吉林大学学报(工学版) ›› 2021, Vol. 51 ›› Issue (3): 1040-1047.doi: 10.13229/j.cnki.jdxbgxb20200198

• 计算机科学与技术 • 上一篇    

软件定义网络的数据中心动态流量调度方案

刘振鹏1,2(),任少松1,李明1,王鑫鹏1,李小菲2()   

  1. 1.河北大学 电子信息工程学院，河北 保定 071002
    2.河北大学 信息技术中心，河北 保定 071002
  • 收稿日期:2020-03-31 出版日期:2021-05-01 发布日期:2021-05-07
  • 通讯作者: 李小菲 E-mail:lzp@hbu.edu.cn;lixiaofei@hbu.edu.cn
  • 作者简介:刘振鹏（1966-），男，教授，博士. 研究方向:网络信息安全,隐私保护,软件定义网络. E-mail:lzp@hbu.edu.cn
  • 基金资助:
    河北省自然科学基金项目(F2019201427);教育部云数融合科教创新基金项目(2017A20004)

Software defines dynamic traffic scheduling scheme for network data center

Zhen-peng LIU1,2(),Shao-song REN1,Ming LI1,Xin-peng WANG1,Xiao-fei LI2()   

  1. 1.College of Electronic Information Engineering，Hebei University，Baoding 071002，China
    2.Information Technology Center，Hebei University，Baoding 071002，China
  • Received:2020-03-31 Online:2021-05-01 Published:2021-05-07
  • Contact: Xiao-fei LI E-mail:lzp@hbu.edu.cn;lixiaofei@hbu.edu.cn

RICH HTML

 8   

PDF (PC)

257

摘要：

针对等价多路径（ECMP）算法没有考虑网络负载和流量特征，很容易将多条大数据流映射到同一路径，造成网络瓶颈链路的问题，提出一种面向软件定义网络（SDN）数据中心的基于网络负载的动态流量调度方案（DTSNL）。该方案结合网络负载和流量的特点，通过合理调度流量，实现网络负载均衡。控制器通过周期性统计Fat-Tree网络拓扑中接入层交换机的流量信息，计算流量阈值，为带宽占比较高的大数据流选择最佳路径。仿真实验表明，相较于ECMP方案和全局首选（GFF）方案，DTSNL方案的网络平均吞吐量、链路使用率、核心交换机负载、链路带宽利用率4项指标都有所提高。

关键词: 数据中心网络, 软件定义网络, 网络负载, Fat-Tree拓扑

Abstract:

The Equal-Cost Multi-Path （ECMP） algorithm does not consider the characteristics of network load and traffic flow， that it is easy to map multiple big data streams to the same path， resulting in network bottleneck link. To overcome this shortcoming， a dynamic traffic scheduling （DTSNL） scheme based on network load for Software Defined Network （SDN） data center is proposed. The scheme combines the characteristics of network load and traffic to schedule the traffic reasonably and achieve network load balancing. The controller calculates the traffic threshold by periodically counting the traffic information of the access layer switch in the Fat-Tree network topology， and chooses the best path for the large data flow with high bandwidth ratio. The simulation results show that， compared with the ECMP scheme and the GFF scheme， the poposed DTSNL scheme improves the network average throughput， link utilization， and core switch load and link bandwidth utilization.

Key words: data center network, software definition network, network load, Fat-Tree topology

中图分类号: 

  • TP393

图1

基于SDN数据中心流量调度框架"

图2

K=4 Fat-Tree网络拓扑"

图3

网络平均吞吐量比较"

图4

链路利用率比较"

图5

核心交换机负载比较"

图6

链路带宽利用率比较"

