Achieving Flexible SLA and Resource Management in Clouds

Abstract

One of the key factors driving Cloud computing is flexible and on-demand resource provisioning in a pay-as-you-go manner. This resource provisioning is based on Service Level Agreements (SLAs) negotiated and signed between customers and providers. Efficient management of SLAs and Cloud resources to reduce cost, achieve high utilization, and generate profit is challenging due to the large-scale nature of Cloud environments and complex resource provisioning processes. In order to advance the adoption of this technology, it is necessary to identify and address the issues preventing proper resource and SLA management. The authors purport that monitoring is the first step towards successful management strategies. Thus, this chapter identifies the SLA management and monitoring challenges in Clouds and federated Cloud environments, and proposes a novel resource monitoring architecture as a basis for resource management in Clouds. It presents the design and implementation of this architecture and presents the evaluation of the architecture using heterogeneous application workloads.