Result Verification Mechanism Based on Availability and Reputation of Resources in P2P Desktop Grid Systems

The recent tendency of transfer from centralized desktop to P2P desktop grids requires redesigning the result verification mechanism that has been developed for the former. Since there is no central server to verify the correctness of task results in P2P desktop grids, it is difficult to intactly apply the existing mechanisms to P2P environments. In this paper, we propose a result verification mechanism based on a task tree that can efficiently provide the result correctness against malicious resources in P2P desktop grids. In the mechanism, a task tree is built based on the availability and reputation of resources, and different result verification methods are used according to level characteristics in the task tree. Numerical analysis results show that our mechanism performs better than the existing ones, in terms of the correctness of task results.

[1]  Stefan Savage,et al.  Understanding Availability , 2003, IPTPS.

[2]  Thomas Hérault,et al.  Computing on large-scale distributed systems: XtremWeb architecture, programming models, security, tests and convergence with grid , 2005, Future Gener. Comput. Syst..

[3]  Yu. A. Zuev.  On the Estimation of Efficiency of Voting Procedures , 1998 .

[4]  Zsolt Németh,et al.  Distributed and Parallel Systems: In Focus Desktop Grid Computing , 2008 .

[5]  David P. Anderson,et al.  BOINC: a system for public-resource computing and storage , 2004, Fifth IEEE/ACM International Workshop on Grid Computing.

[6]  Daniel Zappala,et al.  Cluster Computing on the Fly : P 2 P Scheduling of Idle Cycles in the Internet , 2004 .

[7]  Huaimin Wang,et al.  A P2P approach for global computing , 2003, Proceedings International Parallel and Distributed Processing Symposium.

[8]  Nazareno Andrade,et al.  Discouraging free riding in a peer-to-peer CPU-sharing grid , 2004, Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004..

[9]  Andrew A. Chien,et al.  Scheduling task parallel applications for rapid turnaround on desktop grids , 2005 .

[10]  G. Suryanarayana,et al.  A Survey of Trust Management and Resource Discovery Technologies in Peer-to-Peer Applications , 2004 .

[11]  Andrew A. Chien,et al.  Scheduling Task Parallel Applications for Rapid Turnaround on Enterprise Desktop Grids , 2007, Journal of Grid Computing.

[12]  Mario Lauria,et al.  The organic grid: self-organizing computation on a peer-to-peer network , 2005, IEEE Trans. Syst. Man Cybern. Part A.

[13]  Bradley C. Kuszmaul,et al.  Cilk: an efficient multithreaded runtime system , 1995, PPOPP '95.

[14]  David P. Anderson,et al.  SETI@home-massively distributed computing for SETI , 2001, Comput. Sci. Eng..

[15]  Cécile Germain,et al.  Result checking in global computing systems , 2003, ICS '03.

[16]  Jens Volkert,et al.  Distributed and Parallel Systems , 2000 .

[17]  Luis F. G. Sarmenta.  Sabotage-tolerance mechanisms for volunteer computing systems , 2002, Future Gener. Comput. Syst..