Open Access Open Access  Restricted Access Subscription or Fee Access

A Scheduling Algorithm for Coarse Grain Applications with Spry Technique

S. V. Sudha, K. Thanushkodi

Abstract


Coarse Grain applications require all processes run with a very gross level of synchronization among them. Any collection of concurrent processes that need to communicate or synchronize can benefit from the use of a multiprocessor architecture. This type of application can be achieved from time and space slicing, but the algorithms suffer from fragmentation, where the processors are left idle because jobs cannot be packed with 100% efficiency. This fragmentation results to reduce utilization and poor performance. Spry algorithm concentrates on the above-mentioned problems and the results of the spry algorithm are compared with First Come First Serve. Gang Scheduling and Flexible Co scheduling. Spry Algorithm is implemented with Java thread and the results are compared with the performance metrics like Turn around Time, Mean Response Time, Mean Reaction Time, Mean Slowdown, Mean Utilization and Average waiting time of the Jobs.

Keywords


Parallel Job Scheduling, Performance Metric, Mean Slowdown.

Full Text:

PDF

References


Dan Tsafrir, Yoav Etsion, Dror G. Feitelson, “Backfilling Using System –Generated Predictions Rather than User Runtime Estimates”, IEEE Transaction on Parallel and Distributed Systems, VOL 18, NO 6, pp 789-803, June 2007.

Avi Nissimov and Dror G. Feitelson, “Probabilistic Backfilling,” 13th Workshop on Job Scheduling Strategies for Parallel Processing In Conjuction with 21st ACM International Conference on Super Computing ,pp 102-115, June 2007.

Eitan Frachtenberg, Dror G.Feitalson. Fabrizio Petrini,Juan Fernandez,” Adaptive Parallel Job Scheduling with Flexible Coscheduling”, IEEE Trans. Parallel and Distributed Systems, Vol 16, No 11, pp.1066-1077, November 2005.

C. Anglano, “A Comparative Evaluation of Implicit Coscheduling Strategies for Network of Workstations,” Proc. Ninth Int’l Symposium High Performance Distributed Computing, pp 221-228, August 2000.

C. D. Antonopoulos, D. S. Nikolopoulos and T. S. Papatheodorou, “Informing Algorithms for Efficient Scheduling of Synchronizing Threads on Multiprogrammed SMPs,” Proc International Conference on Parallel processing, pp 123-130, Sept 2001.

E. Franchtenberg, D. G. Feitelson J. Fernandez - Peinador and F. Petrini, “Parallel Job Scheduling under Dynamic Workloads,” ,Proceedings of Ninth Workshop Job Scheduling Strategies for Parallel Processing, pp 208-227, June 2003.

U. Lublin and D. G. Feitelson, “The Workload of Super Computers Modeling the Characteristics of Rigid Jobs,” Journal on .Parallel and Distributed Computing, vol. 63, no. 11, pp. 1105-1122, Nov 2003.

R. Kettimuthu, V. Subramani, .Srinivasan, T. B. Gopalasamy, D. K. Panda and P. Sadayappa, “Selective preemption Strategies for Parallel Job Scheduling ,” Proceedings of International Conference on Parallel Processing, pp 55-71, August 2002.

W. Lee, M. Frank, V. Lee, K. Mackenzie and L. Rudolph, “Implication of I/O for Gang Scheduled Workloads,” Job Scheduling Strategies for Parallel Processing, pp 215-237, 1997.

D. Kerbyson, H. Alme, A. Hoisie, F. Petrini, H. Waserman and Miggints ,. “Predictive Performance and Scalability Modeling of a Large –Scale SMP Clusters”, Proceedings of Symposium, Frontiers of Massively Parallel Computation , Feb 1999.

E. Frachtenberg, F. Petrini, J. Fernandez, S. Pakin and S. Coll , “STROM :Lightning –Fast Resource Management,” Proc Supercomputing conf 2002, Nov 2002.

D. G. Feitelson and L. Rudolph, “Metric and Benchmarking for Parallel Job Scheduling,” Job Scheduling Strategies for parallel Processing, pp 1-24, 1998

S. Srinivasan, R. Kettimathu, V. Subramani and P. Sadayappan, “Selective Reservation Strategies for Backfilling Job Scheduling,” Job Scheduling Strategies for Parallel Processing, PP 55-71, 2002.

D. S. Nikolopoulos and C. D. Polychronopoulos, “Adaptive Scheduling Under Memory Constraints on Non-Dedicated Computational Farme ,” Future Generation Computer Systems, Vol. 19, no. 4, pp 505-519, May 2003.

D. G. Feitelson .Logs of real parallel workloads from production Systems.http://www.cs.hiji.ac.il/labs/parallel/workload/logs.html.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.