Priority Scheduling in MapReduce Based on Queuing Theory

Abstract

MapReduce is a programming model and an associated implementation for processing and generating large data sets. Providing MapReduce as a service is the development future trend. This paper present a queue theory based scheduling scheme for MapReduce framework. The scheme divides users into priority user and non-priority and users respectively corresponding to different queues. The scheme insures priority user has a pre-specified delay and the non-priority queue have a promised utilization ratio. At last, Experiments show the effectiveness of the scheme.