Data networks
LOF: identifying density-based local outliers
SIGMOD '00 Proceedings of the 2000 ACM SIGMOD international conference on Management of data
IEEE Internet Computing
Measuring and analyzing the characteristics of Napster and Gnutella hosts
Multimedia Systems
Characterizing the query behavior in peer-to-peer file sharing systems
Proceedings of the 4th ACM SIGCOMM conference on Internet measurement
Transport layer identification of P2P traffic
Proceedings of the 4th ACM SIGCOMM conference on Internet measurement
Content availability, pollution and poisoning in file sharing peer-to-peer networks
Proceedings of the 6th ACM conference on Electronic commerce
Denial-of-service resilience in peer-to-peer file sharing systems
SIGMETRICS '05 Proceedings of the 2005 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Theory, Volume 1, Queueing Systems
Theory, Volume 1, Queueing Systems
Characterizing unstructured overlay topologies in modern P2P file-sharing systems
IMC '05 Proceedings of the 5th ACM SIGCOMM conference on Internet Measurement
On lifetime-based node failure and stochastic resilience of decentralized peer-to-peer networks
IEEE/ACM Transactions on Networking (TON)
Modeling Heterogeneous User Churn and Local Resilience of Unstructured P2P Networks
ICNP '06 Proceedings of the Proceedings of the 2006 IEEE International Conference on Network Protocols
Trace driven analysis of the long term evolution of Gnutella peer-to-peer traffic
PAM'07 Proceedings of the 8th international conference on Passive and active network measurement
Evaluating the accuracy of captured snapshots by peer-to-peer crawlers
PAM'05 Proceedings of the 6th international conference on Passive and Active Network Measurement
Hi-index | 0.00 |
In this paper, the topology dynamics of Gnutella are studied in phase space. The dynamic progress of peer degree is studied as a time series in two dimensional phase space, which is consisted of numbers of connected leaves and ultras. The reported degrees concentrate on three special software related regions which we name as ultra stable region, leaf stable region and transition belt. A method is proposed on how to classify degree traces in phase space into different categories. Then the connection churn and the degree churn are studied. It shows that the topological structure of Gnutella is more stable in its connection degree than in the topology itself. The connection drop rate is estimated and the lifetime of connections is deduced afterwards. M/M/m/m loss queue system is introduced to model the degree keeping process in Gnutella. This model reveals that the degree stability is ensured by mass new connection efforts. In other words, the stability in topological structure of Gnutella is the results of many essential unstable factors in its topology. We think it raises a challenge to the basic design philosophy for such networks.