Hierarchical scheduling mechanism for grid systems

Grid system is a networked system that enables one to perform high throughput computation by sharing geographically distributed resources. Job scheduling mechanism is an important factor for improving performance of Grid system such as resource utilization and response time. This paper presents a hierarchical job scheduling mechanism for the purpose of addressing the performance improvement of Grid system. It is based on multiple-queue management with respect to both a super-scheduling scheme for distributing jobs to overall nodes and a local scheduling scheme for assigning jobs within a node. Several experiments show that the proposed mechanism achieves higher resource utilization by improving the backfilling ratio and using idle nodes in a Grid system.

[1]  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..

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

[3]  Ladislau Bölöni,et al.  A Comparison of Eleven Static Heuristics for Mapping a Class of Independent Tasks onto Heterogeneous Distributed Computing Systems , 2001, J. Parallel Distributed Comput..

[4]  Hongzhang Shan,et al.  Job Superscheduler Architecture and Performance in Computational Grid Environments , 2003, ACM/IEEE SC 2003 Conference (SC'03).

[5]  Evgenia Smirni,et al.  Multiple-Queue Backfilling Scheduling with Priorities and Reservations for Parallel Systems , 2002, JSSPP.

[6]  Dmitry N. Zotkin,et al.  Job-length estimation and performance in backfilling schedulers , 1999, Proceedings. The Eighth International Symposium on High Performance Distributed Computing (Cat. No.99TH8469).

[7]  Keqin Li,et al.  Job scheduling for grid computing on metacomputers , 2005, 19th IEEE International Parallel and Distributed Processing Symposium.