P2P'08: Engineering Peer-to-Peer Systems

"Engineering = Technology + Economics" H. Schulzrinne from Columbia University said when he opened his keynote at P2P'08 in Aachen, Germany. Well, I guess most of the scientists take care only about the former and ignore the latter. In his talk he clearly outlined the increase of energy and bandwidth consumption when using P2P systems. He also quantified that but, honestly, most of the numbers were related to the US and in Europe these numbers are probably lower. However, he concluded that from an economics' point of view "P2P system shall be deployed only in Alaska and Scandinavia (and only during Winter period)" ;-)

He then defined a P2P system as follows (see also figure on the left side): (1) peers act as client and server, (2) they provide computational/storage resources to other peers, and (3) they're self-organizing and scaling. The latest property is the most important one as (1) and (2) is also true for several proxies out there...

After that he discussed another topic that sounds curious but comes back to the energy issue as mentioned above...

Finally, he also presented some technical details - I hope the slides will be provided through the Web site - and he concluded that we "need more work on diagnostics and management", little work has been done related to services such as transcoding, and standardization is ongoing within IETF.