Churn Resilience of Peer-to-Peer Group Membership: A Performance Analysis

Partitioning is one of the main problems in p2p group membership. This problem rises when failures and dynamics of peer participation, or churn, occur in the overlay topology created by a group membership protocol connecting the group of peers. Solutions based on Gossip-based Group Membership (GGM) cope well with the failures while suffer from network dynamics. This paper shows a performance evaluation of SCAMP, one of the most interesting GGM protocol. The analysis points out that the probability of partitioning of the overlay topology created by SCAMP increases with the churn rate. We also compare SCAMP with DET – another membership protocol that deterministically avoids partitions of the overlay. The comparison points out an interesting trade-off between (i) reliability, in terms of guaranteeing overlay connectivity at any churn rate, and (ii) scalability in terms of creating scalable overlay topologies where latencies experienced by a peer during join and leave operations do not increase linearly with the number of peers in the group.

[1]  Bernadette Charron-Bost,et al.  Simulating Reliable Links with Unreliable Links in the Presence of Process Crashes , 1996, WDAG.

[2]  Tucci Piergiovanni.  Group Membership for Peer-to-Peer Communication , 2005 .

[3]  Anne-Marie Kermarrec,et al.  Peer-to-Peer Membership Management for Gossip-Based Protocols , 2003, IEEE Trans. Computers.

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

[5]  Indranil Gupta,et al.  Fighting fire with fire: using randomized gossip to combat stochastic scalability limits , 2002 .

[6]  Anne-Marie Kermarrec,et al.  The Peer Sampling Service: Experimental Evaluation of Unstructured Gossip-Based Implementations , 2004, Middleware.

[7]  Idit Keidar,et al.  Group communication specifications: a comprehensive study , 2001, CSUR.

[8]  Miguel Castro,et al.  Scribe: a large-scale and decentralized application-level multicast infrastructure , 2002, IEEE J. Sel. Areas Commun..

[9]  Daniel Stutzbach,et al.  Towards a Better Understanding of Churn in Peer-to-Peer Networks , 2004 .

[10]  Flaviu Cristian,et al.  Reaching agreement on processor-group membrship in synchronous distributed systems , 1991, Distributed Computing.

[11]  Kirk L. Johnson,et al.  Overcast: reliable multicasting with on overlay network , 2000, OSDI.

[12]  Kenneth P. Birman,et al.  Using process groups to implement failure detection in asynchronous environments , 1991, PODC '91.

[13]  Flaviu Cristian.  A probabilistic approach to distributed clock synchronization , 1989, [1989] Proceedings. The 9th International Conference on Distributed Computing Systems.

[14]  Kenneth P. Birman,et al.  Reliable communication in the presence of failures , 1987, TOCS.

[15]  John E. Hopcroft,et al.  Correctness of a gossip based membership protocol , 2005, PODC '05.

[16]  Kenneth P. Birman,et al.  Programming with process groups: Group and multicast semantics , 1991 .

[17]  Anne-Marie Kermarrec,et al.  Lightweight probabilistic broadcast , 2003, TOCS.

[18]  Robbert van Renesse,et al.  Reliable Distributed Computing with the Isis Toolkit , 1994 .

[19]  Santosh K. Shrivastava,et al.  Replicated K-resilient objects in Arjuna , 1990, [1990] Proceedings. Workshop on the Management of Replicated Data.