses various strategies to make your web pages
> > > load faster, including:
> > >
> > > Sending your page requests through Google machines dedicated to handling
> > > Google Web Accelerator traffic.
> > >
> > > Storing copies of frequently looked at pages to make them quickly
> > > accessible.
> > >
> > > Downloading only the updates if a web page has changed slightly since
> > > you last viewed it.
> > >
> > > Prefetching certain pages onto your computer in advance.
> > >
> > > Managing your Internet connection to reduce delays.
> > >
> > > Compressing data before sending it to your computer.
> > >
> > >
> >
> > --
> > -----------------
> > Regards,
> > Vikrant
> >
> 
> --
> http://www.cs.unc.edu/~ritesh/
> 


-- 
-----------------
Regards,
Vikrant

From vikrantsk at gmail.com  Thu May  5 03:00:40 2005
From: vikrantsk at gmail.com (Vikrant)
Date: Thu, 5 May 2005 15:30:40 +0530
Subject: [e2e] Google Web Accelerator ....
In-Reply-To: <41B2D59B.8090701@hotpop.com>
References: <0511C607B17F804EBE96FFECD1FD9859319EDF@cs-exs2.cs-nt.bu.edu>
	<42797CC9.40101@cs.stanford.edu>
	<2cbceb1605050421062b3c9058@mail.gmail.com>
	<fc67f8b7050504220023609e92@mail.gmail.com>
	<2cbceb160505042219674bcdea@mail.gmail.com>
	<41B2D59B.8090701@hotpop.com>
Message-ID: <2cbceb1605050503005acad6f0@mail.gmail.com>

No, but access to user preferences via the web requests made by them does

On 12/5/04, alok <alokdube at hotpop.com> wrote:
> Does caching content consitute infringement at all?
> 
> 
> Vikrant wrote:
> 
> >Yes, but that raises the spectre of privacy infringements now or in the future.
> >
> >
> >On 5/5/05, Ritesh Kumar <digitalove at gmail.com> wrote:
> >
> >
> >>   Actually, routing all your web requests through google will give
> >>them a very good dataset for web page popularity. Infact giving a
> >>web-caching service seems to be good service in exchange of that
> >>"private" data.
> >>
> >>Ritesh
> >>
> >>On 5/5/05, Vikrant Kaulgud <vikrantsk at gmail.com> wrote:
> >>
> >>
> >>>Hi,
> >>>I had checked this few days back. Prima facie, it seems to offer a
> >>>higher degree of personalization with intelligent caching etc. Another
> >>>question that always pops up in mind is: Google started as a search
> >>>company, why is it diversifying in to seemingly non-core areas like
> >>>email, web acceleration etc. Is Google becoming a monopoly?...
> >>>
> >>>Rgds
> >>>Vikrant
> >>>
> >>>
> >>>On 5/5/05, Amr A. Awadallah <aaa at cs.stanford.edu> wrote:
> >>>
> >>>
> >>>>Very interested to hear what folks think about this product from Google.
> >>>>As the network becomes faster, and most web servers support compression,
> >>>>is there still value in doing this ? I mean, there is Akamai for
> >>>>embedded objects, etc, but do we need it for the html pages too ?
> >>>>
> >>>>http://webaccelerator.google.com/
> >>>>http://webaccelerator.google.com/support.html
> >>>>
> >>>>Google Web Accelerator uses various strategies to make your web pages
> >>>>load faster, including:
> >>>>
> >>>>Sending your page requests through Google machines dedicated to handling
> >>>>Google Web Accelerator traffic.
> >>>>
> >>>>Storing copies of frequently looked at pages to make them quickly
> >>>>accessible.
> >>>>
> >>>>Downloading only the updates if a web page has changed slightly since
> >>>>you last viewed it.
> >>>>
> >>>>Prefetching certain pages onto your computer in advance.
> >>>>
> >>>>Managing your Internet connection to reduce delays.
> >>>>
> >>>>Compressing data before sending it to your computer.
> >>>>
> >>>>
> >>>>
> >>>>
> >>>--
> >>>-----------------
> >>>Regards,
> >>>Vikrant
> >>>
> >>>
> >>>
> >>--
> >>http://www.cs.unc.edu/~ritesh/
> >>
> >>
> >>
> >
> >
> >
> >
> 
> 


-- 
-----------------
Regards,
Vikrant

From alokdube at hotpop.com  Thu May  5 03:59:27 2005
From: alokdube at hotpop.com (alok)
Date: Thu, 05 May 2005 10:59:27 -0000
Subject: [e2e] Google Web Accelerator ....
In-Reply-To: <2cbceb1605050503005acad6f0@mail.gmail.com>
References: <0511C607B17F804EBE96FFECD1FD9859319EDF@cs-exs2.cs-nt.bu.edu>	
	<42797CC9.40101@cs.stanford.edu>	
	<2cbceb1605050421062b3c9058@mail.gmail.com>	
	<fc67f8b7050504220023609e92@mail.gmail.com>	
	<2cbceb160505042219674bcdea@mail.gmail.com>	
	<41B2D59B.8090701@hotpop.com>
	<2cbceb1605050503005acad6f0@mail.gmail.com>
Message-ID: <41B2E5F8.3090609@hotpop.com>

Hi,

Even Credit card companies do that, they keep track of where one spends 
and then send in their advertisements accordingly.

My question is more of "how do they track the user"? I can understand if 
the user has some unique identifier, but I think it work via things like 
messaging software too, even if I untick the preference when I download 
the software.

