New job selection and location policies for load distributing algorithms

Load distributing algorithms in distributed systems are used to share the resources by distributing the workload. These algorithms have four components: a transfer policy that determines whether a node is in a suitable state to participate in a task transfer; a selection policy that determines which task should be transferred; a location policy that determines to which node a task selected for transfer should be sent; and an information policy which is responsible for triggering the collection of system state information. This paper presents a new load distributing algorithm, SLCT, which uses new job selection and location policies. The selection policy selects the best task for transfer, as compared to only selecting newly-arrived tasks in most existing algorithms. The location policy also finds the best receiver. SLCT is shown to outperform the best-reported load distributing algorithm. The performance of SLCT is evaluated and compared with some existing algorithms.