Longest Prefix Lookup in Named Data Networking: How Fast Can It Be?

摘要

Abstract-Named data networking architectures have emerged and attracted significant attention in recent years. Due to the name space being many orders of magnitude larger and more complex than IP address space, such architectures pose many significant challenges on design of routers and routing algorithms. IP forwarding algorithms are no longer applicable and cannot reach the satisfactory performance. In this paper, we ask ourselves the following question: how fast can the longest prefix name based lookup be? This is a key question to answer in order for named data networking architectures to be potentially successful. As an attempt to answer this question, we present a framework of fast longest prefix name lookup, based on a name space reduction scheme we proposed for named data networking. We also investigate feasible implementations on both CPU and GPU platforms. We demonstrate that we can achieve name lookup throughput as high as more than 37 and 70 million packets per second, respectively, on off-theshelf general-purpose CPU and GPU platforms. These results suggest that achieving high-performance lookup in named data networking architectures is not only feasible but also practical.