Fanlong Zhang, Jianglong Liu, Yuhang Wu, Quan Chen, Yuan Chai, Zhuowei Wang
{"title":"Towards real-time non-preemptive multicast scheduling in reconfigurable data center networks","authors":"Fanlong Zhang, Jianglong Liu, Yuhang Wu, Quan Chen, Yuan Chai, Zhuowei Wang","doi":"10.1007/s12083-024-01804-w","DOIUrl":null,"url":null,"abstract":"<p>Multicast has emerged as a primary communication pattern in datacenter networks due to the increasing demand for distributed data-parallel applications. To accelerate multicast traffic, the emerging reconfigurable circuit technology, which can establish circuit connections among switches, has been proposed as a promising paradigm for datacenter networks. This paper investigates how to accelerate the non-preemptive multicast flows in a demand-aware manner in reconfigurable datacenter networks. Firstly, the problem of scheduling circuit switches to minimize the average completion time is formulated and proved to be NP-hard. To address the conflicts between different multicast flows under the bandwidth constraint, a connection based hypergraph is constructed and then a two round matching algorithm is proposed under the bandwidth constraint. Additionally, to further reduce the average completion time, we introduce a method to utilize the remaining capacity of the ToR switches by splitting the unscheduled flows. The proposed algorithm is proved to have an approximation ratio of <span>\\(2\\sqrt{2n}\\)</span>, where <i>n</i> represents the number of Top-of-Rack (ToR) switches. Finally, the extensive simulations demonstrate the effectiveness of the proposed algorithm in reducing the average completion time of flows compared to state-of-the-art algorithms.</p>","PeriodicalId":49313,"journal":{"name":"Peer-To-Peer Networking and Applications","volume":null,"pages":null},"PeriodicalIF":3.3000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Peer-To-Peer Networking and Applications","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s12083-024-01804-w","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Multicast has emerged as a primary communication pattern in datacenter networks due to the increasing demand for distributed data-parallel applications. To accelerate multicast traffic, the emerging reconfigurable circuit technology, which can establish circuit connections among switches, has been proposed as a promising paradigm for datacenter networks. This paper investigates how to accelerate the non-preemptive multicast flows in a demand-aware manner in reconfigurable datacenter networks. Firstly, the problem of scheduling circuit switches to minimize the average completion time is formulated and proved to be NP-hard. To address the conflicts between different multicast flows under the bandwidth constraint, a connection based hypergraph is constructed and then a two round matching algorithm is proposed under the bandwidth constraint. Additionally, to further reduce the average completion time, we introduce a method to utilize the remaining capacity of the ToR switches by splitting the unscheduled flows. The proposed algorithm is proved to have an approximation ratio of \(2\sqrt{2n}\), where n represents the number of Top-of-Rack (ToR) switches. Finally, the extensive simulations demonstrate the effectiveness of the proposed algorithm in reducing the average completion time of flows compared to state-of-the-art algorithms.
由于对分布式数据并行应用的需求日益增长,组播已成为数据中心网络的主要通信模式。为了加速组播流量,新兴的可重构电路技术(可在交换机之间建立电路连接)被认为是数据中心网络的一种有前途的模式。本文研究了如何在可重构数据中心网络中以需求感知的方式加速非抢占式组播流量。首先,本文提出了调度电路交换机以最小化平均完成时间的问题,并证明该问题具有 NP 难度。为解决带宽约束下不同组播流间的冲突,构建了基于连接的超图,然后提出了带宽约束下的两轮匹配算法。此外,为了进一步缩短平均完成时间,我们引入了一种方法,通过拆分未计划的流量来利用 ToR 交换机的剩余容量。事实证明,所提算法的近似率为(2\sqrt{2n}\),其中 n 代表机架顶端(ToR)交换机的数量。最后,大量的仿真证明,与最先进的算法相比,所提出的算法能有效缩短流量的平均完成时间。
期刊介绍:
The aim of the Peer-to-Peer Networking and Applications journal is to disseminate state-of-the-art research and development results in this rapidly growing research area, to facilitate the deployment of P2P networking and applications, and to bring together the academic and industry communities, with the goal of fostering interaction to promote further research interests and activities, thus enabling new P2P applications and services. The journal not only addresses research topics related to networking and communications theory, but also considers the standardization, economic, and engineering aspects of P2P technologies, and their impacts on software engineering, computer engineering, networked communication, and security.
The journal serves as a forum for tackling the technical problems arising from both file sharing and media streaming applications. It also includes state-of-the-art technologies in the P2P security domain.
Peer-to-Peer Networking and Applications publishes regular papers, tutorials and review papers, case studies, and correspondence from the research, development, and standardization communities. Papers addressing system, application, and service issues are encouraged.