Methodology for Measuring Available Bandwidth on Arbitrary Links
Affiliation:

  • Article
  • | |
  • Metrics
  • |
  • Reference [35]
  • |
  • Related
  • |
  • Cited by [3]
  • | |
  • Comments
    Abstract:

    The available bandwidth measurement is important for many Internet applications, such as network behavior analysis, quality of service (QoS) verification, and so on. Existing available bandwidth measurement toolsmainly measure the available bandwidth for a whole network path, and provide information about the tight link(s)other than vital links. Therefore, this paper presents a novel algorithm called LinkPPQ (trains of pairs of packet-quartets used to measure available bandwidth of arbitrary links), which uses trains of pairs of packet-quartets to measure the available bandwidth of any link along the path, and track the variety of the cross-traffic on it. This paper studies the performance of LinkPPQ in both simulation circumstances and the laboratorial network.Simulation results show that LinkPPQ can accurately measure the available bandwidth of each link on the paths thathave one narrow link or multiple narrow links, under different cross-traffic loads. Most measurement errors are under 30%, and the results are stable. The laboratorial experimental results show that LinkPPQ can accuratelymeasure the available bandwidth in the following situations: a) measuring a link with capacity 100Mbps from a link with capacity 10Mbps; b) monitoring the link with capacity that is ten times of the narrow link next to it on the path;c) estimating the available bandwidth of the narrow links on a path having multiple narrow links.

