Dynamic Scheduling Algorithm for Heterogeneous Environments with Regular Task Input from Multiple Requests

Grids are very dynamic and their workload is impossible to predict. As a result systems using them need to offer mechanisms for adapting to the new configurations. To address this issue many scheduling policies have been created. In a Grid environment in which tasks needing to be scheduled arrive constantly it is costly to lend some computing resources to only one request consisting of jobs and postpone all others as long as the current one is executing. As a result a scheduling algorithm which minimizes each task's estimated execution time by considering the total waiting time of a task, the relocation to a faster resource once a threshold has been reached and the fact that it should not be physically relocated at each reassignment should be considered. This paper tries to offer a solution based on the above. To validate the model a comparison with other scheduling algorithms is performed.

[1]  Jack J. Dongarra,et al.  Experiments with Scheduling Using Simulated Annealing in a Grid Environment , 2002, GRID.

[2]  Yohsuke Kinouchi,et al.  Neural networks for event extraction from time series: a back propagation algorithm approach , 2005, Future Gener. Comput. Syst..

[3]  Andrea C. Arpaci-Dusseau,et al.  The Impact of More Accurate Requested Runtimes on Production Job Scheduling Performance , 2002, JSSPP.

[4]  P. Sadayappan,et al.  Characterization of backfilling strategies for parallel job scheduling , 2002, Proceedings. International Conference on Parallel Processing Workshop.

[5]  Rizos Sakellariou,et al.  An Experimental Investigation into the Rank Function of the Heterogeneous Earliest Finish Time Scheduling Algorithm , 2003, Euro-Par.

[6]  Dror G. Feitelson,et al.  Utilization, Predictability, Workloads, and User Runtime Estimates in Scheduling the IBM SP2 with Backfilling , 2001, IEEE Trans. Parallel Distributed Syst..

[7]  Francine Berman,et al.  Heuristics for scheduling parameter sweep applications in grid environments , 2000, Proceedings 9th Heterogeneous Computing Workshop (HCW 2000) (Cat. No.PR00556).

[8]  Manish Parashar,et al.  Grid Computing — GRID 2002 , 2002, Lecture Notes in Computer Science.

[9]  Selim G. Akl,et al.  Scheduling Algorithms for Grid Computing: State of the Art and Open Problems , 2006 .

[10]  R. F. Freund,et al.  Dynamic matching and scheduling of a class of independent tasks onto heterogeneous computing systems , 1999, Proceedings. Eighth Heterogeneous Computing Workshop (HCW'99).

[11]  Cynthia Bailey Lee,et al.  Are User Runtime Estimates Inherently Inaccurate? , 2004, JSSPP.

[12]  Rizos Sakellariou,et al.  A low-cost rescheduling policy for efficient mapping of workflows on grid systems , 2004, Sci. Program..

[13]  Jarek Nabrzyski,et al.  Dynamic grid scheduling with job migration and rescheduling in the GridLab resource management system , 2004, Sci. Program..

[14]  Celso C. Ribeiro,et al.  Greedy Randomized Adaptive Search Procedures , 2003, Handbook of Metaheuristics.

[15]  Warren Smith,et al.  Predicting Application Run Times Using Historical Information , 1998, JSSPP.

[16]  Henri Casanova,et al.  Extracting Synthetic Multi-Cluster Platform Configurations from Grid'5000 for Driving Simulation Experiments , 2007 .

[17]  Yang Gao,et al.  Adaptive grid job scheduling with genetic algorithms , 2005, Future Gener. Comput. Syst..

[18]  Erik Hagersten,et al.  THROOM — Supporting POSIX Multithreaded Binaries on a Cluster , 2003 .

[19]  Kenichi Hagihara,et al.  A comparison among grid scheduling algorithms for independent coarse-grained tasks , 2004, 2004 International Symposium on Applications and the Internet Workshops. 2004 Workshops..