基于SDN的数据中心动态优先级多路径调度算法

doi:10.3969/j.issn.1006-2475.2020.07.005

计算机与现代化 ›› 2020, Vol. 0 ›› Issue (07): 21-26.doi: 10.3969/j.issn.1006-2475.2020.07.005

基于SDN的数据中心动态优先级多路径调度算法

(1.中国石油大学（华东）计算机科学与技术学院，山东青岛266580；
2.北京交通大学下一代互联网互联设备国家工程实验室，北京100044

出版日期:2020-07-06 发布日期:2020-07-15
作者简介:肖军弼（1968-），男，山东莱州人，副教授，硕士生导师，硕士，研究方向：软件定义网络，计算机网络和应用程序，网络性能及其优化，E-mail: junbixiao@163.com；程鹏（1994-），男，山东潍坊人，硕士研究生，研究方向：SDN架构下数据中心流量调度，E-mail: chengpeng_wf@126.com；谭立状（1995-），男，山东潍坊人，博士研究生，研究方向：启发式算法，下一代互联网技术和数据中心网络，E-mail: lzhtan@bjtu.edu.cn；孟祥泽（1996-），男，山东济南人，硕士研究生，研究方向：计算机网络及应用，E-mail: 1072637852@qq.com。
基金资助:
教育部赛尔网络下一代互联网技术创新项目（NGII20180120， NGII20190116）

Data Center Dynamic Priority Multipath Scheduling Algorithm Based on SDN

(1. College of Computer Science and Technology, China University of Petroleum, Qingdao 266580, China；
2. National Engineering Laboratory for Next Generation Internet Interconnection Devices, Beijing Jiaotong University, Beijing 100044, China)

Online:2020-07-06 Published:2020-07-15

摘要/Abstract

摘要： 随着云计算技术和分布式业务的发展，数据中心内部“东西向”大象流量激增，这部分大象流在调度不当的情况下容易发生碰撞，造成链路拥塞。本文提出一种基于软件定义网络（SDN）的动态优先级多路径调度算法（DPMS）。该算法根据数据中心流量的特点制定大象流和老鼠流调度模型，充分利用各网络节点间的冗余链路，提高资源利用率；并结合组表优化SDN架构中控制器和交换机的通信模式，降低了数据包处理时延。实验结果表明，相比ECMP和Hedera这2种调度策略，DPMS提高了网络吞吐量和链路利用率，减少了平均流完成时间，网络的整体性能有所提高。

关键词: 流量调度, 多路径传输, 软件定义网络；数据中心网络

Abstract: With the development of cloud computing technology and distributed services, the “East-West” elephant flow in the data center has surged. This part of the elephant flow is prone to collisions due to improper scheduling, causing link congestion. This paper proposes a Dynamic Priority Multipath Scheduling algorithm (DPMS) based on Software-Defined Network (SDN). The algorithm develops an elephant flow and mouse flow scheduling model based on the characteristics of data center traffic, makes full use of redundant links between network nodes to improve resource utilization. Combined with the group table, the communication mode between the controller and the switch in the SDN architecture is optimized, and the packet processing delay is reduced. The experimental results show that DPMS improves network throughput and link utilization, reduces average flow completion time, and improves overall network performance compared with ECMP and Hedera scheduling strategies.

Key words: traffic scheduling, multipath transmission, software-defined network, data center network

中图分类号:

TP393

肖军弼, 程鹏, 谭立状, 孟祥泽. 基于SDN的数据中心动态优先级多路径调度算法[J]. 计算机与现代化, 2020, 0(07): 21-26.

XIAO Jun-bi, CHENG Peng, TAN Li-zhuang, MENG Xiang-ze. Data Center Dynamic Priority Multipath Scheduling Algorithm Based on SDN[J]. Computer and Modernization, 2020, 0(07): 21-26.

