To search, Click below search items.


All Published Papers Search Service


Hybrid Job Scheduling Mechanism Using a Backfill-based Multi-queue Strategy in Distributed Grid Computing


Kiejin Park, Changhoon Kang, Sungsook Kim


Vol. 12  No. 9  pp. 39-48


In a distributed computing environment, effective job scheduling is a critical challenge. In this paper, a hybrid job scheduling mechanism is proposed that considers both the meta-scheduling scheme for distributing jobs to overall nodes and the local job scheduling scheme for assigning jobs within a local node at a simultaneous time. Depending on the number of required processors and the expected execution time of jobs, the order of priorities is established. Jobs with high priority are then allocated to a job queue whereas those with low priority are assigned to a backfill queue with remote jobs that are sent from other nodes. Experiments conducted to evaluate the performance of the proposed mechanism show that the utilization of a grid computing system becomes more efficient and waiting times are considerably reduced.


Meta-scheduling, Job scheduling, Backfill scheduling, Distributed Grid computing