Scalable and Adaptive Software Defined Network Management for Cloud-hosted Group Communication Applications

Prithviraj Patil, Akram Hakiri, Shashank Shekhar, A. Gokhale
{"title":"Scalable and Adaptive Software Defined Network Management for Cloud-hosted Group Communication Applications","authors":"Prithviraj Patil, Akram Hakiri, Shashank Shekhar, A. Gokhale","doi":"10.1145/3147213.3147220","DOIUrl":null,"url":null,"abstract":"Group communications form the primary communication pattern for many cloud-hosted applications and cloud infrastructure management services, such as system health monitoring, multimedia distribution, collaborative applications and distributed databases. Although IP multicast has been used to support group communication semantics in diverse Internet-based distributed applications, its deployment in cloud Data Center Networks (DCNs) has been limited due to its higher resource consumption, scalability, and stability issues, which in turn degrades the utility of the cloud. Software Defined Networking (SDN) has enabled the re-engineering of multicast capabilities to overcome these limitations. To that end, this paper presents an autonomous, dynamic and flexible middleware solution called SDN-based Multicast (SDMC), which provides both network load-aware and switch memory-efficient group communication semantics in DCNs. Thus, SDMC improves DCN resource utilization while allowing applications to remain agnostic to the underlying group communication semantics by efficiently toggling between unicast and multicast in accordance with changing network bandwidth and switch memory usage. Empirical studies comparing SDMC with traditional IP multicast shows up to 60% better latency performance for different DCNs topologies, and up to 50% better performance in the switch memory utilization for multicast groups exceeding size 30.","PeriodicalId":341011,"journal":{"name":"Proceedings of the10th International Conference on Utility and Cloud Computing","volume":"48 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the10th International Conference on Utility and Cloud Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3147213.3147220","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Group communications form the primary communication pattern for many cloud-hosted applications and cloud infrastructure management services, such as system health monitoring, multimedia distribution, collaborative applications and distributed databases. Although IP multicast has been used to support group communication semantics in diverse Internet-based distributed applications, its deployment in cloud Data Center Networks (DCNs) has been limited due to its higher resource consumption, scalability, and stability issues, which in turn degrades the utility of the cloud. Software Defined Networking (SDN) has enabled the re-engineering of multicast capabilities to overcome these limitations. To that end, this paper presents an autonomous, dynamic and flexible middleware solution called SDN-based Multicast (SDMC), which provides both network load-aware and switch memory-efficient group communication semantics in DCNs. Thus, SDMC improves DCN resource utilization while allowing applications to remain agnostic to the underlying group communication semantics by efficiently toggling between unicast and multicast in accordance with changing network bandwidth and switch memory usage. Empirical studies comparing SDMC with traditional IP multicast shows up to 60% better latency performance for different DCNs topologies, and up to 50% better performance in the switch memory utilization for multicast groups exceeding size 30.
用于云托管组通信应用的可扩展和自适应软件定义网络管理
组通信是许多云托管应用程序和云基础设施管理服务(如系统运行状况监视、多媒体分发、协作应用程序和分布式数据库)的主要通信模式。尽管IP多播已被用于支持各种基于internet的分布式应用程序中的组通信语义,但由于其较高的资源消耗、可扩展性和稳定性问题,它在云数据中心网络(dcn)中的部署受到限制,这反过来又降低了云的效用。软件定义网络(SDN)使多播功能的重新设计能够克服这些限制。为此,本文提出了一种自主、动态、灵活的中间件解决方案——基于sdn的组播(SDMC),它在dcn中提供了网络负载感知和交换机内存高效的组通信语义。因此,SDMC提高了DCN资源利用率,同时通过根据不断变化的网络带宽和交换机内存使用情况在单播和多播之间有效切换,允许应用程序保持对底层组通信语义的不可知性。比较SDMC和传统IP组播的实证研究表明,对于不同的dcn拓扑,SDMC的延迟性能提高了60%,对于超过30的组播组,交换机内存利用率提高了50%。
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:604180095
Book学术官方微信