An SDN orchestrator for cloud data center: System design and experimental evaluation

The high volatility of Virtual Machine (VM) deployments, the unpredictable traffic patterns, and the oversubscription of Data Center (DC) network links give rise to new challenges in data delivery operations in cloud DCs. These challenges can be addressed through a flexible and agile control of DC networks, which is also coordinated, i.e., orchestrated, with the management of computing resources to improve the usage of DC resources while effectively meeting user demands. In this regard, the Software-Defined Network (SDN) paradigm can play a key role thanks to automated and multi-granular network control operations and to a more effective interworking with applications (e.g., cloud management platforms). This paper presents an SDN-based orchestrator able to coordinate the provision of both cloud and network services while jointly arranging VMs and delivery path allocations based on the current load. This approach assures a proper network resource utilization as well as the convey of VM data across the DC network with better than best-effort quality. A prototype is presented with focus on the software design and on the orchestration strategies exploiting measurement-based load estimation mechanisms. The orchestrator has been thoroughly evaluated through a comprehensive set of experiments carried out using a cloud DC testbed. Results show the effectiveness of the proposed SDN-based orchestration approach and the impact of the orchestration strategies on the DC resource utilization.