Would the not amount to a greater flaw, the fact that someone gives you 
a software without saying "this could be used to track your activities"? 
Does any software today write that?

And even if they do, most users dont get around to reading it as it pops 
up on the worst formatted page on the whole download cycle and the 
default the options will always say "yes send me everything"

And ofcourse it always works the reverse when it actually should be used:
example: M$'s default of 'this software has crashed'
 "send" "dont send" and highlight "dont send" ;)

-thanks

Vikrant wrote:

>No, but access to user preferences via the web requests made by them does
>
>On 12/5/04, alok <alokdube at hotpop.com> wrote:
>  
>
>>Does caching content consitute infringement at all?
>>
>>
>>Vikrant wrote:
>>
>>    
>>
>>>Yes, but that raises the spectre of privacy infringements now or in the future.
>>>
>>>
>>>On 5/5/05, Ritesh Kumar <digitalove at gmail.com> wrote:
>>>
>>>
>>>      
>>>
>>>>  Actually, routing all your web requests through google will give
>>>>them a very good dataset for web page popularity. Infact giving a
>>>>web-caching service seems to be good service in exchange of that
>>>>"private" data.
>>>>
>>>>Ritesh
>>>>
>>>>On 5/5/05, Vikrant Kaulgud <vikrantsk at gmail.com> wrote:
>>>>
>>>>
>>>>        
>>>>
>>>>>Hi,
>>>>>I had checked this few days back. Prima facie, it seems to offer a
>>>>>higher degree of personalization with intelligent caching etc. Another
>>>>>question that always pops up in mind is: Google started as a search
>>>>>company, why is it diversifying in to seemingly non-core areas like
>>>>>email, web acceleration etc. Is Google becoming a monopoly?...
>>>>>
>>>>>Rgds
>>>>>Vikrant
>>>>>
>>>>>
>>>>>On 5/5/05, Amr A. Awadallah <aaa at cs.stanford.edu> wrote:
>>>>>
>>>>>
>>>>>          
>>>>>
>>>>>>Very interested to hear what folks think about this product from Google.
>>>>>>As the network becomes faster, and most web servers support compression,
>>>>>>is there still value in doing this ? I mean, there is Akamai for
>>>>>>embedded objects, etc, but do we need it for the html pages too ?
>>>>>>
>>>>>>http://webaccelerator.google.com/
>>>>>>http://webaccelerator.google.com/support.html
>>>>>>
>>>>>>Google Web Accelerator uses various strategies to make your web pages
>>>>>>load faster, including:
>>>>>>
>>>>>>Sending your page requests through Google machines dedicated to handling
>>>>>>Google Web Accelerator traffic.
>>>>>>
>>>>>>Storing copies of frequently looked at pages to make them quickly
>>>>>>accessible.
>>>>>>
>>>>>>Downloading only the updates if a web page has changed slightly since
>>>>>>you last viewed it.
>>>>>>
>>>>>>Prefetching certain pages onto your computer in advance.
>>>>>>
>>>>>>Managing your Internet connection to reduce delays.
>>>>>>
>>>>>>Compressing data before sending it to your computer.
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>>            
>>>>>>
>>>>>--
>>>>>-----------------
>>>>>Regards,
>>>>>Vikrant
>>>>>
>>>>>
>>>>>
>>>>>          
>>>>>
>>>>--
>>>>http://www.cs.unc.edu/~ritesh/
>>>>
>>>>
>>>>
>>>>        
>>>>
>>>
>>>
>>>      
>>>
>>    
>>
>
>
>  
>



From nossdav2005 at cs.unc.edu  Mon May  9 11:40:58 2005
From: nossdav2005 at cs.unc.edu (nossdav2005@cs.unc.edu)
Date: Mon, 09 May 2005 14:40:58 -0400
Subject: [e2e] [nossdav2005] NOSSDAV 2005 Call For Participation
Message-ID: <LYRIS-4239928-9046319-2005.05.09-14.41.00--end2end-interest#postel.org@listserv.unc.edu>

                           CALL FOR PARTICIPATION

                                NOSSDAV 2005
                        http://www.nossdav.org/2005/

        15th ACM International Workshop on Network and Operating
                System Support for Digital Audio and Video


For fifteen years, NOSSDAV has fostered cutting-edge state-of-the-art
research in multimedia and newly emerging areas such as networked
games and peer-to-peer streaming. The workshop environment encourages
lively discussion among participants and invites strong feedback for
work in progress. For 2005, NOSSDAV will take place in Skamania,
Washington. Located along the beautiful Columbia River about 30 miles
east of Portland, Oregon, Skamania offers a variety of outdoor
activities including golf, river rafting, kayaking, hiking, and quaint
riverfront towns steeped in Lewis-and-Clark-era history.

This year's program includes 33 papers from researchers around the
world. The full program can be found at the workshop website. 
We are also delighted to invite Prof. Harrick Vin as our keynote speaker. 
Prof. Vin has been a long-time contributer to the NOSSDAV community and is 
the  founding Directory of the Distributed Multimedia Computing Laboratory
and co-Directory of the Laboratory of Advanced Systems Research at
UT Austin.

As always, student participation is strongly encouraged. To encourage
a good mix of seasoned researchers as well as students, we will be
offering discounted registration for student members who attend with
their faculty advisor.

More information is available at the workshop website:
    http://www.nossdav.org/2005

Sponsored by ACM SIGMultimedia and in cooperation with SIGMobile.

