Trace-driven Analysis of Migration-based Gang Scheduling Policies for Parallel Computers

Gang scheduling is a job scheduling policy for parallel computers that combines elements of space-sharing and time-sharing. In this paper, we analyze the performance of gang scheduling policies that allow the remapping of an executing job to a new set of processors. Most previously proposed gang-scheduling policies do not allow such job remapping under the assumption that it is prohibitively expensive. Through a detailed trace-driven simulation, we analyze the tradeoo between the beneets and overheads of such job relocation. Our results show that gang-scheduling policies that support such job relocation ooer signiicant performance gains over policies that do not use remapping.