Stability of a Peer-to-Peer Communication System

This paper focuses on the stationary portion of file download in an unstructured peer-to-peer network, which typically follows for many hours after a flash crowd initiation. The model includes the case that peers can have some pieces at the time of arrival. The contribution of this paper is to identify how much help is needed from the seeds, either fixed seeds or peer seeds (which are peers remaining in the system after obtaining a complete collection), to stabilize the system. The dominant cause for instability is the missing piece syndrome, whereby one piece becomes very rare in the network. It is shown that stability can be achieved with only a small amount of help from peer seeds-even with very little help from a fixed seed, peers need dwell as peer seeds on average only long enough to upload one additional piece. The region of stability is insensitive to the piece selection policy. Network coding can substantially increase the region of stability in case a portion of the new peers arrive with randomly coded pieces.

[1]  Muriel Médard,et al.  Algebraic gossip: a network coding approach to optimal multiple rumor mongering , 2006, IEEE Transactions on Information Theory.

[2]  John C. S. Lui,et al.  A Simple Model for Analyzing P2P Streaming Protocols , 2007, 2007 IEEE International Conference on Network Protocols.

[3]  Eddie Kohler,et al.  Clustering and sharing incentives in BitTorrent systems , 2006, SIGMETRICS '07.

[4]  Bruce E. Hajek,et al.  The missing piece syndrome in peer-to-peer communication , 2010, 2010 IEEE International Symposium on Information Theory.

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

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

[7]  R. Srikant,et al.  Modeling and performance analysis of BitTorrent-like peer-to-peer networks , 2004, SIGCOMM '04.

[8]  Stratis Ioannidis,et al.  Distributed caching over heterogeneous mobile networks , 2010, SIGMETRICS '10.

[9]  Donald F. Towsley,et al.  Reciprocity and Barter in Peer-to-Peer Systems , 2010, 2010 Proceedings IEEE INFOCOM.

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

[11]  J. Kingman.  Some inequalities for the queue GI/G/1 , 1962 .

[12]  S. Lakshmivarahan,et al.  Probability and Random Processes , 2007 .

[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]  Arun Venkataramani,et al.  Estimating Self-Sustainability in Peer-to-Peer Swarming Systems , 2010, Perform. Evaluation.

[15]  Keith W. Ross,et al.  Queuing Network Models for Multi-Channel P2P Live Streaming Systems , 2009, IEEE INFOCOM 2009.

[16]  Stratis Ioannidis,et al.  On the stability and optimality of universal swarms , 2011, PERV.

[17]  F. G. Foster.  On the Stochastic Matrices Associated with Certain Queuing Processes , 1953 .

[18]  Laurent Massoulié,et al.  Flow Control for Cost-Efficient Peer-to-Peer Streaming , 2010, 2010 Proceedings IEEE INFOCOM.

[19]  Florian Simatos,et al.  Interacting branching processes and linear file-sharing networks , 2010, Advances in Applied Probability.

[20]  Rudolf Ahlswede,et al.  Network information flow , 2000, IEEE Trans. Inf. Theory.

[21]  Leonard Kleinrock,et al.  Proportional Replication in Peer-to-Peer Networks , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[22]  Laurent Massoulié,et al.  Coupon replication systems , 2008, TNET.

[23]  Michalis Faloutsos,et al.  Is P2P dying or just hiding? [P2P traffic measurement] , 2004, IEEE Global Telecommunications Conference, 2004. GLOBECOM '04..

[24]  Ilkka Norros,et al.  On the stability of two-chunk file-sharing systems , 2009, Queueing Syst. Theory Appl..