Introducing service-level awareness in the cloud

Abstract

Managing the resources of a virtualized data-center is a key issue in cloud computing [1]. Existing research mostly assumes that applications are either allocated the required resources or fail [2--15]. Combined with the fact that most cloud applications have dynamic resource requirements [16], this imposes a fundamental limitation to cloud computing: To guarantee on-demand resource allocations, the data-center needs large spare capacity, leading to inefficient resource utilization.