基于多核处理器的L7-Filter规则匹配改进算法
开篇：润墨网以专业的文秘视角，为您筛选了一篇基于多核处理器的L7-Filter规则匹配改进算法范文，如需获取更多写作素材，在线客服老师一对一协助。欢迎您的阅读与分享！
摘要:针对多核处理器的体系结构和网络数据流在时间上的局部性特点,提出了一种基于多核处理器的分链动态适应算法。该算法通过对网络数据流进行类型分类并根据网络数据流的时间局部性对规则链进行动态优化,从而有效减少了多核处理器下l7-filter对网络数据流的匹配次数,显著提升了规则匹配效率。仿真实验结果表明:在网络数据包个数相同条件下,所提算法在性能上约有7%的提高。随着网络数据包个数的增加,性能优越性更加明显。
关键词:多核处理器;网络数据流;L7-Filter;时间局部性;数据包分类;动态优化
中图分类号: TP301.6;TP393.02文献标志码:A
Improved L7-Filters pattern matching algorithm based on multi-core processors
英文作者名YU Tao*, WU Wei-dong
英文地址(College of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan Hubei 430065, China)
Abstract: According to the architecture of multi-core processors and the temporal local characteristics of network data flow, a division and dynamic adaptation algorithm was proposed based on multi-core processors. Classifying network data flow by the type and optimizing chain of rules dynamically by the temporal locality of network flow, the count of the multi-cores L7-Filter matching network data flow were reduced effectively and the processing efficiency was improved dramatically. The simulation result shows that given the number of packets in the same conditions, the algorithm has about 7 percent improvement of the multi-core processing performance. With the increasing number of network packets, the performance superiority becomes more obvious.
Key words: multi-core processor; network data flow; L7-Filter; temporal locality; packet classification; dynamic optimization
0引言
随着网络爆炸式的增长以及高速以太网的出现(如10GbE),网络流量也随之高速增长,这就对网络服务质量(Quality of Service, QoS)[1]提出了更高的要求。传统的数据包分类技术主要是基于数据包头部信息做出分类决策。然而,当前的许多网络应用会有意或无意利用头部信息隐藏真实的行为,如对等网(Peer-to-Peer, P2P)和超文本传输协议(HyperText Transfer Protocol, .
[11]杨赞,杨林,王宝林,等. 依据流统计特性的文分类规则动态优化[J].计算机应用研究,2011,28(5):1878-1882.
[12](美)约翰逊,(美)威曾格,(美)普拉瓦提. Linux服务器性能调整[M]. 韩智文,译.北京:清华大学出版社,2004:23-24.
[13](美) LOVE R. Linux内核设计与实现[M].3版. 陈莉君,康华,译.北京:机械工业出版社,2011:143-148.
[14]Libnids[CP/OL]. [2010-10-10].libnids.省略/.
[15]徐卫志,宋风龙,刘志勇,等. 众核处理器片上同步机制和评估方法研究[J].计算机学报,2010,33(10):1777-1787.