CompVM: A Complementary VM Allocation Mechanism for Cloud Systems

Abstract

In cloud datacenters, effective resource provisioning is needed to maximize the energy efficiency and utilization of cloud resources while guaranteeing the service-level agreement (SLA) for tenants. To address this need, we propose an initial virtual machine (VM) allocation mechanism (called CompVM) that consolidates complementary VMs with spatial/ temporal awareness. Complementary VMs are the VMs whose total demand of each resource dimension (in the spatial space) nearly reaches their host’s capacity during VM lifetime period (in the temporal space). Based on our observation of the existence of VM resource utilization patterns, the mechanism predicts the resource utilization patterns of VMs. Based on the predicted patterns, it coordinates the requirements of different resources and consolidates complementary VMs in the same physical machine (PM). This mechanism reduces the number of PMs needed to provide VM service, hence increases energy efficiency and resource utilization, and also reduces the number of VM migrations and SLA violations. We further propose a utilization variation-based mechanism, a correlation coefficient-based mechanism, and a VM group-based mechanism to match the complementary VMs in order to enhance the VM consolidation performance. Simulation based on two real traces and real-world testbed experiments shows that CompVM significantly reduces the number of PMs used, SLA violations, and VM migrations of the previous resource provisioning strategies. The results also show the effectiveness of the enhancement mechanisms in improving the performance of the basic CompVM.