基于优先级替换的批量规则快速更新方法研究  被引量:1

Accelerating batch rule update scheme based on priority replacement

在线阅读下载全文

作  者:丁自旋 于金萍[1] 李文斌 毕经平[1] Ding Zixuan;Yu Jinping;Li Wenbin;Bi Jingping(Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190;University of Chinese Academy of Sciences,Beijing 100049)

机构地区:[1]中国科学院计算技术研究所,北京100190 [2]中国科学院大学,北京100049

出  处:《高技术通讯》2021年第6期569-580,共12页Chinese High Technology Letters

基  金:国家自然科学基金(61702470,61472403)资助项目。

摘  要:当前,软件定义网络(SDN)交换机的三态内容寻址存储器(TCAM)基于优先级编码其存储规则的物理位置,因此,当发生规则更新时,TCAM不可避免地会因为新优先级的出现或原有规则优先级的变化而移动大量已有规则的物理位置,产生不可忽视的高时延。本文提出了基于优先级替换的批量规则快速更新方法(BRUS),解决规则更新时因TCAM移动规则而产生的高时延。BRUS引入了基于规则依赖的规则语义一致性,在规则语义一致性的基础上,通过替换插入规则优先级为删除规则的优先级来避免不必要的规则移动,实现快速的规则更新。实验结果表明,BRUS能够有效找到91%以上的替换规则对,从而大幅减少规则更新的移动次数。与最新方法相比,针对批量更新场景,BRUS具有更好的稳定性和适用性。Currently,the physical storage locations of rules in ternary content addressable memory(TCAM)at software-defined networking(SDN)switches depend on the priorities of the rules.Therefore,when updating rules in TCAM,a great quantity of rules will be moved to new locations due to the emergences of new priorities and the modifications of old priorities,resulting in a significantly high latency.To solve the problem,a fast method of batch rule updating scheme(BRUS)based on priority replacement is proposed,which reduces the latency while updating rules in TCAM.BRUS introduces the definition of rule dependency-based semantic consistency.Based on this,BRUS replaces the priorities of inserted rules with the priorities of deleted rules to avoid unnecessary rule movements,and therefore achieving fast rule updating.Experiment results show that BRUS is capable of finding more than 91%replace pairs and significantly reduces rule moves when updating.Compared with the state-of-the-art methods,BRUS is clearly superior in terms of stability and suitability in batch rule-update scenarios.

关 键 词:软件定义网络(SDN) 三态内容寻址存储器(TCAM)更新 规则更新 语义一致性 规则依赖 

分 类 号:TP393.0[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象