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.
展开▼
