Scalability and Performance Considerations for Traffic Classification in Software-Defined Networks

Abstract

Scalable network-wide traffic classification, combined with knowledge of endpoint identities, will enable the next wave of innovation in networking, by exposing a valuable layer of network metadata for applications to consume. We leverage the promising new paradigm of Software-Defined Networking (SDN) to create architecture for scalable traffic classification (TC). In this paper, we demonstrate scalability issues inherent with running full TC services over a traditional SDN architecture through test results. We then propose an architectural modification for scalable TC built atop of widely-available OpenFlow SDN switches, implementing higher-complexity classification functions on commodity hardware. We validate this approach through a prototype implementation, with experimental results that demonstrate the scalability of our approach.