Workshop Co-Chairs:
   Wu-Chi Feng (Portland State University, wuchi at cs.pdx.edu)
   Ketan Mayer-Patel (University of North Carolina, kmp at cs.unc.edu)

Program Committee:

Kevin Almeroth          University of California, Santa Barbara (USA)
Surendar Chandra        Notre Dame (USA)
Wu-Chang Feng           Portland State University (USA)
Carsten Griwodz         University of Oslo (Norway)
Kevin Jeffay            University of North Carolina, Chapel Hill (USA)
Andreas Maute           Lancaster University (UK)
Sue Moon                KAIST (Korea)
Reza Rejaie             University of Oregon (USA)
Henning Schulzrinne     Columbia University (USA)
Prashant Shenoy         University of Massachusetts, Amherst (USA)
Cormac Sreenan          University College Cork (Ireland)
Ooi Wei Tsang           National University of Singapore (Singapore)
Jon Walpole             Portland State University (USA)
Dongyan Xu              Purdue University (USA)


From dedinski at fmi.uni-passau.de  Tue May 10 00:55:11 2005
From: dedinski at fmi.uni-passau.de (Ivan Dedinski)
Date: Tue, 10 May 2005 09:55:11 +0200
Subject: [e2e] IWQoS 2005 Call for Participation
In-Reply-To: <20050427073703.2658.qmail@web15408.mail.cnb.yahoo.com>
References: <20050427073703.2658.qmail@web15408.mail.cnb.yahoo.com>
Message-ID: <428068DF.20201@fmi.uni-passau.de>

Please accept our apologies for multiple copies


CALL FOR PARTICIPATION

********************************************************************
* Thirteenth International Workshop on Quality of Service
* (IWQoS 2005), co-sponsored by IFIP, IEEE, ACM, GI, and EuroNGI
* June 21-23, 2005
* University of Passau, Germany
* http://www.fmi.uni-passau.de/iwqos
*********************************************************************

The 13th IWQoS is hosted by the University of Passau in the ancient and 
historic town of Passau, Germany. IWQoS 2005 will not only live up to 
the excellent technical repuation of its predecessor events but will 
also excell by a rich cultural and social program that will be offered 
at Passau's charming location at the confluence of the three rivers: 
Danube, Inn and Ilz. IWQoS 2005 has been designed to be particulary 
highly interactive and to confront industrial practice with academic 
research.

The program 
(http://www.fmi.uni-passau.de/lehrstuehle/demeer/iwqos/programm.html) 
includes the following highlights:

*******************
Keynote Speakers:
*******************
Randy Katz, "Quality of Service versus Any Service at All", University 
of California, Berkeley, USA
(co-authored by George Porter, Ion Stoica, Scott Shenker and Mel Tsai)

Michael Stal, "Beyond Middleware and QoS - Service-Oriented 
Architectures - Cult or Culture?", Siemens Munich, Germany

********************
Full Paper Sessions:
********************
QoS in Overlay Network
QoS in Wireless Environments
The User Experience of QoS
QoS in Large Scale Systems
Stochastic QoS
QoS in 3rd / 4th Generation Mobile Systems

**************
Panel Session:
**************
?Would self-organized or self-managed networks lead to improved QoS??
by David Hutchison, Lancaster Univ., U.K.

Panellists
G?sli Hj?lmt?sson, Reykjav?k University, Iceland, James P.G. Sterbenz, 
University of Massachussets, Amherst, USA, Giorgio Ventre, University of 
Napoli, Italy, John Vicente, Intel Corporation, USA

**********************
Short paper sessions:
**********************
(1) The Impact of QoS - Where Industry Meets Academia
Part I: QoS in Wireless and Wired Networks, Why Is This Needed?
Part II: Stateful QoS versus Overprovisioning

(2) Work in Progress - Innovative, Provocative and Visionary Statements

*****************************************
Industrial Exhibition and Demonstration
*****************************************

of Tools and Methods related to Quality of Service

******************
Important Dates:
******************
- Hotel reservation cut-off date: May 19th , 2005
(http://www.fmi.uni-passau.de/lehrstuehle/demeer/iwqos/hotel.html)
- Early online registration: May 19th 2005
(http://www.fmi.uni-passau.de/lehrstuehle/demeer/iwqos/reg.html)
- Regular online registration: May 20th - June 20th 2005
(http://www.fmi.uni-passau.de/lehrstuehle/demeer/iwqos/reg.html)
- Late online registration/On-site registration: June 21th - June 23th 2005
- Workshop dates: June 21-23 , 2005
- Workshop reception and welcome party: June 20th, 2005

**************
Social Events:
**************
Monday, 20.06.05
Early Afternoon: Guided Historic Passau Sigthtseeing Tour
Get-Together and Welcome Reception Party

Tuesday, 21.06.05:
Conference Dinner and Banquet at Neuburg Castle

Wednesday, 22.06.05:
Organ Concert in St. Stephan's Cathedral (the world's biggest church organ)
PC Meeting and Dinner (Program Committee only) in "Altem Br?uhaus"

Please have a look at http://www.fmi.uni-passau.de/iwqos for detailed 
information about IWQoS 2005


We are looking forward to welcome you at Passau, June 20th - 23rd 2005!
Best Regards,

Hermann De Meer, University of Passau, Passau, Germany
Nina Bhatti, Hewlett Packard Laboratories, Palo Alto, California USA


IWQoS 2005 (Program) Co-Chairs

From sgovind at hpc.serc.iisc.ernet.in  Sun May 15 09:33:20 2005
From: sgovind at hpc.serc.iisc.ernet.in (S.Govind)
Date: Sun, 15 May 2005 22:03:20 +0530 (IST)
Subject: [e2e] packet reordering in OC 48 links
Message-ID: <Pine.LNX.4.44.0505152202410.2445-100000@hpc.serc.iisc.ernet.in>

hi all


I have currently programmed the intel IXP 2400 Network Processor for IPv4 
forwarding.
Iam able to support line rates up to 3 Gbps (without any QoS provisioning) 
but an area of concern is the reordering, i obtain reordering up to 33% 
(ie: 33 % packets are reordered )for a link with 4000 flows a second 
each TCP flow of size 6.4 KB and 14% reordering for flow size of 640 B.

