基于抽样和Bloom Filters的长流检测

Elephant Flow Detection Based on Sample and Bloom Filters

长流检测对网络检测和管理有着重要的意义.提出一种基于抽样和Bloom Filters的长流检测算法,首先对报文进行抽样,然后通过Bloom Filters哈希运算,在内存中用临时表和流信息表来判断到达阈值的流并维护其信息,满足了高速网络环境下长流检测的要求,在保证测量精度的同时有效得控制了资源消耗.实验分析表明,和已有的方法相比,具有简单易行、资源可控等优点.

Detecting elephant flows is vital to network operation and management. This paper proposes a method based on sampie and Bloom filters to identify elephant flow. It samples the packets first, then employs Bloom filters hash structure, temporary table and flow information table to identify elephant flows and maintain their records, which meets high-speed network＇s demand and controls resources consumption effectively without sacrificing accuracy. The experiment analysis indicates the proposed method can achieve simplicity and controllability compared with other methods.