Performance evaluation of gang scheduling in a two-cluster system with migrations

Gang scheduling is considered to be a highly effective task scheduling policy for distributed systems. In this paper we present a migration scheme which reduces the fragmentation in the schedule caused by gang scheduled jobs which cannot start. Furthermore, the existence of high priority jobs in the workload is addressed by the proposed strategy. High priority jobs need to be started immediately, which can in turn lead to the interruption of a parallel job's execution. A distributed system consisting of two homogeneous clusters is simulated to evaluate the performance. Our simulation results indicate that the proposed strategy can result in a performance boost.