I. Introduction
Cloud computing is attractive to Web service owners because it empowers them to provide highly available and manageable applications at low cost. The dynamic resource provisioning capabilities of cloud infrastructures further enables Web application owners to scale their applications on the fly with low operational cost. A variety of criteria could potentially be used to measure the performance of a dynamic resource provisioning policy. From the Web application user's point of view, however, response time is the most important quality attribute of a Web application, yet current service-level agreements (SLAs) offered by cloud infrastructure providers do not address response time.