Journal of Communications and Networks

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지

Effect of Head of the Line Blocking on Session Initiation Protocol Session Establishment Delays

  • Received : 2007.05.05
  • Accepted : 2008.10.10
  • Published : 2009.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

We have studied the effect of head of the line blocking (HOLB) on session initiation protocol (SIP) session establishment delays. Our results are based on experiments performed in a test bed and on the public Internet. We used the stream control transmission protocol (SCTP) as a transport for SIP because SCTP can be configured to suffer or to avoid HOLB. Our experiments show that the effect of HOLB on session establishment delays generally starts to be significant starting at fairly low packet loss rates. However, there are scenarios where network conditions are good enough to make the effect of HOLB insignificant.

Keywords

References

  1. J. Rosenberg, H. Schulzrinne, G. Camarillo, A. Johnston, J. Peterson, R. Sparks, M. Handley, and E. Schooler, "SIP: Session initiation protocol," Internet Engineering Task Force, Tech. Rep. RFC 3261, June 2002
  2. R. Stewart, Q. Xie, K. Morneault, C. Sharp, H. Schwarzbauer, T. Taylor, I. Rytina, M. Kalla, L. Zhang, and V. Paxson, "Stream control transmission protocol," Internet Engineering Task Force, Tech. Rep. RFC 2960, Oct. 2000
  3. ITU-T, "Network grade of service parameters and target values for ircuitswitched services in the evolving ISDN," International Telecommunication Union, Tech. Rep. Recommendation E.721, May 1999
  4. M. Mathis, J. Mahdavi, S. Floyd, and A. Romanow, "TCP selective acknowledgement options," Internet Engineering Task Force, Tech. Rep. RFC 2018, Oct. 1996
  5. G. Camarillo, H. Schulzrinne, and R. Kantola, "Evaluation of transport protocols for the session initiation protocol," IEEE Network, vol. 17, no. 5, 2003
  6. X. Li, D. Salyers, and A. Striegel, "Improving packet caching scalability through the concept of an explicit end of data marker," in Proc. 1st IEEE Workshop on HOTWEB., 2006
  7. K. Ono and H. Schulzrinne, "The impact of SCTP on server scalability and performance," Dept. of Computer Science, Columbia University, Tech. Rep. CUCS-012-08, Feb. 2008
  8. J. Rosenberg, H. Schulzrinne, and G. Camarillo, "The stream control transmission protocol (SCTP) as a transport for the session initiation protocol(SIP)," Internet Engineering Task Force, Tech. Rep. RFC 4168, Oct. 2005
  9. T. Dierks and E. Rescorla, “The transport layer security (TLS) protocol version 1.1,” Internet Engineering Task Force, Tech. Rep. RFC 4346, Apr. 2006
  10. http://www.isi.edu/nsnam/ns/index.html
  11. K. Grinnem, T. Andersson, and A. Brunstrom, "Performance benefits of avoiding head-of-line blocking in SCTP," in Proc. Autonomic and Autonomous Systems and International Conference on Networking and Services, 2005
  12. M. Scharf and S. Kiesel, "Head-of-line blocking in TCP and SCTP: Analysisand measurements," in Proc. IEEE Globecom, 2006
  13. M. Carson and D. Santay, "NIST net: A linux-based network emulation tool," ACM CCR, vol. 33, no. 3, 2003
  14. http://sourceforge.net/projects/kphone
  15. http://www.internettrafficreport.com
  16. A. Mondal and A. Kuzmanovic, "When tcp friendliness becomes harmful,"in Proc. IEEE Infocom, May 2007
  17. D. Mosberger and T. Jin, "Httperf: A tool for measuring web server performance," Performance Evaluation Review, vol. 26, no. 53, 1998
  18. M. Claypool, R. Kinicki, M. Li, J. Nichols, and H. Wu, "Inferring queue sizes in access networks by active measurement," Dept. of Computer Science,Worcester Polytechnic Institute, Tech. Rep.WPI-CS-TR-04-04, Feb.2004