期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

数据中心网络快速反馈传输控制协议 被引量：3

Transmission Control Protocol with Fast Feedback in Data Center Network
在线阅读 下载PDF
导出
摘要 在数据中心网络中,当多个服务器同时向一个接收端发送数据时,产生的数据流量易在瓶颈交换机的缓冲区溢出,造成丢包事件以及数据重传,导致TCP Incast问题。为此,提出一种可快速反馈的数据中心网络传输控制协议(FFDTCP)。该协议在TCP协议的基础上采用显式拥塞通知机制,利用2个显式拥塞通知位通告4种拥塞级别,发送端根据拥塞信息所表示的拥塞级别快速调整拥塞窗口以减少拥塞,从而避免因瓶颈链路丢包而造成的吞吐量急剧下降问题。NS2仿真实验结果表明,与传统TCP协议相比,FFDTCP协议可以保证较低的时延和较大的吞吐量,有效缓解TCP Incast问题,提高数据中心网络传输性能。 In Data Center Network（ DCN）,Transmission Control Protocol（ TCP） Incast occurs frequently when multiple servers send data to the same receiving end in parallel. Data traffic overflow s the buffer at the bottleneck sw itch,leading to packet losses and subsequently TCP retransmissions. To solve TCP Incast problem,this paper presents TCP w ith fast feedback in DCN（ FFDTCP）. The congestion control algorithm of FFDTCP is based on Explicit Congestion Notification（ ECN） and uses two bits to indicate four levels of congestion degree,then senders adjust congestion window according to the congestion information to achieve the purpose of reducing congestion and avoiding bottleneck link packet loss,leads to a sharp decline in throughput problem. NS2 simulation result show s that the algorithm can guarantee low er latency and higher throughput,effectively mitigate the TCP Incast problem and improve the transmission performance of DCN.
作者 苏凡军 牛咏梅 邵清
机构地区 上海理工大学光电信息与计算机工程学院
出处 《计算机工程》 CAS CSCD 北大核心 2015年第4期107-111,共5页 Computer Engineering
基金 上海智能家居大规模物联共性技术工程中心基金资助项目(GCZX14014) 沪江基金研究基地专项基金资助项目(C14001) 上海理工大学光电学院教师创新能力建设基金资助项目(GDCX-Y-1211)
关键词 数据中心网络 显式拥塞通知机制 传输控制协议 快速反馈 TCP Incast问题 RED算法 Data Center Network（DCN） Explicit Congestion Notification（ECN） mechanism Transmission Control Protocol（TCP） fast feedback TCP Incast problem RED algorithm
分类号 TP393 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献12

  • 1Alizadeh M, Greenberg A, Maltz D A, et al. Data Center TCP ( DCTCP ) [ J ]. ACM SIGCOMM Computer Communication Review ,2010,40(4) :63-74.
  • 2Phanishayee A, Krevat E, Vasudevan V, et al. Measurement and Analysis of TCP Throughput Collapse in Cluster-based Storage Systems [ C ]//Proceedings of the 6th USENIX Conference on File and Storage Technologies, February 26-29, 2008, San Jose USA. Berkeley, USA : USENIX Association, 2008 : 1-14.
  • 3Rewaskar S, Kaur J, Smith F D. A Performance Study of Loss Detection/Recovery, in Real-world TCP Imple- mentations [ C ]//Proceedings of IEEE International Conference on Network Protocols. Washington D. C. , USA : IEEE Press ,2007:256-265.
  • 4Alizadeh M, Javanmard A, Prabhakar B. Analysis of DCTCP: Stability, Convergence, and Fairness [ C ]// Proceedings of ACM SIGMETRICS Joint International Conference on Measurement and Modeling of Computer Systems. New York, USA : ACM Press ,2001:73-84.
  • 5Wu Haitao, Feng Zhenqian, Guo Chuanxiong, et al. ICTCP: Incast Congestion Control for TCP in Data Center Networks [J ]. IEEE/ACM Transactions on Networking ,2013,21 ( 2 ) :345-358.
  • 6Alizadeh M, Atikoglu B, Kabbani A, et al. Data Center Transport Mechanisms:Congestion Control Theory and IEEE Standardization [ C ]//Proceedings of the 46th Annual Allerton Conference on Communication, Control, and Computing, October 1-5,2008, Allerton, USA. Washington D. C., USA: IEEE Press, 2008: 1270-1277.
  • 7McCanne S, Floyd S. Network Simulator -NS-2 [ EB/OL]. 12014-03-15 1. http://www, isi. edu/nsnam/ ns/.
  • 8Ghemawat S, Gobioff H, Leung Shun-Tak. The Google File System [ C ]//Proceedings of ACM Symposium on Operating Systems Principles. New York, USA: ACM Press, 2003 : 29-43.
  • 9de Candia G, Hastorun D, Jampani M, et al. Dynamo: Amazons Highly Available Key-value Store [ C ]// Proceedings of the 21st ACM Symposium on Operating Systems Principles, October 14-17,2007, Skarnania Lodge, USA. New York ,USA :ACM Press ,2007:205-220.
  • 10李震,杜中军.云计算环境下的改进型Map-Reduce模型[J].计算机工程,2012,38(11):27-29. 被引量：7

二级参考文献11

  • 1Foster I, Zhao Yong, Raicu I, et al. Cloud Computing and Grid Computing 360-degree Compared[C]//Proc. of GCE'08. Washington D. C., USA: IEEE Computer Society, 2008.
  • 2Ghemawat S, Gobioff H, Leung S. The Google File System[C]// Proc. of SOSP'03. New York, USA: ACM Press, 2003.
  • 3Chang F, Dean J, Ghemawat S, et al. BigTable: A Distributed Storage System for Structured Data[J]. ACM Trans. on Computer Systems, 2008, 26(2): 1-26.
  • 4Dean J, Ghemawat S. Map-Reduce: Simplified Data Processing on Large Clusters[C]//Proc. of the 6th Symposium 9n Operating System Design and Implementation. New York, USA: ACM Press, 2004.
  • 5Nurmi D, Wolski R, Grzegorczyk C, et al. The Eucalyptus Open- source Cloud-computing System[C]//Proc. of the 9th IEEE/ACM International Symposium on Cluster Computing and the Grid. [S. L]: IEEE Computer Society, 2009.
  • 6Armbrust M, Fox A, Griffith R, et al. Abore the Clouds: Aberkeley View of Cloud Computing[R]. Berkeley, USA: University of California, Berkeley: Technical Report: UCB/EECS-2009-28, 2009.
  • 7Yan Baoqiang, Rhodes P J. Toward Automatic Parallelization of Spatial Computation for Computing Clusters[C]//Proc. of the 17th Intemational Symposium on High Performance Distributed Computing. New York, USA: ACM Press, 2008.
  • 8Nagarajan A B, Mueller F, Engelmann C, et al. Proactive Fault Tolerance for HPC with Xen Virtualization[C]//Proc. of the 21stAnnual Intemational Conference on Supercomputing. New York, USA: ACM Press, 2007.
  • 9Pinar A, Hendrickson B. Exploiting Flexibly Assignable Work to Improve Load Balance[C]//Proc. of the 14th Annual ACM Symposium on Parallel Algorithms. New York, USA: ACM Press, 2002.
  • 10刘怡,张戡.基于负载平衡和经验值的工作流任务分配策略[J].计算机工程,2009,35(21):57-59. 被引量：16

共引文献6

同被引文献11

引证文献3

二级引证文献15

计算机工程
2015年 第4期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部