论文部分内容阅读
OpenFlow软件交换机由于成本低、配置灵活、且便于调度部署,因而广泛应用于软件定义网络试验床的构建,但在应用过程中遭遇到严重的性能瓶颈,流表查找是其中的关键一环.为此,本文应用启发式策略,提出一种面向软件交换机的OpenFlow虚拟流表高效查找算法.首先分析指出掩码遍历是影响流表查找性能的关键因素,进而基于网络流量局部性特点,应用M TF(M ove-To-Front)启发法自适应调整掩码顺序,以加快后续数据包的掩码查找命中速度.最后,借助实际网络流量样本,对本文所提算法的查找性能进行了实验评估.实验结果表明:本文所提算法的平均查找长度明显小于目前主流软件交换机中的流表查找方法,加快了OpenFlow流表查找速度,有效提升了OpenFlow软件交换机的数据转发性能.
OpenFlow software switches are widely used in the construction of software-defined network test beds due to their low cost, flexible configuration, and easy deployment and deployment. However, they encountered serious performance bottlenecks in application process, and flow table lookup is a key element. In this paper, we apply heuristic strategy to propose an efficient OpenFlow virtual flow table lookup algorithm for software switches.Firstly, it is pointed out that the mask traversal is the key factor that affects the performance of flow table lookup. Based on the local characteristics of network traffic, (M ove-To-Front) heuristic adaptively adjusts the mask order to speed up the subsequent packet mask search hits.Finally, with the actual network traffic samples, the performance of the proposed algorithm is evaluated experimentally. The experimental results show that the average search length of the proposed algorithm is significantly less than that of current mainstream software switches, accelerating the search speed of OpenFlow flow tables and effectively improving the data forwarding performance of OpenFlow software switches.