Modeling and Evaluating Cross-layer Elasticity Strategies in Cloud Systems

Abstract

Clouds are complex systems that provide computing resources in an elastic way. Elasticity property allows their adaptation to input workload by (de)provisioning resources as the demand rises and drops. However, due to the numerous overlapping factors that impact their elasticity and the unpredictable nature of the workload, providing accurate action plans to manage cloud systems' elastic adaptations is a particularly challenging task. In this paper, we propose an approach based on Bigraphical Reactive Systems (BRS) to model cloud structures and their elastic behavior. We design elasticity strategies that operate at service and infrastructure cloud levels to manage the elastic adaptations. Besides, we provide a Maude encoding to permit generic executability and formal verification of the elastic behaviors. One step ahead, we show how the strategies can be combined at both levels to provide different high-level elastic behaviors. Finally, we evaluate the different cross-layer combinations using Queuing Theory.

Formalizing and simulating cross-layer elasticity strategies in Cloud systems

“…In order to simulate and illustrate the defined elasticity strategies, we designed a program which works according to the MAPE (Monitor, Analyze, Plan, Execute) autonomic control loop [25]. The tool enables simulating and monitoring a managed elastic Cloud system during its runtime.…”

“…Elasticity allows to efficiently control resources provisioning according to workload fluctuation in a way to maintain an adequate quality of service (QoS) while minimizing operating cost [15]. Such a behavior is implemented by an elasticity controller: an entity usually based on a closed control loop which decides of the elasticity actions to be triggered to adapt to the demand [25]. In fact, managing a Cloud system's elasticity can be particularly challenging.…”