A SLA-based cloud resource provisioning optimisation mechanism for multi-tenant applications

摘要

As cloud resources exhibit the characteristics of dynamic and scalability, an increasing number of service providers deploy their multi-tenant applications to Cloud. For cloud service providers, how to arrange the allocation of application resources reasonably, in order to not only satisfy the service level agreements (SLAs) of diverse tenants, but also maximise their resource utilisation, has become a major challenge. In this paper, we propose a SLA-based resource provisioning optimisation mechanism for multi-tenant applications. Based on the invoking relationships among services and the workload of service instances, the mechanism divides the tenants' SLA into SLA constraints, and maps each SLA constraint to the corresponding service. In addition, the mechanism uses an optimised round-robin scheduling policy to improve the resource utilisation of each service instance, and employs a defragmentation optimisation algorithm to control the scale of service instances and increase the overall resource utilisation. The experimental results show that the proposed mechanism is feasible and effective.