« Baggesen on school vouchers in Sweden and US | Main | AER 2008, 98:3 Pride and Prejudice: The Human Side of Incentive Theory »
söndag
sep282008

Egoistic torrent clients?

Carra, Damiano, Giovanni Neglia, och Pietro Michiardi. 2008. "On the Impact of Greedy Strategies in BitTorrent Networks: The Case of BitTyrant." 2008 Eighth International Conference on Peer-to-Peer Computing:311-320.

The success of BitTorrent has fostered thedevelopment of variants to its basic components. Some of the variantsadopt greedy approaches aiming at exploiting the intrinsic altruism ofthe original version of BitTorrent in order to maximize the benefit ofparticipating to a torrent. In this work we study BitTyrant, a recentlyproposed strategic client. BitTyrant tries to determine the exactamount of contribution necessary to maximize its download rate bydynamically adapting and shaping the upload rate allocated to itsneighbors. We evaluate in detail the various mechanisms used byBitTyrant to identify their contribution to the performance of theclient. Our findings indicate that the performance gain is due to theincreased number of connections established by a BitTyrant client,rather than for its subtle uplink allocation algorithm; surprisingly,BitTyrant reveals to be altruistic and particularly efficient indisseminating the content, especially during the initial phase of thedistribution process. The apparent gain of a single BitTyrant client,however, disappears in the case of a widespread adoption: our resultsindicate a severe loss of efficiency that we analyzed in detail. Incontrast, a widespread adoption of the latest version of the mainlineBitTorrent client would provide increased benefit for all peers.

Reader Comments

There are no comments for this journal entry. To create a new comment, use the form below.

PostPost a New Comment

Enter your information below to add a new comment.

My response is on my own website »
Author Email (optional):
Author URL (optional):
Post:
 
All HTML will be escaped. Hyperlinks will be created for URLs automatically.