An efficient bandwidth reservation policy for data-intensive applications in cloud

Abstract

Recently, more and more data-intensive applications have been deployed in cloud platforms due to its cost-effective and elastic capability. Although computing resources (i.e., CPU and RAM) can be provisioned in on-demand manner, the network bandwidth has enforce certain admission controlling for providing desirable quality-of-service (QoS). As a result, data-intensive applications often suffer from high delay during the phase of bulk data transferring between computing nodes. In this paper, we present an integrated bandwidth reservation algorithm, which combines different admission controlling policies and minimises the finishing time for all jobs in an online manner. Performance evaluation on a real-world cloud platform shows that the proposed reservation algorithm can ensure efficient bulk data transferring even when the system is facing heavy workloads.