A paralleled Packet Classification algorithm based on Plus Bits and Bloom Filter

Packet classification (PC) is an important technology for next generation network services. Even though some PC algorithms for IPv6 have been proposed, most of them are precluded from commercial equipments due to high memory requirements, low searching speed, or expensive cost. In this paper, we propose an efficient paralleled IPv6 packet classification scheme; called Plus Bits and Bloom Filter based Packet Classification (B3PC). It introduces a small structure, called Plus Bits, which takes only 20 bits and can reduce many memory accesses by a few CPU operations. Meanwhile, we design a new searching scheme to make the highest priority match performance comparable to most specific match. Experimental results show that the hardware implementation of this scheme handles 4K rules by involving few memory, and finds the highest priority rule in about 8 memory accesses without regard to the single field searching.

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

[2]  Guru M. Parulkar,et al.  Detecting and resolving packet filter conflicts , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

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

[4]  Xiaohong Huang,et al.  A Dynamic Binary Hash Scheme for IPv6 Lookup , 2008, IEEE GLOBECOM 2008 - 2008 IEEE Global Telecommunications Conference.

[5]  Ioannis Papaefstathiou,et al.  Memory-Efficient 5D Packet Classification At 40 Gbps , 2007, IEEE INFOCOM 2007 - 26th IEEE International Conference on Computer Communications.

[6]  Robert M. Hinden,et al.  IP next generation overview , 1996, CACM.

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