NFV-VITAL: A framework for characterizing the performance of virtual network functions

Network Function Virtualization (NFV) brings a cloud service automation paradigm to demand-driven elastic flexing of infrastructure resources. Thus, it is essential to characterize the impact of hardware and virtualization options on the virtual network function (VNF) performance, and on the load on underlying infrastructure. In this paper, we present VNF characterization case studies with three sample open-source VNF platforms, the Clearwater IMS VNF and two intrusion detection system VNFs (Snort and Suricata). We demonstrate that VNF characterization is vital for optimizing VNF performance, as well as efficient utilization of infrastructure resources. We use the lessons learned from our case studies to design and implement a VNF characterization framework, NFV-VITAL, to characterize VNFs based on user preferences and available resources. We demonstrate how NFV-VITAL can automatically determine optimal configurations under different workloads with the three sample VNFs.