An Analytical Study of a Structured Overlay in the Presence of Dynamic Membership

In this paper, we present an analytical study of dynamic membership (aka churn) in structured peer-to-peer networks. We use a fluid model approach to describe steady-state or transient phenomena and apply it to the Chord system. For any rate of churn and stabilization rates and any system size, we accurately account for the functional form of the probability of network disconnection as well as the fraction of failed or incorrect successor and finger pointers. We show how we can use these quantities to predict both the performance and consistency of lookups under churn. All theoretical predictions match simulation results. The analysis includes both features that are generic to structured overlays deploying a ring as well as Chord-specific details and opens the door to a systematic comparative analysis of, at least, ring-based structured overlay systems under churn.

[1]  L. Tu.  The Life and Works of , 2006 .

[2]  Robert Tappan Morris,et al.  A performance vs. cost framework for evaluating DHT design tradeoffs under churn , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

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

[4]  W. Ebeling.  Stochastic Processes in Physics and Chemistry , 1995 .

[5]  Miguel Castro,et al.  Performance and dependability of structured peer-to-peer overlays , 2004, International Conference on Dependable Systems and Networks, 2004.

[6]  Seif Haridi,et al.  A Physics-Inspired Performance Evaluation of a Structured Peer-to-Peer Overlay Network , 2005, Parallel and Distributed Computing and Networks.

[7]  Karl Aberer,et al.  Efficient, self-contained handling of identity in peer-to-peer systems , 2004, IEEE Transactions on Knowledge and Data Engineering.

[8]  Dong Xuan,et al.  On resilience of structured peer-to-peer systems , 2003, GLOBECOM '03. IEEE Global Telecommunications Conference (IEEE Cat. No.03CH37489).

[9]  James Aspnes,et al.  Fault-tolerant routing in peer-to-peer systems , 2002, PODC '02.

[10]  John Kubiatowicz,et al.  Handling churn in a DHT , 2004 .

[11]  David R. Karger,et al.  Chord: a scalable peer-to-peer lookup protocol for internet applications , 2003, TNET.

[12]  D. Mitra,et al.  Stochastic theory of a data-handling system with multiple sources , 1982, The Bell System Technical Journal.

[13]  Seif Haridi,et al.  A Statistical Theory of Chord Under Churn , 2005, IPTPS.

[14]  F. Clevenot,et al.  A simple fluid model for the analysis of the squirrel peer-to-peer caching system , 2004, IEEE INFOCOM 2004.

[15]  David R. Karger,et al.  Chord: A scalable peer-to-peer lookup service for internet applications , 2001, SIGCOMM '01.

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

[17]  David R. Karger,et al.  Analysis of the evolution of peer-to-peer systems , 2002, PODC '02.

[18]  Seif Haridi,et al.  Comparing Maintenance Strategies for Overlays , 2008, 16th Euromicro Conference on Parallel, Distributed and Network-Based Processing (PDP 2008).

[19]  Maurice Yacowar,et al.  The Life and Work , 1993 .

[20]  N. Kampen,et al.  Stochastic processes in physics and chemistry , 1981 .

[21]  Seif Haridi,et al.  DKS(N, k, f): a family of low communication, scalable and fault-tolerant infrastructures for P2P applications , 2003, CCGrid 2003. 3rd IEEE/ACM International Symposium on Cluster Computing and the Grid, 2003. Proceedings..