Optimal Scheduling Algorithm of MapReduce Tasks Based on QoS in the Hybrid Cloud

Abstract

Research on MapReduce tasks scheduling method for the hybrid cloud environment to meet QoS is of great significance. Considering that traditional scheduling algorithms cannot fully maximize efficiency of the private cloud and minimize costs under the public cloud, this paper proposes a MapReduce task optimal scheduling algorithm named MROSA to meet deadline and cost constraints. Private cloud scheduling improves the Max-Min strategy, reducing job execution time. The algorithm improves the resource utilization of the private cloud and the QoS satisfaction. In order to minimize the public cloud cost, public cloud scheduling based on cost optimization selects the best public cloud resources according to the deadline. Experimental results show that the proposed algorithm in this paper has less job execution time, higher QoS satisfaction than the Fair scheduler and FIFO scheduler. It also has more cost savings and shorter job completion time than recent similar studies.