SDN中的端到端时延

J4 ›› 2016, Vol. 38 ›› Issue (01): 67-72.

SDN中的端到端时延

黄晓鹏1，黄传河1，农黄武1，杨丹凤1，杨金羚2

（1.武汉大学计算机学院，湖北武汉 430072；2.四川大学计算机学院，四川成都 410044）

收稿日期:2015-08-11 修回日期:2015-10-27 出版日期:2016-01-25 发布日期:2016-01-25
基金资助:
国家自然科学基金(61373040,61173137);教育部博士点基金(20120141110073)

End-to-end delay in software defined networks

HUANG Xiaopeng1,HUANG Chuanhe1,NONG Huangwu1,Yang Danfeng1,YANG Jinling2

（1.School of Computer，Wuhan University，Wuhan 430072;2.School of Computer,Sichuan University，Chengdu 410044，China）

Received:2015-08-11 Revised:2015-10-27 Online:2016-01-25 Published:2016-01-25

摘要/Abstract

摘要：

随着大规模SDN的不断发展，用来管理和衡量网络性能的指标也越来越重要。端到端时延就是其中重要的部分，针对该指标已经提出了很多计算的方法，主要分为主动探测和被动探测，但是各有优缺点。因此，提出一种主动探测和被动探测相结合的方法，通过特殊方法计算出第一个数据包的时延，再通过快速方法计算相邻数据包端到端时延之差，得到所有数据包的端到端时延。实验结果表明，新方法在时钟不同步的情况下，可以有效地计算出端到端时延。

关键词: 软件定义网络, 时钟漂移, 时钟同步, 端到端时延, 网络仿真

Abstract:

With the deployment of large scale software defined networks (SDNs), metrics used to monitor and measure network performance become increasingly important. Endtoend delay is an important part of the indicators, and a number of methods for endtoend delay calculation have been proposed. These methods can be divided into two groups:active detection and passive detection, each with advantages and disadvantages. We propose a method combining active and passive detections. We first calculate the first packet delay, and then calculate the difference of end-to-end delay between adjacent packets, thus obtaining all the end-to-end packet delay. Experimental results show that our approach achieves high calculation performance without clock synchronization.

Key words: software defined network(SDN);clock skew;clock synchronization;end-to-end delay;network simulation

黄晓鹏1，黄传河1，农黄武1，杨丹凤1，杨金羚2. SDN中的端到端时延[J]. J4, 2016, 38(01): 67-72.

HUANG Xiaopeng1,HUANG Chuanhe1,NONG Huangwu1,Yang Danfeng1,YANG Jinling2. End-to-end delay in software defined networks [J]. J4, 2016, 38(01): 67-72.

参考文献［15］

［1］	Nunes B A A，Mcndonca M, Nguycn XN，et al.A survey of softwaredefined networking:Past,present,and future of programmable networks［J］.IEEE Communications Surveys & Tutorials，2014,16(3):16171634．
［2］	Kim H, Feamster N. Improving network management with software defined networking［J］.Communications Mangazine,IEEE，2013，51（2）:114119．
［3］	Yeganeh S H，Tootoonchian A，Ganjali Y.On scalability of software defined networking［J］.Communications Magazine，IEEE ，2013，51（2）：136141．
［4］	Chowdhury S R,David R,Bari M F，et al.PayLess:A low cost network monitoring framework for software defined networks［C］∥Proc of Network Operations and Management Symposium，2014:19．
［5］	Raayatpanah M A,SalehiFathabadi H,Khalaj B H，et al.Bounds on endtoend statistical delay and jitter in multiple multicast coded packet networks［J］.Journal of Network and Computer Applications,2014,41(5):217227．
［6］	Xu Wenjun,Zhou Zude,Liu Quan. Hybrid oneway delay estimation for networked control system［J］.Advances in Engineering Software,2010，41（5）:705711．
［7］	Altukhov V,Chemeritskiy E.On realtime delay monitoring in softwaredefined networks［C］∥Proc of 2014 1st International Science and Technology Conference（Modern Networking Technologies）,2014:16．
［8］	Phemius K,Bouet M.Monitoring latency with openflow［C］∥Proc of 2013 9th International Conference on Network and Service Management，2013:122125．
［9］	Jia Xiaohua,Li Deying,Hu Xiaodong，et al.Optimal placement of web proxies for replicated web servers in the Internet［J］.The Computer Journal，2001，44（5）:329339．
［10］	Tan Rui,Xing Guoliang，Jia Xiaohua，et al.Exploiting data fusion to improve the coverage of wireless sensor networks［J］.IEEE/ACM Tranactions on Networking，2012,20（2）:450462．
［11］	Zhong Ziguo， Chen Pengpeng, He Tian.Ondemand time synchronization with predicatable accuracy［C］∥Proc of INFOCOM,2011:24802488．
［12］	Sun Peng,Yu Minlan，Freedman M J，et al.HONE:Joint hostnetwork traffic management in softwaredefined networks［J］.Journal of Network and Systems Management，2015，23（2）:374399．
［13］	Lantz B,Heller B,McKeown N.A network in a laptop:Rapid prototyping for softwaredefined networks［C］∥Proc of the 9th ACM SIGCOMM Workshop on Hot Topics in Networks，2010:19．
［14］	Avallone S,Guadagno S,Emma D.DITG distributed internet traffic generator［C］∥Proc of the 1st International Conference on the Quantitative Evaluation of Systems ,2004:316317．
［15］	Himanshu A. WiresharkThe best open source network packet analyzer［EB/OL］.(20120923).［20150516］.http://www.ibm.com/developerworks/mydeveloperworks/blogs/6e6f6d1b95C346df8a26b7efd8ee4b57/entry/wireshart_the_open_source_network_packet_analyzer_part_i60?lang=en.

