Dynamic Load Balancing in PVM Using Intelligent Application

Authors: Kashif Bilal, Tassawar Iqbal, Asad Ali Safi, Nadeem Daudpota

Abstract:

This paper deals with dynamic load balancing using PVM. In distributed environment Load Balancing and Heterogeneity are very critical issues and needed to drill down in order to achieve the optimal results and efficiency. Various techniques are being used in order to distribute the load dynamically among different nodes and to deal with heterogeneity. These techniques are using different approaches where Process Migration is basic concept with different optimal flavors. But Process Migration is not an easy job, it impose lot of burden and processing effort in order to track each process in nodes. We will propose a dynamic load balancing technique in which application will intelligently balance the load among different nodes, resulting in efficient use of system and have no overheads of process migration. It would also provide a simple solution to problem of load balancing in heterogeneous environment.

Keywords: PVM, load balancing, task allocation, intelligent application.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1075296

References:

[1] V. S. Sunderam, "PVM A framework for parallel distributed computing", Concurrency, Practice and Experience by John Wiley & Sons Vol. 2(4), pages 315--339, December, 1990.
[2] A. Osman, H. Ammar, "Dynamic Load Balancing Strategies for Parallel Computers", International Symposium on Parallel and Distributed Computing (ISPDC), Romania, July 2002.
[3] Hillis, W.D. "The Connection Machine" MIT press, Cambridge, 1985.
[4] Powley, C., Ferguson, C. and Korf, R. E. "Depth-First Heuristic Search on a SIMD Machine", Artificial Intelligence, vol. 60, pages.199-242, 1993.
[5] Fonlupt, C., Marquet, P. and Dekeyser, J. "Data-parallel loadbalancing strategies", Parallel Computing, pages1665-1684, 1998.
[6] Dekeyser, J. L., Fonlupt, C. and Marquet, P. "Analysis of Synchronous Dynamic Load Balancing algorithms, Parallel Computing", State-of-the Art Perspective (ParCo'95), vol. 11 of Advances in Parallel Computing, pages 455--462, Gent, Belgium, September 1995.
[7] Subramanian, R. and Scherson, "An Analysis of Diffusive Load Balancing". Proceedings of Sixth Annual ACM Symposium on Parallel Algorithms and Architectures, pages 220ÔÇö225, June 1994.
[8] Leen Dikken, Frank van Der Linden, Joep Vesseur and Peter Sloot, "Dynamic PVM", Parallel Scientific Computing and Simulation Group, Springer Verlag, April 1994.
[9] M.J Litzkow, M.Livny. "Condor - A hunter of idle workstation", 8th International Conference on Distributed Computing Systems, San Jose, California, June 1988.
[10] K.A. Iskra, Z.W. Hendrikse, G. D. van Albada, B.J. Overeinder, P.M.A Sloot, "Experiments with Migration of PVM Tasks", Proceedings of the sixth annual conference of the Advanced school for Computing and Imaging ASCI , June, 2000.
[11] Ravikanth Nasika Partha Dasgupta "Transparent Migration of Distributed Communicating Processes", 13th ISCA International Conference of Parallel and Distributed Computing Systems, Aug, 2000.
[12] David J. Jackson Chris W. Humphres, "A Simple Yet Effective Load Balancing Extension to the PVM Software System", Parallel Computing, Volume 22, pages 1647-1660, February, 1997.
[13] A.I Geis, "Building a Foundation for the Next PVM", Petascale Virtual Machines, Springer-Verlag, London, 2001
[14] Dennis Guster, Abdullah Al-Hamamah, Paul Safonov, Elizabeth Bachman, "Computing and network Performance of a distributed parallel processing environment using MPI and PVM communication methods", Journal of Computing Sciences in Colleges USA April 2003
[15] Arthur Trey, Nelson Michael L. "Intel NX to PVM3.2 Message Passing Conversion Library", NASA Langley Technical Report Server, October 2003.