A New Available Bandwidth Measurement Technique with Accurate Capacity Estimation

정확한 고정대역폭 추정을 통한 새로운 가용대역폭 측정 기법

  • 조성호 (서울대학교 전기.컴퓨터공학부) ;
  • 최한 (서울대학교 전기.컴퓨터공학부) ;
  • 김종권 (서울대학교 전기.컴퓨터공학부)
  • Published : 2005.08.01

Abstract

Measuring the end-to-end available bandwidth in the Internet is a useful tool for distributedapplication services or QoS (Quality-of-Service) guarantee. To measure the end-to-end available bandwidth, Single-hop Gap model-based packet train measurement techniques are well-known. However, the error of packet train output gap can happen by network topologies. This error of the output gap causes the inaccuracy of the available bandwidth measurement. In this paper, we propose a new end-to-end available bandwidth measurement technique with accurate capacity measurement and fast convergence methods. To solve the erroneous capacity measurement problem of the back-to-back packet train transmission, we propose a new available bandwidth measurement method by decoupling the capacity measurement with the initial gap of the packet train. Also, we propose a new technique to predict the proper initial gap of the packet train for faster convergence. We evaluate our proposed method by the simulation in various topologies comparing with previous methods.

인터넷에서 단대단 (end-to-end) 가용대역폭 측정은 분산된 응용 서비스, 단대단 QoS 보장 등에 유용하게 이용할 수 있다. 일반적으로 단대단 가용대역폭 측정에는 단일-홉 갭 모델에 기반한 패킷 트레인 (packet train) 전송을 통한 측정이 많이 사용되고 있다. 하지만 패킷 트레인의 출력 간격은 네트워크 망 구성과 경쟁 트래픽에 의해서 영향을 받으므로, 이 때 발생한 오차에 의해서 가용대역폭 측정에도 오차가 발생하게 된다. 본 논문에서는 기존의 방법들이 가지고 있는 연이은 (bach-to-back) 패킷 트레인을 전송하여 링크의 고정대역폭을 측정에 의한 부정확성을 해결하기 위해서 패킷 트레인의 초기 갭에 영향을 받지 않는 가용대역폭 측정 알고리즘을 제안한다 또한 빠른 측정을 위해서 패킷 트레인 전송 시 적절한 초기 간격을 예측하는 방법을 제안한다. 제안하는 방법의 성능을 검증하기 위해서 다양한 망구조에서 실험을 통해서 기존의 기법들과 비교하였다.

Keywords

References

  1. Presuhn, R., Case, J., McCloghrie, K., Rose, M. and Waldbusser, S., 'Version 3 of the Protocol Operations for the Simple Network Management Protocol (SNMP),' IETF RFC 3416
  2. Oetiker, T. Multi Router Traffic Grapher (MRTG), http://people.ee.ethz.ch/~oetiker/webtools/mrtg/
  3. Oetiker, T. Round Robin Database (RRD), http://people.ee.ethz.ch/~oetiker/webtools/rrdtool/
  4. Carter, R. and Crovella, M., 'Measuring Bottleneck Link Speed in Packet-switched Networks,' Performance Evaluation, Vol. 27, No. 28, pp. 297-318, 1996
  5. Paxson, V., 'Measurements and Analysis of End-to-end Internet Dynamics,' PhD thesis, University of California, Berkeley, 1997
  6. Dovrolis, C., Ramanathanm, P., Moore, D., 'What Do Packet Dispersion Techniques Measure?,' IEEE INFOCOM, pp. 905-914, 2001 https://doi.org/10.1109/INFCOM.2001.916282
  7. Kapoor, R., Chen, L., Lao, L., Gerla M., and Sanadidi, M., 'CapProbe: A Simple and Accurate Capacity Estimation Technique,' ACM SIGCOMM, 2004
  8. Ribeiro, V., Coates, M., Hiedi, R. Sarvotham, S., Hendricks, B. and Baraniuk, R., 'Multifractal Cross-Traffic Estimation,' In ITC Specialist Seminar on IP Traffic Measurement, Modeling and Management, 2000
  9. Hu, N. and Steenkiste, P., 'Evaluation and Characterization of Available Bandwidth Probing Techniques,' IEEE Journal on Selected Areas in Communications, Vol. 21. No. 6, pp. 879-894, 2003 https://doi.org/10.1109/JSAC.2003.814505
  10. Strauss, J., Katabi, D., Kaashoek, F., 'A Measurement Study of Available Bandwidth Estimation Tools,' ACM SIGCOMM Internet Measurement Workshop, 2003
  11. Melander, B., Bjorkman, M. and Gunningberg, P., 'A New End-to-End Probing and Analysis Method for Estimating Bandwidth Bottlenecks,' IEEE Global Internet Symposium, 2000
  12. Ribeiro, V., Riedi, R., Baraniuk, R., Navratil, J. and Cottrell, L., 'pathChirp: Efficient Available Bandwidth Estimation for Network Paths,' Passive and Active Measurements (PAM) workshop, 2003
  13. Jain, M. and Dovrolis, C., 'End-to-End Available Bandwidth: Measurement Methodology, Dynamics, and Relation with TCP Throughput,' ACM SIGCOMM, pp. 295-308, 2002 https://doi.org/10.1145/964725.633054
  14. Akella, A., Seshan, S. and Shaikh, A. 'An Empirical Evaluation of Wide-area Internet Bottlenecks,' ACM IMC. 2003 https://doi.org/10.1145/948205.948219
  15. Jacobson. V., 'Pathchar-A tool to Infer Characteristics of Internet Paths,' Presented as April 97 MSRI talk, 1997
  16. Hu, N., Li, L., Mao, Z., Steenkiste, P. and Wang, J., 'Locating Internet Bottlenecks: Algorithms, Measurements, and Implications,' ACM SIGCOMM, 2004 https://doi.org/10.1145/1015467.1015474
  17. Johnsson, A., Melander, B. and Bjorkman, M., 'On the Analysis of Packet-Train Probing Schemes,' CIC, 2004
  18. Claffy, K., Miller, G. and Thompson, K., 'The Nature of the Beast: Recent Traffic Measurements from an Internet Backbone,' presented at the ISOC INET Conf., 1998
  19. ns-2 simulator, http://www.isi.edu/nsnam/ns/, 2005