Hostname: page-component-77f85d65b8-45ctf Total loading time: 0 Render date: 2026-04-18T05:48:17.628Z Has data issue: false hasContentIssue false
  • English
  • Français

Generalized processor sharing queues with heterogeneous traffic classes

Part of: Computer system organization Special processes Operations research and management science

Published online by Cambridge University Press:  01 July 2016

Sem Borst ,
Michel Mandjes  and
Miranda van Uitert
Sem Borst*
Affiliation:
CWI, Amsterdam, Bell Laboratories Lucent Technologies and Eindhoven University of Technology
Michel Mandjes*
Affiliation:
CWI, Amsterdam, Bell Laboratories Lucent Technologies and University of Twente
Miranda van Uitert*
Affiliation:
CWI, Amsterdam
*
∗ Postal address: CWI, PO Box 94079, 1090 GB Amsterdam, The Netherlands.
∗ Postal address: CWI, PO Box 94079, 1090 GB Amsterdam, The Netherlands.
∗ Postal address: CWI, PO Box 94079, 1090 GB Amsterdam, The Netherlands.
Get access Rights & Permissions [Opens in a new window]

Abstract

We consider a queue fed by a mixture of light-tailed and heavy-tailed traffic. The two traffic flows are served in accordance with the generalized processor sharing (GPS) discipline. GPS-based scheduling algorithms, such as weighted fair queueing (WFQ), have emerged as an important mechanism for achieving service differentiation in integrated networks. We derive the asymptotic workload behaviour of the light-tailed traffic flow under the assumption that its GPS weight is larger than its traffic intensity. The GPS mechanism ensures that the workload is bounded above by that in an isolated system with the light-tailed flow served in isolation at a constant rate equal to its GPS weight. We show that the workload distribution is, in fact, asymptotically equivalent to that in the isolated system, multiplied by a certain prefactor, which accounts for the interaction with the heavy-tailed flow. Specifically, the prefactor represents the probability that the heavy-tailed flow is backlogged long enough for the light-tailed flow to reach overflow. The results provide crucial qualitative insight in the typical overflow scenario.

Keywords

Fluid queuegeneralized processor sharing (GPS)heavy-tailed trafficlarge deviationqueue length asymptoticsregular variationweighted fair queueing (WFQ)

MSC classification

Primary: 60K25: Queueing theory
Secondary: 68M20: Performance evaluation; queueing; scheduling 90B18: Communication networks 90B22: Queues and service

Information

Type
General Applied Probability
Information
Advances in Applied Probability , Volume 35 , Issue 3 , September 2003 , pp. 806 - 845
Copyright
Copyright © Applied Probability Trust 2003 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

