Shared Entry Logger to Eliminate Duplicate Requests to SDN Controller

A. Asaduzzaman, A. Almohaimeed, K. K. Chidella
{"title":"Shared Entry Logger to Eliminate Duplicate Requests to SDN Controller","authors":"A. Asaduzzaman, A. Almohaimeed, K. K. Chidella","doi":"10.1109/CCWC.2019.8666595","DOIUrl":null,"url":null,"abstract":"In network architecture domain, software-defined networking (SDN) provides programmable network infrastructure and improves management at the controlling layer level. However, SDN structure is centralized and hence introduces new challenges related to performance and security that require new adaptations. An important problem is that some incoming packets are similar to old packets that have already been processed by the SDN controller. This paper proposes a new model for entry logging with an aim to minimize the number of requests the SDN controller processes. This is achieved by the provision of a logging technique for management of OpenFlow communications. A shared memory is introduced to store recently processed entries to save time and effort for future lookups. The proposed SDN architecture adapts the memory to ensure the controller avoids sending duplicate entries and facilitates switches to obtain an external backup storage. Experimental results show an approximate 30% decrease in the communication load on the controller while maintaining lower latency in the total processing time.","PeriodicalId":132812,"journal":{"name":"2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCWC.2019.8666595","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

Abstract

In network architecture domain, software-defined networking (SDN) provides programmable network infrastructure and improves management at the controlling layer level. However, SDN structure is centralized and hence introduces new challenges related to performance and security that require new adaptations. An important problem is that some incoming packets are similar to old packets that have already been processed by the SDN controller. This paper proposes a new model for entry logging with an aim to minimize the number of requests the SDN controller processes. This is achieved by the provision of a logging technique for management of OpenFlow communications. A shared memory is introduced to store recently processed entries to save time and effort for future lookups. The proposed SDN architecture adapts the memory to ensure the controller avoids sending duplicate entries and facilitates switches to obtain an external backup storage. Experimental results show an approximate 30% decrease in the communication load on the controller while maintaining lower latency in the total processing time.
共享条目记录器消除对SDN控制器的重复请求
在网络体系结构领域,软件定义网络(SDN)提供了可编程的网络基础设施,提高了控制层的管理水平。然而,SDN结构是集中式的,因此引入了与性能和安全性相关的新挑战,需要进行新的调整。一个重要的问题是,一些传入的数据包类似于已经被SDN控制器处理过的旧数据包。本文提出了一种新的入口记录模型,其目的是尽量减少SDN控制器处理的请求数量。这是通过提供用于管理OpenFlow通信的日志技术来实现的。引入共享内存来存储最近处理过的条目,从而为以后的查找节省时间和精力。提出的SDN架构通过调整内存来保证控制器不发送重复的表项,并方便交换机获取外部备份存储。实验结果表明,在保持较低的总处理时间延迟的同时,控制器上的通信负载减少了约30%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信