Abstract
In this article we present an improvement on the loadba lancing of a parallel cluster environment, considering the MPI parallel programming paradigm and employing a mobile agent system. Our approach is to apply the mobile agent technology to provide a better scheduling, which couldre present in a cluster configuration an enhancement on the loadb alancing. MPI in cluster of heterogeneous machines could leadp arallel programmers to obtain frustratedresu lts, mainly because of the lack of an even distribution of the workload in the cluster. As a result, before submitting a MPI application to a cluster, we use the Aglets mobile agent package to acquire a more precise information of machines’ workload. Therefore, with a more precise knowledge of the load (and characteristics) in each machine, we are ready to gather lightweight workstations to form a cluster. Our empirical results indicates that it is possible to spendless elapsed time when considering the execution of a parallel application using the agent approach in comparison to an ordinary MPI environment.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
M.L. Michael J. Litzkow and M.W. Mutka, “Condor-A Hunter of Idle Workstations,” Proceedings of IEEE 8th International Conference on Distributed Computing Systems, pp. 104–111, 1988.
J. Suplick, “An Analysis of LoadBalancing Technology,” January 1994.
I.B.M.Corporation, IBM LoadLever: User’s Guide. Kingston, NY: IBM, September 1993.
MPI-Forum, “MPI: A Message-Passing Interface Standard,” International Journal of Supercomputer Application, vol. 8,no. 3-4, 1994.
A.B. Al Geist, Jack Dongarra and V. Sunderam, PVM: User’s Guide and Reference Manual (Version 3.3). Oak Ridge, USA: Oak Ridge National Laboratory Technical Report ORNL/TM-12187, May 1994.
J. R.C. et al, “Project Zeus,” IEEE Network, pp. 20–30, 1993.
N.J.B. Fleish, R. Hyde, “Mirage+: a kernel implementation of distributed shared memory on a network of workstations,” Software: Practuce and Experience, pp. 1–21, March 1994.
C.T.D. Scales, K. Gharachorloo, “Shasta: A Low-OverheadSo ftware-Only Approach for Supporting Fine Grain Shared Memory,” Aplos-96, 1996.
M. Dantas and E. Zaluska, “Improving Load Balancing in an MPI Environment with Resource Management,” Lecture Notes in Computer Science, Proceedings of the HPCN Europe 1996, Brussels, Belgium, pp. 959–960, April 1996.
M. Dantas and E. Zaluska, “Efficient scheduling of mpi applications on network of workstations,” Future Generation Computer Systems, vol. 13, pp. 489–499, May 1998.
D.B. Lange and M. Oshima, “Programming and deploying java mobile agents with aglets,” November 1998.
D. College, “D’agent,” http://agent.cs.dartmouth.edu/software/agent2.0/download.html.
D. Johansen, R. van Renesse, and F.B. Shneider, “An introduction to the tacoma distributed system-version 1.0,” June 1995.
R.G. et al, “Mobile agents: The next generation in distributed computing,” IEEE-Proceedings of the 2nd AIZU International Simposium on Parallel Algorithms / Architecture Synthesis (pAs’97), pp. 8–24, 1997.
G. Magic, “General magic,” http://www.genmagic.com/telescript.
J. White, “Mobile agent white paper,” http://www.genmagic.com/agents/Whitepaper/whitepaper.html, 1996.
IBM, “Aglets home page”, http://www.trl.ibm.co.jp/aglets/index.html.
H. Peine, “An introduction to mobile agent programming and the ara system,” 1996.
W.L. Dejan S. Millojicic and D. Chauhan, “Mobile objects andagen ts (moa), ” http://www.opengroup.org.
B. Pierce, “Mobile agent computing: A white paper,” http://www.cis.upenn.edu/~bcpierce/courses/629/papers/Concordia-WhitePaper.html, 1997.
C. University, “Concordia mobile agent site,” http://www.meitca.com/HSL/Projects/Concordia.
D.M. et al, “Masif-the OMG mobile agent system interoperability facility,” September 1998.
J. Baumann, F. Hohl, K. Rothermel, and M. Straber, “Mole-concepts of mobile agent system,” IPVR (Institute for Parallel and Distributed High-Performance Computers-University of Stuttgart, no. 1997/15, 1997.
G. Glass, “Voyager. overview of voyager: Objectspace’s produtct family for state-of-the-art distributed computing,” 1999.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dantas, M.A.R., Lopes, F.M. (2001). Improving Load Balancing in a Parallel Cluster Environment Using Mobile Agents. In: Hertzberger, B., Hoekstra, A., Williams, R. (eds) High-Performance Computing and Networking. HPCN-Europe 2001. Lecture Notes in Computer Science, vol 2110. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48228-8_53
Download citation
DOI: https://doi.org/10.1007/3-540-48228-8_53
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42293-8
Online ISBN: 978-3-540-48228-4
eBook Packages: Springer Book Archive