摘要
为有效解决多级流表因压缩流表项空间引起的网络延迟问题,提出一种平衡时空的自适应多级流表构建方法。把流表空间划分为实时更新区和多级流表存储区;通过研究流表资源的压缩率和网络延迟之间的平衡关系,提出多级流表的级数约束不等式组;基于级数约束不等式组和匹配域的重复率,将单流表划分为多级流表,实现流表项的鲁棒性压缩存储和快速查找。实验结果表明,该方法鲁棒地压缩了流表项,节约了流表的存储空间,减少了因压缩流表项空间引起的网络延迟,提高了交换机的数据转发量。
To effectively solve the problem of network delay caused by compressing space for multiple-table,an adaptive method balancing time and space for multiple-table construction was proposed.The flow table space was divided into real-time update area and multiple-table area.A constrained inequalities group of multiple-table series was put forward based on studying the balance of compression rate of multiple-table and network delay.The single flow table was divided into multiple-table based on the constrained inequalities group and the repetitive rate of match fields,and the robustness of compression and quick search were realized.Experimental results indicate that the method is robust to compress the flow table,saves the storage space,reduces the network latency caused by the multiple-table compression,and increases the amount of data forwarded per unit time.
出处
《计算机工程与设计》
北大核心
2017年第3期830-836,共7页
Computer Engineering and Design
基金
国家自然科学基金项目(61379079)
河南省国际合作基金项目(152102410021)
国家973重点基础研究发展计划基金项目(2012CB315901)
关键词
多级流表
构建
查找
级数约束
匹配域
重复率
multiple-table
construction
searching
flow table series constraints
match fields
repetitive rate