The packets are assumed to be arriving at a constant interval of time and 
of constant size (64 B ), this assumption is used for DoS attacks.

I am novice in networking, i have a few queries regarding the above 
results.

Are these numbers (reordering) indicative of current OC 48 links, 


Any comments and/or suggestions on the above  is most welcome

Thanking You,
Govind


-- 



From nischal at lamar.colostate.edu  Sun May 15 13:42:41 2005
From: nischal at lamar.colostate.edu (Nischal Piratla)
Date: Sun, 15 May 2005 14:42:41 -0600
Subject: [e2e] packet reordering in OC 48 links
Message-ID: <42E10F8D@webmail.colostate.edu>

Govind,
We feel that it is quite reasonable to see such high amounts of reordering. In 
fact, we are working on this very problem.

Most of the reordering that occurs within the routers is countered by either 
input reordering (packets of same flow are added to same queue) or output 
reordering (packets from same flow are tagged at the input, and are collected 
to be sent in order at the output). However, due to increasing table sizes, 
difference in the rates of increase in network speeds vs. the computing 
speeds, etc., higher parallelism is inevitable and the methods stated above 
may not be useful. We discussed a little more about it in our recent paper:

http://lamar.colostate.edu/~nischal/Papers/Networking2005_RD.pdf

Also, to understand the amount and extent of reordering, we suggest 'Reorder 
Density' metric that comprehensively illustrates reordering. There are perl 
scripts and Java applets readily available for the same on this site:

http://www.cnrl.colostate.edu/packet_reorder.html

- Nischal Piratla


>===== Original Message From "S.Govind" <sgovind at hpc.serc.iisc.ernet.in> =====
>hi all
>
>
>I have currently programmed the intel IXP 2400 Network Processor for IPv4
>forwarding.
>Iam able to support line rates up to 3 Gbps (without any QoS provisioning)
>but an area of concern is the reordering, i obtain reordering up to 33%
>(ie: 33 % packets are reordered )for a link with 4000 flows a second
>each TCP flow of size 6.4 KB and 14% reordering for flow size of 640 B.
>
>The packets are assumed to be arriving at a constant interval of time and
>of constant size (64 B ), this assumption is used for DoS attacks.
>
>I am novice in networking, i have a few queries regarding the above
>results.
>
>Are these numbers (reordering) indicative of current OC 48 links,
>
>
>Any comments and/or suggestions on the above  is most welcome
>
>Thanking You,
>Govind
>
>
>--

/******************************************
Research Assistant
Computer Networking Research Laboratory
Department of Electrical and Computer Eng.
1373, Colorado State University, 
Fort Collins, CO 80523 USA
http://www.cnrl.colostate.edu
http://lamar.colostate.edu/~nischal
*******************************************


From cannara at attglobal.net  Sun May 15 14:57:21 2005
From: cannara at attglobal.net (Cannara)
Date: Sun, 15 May 2005 14:57:21 -0700
Subject: [e2e] packet reordering in OC 48 links
References: <42E10F8D@webmail.colostate.edu>
Message-ID: <4287C5C1.AD100A0D@attglobal.net>

The problem has been solved by some network-processor vendors for a few years
now.  For example, see the specs for the IQ2200 by Vitesse, that's been used
to handle 4 parallel, FDX 1Gb/s ports in equipment by various manufacturers,
including Cisco.

Alex

Nischal Piratla wrote:
> 
> Govind,
> We feel that it is quite reasonable to see such high amounts of reordering. In
> fact, we are working on this very problem.
> 
> Most of the reordering that occurs within the routers is countered by either
> input reordering (packets of same flow are added to same queue) or output
> reordering (packets from same flow are tagged at the input, and are collected
> to be sent in order at the output). However, due to increasing table sizes,
> difference in the rates of increase in network speeds vs. the computing
> speeds, etc., higher parallelism is inevitable and the methods stated above
> may not be useful. We discussed a little more about it in our recent paper:
> 
> http://lamar.colostate.edu/~nischal/Papers/Networking2005_RD.pdf
> 
> Also, to understand the amount and extent of reordering, we suggest 'Reorder
> Density' metric that comprehensively illustrates reordering. There are perl
> scripts and Java applets readily available for the same on this site:
> 
> http://www.cnrl.colostate.edu/packet_reorder.html
> 
> - Nischal Piratla
> 
> >===== Original Message From "S.Govind" <sgovind at hpc.serc.iisc.ernet.in> =====
> >hi all
> >
> >
> >I have currently programmed the intel IXP 2400 Network Processor for IPv4
> >forwarding.
> >Iam able to support line rates up to 3 Gbps (without any QoS provisioning)
> >but an area of concern is the reordering, i obtain reordering up to 33%
> >(ie: 33 % packets are reordered )for a link with 4000 flows a second
> >each TCP flow of size 6.4 KB and 14% reordering for flow size of 640 B.
> >
> >The packets are assumed to be arriving at a constant interval of time and
> >of constant size (64 B ), this assumption is used for DoS attacks.
> >
> >I am novice in networking, i have a few queries regarding the above
> >results.
> >
> >Are these numbers (reordering) indicative of current OC 48 links,
> >
> >
> >Any comments and/or suggestions on the above  is most welcome
> >
> >Thanking You,
> >Govind
> >
> >
> >--
> 
> /******************************************
> Research Assistant
> Computer Networking Research Laboratory
> Department of Electrical and Computer Eng.
> 1373, Colorado State University,
> Fort Collins, CO 80523 USA
> http://www.cnrl.colostate.edu
> http://lamar.colostate.edu/~nischal
> *******************************************

