计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (26): 106-109.

• 网络、通信与安全 • 上一篇    下一篇

大规模多串匹配算法的访存行为分析

陈小军1,张志斌1,刘燕兵1,郭 莉2   

  1. 1.中国科学院 计算技术研究所,北京 100080
    2.中国科学院 研究生院,北京 100039
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-09-11 发布日期:2007-09-11
  • 通讯作者: 陈小军

Charactering memory access behavior of large scale multi-string matching algorithms

CHEN Xiao-jun1,ZHANG Zhi-bin1,LIU Yan-bing1,GUO Li2   

  1. 1.Institution of Computing Technology,Chinese Academy of Science,Beijing 100080,China
    2.Graduate University of Chinese Academy of Sciences,Beijing 100039,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-09-11 Published:2007-09-11
  • Contact: CHEN Xiao-jun

摘要: 随着网络带宽的日益增长,病毒和非法信息的形式越来越多,网络安全系统处理的压力越来越大。多串匹配算法作为大部分网络安全系统中的核心扫描部分其性能尤为重要。从微处理器体系结构的角度,用模拟的方法分析了SBOM、AC、WM等三种精确多串匹配算法在大规模规则库的情况下,其性能影响的各种因素,特别是其访存行为特征,并从算法原理上解释了访存性为是如何被影响的。指出当规则库规模增到5 000时,由Cache失效引起的性能损失占全部开销的近10%,而且比重随着规则库规模增大而继续变大。

关键词: 多串匹配, 网络安全, 访存行为, Cache失效

Abstract: Multi-string matching algorithms,as one of the most significant parts in network security system,its performance decides the efficiency of traffic inspection.Analyze the various factors especially memory access behaviors that impact the performance of multi-string matching algorithms.In three typical algorithms,about 10% performance drops are caused by Cache misses with 5 000 patterns.The trend of the drops is enlarging with increasing patterns.

Key words: multi-string matching algorithms, network security, memory access behavior, Cache miss