1 Hwang R H, Tseng H P, Tang Y C. Design of SDN-enabled cloud data center[C]∥Proceedings of IEEE International Conference on Smart City/SocialCom/SustainCom (Smart City), Chengdu, China, 2016:950-957.
2 Cao Y, Xu M, Fu X, et al. Explicit multipath congestion control for data center networks[J/OL]. [2020-03-14].
3 Song Z, Zhang T, Li Q, et al. START: Sensible traffic scheduling in dynamic data center networks[C]∥Proceedings of IEEE 36th International Performance Computing and Communications Conference, San Diego, USA, 2017:1-8.
4 Sarvabhatla M, Konda S, Vorugunti C S, et al. A dynamic and energy efficient greedy scheduling algorithm for cloud data centers[C]∥Proceedings of IEEE International Conference on Cloud Computing in Emerging Markets, Bangalore, India, 2017:47-52.
5 Benson T, Akella A, Maltz D A. Network traffic characteristics of data centers in the wild[J/OL].[2020-03-15].
6 Schaller S, Hood D. Software defined networking architecture standardization[J]. Computer Standards & Interfaces, 2017:54(4):197-202.
7 沈军,周晓,吉祖勤. 服务动态扩展网络及其结点系统模型的实现[J]. 吉林大学学报:工学版, 2019, 49(6):2058-2068.
Shen Jun, Zhou Xiao, Ji Zu-qin. Implementation of service dynamic extended network and its node system model[J]. Journal of Jilin University(Engineering and Technology Edition), 2019,49(6):2058-2068.
8 张沪寅,汪思思,钱龙,等. 面向SDN数据中心网络的路径资源管理节能机制研究[J]. 小型微型计算机系统,2017,38(4):755-760.
Zhang Hu-yin,Wang Si-si,Qian Long, et al. SDN data center networks oriented energy saving mechanism research based on the path resource management[J]. Journal of Chinese Computer Systems, 2017,38(4):755-760.
9 Azzouni A, Boutaba R, Pujolle G. NeuRoute: predicyive dynamic routing for software defined networks[C]∥Proceedings of 13th International Conference on Network and Service Management(CNSM), Tokyo, Japan, 2017:1-6.
10 陈琳, 张富强. 面向SDN数据中心网络最大概率路径流量调度算法[J]. 软件学报, 2016, 27(2):254-260.
Chen Lin, Zhang Fu-qiang. Maximum probability path traffic scheduling algorithm for SDN data center network[J]. Journal of Software, 2016, 27(2):254-260.
11 魏晓辉, 刘智亮, 庄园,等. 支持大规模流数据在线处理的自适应检查点机制[J]. 吉林大学学报:工学版, 2017, 47(1):199-207.
Wei Xiao-hui, Liu Zhi-liang, Zhuang Yuan, et al.Adaptive checkpoint mechanism supporting large-scale stream data processing[J]. Journal of Jilin University(Engineering and Technology Edition), 2017, 47(1):199-207.
12 Lan Yuan-liang,Wang Kuo-chen,Yi-huai Hsu. Dynamic load-balanced path optimization in SDN-based data center networks[J/OL].[2020-03-20].
13 Zhang Hai-long, Guo Xiao, Yan Jin-yao, et al. SDN-based ECMP algorithm for data center networks[C]∥Proceedings of the 2014 IEEE Computing, Communications and IT Applications Conference, Beijing, China, 2014:13-18.
14 Al-Fares M, Radhakrishnan S, Raghavan B, et al. Hedera: dynamic flow scheduling for data center networks[C]∥Proceedings of the 7th USENIX Conference on Networked Systems Design and Implementation, San Jose, CA, USA,2010:281-296.
15 金子晋, 兰巨龙, 江逸茗, 等. SDN环境下基于Q_Learning算法的业务划分路由选路机制[J]. 网络与信息安全学报, 2018,4(9):17-22.
Jin Zi-jin, Lan Ju-long, Jiang Yi-ming, et al. Q_Learning based business differentiating routing mechanism in SDN architecture[J]. Chinese Journal of Network and Information Security, 2018,4(9):17-22.
16 Khan A Z, Qazi I A. RecFlow: SDN-based receiver-driven flow scheduling in datacenters[J/OL]. [2020-03-20].
17 陆一飞, 朱书宏. 数据中心网络下基于SDN的TCP拥塞控制机制研究与实现[J]. 计算机学报, 2017, 40(9):2167-2180.
Lu Yi-fei, Zhu Shu-hong. Research and Implementation of TCP Congestion Control Mechanism Based on SDN in Data Center Network[J]. Chinese Journal of Computers,2017, 40(9):2167-2180.
18 Cianfrani A, Eramo V, Listanti M, et al. An OSPF enhancement for energy saving in ip networks[C]∥Proceedings of the Computer Communications Workshops, Shanghai, China, 2011:325-330.
19 左青云, 陈鸣, 赵广松, 等. 基于OpenFlow的SDN技术研究[J]. 软件学报, 2013, 24(5):1078-1097.
Zuo Qing-yun, Chen Ming, Zhao Guang-song, et al. Research on SDN technology based on OpenFlow[J]. Journal of Software, 2013, 24(5): 1078-1097.
20 Jin Y Y. Finding the K shortest loopless paths in a network[J]. Management Science, 1971, 17(11):712-716.
21 Lantz B, Heller B, McKeown N. A network in a laptop: rapid prototyping for software-defined networks[C]∥Proceedings of the 10th ACM SIGCOMM Workshop on Hot Topics in Networks, New York, NY, USA,2010:19.
[1] 沈军,周晓,吉祖勤. 服务动态扩展网络及其结点系统模型的实现[J]. 吉林大学学报(工学版), 2019, 49(6): 2058-2068.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 《吉林大学学报(工学版)》编辑部
地址：长春市人民大街5988号　电话：+86-431-85095297　传真：+86-431-85094074　E-mail: xbgxb@jlu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发