From nischal at lamar.colostate.edu  Sun May 15 15:37:20 2005
From: nischal at lamar.colostate.edu (Nischal Piratla)
Date: Sun, 15 May 2005 16:37:20 -0600
Subject: [e2e] packet reordering in OC 48 links
Message-ID: <42E16C9E@webmail.colostate.edu>

Alex,
Thank you for the pointer. 
However, I am still concerned about a couple of things:
1. Will we be able to continue the handling of the order of packets in 
routers, with the known trends of network speeds?
2. As you mentioned in your posting earlier:
http://www.postel.org/pipermail/end2end-interest/2004-August/004234.html
Will we still see reordering with multiple interfaces on NPUs?

- Nischal


>===== Original Message From cannara at attglobal.net =====
>The problem has been solved by some network-processor vendors for a few years
>now.  For example, see the specs for the IQ2200 by Vitesse, that's been used
>to handle 4 parallel, FDX 1Gb/s ports in equipment by various manufacturers,
>including Cisco.
>
>Alex
>
>Nischal Piratla wrote:
>>
>> Govind,
>> We feel that it is quite reasonable to see such high amounts of reordering. 
In
>> fact, we are working on this very problem.
>>
>> Most of the reordering that occurs within the routers is countered by 
either
>> input reordering (packets of same flow are added to same queue) or output
>> reordering (packets from same flow are tagged at the input, and are 
collected
>> to be sent in order at the output). However, due to increasing table sizes,
>> difference in the rates of increase in network speeds vs. the computing
>> speeds, etc., higher parallelism is inevitable and the methods stated above
>> may not be useful. We discussed a little more about it in our recent paper:
>>
>> http://lamar.colostate.edu/~nischal/Papers/Networking2005_RD.pdf
>>
>> Also, to understand the amount and extent of reordering, we suggest 
'Reorder
>> Density' metric that comprehensively illustrates reordering. There are perl
>> scripts and Java applets readily available for the same on this site:
>>
>> http://www.cnrl.colostate.edu/packet_reorder.html
>>
>> - Nischal Piratla
>>
>> >===== Original Message From "S.Govind" <sgovind at hpc.serc.iisc.ernet.in> 
=====
>> >hi all
>> >
>> >
>> >I have currently programmed the intel IXP 2400 Network Processor for IPv4
>> >forwarding.
>> >Iam able to support line rates up to 3 Gbps (without any QoS provisioning)
>> >but an area of concern is the reordering, i obtain reordering up to 33%
>> >(ie: 33 % packets are reordered )for a link with 4000 flows a second
>> >each TCP flow of size 6.4 KB and 14% reordering for flow size of 640 B.
>> >
>> >The packets are assumed to be arriving at a constant interval of time and
>> >of constant size (64 B ), this assumption is used for DoS attacks.
>> >
>> >I am novice in networking, i have a few queries regarding the above
>> >results.
>> >
>> >Are these numbers (reordering) indicative of current OC 48 links,
>> >
>> >
>> >Any comments and/or suggestions on the above  is most welcome
>> >
>> >Thanking You,
>> >Govind
>> >

/******************************************
Research Assistant
Computer Networking Research Laboratory
Department of Electrical and Computer Eng.
1373, Colorado State University, 
Fort Collins, CO 80523 USA
http://www.cnrl.colostate.edu
http://lamar.colostate.edu/~nischal
*******************************************


From aatlas at avici.com  Sun May 15 16:30:10 2005
From: aatlas at avici.com (Alia Atlas)
Date: Sun, 15 May 2005 19:30:10 -0400
Subject: [e2e] packet reordering in OC 48 links
In-Reply-To: <42E10F8D@webmail.colostate.edu>
Message-ID: <5.1.0.14.2.20050515192846.01e7f4c0@10.2.0.68>

In general, a router shouldn't reorder packets.  This doesn't lead to 
acceptable behavior for many applications. While parallelism is reasonable 
and necessary, there are a number of mechanisms possible to ensure that 
packet re-ordering doesn't occur as a result.

