On Application-aware and On-demand Service Composition in Heterogenous NFV Environments

In this work, we try to further enhance the flexibility and cost-effectiveness of network function virtualization (NFV) by considering virtual network function service chaining (vNF-SC) in a heterogeneous NFV environment that can instantiate vNFs on virtual machines (VMs), docker containers, and SmartNICs. Specifically, we first lay out the network model, build a real network testbed that supports vNF deployment on kernel-based VMs, docker containers, and commercial SmartNICs, and then conduct experiments to measure the throughput and latency of traffic processing and memory usage of four types of vNFs implemented on them. Next, based on the measurement results, we formulate an integer linear programming (ILP) model to optimize the application-aware vNF-SC provisioning in the heterogenous NFV environment. Finally, we design and perform two experiments to demonstrate that our heterogeneous NFV environment can combine the advantages of VM/docker container/SmartNIC to provide enhanced flexibility for realizing on-demand and application-aware vNF-SC composition.