Assessing the value of containers for NFVs: A detailed network performance study

Since its introduction in 2012, telecommunications operators have been applying the Network Function Virtualization principle to their core infrastructure, leading to more agile and cost-efficient deployments. While these Virtualized Network Functions (VNFs) are traditionally implemented using Virtual Machines (VMs), efforts are starting to shift to containerized VNF implementations, further improving agility and cost-efficiency. Furthermore, telecom applications often require extreme networking performance in terms of throughput and latency. While research has shown that containers outperform VMs on this front, it is currently unclear how the choice of container provider influences network performance. In this paper we compare the networking performance of Linux container implementations Docker, rkt and LXC. Throughput and latency are evaluated for single-host host, bridge (or NAT) and macvlan network configurations. This is, to the best of our knowledge, the first comparison featuring all three major Linux container implementations. We show that LXC performs best, with Docker and rkt showing throughputs of respectively up to 35 % and 58 % lower. Of the considered networking implementations, the macvlan network performs best. While it experiences a significant performance degradation when many containers are chained together, a single container using macvlan can outperform even a bare metal implementation when enough CPU resources are available.