基于OpenFlow的报文分类算法研究与实现

随着软件定义网络、OpenFlow等技术的兴起，传统的基于5元组的报文分类技术已不能满足OpenFlow基于多元组的细粒度流量控制需求。因此，以分析已有的报文分类算法为基础，采用分而治之的思想，针对OpenFlow报文分类的精确匹配需求，设计实现了一种基于Hash的计数型链表Bloom Filter算法--OF_CBF算法。针对OpenFlow报文分类的通配匹配需求，借鉴正则表达式匹配算法思想，设计实现了基于有限自动机的报文匹配算法--OF_FSMP算法。对两种算法进行分析验证，并初步对两种算法进行了性能分析。

Study and implementation of packet classification algorithms for OpenFlow

With the emergence of software defined network and OpenFlow in recent years, fine grained flow control based on the multi tuple packet classification makes a huge challenge to the traditional 5 tuple packet classification. The basic concept of packet classification, some typical packet classification algorithms and the packet classification for OpenFlow are introduced. For the demand of exact match in the OpenFlow packet classification, a counting and linked list Bloom Filter base on Hash, named OF_CBF, is designed and implemented. And it is tested and analyzed. For the demand of wildcard match in the OpenFlow packet classification, an algorithm based on finite state machine, named OF_FSMP is designed, implemented, tested and analyzed.