Content-based route lookup using CAMs

Abstract

The applications of the Internet have evolved from being host-centric to being more content-oriented, such as file sharing, online audio and video applications, which constitute the majority of Internet traffic [1]. Several future Internet architectures, putting the content (or information) in the fore-front, have lately been proposed in order to solve the limitations of the current architecture (i.e. insufficient bandwidth to servers, lack of security, mobility, virtualization, user/data centricity, etc.). However, one of the greatest challenges of a novel content-oriented Internet architecture lies in the complexity of looking up long, variable length names compared to the current 32 bit long IPv4 (or even 128 bit IPv6) addresses of today's networks. The success of widely adopting any content-oriented architecture highly depends on the success of designing algorithms that allow these complex names to be looked up at high-speed. Ternary Content Addressable Memories (TCAMs) are widely used in high-speed routers to find matching routes for packets in a routing table. They enable the longest prefix matching (LPM) operation on fixed length addresses to complete in a single clock cycle, however, they are not efficient to store and lookup name prefixes with variable lengths such as the ones proposed in name-based routing [2]-[9]. In this paper, we propose an efficient name-based longest prefix matching algorithm for information-centric networks using TCAMs. In our algorithm, we split incoming prefixes in fixed blocks and subsequently hash these blocks for fixed length storage. Our approach is flexible to support both hierarchical name based routing lookup and flat name based routing lookup. In addition, our approach can be easily modified to support multiple matchings instead of the longest prefix matching. The simulation results demonstrate that our approach is able to provide efficient name-based routing lookup even for the fastest backbone routers (i.e. 100+ Gbps).