A Design Space for Dynamic Service Level Agreements in OpenStack

This paper develops a research and development plan for dynamic service level agreements (SLAs) in Open Stack to support cloud applications that may have changing resources requirements. The fundamental SLA functions are reviewed: Admission Control, Monitoring, SLA Evaluation, and SLA Enforcement - a classic autonomic control cycle. We then identify five basic Load Types that a dynamic SLA system must manage: Best Effort, Throttled, Load Migration, Preemption and Spare Capacity. The key to meeting application SLA requirements under changing surge conditions is to also manage the spare surge capacity. The use of this surge capacity could be managed by one of several identified load migration policies. A more detailed SLA architecture for Open Stack is presented that discusses specific SLA components that would need to be developed for an end-to-end, dynamic SLA capability. Based on this architecture, a research and development plan is presented. Cloud SLAs and cloud performance management are important topics in the wider cloud marketplace. The cloud community would be well-served to track developments in the IEEE, Open Grid Forum, Tele Management Forum, and the NSF Center for Cloud and Autonomic Computing.