Robustness of a P2P community management system based on two-level hierarchical DHT overlays

The popularity of community-centric applications has rapidly grown during the recent years. In this paper, we evaluate the robustness of a P2P community management system, where communities are established as autonomous DHT overlays that are advertised in a global DHT overlay. The evaluation is based on the experimental measurements conducted using a DHT-based protocol with two DHT algorithms called Kademlia and Chord. The robustness of the P2P community management system was evaluated with different levels of churn and node activity, in terms of nodes' look-up success ratio, network traffic load and average hop count. The P2P community management system was also compared against a flat DHT structure where all the community related activities are performed in a single DHT overlay. The evaluation results suggest that the P2P community management system performs very well in an environment with high level of churn, the performance improvement being especially significant with Chord.

[1]  David Mazières,et al.  Kademlia: A Peer-to-Peer Information System Based on the XOR Metric , 2002, IPTPS.

[2]  Mika Ylianttila,et al.  Performance evaluation of a Kademlia-based communication-oriented P2P system under churn , 2010, Comput. Networks.

[3]  Giovanni Chiola,et al.  Optimizing the finger tables in Chord‐like DHTs , 2008, Concurr. Comput. Pract. Exp..

[4]  Henning Schulzrinne,et al.  Peer-to-Peer Protocol (P2PP) , 2007 .

[5]  Diomidis Spinellis,et al.  A survey of peer-to-peer content distribution technologies , 2004, CSUR.

[6]  R. Stephenson.  A and V , 1962, The British journal of ophthalmology.

[7]  Anirban Mondal,et al.  Research issues and overview of economic models in Mobile-P2P networks , 2007 .

[8]  Gonzalo Camarillo,et al.  Estimating operating conditions in a Peer-to-Peer Session Initiation Protocol overlay network , 2010, 2010 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW).

[9]  Minglu Li,et al.  SChord: Handling Churn in Chord by Exploiting Node Session Time , 2005, GCC.

[10]  Taieb Znati,et al.  Modeling Churn in P2P Networks , 2007, 40th Annual Simulation Symposium (ANSS'07).

[11]  Robert Tappan Morris,et al.  Comparing the Performance of Distributed Hash Tables Under Churn , 2004, IPTPS.

[12]  Andy Oram,et al.  Peer-to-peer , 2008, Nature Immunology.

[13]  Giovanni Chiola,et al.  Optimizing the finger table in chord-like DHTs , 2006, Proceedings 20th IEEE International Parallel & Distributed Processing Symposium.

[14]  Daishi Kato,et al.  Evaluating DHT Implementations in Complex Environments by Network Emulator , 2007, IPTPS.

[15]  Calton Pu,et al.  A Utility-Aware Middleware Architecture for Decentralized Group Communication Applications , 2007, Middleware.

[16]  Mika Ylianttila,et al.  Improving Community Management Performance with Two-Level Hierarchical DHT Overlays , 2010 .

[17]  Xiaohui Huang,et al.  Resource discovery in locality-aware group-based semantic overlay of peer-to-peer networks , 2006, InfoScale '06.

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

[19]  Mika Ylianttila,et al.  User Evaluation of a Community-centric Music Voting Service , 2010, J. Digit. Content Technol. its Appl..

[20]  J.K. Nurminen,et al.  Optimizing Energy Consumption of Mobile Nodes in Heterogeneous Kademlia-Based Distributed Hash Tables , 2008, 2008 The Second International Conference on Next Generation Mobile Applications, Services, and Technologies.

[21]  Gonzalo Camarillo,et al.  Evaluation of DHTs from the viewpoint of interpersonal communications , 2007, MUM.

[22]  Mika Ylianttila,et al.  Comparing the performance and efficiency of two popular DHTs in interpersonal communication , 2011, 2011 IEEE Wireless Communications and Networking Conference.