International Workshop on Challenges of Large Applications in Distributed Environments
Resource Co-allocation for Parallel Tasks in Computational Grids
Seattle, Washington
June 21-June 21
ISBN: 0-7695-1984-9
Lizhe Wang, Nanyang Technological University, Singapore
Wentong Cai, Nanyang Technological University, Singapore
Bu-Sung Lee, Nanyang Technological University, Singapore
Wei Jie, Institute of High Performance Computing, Singapore
Tasks running in computational Grids may require multiple types of resources simultaneously. Thus, co-allocation of multiple types of resources is needed when scheduling tasks. Traditional list scheduling heuristics cannot address the problem of resource co-allocation in computational Grids. This paper presents models for computational Grids and paral-lel tasks running in computational Grids. Based on these models, a parallel task scheduling algorithm for resource co-allocation in computational Grids is proposed. The algorithm identifies the critical resource of parallel tasks and tries to schedule a task as early as possible when all the resources required by the task are available. Simulation results show that the algorithm can gain performance improvement, especially in the resource competitive computational Grid.
Index Terms:
computational Grid, resource co-allocation, parallel task scheduling
Citation:
Lizhe Wang, Wentong Cai, Bu-Sung Lee, Simon See, Wei Jie, "Resource Co-allocation for Parallel Tasks in Computational Grids," clade, pp.88, International Workshop on Challenges of Large Applications in Distributed Environments, 2003