Re: [alto] Paper on "Pushing BitTorrent Locality to the Limit"

Dear Maciek,

Thanks a lot for the pointer.

The P4P trials used Pando client, which is similar to standard BT client. 
In addition to the Pando client, in the past we have also tried other 
clients such as standard BT and Maze (a file sharing client). The standard 
BT experiments were done at PlanetLab, and the Maze experiment was done in 
China. Both are real experiments, although they are not comparable with 
the scale of the Pando experiment.

There is some detail about some of the experiments in a paper:
http://cs-www.cs.yale.edu/homes/yry/projects/p4p/p4p-sigcomm08.pdf

There is a thread about the setup of the Pando experiments (you may need 
to trace multiple emails):
http://www.ietf.org/mail-archive/web/p2pi/current/msg00884.html
http://www.ietf.org/mail-archive/web/p2pi/current/msg00886.html

A discussion of the P4P framework can be found at:
http://www.ietf.org/internet-drafts/draft-p4p-framework-00.txt

Some more slides about the implementations on the tracker side:
http://cs-www.cs.yale.edu/homes/yry/projects/p4p/p4p-implementation.ppt

To fully appreciate some detail of the results, you may need more details 
of the exact algorithms (e.g., the application optimization algorithm). We 
can give you pointer too.

Richard

On Wed, 3 Dec 2008, 2:44pm +0100, Maciej Wojciechowski wrote:

> Enrico,
> 
> On Dec 3, 2008, at 2:12 PM, Enrico Marocco wrote:
> >The P4P solution has been studied in the real world as well, with real
> >users and a proprietary client running a variant of the bittorrent protocol.
> >
> >Results collected on the Comcast's network are discussed in
> >http://tools.ietf.org/id/draft-livingood-woundy-p4p-experiences.
> 
> Thanks for the link - I was unaware of this trial. Unfortunately, the 
> draft discusses mostly the results and does not give much technical 
> information on how the trial was exactly set up. One of the things that 
> I'm missing is: how did the users actually find the content that was 
> distributed in the trial?
> 
> Could you provide a link to a more in-depth explanation of the actual 
> experiment? Based on the draft itself it is very hard for me to analyze 
> applicability of the presented results.
> 
> Regards,
> Maciek Wojciechowski
> _______________________________________________
> alto mailing list
> alto@ietf.org
> https://www.ietf.org/mailman/listinfo/alto
> 
_______________________________________________
alto mailing list
alto@ietf.org
https://www.ietf.org/mailman/listinfo/alto