Alia

At 04:42 PM 5/15/2005, Nischal Piratla wrote:
>Govind,
>We feel that it is quite reasonable to see such high amounts of 
>reordering. In
>fact, we are working on this very problem.
>
>Most of the reordering that occurs within the routers is countered by either
>input reordering (packets of same flow are added to same queue) or output
>reordering (packets from same flow are tagged at the input, and are collected
>to be sent in order at the output). However, due to increasing table sizes,
>difference in the rates of increase in network speeds vs. the computing
>speeds, etc., higher parallelism is inevitable and the methods stated above
>may not be useful. We discussed a little more about it in our recent paper:
>
>http://lamar.colostate.edu/~nischal/Papers/Networking2005_RD.pdf
>
>Also, to understand the amount and extent of reordering, we suggest 'Reorder
>Density' metric that comprehensively illustrates reordering. There are perl
>scripts and Java applets readily available for the same on this site:
>
>http://www.cnrl.colostate.edu/packet_reorder.html
>
>- Nischal Piratla
>
>
> >===== Original Message From "S.Govind" <sgovind at hpc.serc.iisc.ernet.in> 
> =====
> >hi all
> >
> >
> >I have currently programmed the intel IXP 2400 Network Processor for IPv4
> >forwarding.
> >Iam able to support line rates up to 3 Gbps (without any QoS provisioning)
> >but an area of concern is the reordering, i obtain reordering up to 33%
> >(ie: 33 % packets are reordered )for a link with 4000 flows a second
> >each TCP flow of size 6.4 KB and 14% reordering for flow size of 640 B.
> >
> >The packets are assumed to be arriving at a constant interval of time and
> >of constant size (64 B ), this assumption is used for DoS attacks.
> >
> >I am novice in networking, i have a few queries regarding the above
> >results.
> >
> >Are these numbers (reordering) indicative of current OC 48 links,
> >
> >
> >Any comments and/or suggestions on the above  is most welcome
> >
> >Thanking You,
> >Govind
> >
> >
> >--
>
>/******************************************
>Research Assistant
>Computer Networking Research Laboratory
>Department of Electrical and Computer Eng.
>1373, Colorado State University,
>Fort Collins, CO 80523 USA
>http://www.cnrl.colostate.edu
>http://lamar.colostate.edu/~nischal
>*******************************************



From cannara at attglobal.net  Sun May 15 21:39:34 2005
From: cannara at attglobal.net (Cannara)
Date: Sun, 15 May 2005 21:39:34 -0700
Subject: [e2e] packet reordering in OC 48 links
References: <42E16C9E@webmail.colostate.edu>
Message-ID: <42882406.495DC298@attglobal.net>

Omygod, there are links to the past -- I feel like Tom DeLay (not)!  I'll
repeat:  "The designers of most NPUs considered reordering a no-no, so
provided built-in hardware to track flows, as identified in simplest form by
tuples, like: input-interface, port/channel, IP details, etc."  So, packets
are expected to arrive on multiple interfaces, yet be kept in the same flow,
as for instance, a Cisco router will do if set to use parallel T1s in a
certain forwarding mode.  Any router that can't uniquely associate every
packet in a stream for output on the right interface, regardless of input
interface, isn't worth buying.  

And, if link speed challenges router vendors, use slower interfaces -- we can
get a lot of performance back by simply fixing the Internet to do what it
always should have done, to avoid spam, etc.

Alex

Nischal Piratla wrote:
> 
> Alex,
> Thank you for the pointer.
> However, I am still concerned about a couple of things:
> 1. Will we be able to continue the handling of the order of packets in
> routers, with the known trends of network speeds?
> 2. As you mentioned in your posting earlier:
> http://www.postel.org/pipermail/end2end-interest/2004-August/004234.html
> Will we still see reordering with multiple interfaces on NPUs?
> 
> - Nischal
> 
> >===== Original Message From cannara at attglobal.net =====
> >The problem has been solved by some network-processor vendors for a few years
> >now.  For example, see the specs for the IQ2200 by Vitesse, that's been used
> >to handle 4 parallel, FDX 1Gb/s ports in equipment by various manufacturers,
> >including Cisco.
> >
> >Alex
> >
> >Nischal Piratla wrote:
> >>
> >> Govind,
> >> We feel that it is quite reasonable to see such high amounts of reordering.
> In
> >> fact, we are working on this very problem.
> >>
> >> Most of the reordering that occurs within the routers is countered by
> either
> >> input reordering (packets of same flow are added to same queue) or output
> >> reordering (packets from same flow are tagged at the input, and are
> collected
> >> to be sent in order at the output). However, due to increasing table sizes,
> >> difference in the rates of increase in network speeds vs. the computing
> >> speeds, etc., higher parallelism is inevitable and the methods stated above
> >> may not be useful. We discussed a little more about it in our recent paper:
> >>
> >> http://lamar.colostate.edu/~nischal/Papers/Networking2005_RD.pdf
> >>
> >> Also, to understand the amount and extent of reordering, we suggest
> 'Reorder
> >> Density' metric that comprehensively illustrates reordering. There are perl
> >> scripts and Java applets readily available for the same on this site:
> >>
> >> http://www.cnrl.colostate.edu/packet_reorder.html
> >>
> >> - Nischal Piratla
> >>
> >> >===== Original Message From "S.Govind" <sgovind at hpc.serc.iisc.ernet.in>
> =====
> >> >hi all
> >> >
> >> >
> >> >I have currently programmed the intel IXP 2400 Network Processor for IPv4
> >> >forwarding.
> >> >Iam able to support line rates up to 3 Gbps (without any QoS provisioning)
> >> >but an area of concern is the reordering, i obtain reordering up to 33%
> >> >(ie: 33 % packets are reordered )for a link with 4000 flows a second
> >> >each TCP flow of size 6.4 KB and 14% reordering for flow size of 640 B.
> >> >
> >> >The packets are assumed to be arriving at a constant interval of time and
> >> >of constant size (64 B ), this assumption is used for DoS attacks.
> >> >
> >> >I am novice in networking, i have a few queries regarding the above
> >> >results.
> >> >
> >> >Are these numbers (reordering) indicative of current OC 48 links,
> >> >
> >> >
> >> >Any comments and/or suggestions on the above  is most welcome
> >> >
> >> >Thanking You,
> >> >Govind
> >> >
> 
> /******************************************
> Research Assistant
> Computer Networking Research Laboratory
> Department of Electrical and Computer Eng.
> 1373, Colorado State University,
> Fort Collins, CO 80523 USA
> http://www.cnrl.colostate.edu
> http://lamar.colostate.edu/~nischal
> *******************************************

