Research on IP classification algorithm based on multibit-trie tree

Real time traffic measurement of network is becoming increasingly important for managing and controlling network. Flows-based traffic measurement is one of the methods. How to match the packets with a specific flow is one of key issues in specific flows-based measurement. This paper presents a method for this purpose, namely Multibit-trie Tree Classification Algorithm (for short, MTC Algorithm) algorithm, which is based on Non-Collision Hash Trie-Tree Algorithm and Grid of Tries algorithm. The core of algorithm has 4 parts: 1) constructing hash function mainly based on destination port and protocol type field so that the hash function can avoid space explosion problem; 2) incorporating two kinds of algorithm, which are the multibit-trie algorithm and the algorithm of Grid of Tries as well as transforming Grid of Tries for the Trie-tree pruned in order to reduce space complexity; 3) incorporating no using mltibit-trie item; 4) adding a floor for source port number (or source port range). Test results show that the classification rate of MTC algorithm is up to 2 million packets per second and the maximum memory consumed is 8MB for 10,000 rules.