Layer Partitioned Search Tree for Packet Classification

Packet classification is an important building block of the Internet routers for many network applications. In this paper, we propose a scheme called Layer Partitioned Search Tree (LPST) to solve multi-field packet classification problem. LPST improves the traditional decision tree based schemes (e.g. Hyper Cuts and EffiCuts) by reconstructing the leaf nodes of the decision tree as an approximately balanced search tree. The rules may be stored not only in the buckets of leaf nodes but also in the internal nodes of LPST. Thus, searches on LPST may be completed immediately without searching all the buckets on the path to some leaf node if the packet already matches an internal node. The experimental results show that LPST requires less memory storage even if LPST categorizes the rules by two fields to reduce rule duplication rather than five fields in EffiCuts. Besides, in terms of number of memory accesses, LPST is better than Hyper Cuts and EffiCuts.

[1]  Marco Pellegrini,et al.  Packet classification via improved space decomposition techniques , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

[2]  Thomas Y. C. Woo.  A modular approach to packet classification: algorithms and results , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[3]  Nick McKeown,et al.  Classifying Packets with Hierarchical Intelligent Cuttings , 2000, IEEE Micro.

[4]  Anja Feldmann,et al.  Tradeoffs for packet classification , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[5]  Yeim-Kuan Chang,et al.  Efficient Multidimensional Packet Classification with Fast Updates , 2009, IEEE Transactions on Computers.

[6]  George Varghese,et al.  Scalable packet classification , 2001, SIGCOMM '01.

[7]  Jonathan S. Turner,et al.  ClassBench: A Packet Classification Benchmark , 2005, IEEE/ACM Transactions on Networking.

[8]  Nick McKeown,et al.  Algorithms for packet classification , 2001, IEEE Netw..

[9]  Baohua Yang,et al.  Packet Classification Algorithms: From Theory to Practice , 2009, IEEE INFOCOM 2009.

[10]  T. N. Vijaykumar,et al.  EffiCuts: optimizing packet classification for memory and throughput , 2010, SIGCOMM '10.

[11]  Venkatachary Srinivasan,et al.  Packet classification using tuple space search , 1999, SIGCOMM '99.

[12]  George Varghese,et al.  Packet classification using multidimensional cutting , 2003, SIGCOMM '03.

[13]  David E. Taylor.  Survey and taxonomy of packet classification techniques , 2005, CSUR.

[14]  Sartaj Sahni,et al.  $O(\log W)$ Multidimensional Packet Classification , 2007, IEEE/ACM Transactions on Networking.

[15]  Sartaj Sahni,et al.  O(logW) multidimensional packet classification , 2007, TNET.

[16]  Nick McKeown,et al.  Packet classification on multiple fields , 1999, SIGCOMM '99.

[17]  Hung-Hsiang Jonathan Chao,et al.  Next generation routers , 2002, Proc. IEEE.

[18]  T. V. Lakshman,et al.  High-speed policy-based packet forwarding using efficient multi-dimensional range matching , 1998, SIGCOMM '98.

[19]  Jonathan S. Turner,et al.  Packet classification using extended TCAMs , 2003, 11th IEEE International Conference on Network Protocols, 2003. Proceedings..

[20]  Anand Rangarajan,et al.  Algorithms for advanced packet classification with ternary CAMs , 2005, SIGCOMM '05.