From kkrama at research.att.com  Mon May 16 10:37:43 2005
From: kkrama at research.att.com (K. K. Ramakrishnan)
Date: Mon, 16 May 2005 13:37:43 -0400
Subject: [e2e] Extended Deadline for LANMAN 2005 (Deadline May 23, 2005)]
Message-ID: <4288DA67.3010204@research.att.com>

Due to requests and the many conference paper deadlines last week,
we've extended the deadline for LANMAN 2005.

(Our apologies if you receive multiple copies of this message)
Note: updated deadline of May 23, 2005, 8 pm EDT.
======
                                    Call for Papers
  14th IEEE Workshop on Local and Metropolitan Area Networks (LANMAN 2005)
            September 18-21, 2005, Chania, Island of Crete, Greece
                     http://www.ieee-lanman.org
       Sponsored by: IEEE Communications Society

-- 
K. K. Ramakrishnan                     Email: kkrama at research.att.com
AT&T Labs-Research, Rm. A117           Tel: (973)360-8764
180 Park Ave, Florham Park, NJ 07932   Fax: (973) 360-8871
      URL: http://www.research.att.com/info/kkrama

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.postel.org/pipermail/end2end-interest/attachments/20050516/619a7dca/attachment-0001.html
-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: call-for-papers_revised.txt
Url: http://www.postel.org/pipermail/end2end-interest/attachments/20050516/619a7dca/call-for-papers_revised-0001.txt

From revans at emea.att.com  Fri May 27 06:10:39 2005
From: revans at emea.att.com (Evans, Roy)
Date: Fri, 27 May 2005 14:10:39 +0100
Subject: [e2e] Packet re-ordering & NewReno
Message-ID: <7FC4591491592043B3664FBAF12EE9BE033BABF1@gbhavmsx02.emea.att.com>

I am trying to close off a problem I was working on last month , which TCP stack has it wrong. rtfm of course , but thus far I cannot find the manual to read.

I think I am seeing chronic reduction of a senders congestion window as an apparent consequence of using newreno


Box A  ftps to box B
In the network I am looking at, round trip time ~ 250ms .  Box A is in UK , Box B on pacific rim.
Box A puts 128KB in flight ,  window scale is x8 , 128KB is the default tcp transmit buffer for the interface on box A.
No packet loss between A&B of any significance
A implements NewReno fast retransmit

Something re-orders packets between A&B , lets say  1,3,4,5,6,2,7,8,9..endofwindow  within the 128K in-flight .    I am suspecting the 'something' was within box A's IP stack , but was unable to capture this in any trace & of course operating system levels have been changed.   In principle, it could be network  because I do mess around with DSCP bits in the network with a view to doing sensible things in congestion , traffic in an individual flow could get into different Qs & cisco is quite capable of re-ordering packets c/o its Q scheduling.

For simplicity of explanation,  lets say B acknowledges every packet  rather than one in every two.

At A:

<--  1-ack  ( to packet 1 )
<--  1-ack  ( to packet 3 ) first duplicate ack
<--  1-ack  ( to packet 4 ) 2nd duplicate ack
<--  1-ack  ( to packet 5 ) 3rd duplicate ack
A enters fast retransmit
recover = 'endofwindow'

-->  2-retransmit
<--  1-ack ( to packet 6 )
<--  2-ack ( to packet 2 ) , according to newreno this is a partial ack
-->  3-retransmit
<--  7-ack
-->  8-retransmit

.. transmit new data if permitted by the cwnd
..
<--  endofwindow-ack


A exits new-reno , with its congestion window reduced accordingly.   I cannot fault this per newreno documentation , but in an ideal world I'd have hoped that A would have exited fast-retransmit earlier , on the receipt of 2-ack (?).

Anyhow, its what happens next that I am getting excited about, ok perhaps confused by.

There is a bunch of retransmitted data in flight in the network , followed by new & retransmitted data.

The retransmitted data hits B , B responds with endofwindow-ack again.   To me, this seems a reasonable response

So , I end up with a stream of endofwindow-acks flowing back to A

..which triggers a fast / newreno response  & its reduction of ssthresh & cwnd

another round-trip time later , new-reno exits , with a bunch of retransmitted data in flight in the network , triggering duplicate acks , triggering a third fast/newreno response.


Any thoughts on what the protocol error is ?