[1]	黄晓鹏1，黄传河1，农黄武1，杨丹凤1，杨金羚2. SDN中的端到端时延[J]. J4, 20160101, 38(01): 67-72.
[2]	苟平章, 马琳, 郭保永, 原晨. 基于软件定义网络的多约束QoS双路径路由优化方法[J]. 计算机工程与科学, 2023, 45(01): 46-56.
[3]	周静, 关玉蓉. 基于SDN的DWSN技术分析及性能优化研究[J]. 计算机工程与科学, 2021, 43(08): 1413-1421.
[4]	李波, 侯鹏, 牛力, 武浩, 丁洪伟. 基于软件定义网络的云边协同架构研究综述[J]. 计算机工程与科学, 2021, 43(02): 242-257.
[5]	赵宇1,2，殷树娟1，李翔宇2. 一种可重构以太网数据包解析器中可重构单元的设计[J]. 计算机工程与科学, 2020, 42(02): 220-228.
[6]	谢莹，邱为好，孙志刚，全巍. FAE:一种OpenFlow协议FlowMod消息的action扩展机制[J]. 计算机工程与科学, 2019, 41(07): 1176-1183.
[7]	刘世文1,5，马多耀2,4，雷程1,3,5，尹少东2,4，张红旗1,5. 基于网络安全态势感知的主动防御技术研究[J]. 计算机工程与科学, 2018, 40(06): 1057-1061.
[8]	汪强1,2，葛俊强1,2，常坤1,2，王小东1,2，田野1,2. 基于协议无感知转发技术的信息中心网络：设计、实现与应用[J]. 计算机工程与科学, 2018, 40(03): 431-438.
[9]	唐勇，王卫振，汪文勇，徐宾伟. SDN与传统IP网络互联架构的设计与实现[J]. 计算机工程与科学, 2017, 39(12): 2210-2216.
[10]	姜腊林，彭霞，熊兵. 基于混合制排队模型的SDN控制器性能评估研究[J]. 计算机工程与科学, 2017, 39(01): 86-91.
[11]	秦济龙1，李庆华2，王恩东1，公维锋1，张峰1，牛赟3，乌力吉3，张向民3. 一种路由交换阵列节点芯片及其系统的设计与实现[J]. 计算机工程与科学, 2016, 38(12): 2392-2401.
[12]	张颖星，姚益平. 面向社会网络仿真的混合时间管理算法[J]. J4, 2012, 34(11): 77-82.
[13]	崔建群1，赖敏财1，蒋文斌2，陈传河1. OverSim：可扩展的应用层组播网络仿真框架[J]. J4, 2012, 34(10): 1-5.
[14]	李学桥，陈园，梁爽. 基于IEEE1588协议的精确时钟同步算法改进[J]. J4, 2011, 33(2): 42-45.
[15]	胡斌[1,2] 章德宾[1,2] 张金隆[1]. DotNet环境下分布式并发离散事件仿真建模与实现[J]. J4, 2007, 29(7): 96-101.