    Reference
    [1] Zhang Y, Duffield N, Paxson V, Shenker S. On the constancy of Internet path properties. In: Proc. of the IMC. San Francisco, 2001.197?211. http://portal.acm.org/citation.cfm?doid=505202.505228
    [2] Paxson V. End-to-End routing behavior in the Internet. IEEE/ACM Trans. on Networking, 1997,5(5):601?615.
    [3] Net-snmp. http://net-snmp.sourceforge.net/
    [4] cflow. http://www.gnu.org/software/cflow/
    [5] sflow. http://www.sflow.org/
    [6] NetFlow. http://www.cisco.com/go/netflow/
    [7] Hu N, Steenkiste P. Evaluation and characterization of available bandwidth probing techniques. IEEE Journal on Selected Areas in Communications, 2003,21(6):879?894.
    [8] Navratil J, Cottrell RL. ABwE: A practical approach to available bandwidth estimation. In: Proc. of the Passive and Active Measurement Workshop. La Jolla, 2003. http://www-iepm.slac.stanford.edu/tools/abing/abwe-pam03-paper.pdf
    [9] Ribeiro V, Coates M, Riedi R, Sarvotham S, Hendricks B, Baraniuk R. Multifractal cross-traffic estimation. In: Proc. of the ITC Specialist Seminar on IP Traffic Measurement, Modeling and Management. Monterey, 2000. http://www.stat.rice.edu/~vinay/talks/itc00_talk.ps.gz
    [10] Ribeiro VJ, Riedi RH, Baraniuk RG, Navratil J, Cottrell L. pathChirp: Efficient available bandwidth estimation for network paths.In: Proc. of the PAM. San Diego, 2003. 200?211. http://www-ece.rice.edu/~vinay/papers/pam03.pdf
    [11] Strauss J, Katabi D, Kaashoek F. A measurement study of available bandwidth estimation tools. In: Proc. of the IMC. Miami, 2003.39?44. http://www.icir.org/vern/imc-2003/papers/p332-strauss.pdf
    [12] Jain M, Dovrolis C. End-to-End available bandwidth: Measurement methodology, dynamics, and relation with TCP throughput.IEEE/ACM Trans. on Networking, 2003,11(4):537?549.
    [13] Melander B, Bjorkman M, Gunningberg P. Regression-Based available bandwidth measurements. In: Proc. of the SPECTS. San Diego, 2002. http://www.sics.se/cna/connected/spects2002.pdf
    [14] Sommers J, Barford P, Willinger W. Laboratory-Based calibration of available bandwidth estimation tools. Microprocessors and Microsystems, 2007,31(4):222?235.
    [15] Ns2: Network simulator. http://nsnam.isi.edu/nsnam/index.php/Main_Page 何莉 等:一种测量任意链路可用带宽的方法 1013
    [16] Prasad R, Dovrolis C, Murray M, Claffy K. Bandwidth estimation: Metrics, measurement techniques, and tools. IEEE Network,2003,17(6):27?35.
    [17] Keshav S. A control-theoretic approach to flow control. In: Proc. of the ACM SIGCOMM’91, Vol.21. Zurich, 1991. 3?15.https://eprints.kfupm.edu.sa/17135/1/17135.pdf
    [18] Carter R, Crovella M. Measuring bottleneck link speed in packet-switched networks. Performance Evaluation, 1996,27-28:297?318.
    [19] Network characterization service (NCS). http://www-didc.lbl.gov/NCS/
    [20] Dovrolis C, Ramanathan P, Moore D. What do packet dispersion techniques measure? In: Proc. of the IEEE INFOCOM. Anchorage,2001. 905?914. http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=916282
    [21] Antoniades D, Athanatos M, Papadogiannakis A, Markatos EP, Dovrolis C. Available bandwidth measurement as simple as running wget. In: Proc. of the PAM. Adelaide, 2006. http://www.ics.forth.gr/~papadog/abget/abget.pdf
    [22] Lv SH, Cai ZP, Yin JP, Zhao WT. Towards estimating available bandwidth on Network paths with application requirements.Chinese Journal of Electronics, 2006,34(10):1793?1798 (in English with Chinese abstract).
    [23] Liu M, Li ZC, Guo XB, Deng H. An end-to-end available bandwidth estimation methodology. Jounal of Software, 2006,17(1):108?116 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/17/108.htm
    [24] Liu X, He L, Yu S. Algorithms of accurate network available bandwidth measurment. Acta Electronica Sinica, 2007,35(1):68?72(in Chinese with English abstract).
    [25] Akella A, Seshan S, Shaikh A. An empirical evaluation of wide-area Internet bottlenecks. In: Proc. of the IMC. Miami, 2003.101?114. http://portal.acm.org/citation.cfm?id=948219
    [26] Hu N, Li LE, Mao ZM, Steenkiste P, Wang J. Locating Internet bottlenecks: Algorithms, measurements, and implications. In: Proc.of the ACM SIGCOMM. Portland, 2004. http://www.cs.cmu.edu/~hnn/papers/bottleneck.pdf
    [27] Ribeiro VJ, Riedi RH, Baraniuk RG. Spatio-Temporal available bandwidth estimation with STAB. IEEE Internet Computing Magazine, 2004,8(5):34?41.
    [28] Harfoush K, Bestavros A, Byers J. Measuring bottleneck bandwidth of targeted path segments. In: Proc. of the IEEE INFOCOM.San Francisco, 2003. 2079?2089. http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1209229
    [29] Lai K, Baker M. Measuring link bandwidths using a deterministic model of packet delay. In: Proc. of the ACM SIGCOMM.Stockholm, 2000. 283?294. http://www.hpl.hp.com/personal/Kevin_Lai/projects/nettimer/publications/sigcomm2000/deterministic.pdf
    [30] Pasztor A, Veitch D. Active probing using packet quartets. In: Proc. of the IMC. Marseille, 2002. 293?305. http://www.icir.org/vern/imw-2002/imw2002-papers/144.ps.gz
    [31] Liu X, Ravindran K, Loguinov D. A queueing-theoretic foundation of available bandwidth estimation: Single-Hop analysis.IEEE/ACM Trans. on Networking, 2007,15(4):918?931.
    [32] MAWI. http://tracer.csl.sony.co.jp/mawi/
    [33] Tcpreplay. http://tcpreplay.synfin.net/trac/wiki/ 附中文参考文献:
    [23] 刘敏,李忠诚,过晓冰,邓辉.端到端的可用带宽测量方法.软件学报,2006,17(1):108?116. http://www.jos.org.cn/1000-9825/17/108.htm
    [24] 刘星成,何莉,余顺争.网络可用带宽的高精度测量算法.电子学报,2007,35(1):68?72.
    Related
    Comments
    Comments
    分享到微博
    Submit
Get Citation

何莉,余顺争.一种测量任意链路可用带宽的方法.软件学报,2009,20(4):997-1013

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:December 15,2007
  • Revised:February 27,2008
You are the first2051354Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address:4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code:100190
Phone:010-62562563 Fax:010-62562533 Email:jos@iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063