Traffic capture beyond 10 Gbps: Linear scaling with multiple network interface cards on commodity servers

As the number of users on Internet is increasing day by day, Network traffic rate is going up exponentially. The traffic analysis capability also need to be scaled up correspondingly to handle this high traffic rates. The modern commodity platforms equipped with processors rich in number of cores and having hyper threading technology has enabled emergence of software based solutions rather than dedicated platforms for traffic analysis. But the general purpose network stacks provided by operating systems focus more on compatibility and hence are not able to fully exploit the hardware capabilities of these platforms. Lot of work is reported on customizing the stack for packet capture and achieving line rate (10 Gbps) performance on a single Network Interface Card (NIC). Some work is also reported on use of multiple 10GbE NICs for handling traffic beyond 10 Gbps. This paper brings out through experimental setup and observations the issues involved in linear scaling of performance with additional NICs on commodity Non Uniform Memory Access (NUMA) servers. It shows that linear scaling requires optimum configurations of compute, memory and network resources especially affinity of NICs to NUMA nodes. Using these configurations we are able to achieve linear scaling of traffic analysis capability with additional 10 GbE NICs. We report scaled performance upto 40 Gbps with the use of four NIC cards.