Applying Processes Rescheduling over Irregular BSP Application
This paper shows an evaluation of processes rescheduling over an irregular BSP (Bulk Synchronous Parallel) application. Such application is based on dynamic programming and its irregularity is presented through the variation of computation density along the matrix’ cells. We are using MigBSP model for processes rescheduling, which combines multiple metrics - Computation, Communication and Memory - to decide about processes migration. The main contribution of this paper includes the viability to use processes migration on irregular BSP applications. Instead to adjust the load of each process by hand, we presented that automatic processes rebalancing is an effortless technique to obtain performance. The results showed gains greater than 10% over our multi-cluster architecture. Moreover, an acceptable overhead from MigBSP was observed when no migrations happen during application execution.
KeywordsProcess Migration Migration Cost Application Execution Adaptive Load Destination Processor
- 2.Bonorden, O., Gehweiler, J., auf der Heide, F.M.: Load balancing strategies in a web computing environment. In: Conf. on Parallel Processing and Applied Mathematics, pp. 839–846 (2005)Google Scholar
- 6.Casanova, H., Legrand, A., Quinson, M.: Simgrid: A generic framework for large-scale distributed experiments. In: Conf. Comp. Modeling and Simulation, pp. 126–131. IEEE, Los Alamitos (2008)Google Scholar
- 7.Huang, C., Zheng, G., Kale, L., Kumar, S.: Performance evaluation of adaptive mpi. In: Symp. on Principles and pract. of parallel programming, pp. 12–21. ACM Press, New York (2006)Google Scholar
- 8.Moreno-Vozmediano, R., Alonso-Conde, A.B.: Influence of grid economic factors on scheduling and migration. In: Daydé, M., Dongarra, J., Hernández, V., Palma, J.M.L.M. (eds.) VECPAR 2004. LNCS, vol. 3402, pp. 274–287. Springer, Heidelberg (2005)Google Scholar
- 9.Bhandarkar, M.A., Brunner, R., Kale, L.V.: Run-time support for adaptive load balancing. In: IPDPS 2000: Proceedings of the 15 IPDPS 2000 Workshops on Parallel and Distributed Processing, pp. 1152–1159. Springer, London (2000)Google Scholar