Scalable packet classification based on rule categorization and cross-producting

Abstract

Packet classification performs multidimensional point location upon fields in packet headers to categorize packets into multiple forwarding classes based on pre-defined rules. It plays an important role for the data plane of software-defined networking (SDN). Packet classification is also applied to support quality of service and network security. In this work, we propose an algorithm, Segregated Cross-producting, to improve the scalability of cross-producting in term of storage. Our algorithm starts by categorizing rules according to their length combinations, where the rules of the same length combination do not incur any storage penalty for cross-producting. Then, the algorithm selectively merges rules of different length combinations to improve the search performance. Our scheme is suitable for parallel implementation to further improve speed performance and can support real-time incremental updates. We extensively evaluate the performance of our scheme with rulesets of different sizes and characteristics. The experiment results show that our scheme can provide superior scalability for both speed and space performance.