Roy Evans 
AT&T 
Home Office  +44-(0)1422 342472
Home Office: +44-(0)1904 672669 
Mobile Number - 07740 056695 


From dga+ at cs.cmu.edu  Sat May 28 09:40:21 2005
From: dga+ at cs.cmu.edu (David Andersen)
Date: Sat, 28 May 2005 12:40:21 -0400
Subject: [e2e] [Ann] MONET 0.1 - multi-homed web proxy
Message-ID: <21ace7b4e316c29e4fa2a024d94ca4f9@cs.cmu.edu>

Apologies if you heard my mention of this at NSDI -

We're pleased to announce the release of MONET, a Multi-Homed Overlay
Network web proxy, based upon Squid.  MONET issues multiple requests
over multiple locally connected Internet links to provide highly
resilient Web access.  Current deployments include a proxy at MIT that
is multi-homed to three networks, and various home proxies that help
load-balance between DSL and Cable modem links.  MONET accesses
multiple paths from itself to a Web site in three ways:

   - Multiple local Internet connections (multihoming w/out BGP...)
   - Optionally using an overlay network of peer proxies
   - Contacting multiple servers announced via the DNS

Our results suggest that MONET can increase the reliability of Web
access to major sites by a factor of about 8.  (We can't help much if
the Web site you're trying to visit is behind a DSL line and is
slashdotted...).  It's also a very nice way to load balance between
smaller links - I've been using it at home for a long time to do this,
and it works very well.

The code is labeled 0.1, which you should interpret as "grad-student
quality, but runs in production" -- it has many rough edges as far as
configuration goes, but the code itself has been in daily use by about
50 people for over two years now.  Perhaps the major caveat is that to
run it on a machine that gets its IP addresses via DHCP requires some
supporting scripts.  If you find yourself using it in that environment,
drop me a note and I'll share the hacked up scripts I've got.

Code, papers, etc.:

http://nms.lcs.mit.edu/ron/ronweb/

   -Dave


From floyd at icir.org  Tue May 31 17:12:12 2005
From: floyd at icir.org (Sally Floyd)
Date: Tue, 31 May 2005 17:12:12 -0700
Subject: [e2e] a new IRTF group on Transport Models
Message-ID: <200506010012.j510CCD4086403@cougar.icir.org>

I am proposing a new IRTF group, the Transport Models Research
Group, whose goal is to improve our methodologies for evaluating
transport protocols.  This is likely to be a mailing-list-only
research group, and the proposed charter is on the web site at
"http://www.icir.org/tmrg/".  People who are interested could
look at the web site, or join the mailing list.  Any feedback
(on the tmrg mailing list) would be welcome.

The proposed charter is appended below.

As a part of this effort, I have also produced a first pass
at a document on metrics for evaluating congestion control
mechanisms, "Metrics for the Evaluation of Congestion Control
Mechanisms", available from
"http://www.icir.org/floyd/papers/draft-floyd-transport-metrics-00.txt".
Any feedback or contributions would be welcome.

Thanks.

- Sally
http://www.icir.org/floyd/

Proposed charter:

The Transport Models Research Group (TMRG) is chartered to produce
a series of documents on Models for the Evaluation of Transport
Protocols.  The documents will include a survey of models used in
simulations, analysis, and experiments for the evaluation of transport
protocols.  The output of the research group will also include a
broad set of simulation test suites, and a set of recommendations
for test suites for experiments in test beds.  The goal of the work
is to improve our methodologies for evaluating transport protocols.

The first set of documents will consider models for the evaluation
of congestion control mechanisms.  This work will include the
simulation test suites and recommendations for experiments mentioned
above.  Later documents are expected to address models for the
evaluation of other aspects of transport protocols (e.g., connection
establishment, security, perhaps QoS mechanisms).

The models produced by this group will not have any formal relationship
to the IETF standards process.  That is, this research group will
not produce recommendations for the IETF on using simulation or
experimental test suites to evaluate transport-related features for
standardization.  At the same time, one intended use of the test
suites is for comparative evaluations of different proposed congestion
control mechanisms.

This research group is not chartered to discuss the design of new
congestion control mechanisms, or to discuss modifications to
existing congestion control mechanisms, except in terms of the
models needed for the evaluation of such mechanisms.  The group is
also not chartered to produce evaluations of specific congestion
control mechanisms.

From weigengyu at hotmail.com  Tue May 31 22:01:05 2005
From: weigengyu at hotmail.com (weigengyu)
Date: Wed, 1 Jun 2005 13:01:05 +0800
Subject: [e2e] a new IRTF group on Transport Models
References: <200506010012.j510CCD4086403@cougar.icir.org>
Message-ID: <BAY22-DAV5561BE95E5B67DACC35BFB3050@phx.gbl>

Hi,
By considering end2end transport layer protocol,
whether packet drop rates of the metrics should be segment drop (error) rates?

Gengyu

----- Original Message ----- 
From: "Sally Floyd" <floyd at icir.org>
To: <end2end-interest at postel.org>
Sent: Wednesday, June 01, 2005 8:12 AM
Subject: [e2e] a new IRTF group on Transport Models


>I am proposing a new IRTF group, the Transport Models Research
> Group, whose goal is to improve our methodologies for evaluating
> transport protocols.  This is likely to be a mailing-list-only
> research group, and the proposed charter is on the web site at
> "http://www.icir.org/tmrg/".  People who are interested could
> look at the web site, or join the mailing list.  Any feedback
> (on the tmrg mailing list) would be welcome.
> 
> The proposed charter is appended below.
> 
> As a part of this effort, I have also produced a first pass
> at a document on metrics for evaluating congestion control
> mechanisms, "Metrics for the Evaluation of Congestion Control
> Mechanisms", available from
> "http://www.icir.org/floyd/papers/draft-floyd-transport-metrics-00.txt".
> Any feedback or contributions would be welcome.
> 
> Thanks.
> 
> - Sally
> http://www.icir.org/floyd/
>