参考文献

［1］ BENSON T, ANAND A, AKELLA A, et al. Understanding data center traffic characteristics［J］. ACM SIGCOMM Computer Communication Review, 2010,40(1):92-99.
［2］〖KG-*7〗 KANDULA S, SENGUPTA S, GREENBERG A, et al. The nature of data center traffic: Measurements & analysis［C］// Proceedings of the 9th ACM SIGCOMM Conference on Internet Measurement. 2009:202-208.
［3］ HU F, HAO Q, BAO K. A survey on software defined networking (SDN) and openflow: From concept to implementation［J］. IEEE Communications Surveys & Tutorials, 2014,16(4):2181-2206.
［4］ KIRKPATRICK K. Software-defined networking［J］. Communications of the ACM, 2013,56(9):16-19.
［5］ MCKEOWN N, ANDERSON T, BALAKRISHNAN H, et al. OpenFlow: Enabling innovation in campus networks［J］. ACM SIGCOMM Computer Communication Review, 2008,38(2):69-74.
［6］ ALFARES M, LOUKISSAS A, VAHDAT A, et al. A scalable, commodity data center network architecture［J］. ACM SIGCOMM Computer Communication Review, 2008,38(4):63-74.
［7］ ZHANG H, GUO X, YAN J, et al. SDN-based ECMP algorithm for data center networks［C］// 2014 IEEE Computers, Communications and IT Applications Conference. 2014:13-18.
［8］ ALFARES M, RADHAKRISHNAN S, RAGHAVAN B, et al. Hedera: Dynamic flow scheduling for data center networks［C］// Proceedings of the 7th USENIX Symposium on Networked Systems Design and Implementation. 2010:281-296.
［9］左青云,陈鸣,赵广松,等. 基于OpenFlow的SDN技术研究［J］. 软件学报, 2013(5):1078-1097.
［10］CURTIS A R, MOGUL J C, TOURRILHES J, et al. DevoFlow: Scaling flow management for high-performance networks［J］. ACM SIGCOMM Computer Communication Review, 2011,41(4):254-265.
［11］ZHANG Y X, CUI L, ZHANG Y, et al. A stable matching based elephant flow scheduling algorithm in data center networks［J］. Computer Networks, 2017,120(19):186-197.
［12］MORI T, KAWAHARA R, NAITO S, et al. On the characteristics of Internet traffic variability: Spikes and elephants［J］. IEICE Transactions on Information and Systems, 2004,87(12):2644-2653.
［13］ALIZADEH M, GREENBERG A, MALTZ D A, et al. Data center TCP (DCTCP)［J］. ACM SIGCOMM Computer Communication Review, 2010,40(4):63-74.
［14］PHAAL P. sFlow Specification Version 5［M/OL］. ［2016-01-20］. http://sflow. org/sflow_version_5.txt.
［15］韩慧芳,杨珂玲,张建军. Pareto分布中形状参数的估计问题［J］. 统计与决策, 2007(24):10-12.
［16］陈月萍．连续型幂律分布的统计性质［D］．福州：福建师范大学， 2012．
［17］TAN L Z, SU W, GAO S, et al. L4S: Low-speed software synergetic sampling and detecting long flow for data center network［C］// 2018 IEEE International Conference on Networking and Network Applications. 2018:169-174.
［18］MORI T, UCHIDA M, KAWAHARA R, et al. Identifying elephant flows through periodically sampled packets［C］// Proceedings of the 4th ACM SIGCOMM Conference on Internet Measurement. 2004:115-120.
［19］田雨.基于OpenFlow网络的大象流检测调度的研究［D］. 北京：北京工业大学， 2017.
［20］MINRIK T, SUFLIARSKY J, TRUPL J, et al. 2013 9th international conference on network and service management(CNSM)［J］. Journal of Infection, 2013,34(1):91.
［21］CHANG L, LIN X, QIN L, et al. Efficiently computing Top-K shortest path join［C］// International Conference on Extending Database Technology. 2015:133-144.
［22］GAO Y Q, YU L. A power and performance aware routing algorithm for Fat tree networks［C］// IEEE International Conference on Big Data Security on Cloud. 2017:173-178.
［23］ZHAO G, XU H, CHEN S, et al. Deploying default paths by joint optimization of flow table and group table in SDNs［C］// IEEE International Conference on Network Protocols. 2017:1-10.
［24］LANTZ B， HELLER B， MCKEOWN N． A network in a laptop:Rapid prototyping for software-defined networks［C］// ACM SIGCOMM Workshop on Hot Topics in Networks． 2010:1-6.

基于SDN的数据中心动态优先级多路径调度算法

Data Center Dynamic Priority Multipath Scheduling Algorithm Based on SDN

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价