Graph Partitioning Strategies for Efficient BFS in Shared-Nothing Parallel Systems
Traversing massive graphs as efficiently as possible is essential for many applications. Many common operations on graphs, such as calculating the distance between two nodes, are based on the Breadth First Search traversal. However, because of the exhaustive exploration of all the nodes and edges of the graph, this operation might be very time consuming. A possible solution is distributing the graph among the nodes of a shared-nothing parallel system. Nevertheless, this operation may generate a large amount of inter-node communication. In this paper, we propose two graph partitioning techniques and improve previous distributed versions of BFS in order to reduce this communication.
KeywordsDistributed Graphs Graph Partitioning Distributed BFS Graph Databases
Unable to display preview. Download preview PDF.
- 4.Demetrescu, C., Goldberg, A.V., Johnson, D.S.: 9th dimacs challenge 9 benchmark platform, version 1.1(october 30, 2006), http://www.dis.uniroma1.it/~challenge9
- 5.Fiduccia, C.M., Mattheyses, R.M.: A linear-time heuristic for improving network partitions. In: DAC 1982: Proceedings of the 19th Design Automation Conference, pp. 175–181. IEEE Press, Piscataway (1982)Google Scholar
- 8.Martínez-Bazan, N., Muntés-Mulero, V., Gómez-Villamor, S., Nin, J., Sánchez-Martínez, M.-A., Larriba-Pey, J.-L.: Dex: high-performance exploration on large graphs for information retrieval. In: CIKM 2007: Proceedings of the sixteenth ACM conference on Conference on information and knowledge management, pp. 573–582. ACM, New York (2007)CrossRefGoogle Scholar
- 9.Özsu, M.T., Valduriez, P.: Principles of distributed database systems, 2nd edn. Prentice-Hall, Inc., Upper Saddle River (1999)Google Scholar
- 12.van Helden, J., Naim, A., Mancuso, R., Eldridge, M., Wernisch, L., Gilbert, D., Wodak, S.: Representing and analysing molecular and cellular function using the computer. Biological Chemistry 381(i9–10), 921–935 (2000)Google Scholar
- 13.Yoo, A., Chow, E., Henderson, K., McLendon, W., Hendrickson, B., Catalyurek, U.: A scalable distributed parallel breadth-first search algorithm on bluegene/l. In: SC 2005: Proceedings of the, ACM/IEEE conference on Supercomputing, p. 25. IEEE Computer Society, Washington (2005)Google Scholar