计算机科学 ›› 2017, Vol. 44 ›› Issue (2): 171-175.doi: 10.11896/j.issn.1002-137X.2017.02.026
乔焰,焦俊,饶元
QIAO Yan, JIAO Jun and RAO Yuan
摘要： 数据中心是云计算等大型分布式计算服务的基础,有效地设计与管理数据中心需要遵循数据中心网络的端到端流量特征。然而直接地测量网络的端到端流量需要耗费巨大的软件成本和硬件成本,并且由于数据中心网络结构的特殊性,传统的计算机网络采用的流量估计方法也无法适用于现有的数据中心网络。为解决以上问题,首先依据数据中心的资源分配和链路利用率情况提取出网络的粗粒度流量特征,在此基础上提出一种基于重力模型和网络层析技术的数据中心端到端流量估计算法。与现有的流量推理算法Tomogravity和ELIA在NS3搭建的不同规模的数据中心网络中进行性能对比,实验结果表明,所提算法能有效地利用提取出的粗粒度流量特征,在保证计算效率的前提下将计算准确度大幅提升,可满足当前数据中心网络实时获取端到端流量数据的需求。
| [1] AKELLA A,BENSON T,CHANDRASEKAREN B,et al.AUniversal Approach to Data Center Network Design [C]∥Proceedings of ACM International Conference on Distributed Computing and Networking (ICDCN).Goa,India,2015. [2] ZHU G M,XIE X H,GUO D K,et al.High Performance Expandable Data Center Networking Structure[J].Journal of Software,2014:25(6):1399-1351.(in Chinese) 朱桂明,谢向辉,郭得科,等.一种高吞吐量、高可扩展数据中心网络结构[J].软件学报,2014,25(6):1399-1351. [3] LI D,WU J.On the design and analysis of Data Center Network architectures for interconnecting dual-port servers [C]∥Proceedings of IEEE INFOCOM.Toronto,ONT,CA,2014:1851-1859. [4] GAO F.A Study of Circuitous Routing Method in Data Center Networks[D].Beijing:Beijing Jiaotong University,2015.(in Chinese) 高飞.数据中心网络迂回路由方法的研究[D].北京:北京交通大学,2015. [5] BELABED D,SECCI S,PUJOLLE G,et al.On Traffic Fairness in Data Center Fabrics[C]∥Proc.of IEEE CloudNet.Luxembourg,2014:40-45. [6] LUO L,WU W J,ZHANG F.Energy Modeling Based on Cloud Data Center[J].Journal of Software,2014,7(7):1371-1387.(in Chinese) 罗亮,吴文峻,张飞.面向云计算数据中心的能耗建模方法[J].软件学报,2014,7(7):1371-1387. [7] MALBOUBI M,WANG L,CHUAH C N,et al.Intelligent SDN based traffic (de)Aggregation and Measurement Paradigm (iSTAMP)[C]∥Proceedings of IEEE INFOCOM.Toronto,CA,2014:934-942. [8] BENSON T,AKELLA A,MALTZ D A.Network Traffic Cha-racteristics of Data Centers in the Wild[C]∥Proc.of ACM IMC.Melbourne,Australia,2010:267-280. [9] BENSON T,ANAND A,AKELLA A,et al.Understanding Data Center Traffic Characteristics[C]∥Proceedings of ACM SIGCOMM.New Delhi,2010. [10] KANDULA S,SENGUPTA S,GREENBEG A.The Nature of Data Center Traffic:Measurements & Analysis[C]∥Proc.of ACM IMC.Chicago,Illinois,2009:202-208. [11] LARA A,KOLASNI A,RAMAMURTHY B.Network innovation using openflow:A survey [J].Communications Surveys & Tutorials,IEEE,2014,16(1):493-512. [12] ZHANG Y,ROUGHAN M,DUFFIELD N.Fast Accurate Com-putation of Large-scale IP Traffic Matrices from Link Loads [C]∥Proc.of ACM SIGMETRICS.California,USA,2003,206-217. [13] ROUGHAN M,ZHANG Y,WILLINGER W,et al.Spatio-temporal compressive sensing and internet traffic matrices (exten-ded version)[J].IEEE/ACM Transactions on Networking,2012,20(3):662-676. [14] QIAO Y,QIU X S,MENG L M.Efficient Loss Inference Algorithm Using Unicast End-to-End Measurements [J].Journal of Network and Systems Management,2013,21(2):169-193. [15] Cisco Systems Inc,Cisco Data Center Infrastructure 2.5 Design Guide .http://www.cisco.com/application/pdf/en/us/guest/netsol/ns107/c649/ccmi/newlinegration/underline/space09186a008073377d.pdf,2007. [16] SRIKANTH K,JITENDRA P,PARAMVIR B.Flyways To De-Congest Data Center Networks[C]∥Proc.of ACM HotNets.2009. [17] Hopps C.Analysis of an Equal-Cost Multi-Path Algorithm.http://www.hjp.at/doc/rfc/rfc2991.html,2000. |
| No related articles found! |
|
||
首页