Towards Intelligent Management in VM-based Resource Providers

In this paper, we present and evaluate an algorithm to provide autonomous management in VM-based resource providers. We provide a solution to adjust the resources needed by each VM according to demand. We achieve this with a policy that meets at least the agreed application-level QoS, and a priority weight-based mechanism to spread the unused resources between the contending VMs that run over their QoS requirements. The proposed algorithm is implemented in a two processors node with Xen virtualization solution and credit scheduler. The results show that we can better manage physical resources by dynamically adjusting local resources according to demand.