Modeling seed scheduling strategies in BitTorrent

BitTorrent has gained momentum in recent years as an effective means of distributing digital content in the Internet. Despite the remarkable scalability and efficiency properties that characterize BitTorrent in the long haul, several studies identify the source of the content as the main culprit for the poor performance of the system in a transient regime where user requests for a popular content swamp the source and in case of high node churn. Our work models the scheduling decisions made at the source (called the seed) for selecting which pieces of the content to inject in the system through a stochastic optimization process and provides an analytical framework to compare different strategies. We define a new piece selection algorithm (called proportional fair scheduling, PFS) that incorporates the seed's limited vision of the system dynamics in terms of user requests so as to ensure a better content distribution among the users. We prove convergence of PFS and compare its short and long term performance against the mainline BitTorrent implementation and the "smart seed" technique recently introduced in [9]. Our results show that PFS induces substantial improvements on both system performance, by decreasing the download time at the users, and system robustness against peer dynamics, by quickly reacting to sudden changes in the request patterns of the users.

[1]  Gustavo de Veciana,et al.  Service capacity of peer to peer networks , 2004, IEEE INFOCOM 2004.

[2]  Philip A. Whiting,et al.  Convergence of proportional-fair sharing algorithms under general conditions , 2004, IEEE Transactions on Wireless Communications.

[3]  Mikel Izal,et al.  Dissecting BitTorrent: Five Months in a Torrent's Lifetime , 2004, PAM.

[4]  Rayadurgam Srikant,et al.  Modeling and performance analysis of BitTorrent-like peer-to-peer networks , 2004, SIGCOMM 2004.

[5]  Bin Fan,et al.  Stochastic Differential Equation Approach to Model BitTorrent-like P2P Systems , 2006, 2006 IEEE International Conference on Communications.

[6]  Guillaume Urvoy-Keller,et al.  Rarest first and choke algorithms are enough , 2006, IMC '06.

[7]  Jean-Yves Le Boudec,et al.  A unified framework for max-min and min-max fairness with applications , 2007, TNET.

[8]  Fabien Mathieu,et al.  Missing Piece Issue and Upload Strategies in Flashcrowds and P2P-assisted Filesharing , 2006, Advanced Int'l Conference on Telecommunications and Int'l Conference on Internet and Web Applications and Services (AICT-ICIW'06).

[9]  Harold J. Kushner,et al.  Stochastic Approximation Algorithms and Applications , 1997, Applications of Mathematics.

[10]  Venkata N. Padmanabhan,et al.  Analyzing and Improving a BitTorrent Networks Performance Mechanisms , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[11]  Guillaume Urvoy-Keller,et al.  Impact of Inner Parameters and Overlay Structure on the Performance of BitTorrent , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[12]  B. Cohen,et al.  Incentives Build Robustness in Bit-Torrent , 2003 .

[13]  Christos Gkantsidis,et al.  Network coding for large scale content distribution , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

[14]  A. C. Brooms.  Stochastic Approximation and Recursive Algorithms with Applications, 2nd edn by H. J. Kushner and G. G. Yin , 2006 .

[15]  Kam-Wing Ng,et al.  Modeling, Analysis and Improvement for BitTorrent-Like File Sharing Networks , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.