Simple and fast IP lookups using binomial spanning trees

High performance Internet routers require an efficient IP lookup algorithm to forward millions of packets per second. Various binary trie data structures are normally used in software-based routers. Binary trie based lookup algorithms are simple not only for searching for the longest prefix match but also for updating the routing table. In this paper, we propose a new IP lookup algorithm based on binomial spanning trees. The proposed algorithm has the same advantages of simple search and update processes as the ones based on binary trie. However, the performance of the proposed algorithm in terms of memory requirement and the lookup time is better than the schemes based on binary tries, such as path-compression and level-compression. q 2004 Elsevier B.V. All rights reserved.