Abstract
Classical quality of service (QoS) measures such as packet loss probability, delay or delay variation are available for non-elastic network traffic. However, most of today’s data traffic is transported over the Transmission Control Protocol (TCP) in the Internet, and TCP uses a flow control mechanism to adapt a connection’s hit rate to the resources available in the network in order to get the same “fair share” of bandwidth as the other TCP connections sharing the same bottleneck link. Recent efforts in describing elastic traffic have recalled Processor Sharing models and tried to establish bandwidth related QoS measures such as “delay factors” or “fun factors” to describe the user perceived quality of service for elastic traffic applications. In this paper we discuss possible definitions of fun factors as well as DNS and TCP properties that influence the bit rates achievable with elastic traffic. Measurement results give an indication of the rates occurring in the Internet. They also reveal the delays and success rates to be expected from DNS requests, which can be a major cause of delay in HTTP retrievals.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bodamer, S., Charzinski, J.: Evaluation of Effective Bandwidth Schemes for Self-Similar Traffic. Proc. ITC Spec. Seminar on IP Traffic, Monterey, CA, USA (2000)
Braden, R. (Ed.): Requirements for Internet Hosts - Communication Layers. Internet RFC 1122(1989)
Charzinski, J.: Fun Factor Dimensioning for Elastic Traffic. Proc. ITC Spec. Seminar on IP Traffic, Monterey, CA, USA (2000)
Charzinski, J.: HTTP/TCP Connection and Flow Char. Pcrf. Eval. 42 (2000) 149-162
Crovella, M.E., Bestavros, A.: Self-Similarity in World Wide Web Traffic: Evidence and Possible Causes. IEEE/ACM Trans. Networking 5 (1997) 835-846
Heyman, D.P, Lakshman, TV., Neidhardt, A.L.: A New Method for Analysing Feedback-Based Protocols with Applications to Engineering Web Traffic over the Internet. Proc. ACM Sigmetrics’97, Seattle, WA, USA; ACM Perf. Eval. Review 25 24-38
Huitema, C., Weerahandi, S.: Internet measurements: the rising tide and the DNS snag. Proc. ITC Spec. Seminar on IP Traffic, Monterey, CA, USA (2000)
Krishnamurthy, B., Wills, C.E.: Analyzing factors that influence end-to-end Web performance. Computer Networks 33 (2000) 17-32.
Leland, W.E., Taqqu, M.S., Willinger, W., Wilson, D.V.: On the Self-Similar Nature of Ethernet Traffic. Proc. ACM Sigcomm’93, San Francisco, CA, USA (1993) 183-193
Lindberger, K.: Balancing Quality of Service, Pricing and Utilization in Multiservice Networks with Stream and Elastic Traffic. Proc. ITC 16, Edinburgh, UK (1999) 1127-1136
McCannc, S., Lcrcs, C., Jacobson, V.: tepdump. LBNL Network Research Group, rtp://ftp.cc.lbl.gov/tcpdump.lar.z
Padhye, J., Firoiu, V., Towsley, D., Kurosc, J.: Modeling TCP Throughput: A Simple Model and its Empirical Validation. Proc. ACM Sigcomm’98, Vancouver, Canada (1998)
Padmanabhan, V.N. Mogul, J.C.: Improving HTTP Latency. Comp. Netw. and ISDN Systems 28 (1995) 24-35
Riedl, A., Perske, M., Bauschert, T, Probst, A.: Dimensioning of IP Access Networks with Elastic Traffic. Proc. Networks 2000, Toronto, Canada (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Charzinski, J. (2001). Fun Factor Characterization of User Perceived Quality of Service for Elastic Internet Traffic. In: Killat, U., Lamersdorf, W. (eds) Kommunikation in Verteilten Systemen (KiVS). Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-56675-2_37
Download citation
DOI: https://doi.org/10.1007/978-3-642-56675-2_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41645-6
Online ISBN: 978-3-642-56675-2
eBook Packages: Springer Book Archive