A Hybrid Approach to Scalable Name Prefix Lookup

Abstract

Name prefix lookup is a core function in Named Data Networking (NDN). It is challenging to perform high-speed name-based longest prefix match lookups against a large amount of variable-length, hierarchical name prefixes in NDN. However, prior work concentrates on software-based name prefix lookup, and can't satisfy the scalability demands of high-speed lookups, low memory cost, and fast incremental updates. In this paper, we propose a hybrid approach to scalable name prefix lookup with hardware and software. We propose SACS, a shape and content search framework with ternary content addressable memories (TCAMs) and static random memory access memories (SRAMs). SACS aims to achieve high-speed lookups and low memory cost, while sustaining fast incremental updates. In SACS, a TCAM-based shape search module is first used to determine a subset of possible matching prefixes, and then a SRM-based content search module is used on the subset to find the longest matching prefix. For SACS, we propose a first shrinking least load algorithm to pack large amounts of shapes of name prefixes in a small TCAM. A shape of a name prefix is a sequence of its component lengths. We also propose a dual fingerprint-based hash table to improve the content search performance in SRAMs. Experimental results demonstrate that SACS outperforms state-of-the-art schemes by achieving up to 2.4X higher lookup throughput, up to 53% lower memory cost, and up to 96% higher insert throughput.