The Distributed Spanning Tree Structure

Search algorithms are a key issue to share resources in large distributed systems as peer networks. Several distributed interconnection structures and algorithms have already been studied in this context. With expanding ring algorithms, the efficiency of searches depends on the topology used to send query requests and the dynamics of the structure. In this paper, we present an interconnection structure that limits the number of messages needed for search queries. This structure, called distributed spanning tree (DST), defines each node as the root of a spanning tree. So, it behaves as a tree for the number of messages but it balances the load generated by the requests among computers, and thus, it avoids to overload the root node. This structure is scalable because it needs only a logarithmic memory space per computer to be maintained. A formal and practical description of the structure is presented and we describe traversal algorithms. Simulations show that DST based searches behave better than randomly generated graphs and trees as it generates less messages to query all computers while avoiding the tree bottlenecks.

[1]  Miguel Castro,et al.  SplitStream: High-Bandwidth Content Distribution in Cooperative Environments , 2003, IPTPS.

[2]  Henri Casanova,et al.  A GridRPC Model and API for End-User Applications , 2004 .

[3]  David E. Culler,et al.  Scalable, distributed data structures for internet service construction , 2000, OSDI.

[4]  Frédéric Suter,et al.  A Scalable Approach to Network Enabled Servers , 2002, ASIAN.

[5]  Zahir Tari,et al.  A query propagation approach to improve CORBA Trading Service scalability , 2000, Proceedings 20th IEEE International Conference on Distributed Computing Systems.

[6]  Ajoy Kumar Datta,et al.  A Semantic Overlay for Self- Peer-to-Peer Publish/Subscribe , 2006, 26th IEEE International Conference on Distributed Computing Systems (ICDCS'06).

[7]  Mohan Kumar,et al.  The hierarchical cliques interconnection network , 2004, J. Parallel Distributed Comput..

[8]  Magdy A. Bayoumi,et al.  The Hierarchical Hypercube: A New Interconnection Topology for Massively Parallel Systems , 1994, IEEE Trans. Parallel Distributed Syst..

[9]  Rajmohan Rajaraman,et al.  Accessing Nearby Copies of Replicated Objects in a Distributed Environment , 1997, SPAA '97.

[10]  Jean-Marc Nicod,et al.  Evaluation of the DIET hierarchical metacomputing architecture , 2001, Scalable Comput. Pract. Exp..

[11]  Jean-Marc Nicod,et al.  Scalability in a Grid server discovery mechanism , 2004, Proceedings. 10th IEEE International Workshop on Future Trends of Distributed Computing Systems, 2004. FTDCS 2004..

[12]  B. Cohen,et al.  Incentives Build Robustness in Bit-Torrent , 2003 .

[13]  Mikel Izal,et al.  Dissecting BitTorrent: Five Months in a Torrent's Lifetime , 2004, PAM.

[14]  Sylvain Dahan.  Distributed spanning tree algorithms for large scale traversals , 2005, 11th International Conference on Parallel and Distributed Systems (ICPADS'05).

[15]  Antony I. T. Rowstron,et al.  Pastry: Scalable, Decentralized Object Location, and Routing for Large-Scale Peer-to-Peer Systems , 2001, Middleware.

[16]  Jean-Marc Nicod,et al.  The distributed spanning tree: a scalable interconnection topology for efficient and equitable traversal , 2005, CCGrid 2005. IEEE International Symposium on Cluster Computing and the Grid, 2005..

[17]  Jon Crowcroft,et al.  A survey and comparison of peer-to-peer overlay network schemes , 2005, IEEE Communications Surveys & Tutorials.

[18]  David Thomas,et al.  The Art in Computer Programming , 2001 .

[19]  Eddy Caron,et al.  Diet: A Scalable Toolbox to Build Network Enabled Servers on the Grid , 2006, Int. J. High Perform. Comput. Appl..