用于特定流匹配的随机矩阵映射Hash算法研究

Research on stochastic matrix mapping Hash for specific flow matching

针对常规的Hash算法用于流匹配时冲突率高且不可控制的缺点,提出了一种随机矩阵映射Hash算法。该算法通过预先优选一个随机数矩阵,然后将大集合的元素分块映射成随机矩阵中的元素,从而把一个大集合映射到一个小集合。测试结果表明,该算法运算速度快、空间利用率高、冲突率低,用于流匹配时匹配速度可以达到2Mpacket/s,支持规则数达5万条以上。

Because a general Hash algorithm had high collision rate and was not controlled while be used to flow matching, a stochastic matrix mapping Hash algorithm was presented, in which the elements of a large set were mapped into a small set through a pre-choosing stochastic number matrix. Tests show that the algorithm has high operation speed, high storage utilization rate and low collision rate, its flow matching speed is up to 2 million packets per second and it supports 50000 matching rules.