The functionality covered by this project will be implemented in the form of services separate from the core OpenStack services. The services of this project will interact with the core OpenStack services using their public APIs. It will be required to create a new Keystone user within the service tenant. The project will also require a new MySQL database for storing historical data on the resource usage by VMs. The project will provide a script for automated initialization of the database. The services provided by the project will need to be run on the management as well as compute hosts.
The problem of data center operation is high energy consumption, which has risen by 56% from 2005 to 2010, and in 2010 accounted to be between 1.1% and 1.5% of the global electricity use [3]. Apart from high operating costs, this results in substantial carbon dioxide (CO2) emissions, which are estimated to be 2% of the global emissions [4]. The problem has been partially addressed by improvements in the physical infrastructure of modern data centers. As reported by the Open Compute Project, Facebook’s Oregon data center achieves a Power Usage Effectiveness (PUE) of 1.08, which means that approximately 93% of the data center’s energy consumption are consumed by the computing resources. Therefore, now it is important to focus on the resource management aspect, i.e. ensuring that the computing resources are efficiently utilized to serve applications.
+The problem of data center operation is high energy consumption, which has risen by 56% from 2005 to 2010, and in 2010 accounted to be between 1.1% and 1.5% of the global electricity use [3]. Apart from high operating costs, this results in substantial carbon dioxide (CO2) emissions, which are estimated to be 2% of the global emissions [4]. The problem has been partially addressed by improvements in the physical infrastructure of modern data centers. As reported by the Open Compute Project, Facebook’s Oregon data center achieves a Power Usage Effectiveness (PUE) of 1.08, which means that approximately 93% of the data center’s energy consumption are consumed by the computing resources. Therefore, now it is important to focus on the resource management aspect, i.e. ensuring that the computing resources are efficiently utilized to serve applications.
Dynamic consolidation of VMs has been shown to be efficient in improving the utilization of data center resources and reducing energy consumption, as demonstrated by numerous studies [5–16]. In this project, we aim to implement an extensible framework for dynamic VM consolidation specifically targeted at the OpenStack platform.