Service Level Agreement Based Distributed Resource Allocation for Streaming Hosting Systems

The trend to outsourcing network services to third parties in a utility model has resulted in a new distributed application model where the hosting service, service providers and end clients constitute a co-dependent profit ecosystem. SLAs provide a means for the service providers to specify their target levels of performance and reliability and for the hosting service to arbitrate among competing services under resource constraint. In this paper, we propose a number of design principles for specifying and enforcing SLAs that allow service providers to obtain expected throughput from hosting systems. We propose and evaluate an algorithm, Squeeze, based on pricing and penalties that allows the hosting service to maximize its profits while flexibly allocating available system resources among competing services based on prespecified SLAs and dynamically changing client access characteristics.