A novel eviction policy based on shortest remaining time for software defined networking flow tables

IF 1.5 4区计算机科学 Q3 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Network Management Pub Date : 2023-12-21 DOI:10.1002/nem.2257

Kavi Priya Dhandapani, Mirnalinee Thanganadar Thangathai, Shahul Hamead Haja Moinudeen

{"title":"A novel eviction policy based on shortest remaining time for software defined networking flow tables","authors":"Kavi Priya Dhandapani, Mirnalinee Thanganadar Thangathai, Shahul Hamead Haja Moinudeen","doi":"10.1002/nem.2257","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>Software defined networking is a modern paradigm that divides the control plane from the data plane for improved network manageability. A flow table in the data plane has limited and expensive memory called TCAM. The presence of unwanted flow rules would lead to flow bloat conditions and make the lookup operation inefficient. Eviction schemes based on LRU policy have been widely studied in the literature which preempts the life of the least recently used flow rule and reduces the occupancy of the flow table. LRU considers the past behavior for the eviction of a flow rule. This paper proposes a novel policy that preempts a flow rule by considering its future characteristic, the shortest remaining time (SRT). A rule with a higher probability of being used is avoided from eviction to mitigate the degradation of performance. The modeling of the SRT technique exhibits better utilization of a flow rule that has higher probability of being used. On the other hand, LRU does not guarantee that the evicted flow rule will not be used frequently in the future and it has been shown that an incorrectly evicted flow rule incurs controller delay. The experimental results show that for different traffic rates, SRT has reduced the delay by 15%, reinstallation count by 25%, and jitter by 40%. SRT has increased utilization by 22% compared to LRU.</p>\n </div>","PeriodicalId":14154,"journal":{"name":"International Journal of Network Management","volume":"34 3","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2023-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Network Management","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/nem.2257","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

Software defined networking is a modern paradigm that divides the control plane from the data plane for improved network manageability. A flow table in the data plane has limited and expensive memory called TCAM. The presence of unwanted flow rules would lead to flow bloat conditions and make the lookup operation inefficient. Eviction schemes based on LRU policy have been widely studied in the literature which preempts the life of the least recently used flow rule and reduces the occupancy of the flow table. LRU considers the past behavior for the eviction of a flow rule. This paper proposes a novel policy that preempts a flow rule by considering its future characteristic, the shortest remaining time (SRT). A rule with a higher probability of being used is avoided from eviction to mitigate the degradation of performance. The modeling of the SRT technique exhibits better utilization of a flow rule that has higher probability of being used. On the other hand, LRU does not guarantee that the evicted flow rule will not be used frequently in the future and it has been shown that an incorrectly evicted flow rule incurs controller delay. The experimental results show that for different traffic rates, SRT has reduced the delay by 15%, reinstallation count by 25%, and jitter by 40%. SRT has increased utilization by 22% compared to LRU.

Abstract Image

查看原文本刊更多论文

基于软件定义网络流表最短剩余时间的新型驱逐策略

软件定义网络是一种现代范式，它将控制平面与数据平面分开，以提高网络的可管理性。数据平面中的流量表内存有限且昂贵，称为 TCAM。不需要的流量规则的存在会导致流量膨胀，使查找操作效率低下。基于 LRU 策略的驱逐方案已在文献中得到广泛研究，该方案会抢占最近使用最少的流规则的生命周期，减少流表的占用率。LRU 在驱逐流量规则时考虑了过去的行为。本文提出了一种新策略，即通过考虑流量规则的未来特性--最短剩余时间（SRT）--来抢占流量规则。避免驱逐使用概率较高的规则，以减轻性能下降。SRT 技术的建模表明，被使用概率较高的流量规则能得到更好的利用。另一方面，LRU 并不能保证被驱逐的流量规则在未来不会被频繁使用，而且事实证明，错误驱逐的流量规则会造成控制器延迟。实验结果表明，对于不同的流量，SRT 将延迟减少了 15%，重新安装次数减少了 25%，抖动减少了 40%。与 LRU 相比，SRT 提高了 22% 的利用率。

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

International Journal of Network Management COMPUTER SCIENCE, INFORMATION SYSTEMS-TELECOMMUNICATIONS

CiteScore

5.10

自引率

6.70%

发文量

审稿时长

>12 weeks

期刊介绍： Modern computer networks and communication systems are increasing in size, scope, and heterogeneity. The promise of a single end-to-end technology has not been realized and likely never will occur. The decreasing cost of bandwidth is increasing the possible applications of computer networks and communication systems to entirely new domains. Problems in integrating heterogeneous wired and wireless technologies, ensuring security and quality of service, and reliably operating large-scale systems including the inclusion of cloud computing have all emerged as important topics. The one constant is the need for network management. Challenges in network management have never been greater than they are today. The International Journal of Network Management is the forum for researchers, developers, and practitioners in network management to present their work to an international audience. The journal is dedicated to the dissemination of information, which will enable improved management, operation, and maintenance of computer networks and communication systems. The journal is peer reviewed and publishes original papers (both theoretical and experimental) by leading researchers, practitioners, and consultants from universities, research laboratories, and companies around the world. Issues with thematic or guest-edited special topics typically occur several times per year. Topic areas for the journal are largely defined by the taxonomy for network and service management developed by IFIP WG6.6, together with IEEE-CNOM, the IRTF-NMRG and the Emanics Network of Excellence.