Dynamite-blasting obstacles to parallel cluster computing
Workstations make up a very large fraction of the total available computing capacity in many organisations. In order to use this capacity optimally, dynamic allocation of computing resources is needed. The Esprit project Dynamite addresses this load balancing problem through the migration of tasks in a dynamically linked parallel program. An important goal of the project is to accomplish this in a manner that is transparent both to the application programmer and to the user. As a test bed, the Pam-Crash software from ESI is used.
KeywordsMigration Decider Load Imbalance Task Migration Message Monitoring Target Machine
Unable to display preview. Download preview PDF.
- http://www.genias.de/products/codineGoogle Scholar
- J. Pruyne and M. Livny, Managing Checkpoints for Parallel Programs—Proc. IPPS Second Workshop on Job Scheduling Strategies for Parallel Processing, 1996Google Scholar
- M. Litzkow, T. Tannenbaum, J. Basney and M. Livny, Checkpoint and Migration of Unix Processes in the Condor Distributed Processing System—Technical Report 1346, University of Wisconsin, WI, USA, 1997.Google Scholar
- J. Casas, D.L. Clark, R. Konoru, S.W. Otto, R.M. Prouty and J. Walpole, MPVM: A migration transparent version of PVM, Usenix Computer Systems, v. 8, n. 2, Spring, pp. 171–216, 1995.Google Scholar
- J. Casas, D. Clark, P. Galbiati, R. Konuru, S. Otto, R. Prouty and J. Walpole, MIST: PVM with Transparant Migration and Checkpointing, Third Annual PVM Users' Group Meeting, Pittsburgh, PA, 1995Google Scholar
- J. Robinson, S.H. Russ, B. Flachs, B. Heckel, A Task Migration Implementation of the Message-Passing Interface. Proceedings of the 5th IEEE international symposium on high performance distributed computing, pp. 61–68, 1996Google Scholar
- Matthias Brune, Jörn Gehring and Alexander Reinefeld, Heterogeneous Message Passing and a Link to Resource Management, Journal on Supercomputing, Vol. 11, Kluwer, Boston, pp 355–369, 1997, http://www.uni-paderborn.de/pc2/services/public/1997/97012.ps.ZGoogle Scholar
- J. Casas, R. Konoru, S.W. Otto, R. Prouty and J. Walpole, Adaptive load migration systems for PVM, Proceeedings of Supercomputing '94, Washington DC, pp. 390–399, 1994Google Scholar
- M. Hamdi and C.K. Lee, Dynamic load balancing of data parallel applications on a distributed network, Proceedings of 1995 International Conference on Supercomputing, Barcelona, pp. 170–179, 1995Google Scholar
- R. Diekmann, B. Monien and R. Preis, Load Balancing Strategies for Distributed Memory Machines, Parallel and Distributed Processing for Computational Mechanics: Systems and Tools, B.H.V. Topping (ed.), Saxe-Coburg, 1998Google Scholar
- T. Decker, M. Fischer, R. Lüling and S. Tschöke, A Distributed Load Balancing Algorithm for Heterogeneous Parallel Computing Systems, Proceedings of the 1998 International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA'98), H. R. Arabnia (ed.), CSREA Press, Volume II, pp. 933–940, 1998.Google Scholar
- http://www.esi.fr/products/crash/index.htmlGoogle Scholar