[1] Anantharam, V. (1988). How large delays build up in a GI/G/1 queue. Queueing Systems 5, 345–368.CrossRefGoogle Scholar
[2] Borst, S. C. and Zwart, A. P. (2003). A reduced-peak equivalence for queues with a mixture of light-tailed and heavy-tailed input flows. Adv. Appl. Prob. 35, 793–805.Google Scholar
[3] Borst, S. C., Boxma, O. J. and Jelenković, P. R. (1999). Induced burstiness in generalized processor sharing queues with long-tailed traffic flows. In Proc. 37th Annual Allerton Conf. Commun. Control Comput. (Urbana-Champaign, IL, September 1999), pp. 316–325.Google Scholar
[4] Borst, S. C., Boxma, O. J. and Jelenković, P. R. (2000). Asymptotic behavior of generalized processor sharing with long-tailed traffic sources. In Proc. IEEE Infocom 2000 (Tel-Aviv, March 2000), Vol. 2, pp. 912–921.Google Scholar
[5] Borst, S. C., Boxma, O. J. and Jelenković, P. R. (2003). Reduced-load equivalence and induced burstiness in GPS queues with long-tailed traffic flows. Queueing Systems 43, 273–306.Google Scholar
[6] Borst, S. C., Boxma, O. J. and van Uitert, M. J. G. (2001). Two coupled queues with heterogeneous traffic. In Teletraffic Engineering in the Internet Era (Proc. ITC-17, Salvador da Bahia, Brazil), eds Moreira de Souza, J., da Fonseca, N. L. S. and de Souza e Silva, E. A., North-Holland, Amsterdam, pp. 1003–1014.Google Scholar
[7] Boxma, O. J., Deng, Q. and Zwart, A. P. (2002). Waiting-time asymptotics for the M/G/2 queue with heterogeneous servers. Queueing Systems 40, 5–31.Google Scholar
[8] Dumas, V. and Simonian, A. (2000). Asymptotic bounds for the fluid queue fed by sub-exponential on/off sources. Adv. Appl. Prob. 32, 244–255.Google Scholar
[9] Elwalid, A. I. and Mitra, D. (1991). Analysis and design of rate-based congestion control of high speed networks, I: stochastic fluid models, access regulation. Queueing Systems 9, 29–64.Google Scholar
[10] Elwalid, A. I. and Mitra, D. (1993). Effective bandwidth of general Markovian traffic sources and admission control of high speed networks. IEEE/ACM Trans. Networking 1, 329–343.Google Scholar
[11] Glynn, P. W. and Whitt, W. (1994). Logarithmic asymptotics for steady-state tail probabilities in a single-server queue. In Studies in Applied Probability (J. Appl. Prob. Spec. Vol. 31A), eds Galambos, J. and Gani, J., Applied Probability Trust, Sheffield, pp. 131–156.Google Scholar
[12] Jelenković, P. R. and Lazar, A. A. (1999). Asymptotic results for multiplexing subexponential on–off processes. Adv. Appl. Prob. 31, 394–421.Google Scholar
[13] Kesidis, G., Walrand, J. and Chang, C.-S. (1993). Effective bandwidths for multi-class Markov fluids and other ATM sources. IEEE/ACM Trans. Networking 1, 424–428.Google Scholar
[14] Kosten, L. (1986). Liquid models for a type of information buffer problem. Delft Progress Rep. 11, 71–86.Google Scholar
[15] Mandjes, M. and Borst, S. C. (2000). Overflow behavior in queues with many long-tailed inputs. Adv. Appl. Prob. 32, 1150–1167.CrossRefGoogle Scholar
[16] Mandjes, M. and Ridder, A. (1995). Finding the conjugate of Markov fluid processes. Prob. Eng. Inf. Sci. 9, 297–315.CrossRefGoogle Scholar
[17] Pakes, A. G. (1975). On the tails of waiting-time distributions. J. Appl. Prob. 12, 555–564.Google Scholar
[18] Parekh, A. and Gallager, R. (1993). A generalized processor sharing approach to flow control in integrated services networks: the single node case. IEEE/ACM Trans. Networking 1, 344–357.Google Scholar
[19] Parekh, A. and Gallager, R. (1994). A generalized processor sharing approach to flow control in integrated services networks: the multiple node case. IEEE/ACM Trans. Networking 2, 137–150.Google Scholar
[20] Paxson, A. and Floyd, S. (1995). Wide area traffic: the failure of Poisson modeling. IEEE/ACM Trans. Networking 3, 226–244.CrossRefGoogle Scholar
[21] Resnick, S. and Samorodnitsky, G. (1999). Activity periods of an infinite server queue and performance of certain heavy tailed fluid queues. Queueing Systems 33, 43–71.Google Scholar
[22] Willinger, W., Taqqu, M. S., Sherman, R. and Wilson, D. V. (1997). Self-similarity through high-variability: statistical analysis of ethernet LAN traffic at the source level. IEEE/ACM Trans. Networking 5, 71–86.CrossRefGoogle Scholar
[23] Zwart, A. P., Borst, S. C. and Mandjes, M. (2003). Exact asymptotics for fluid queues fed by multiple heavy-tailed on–off flows. To appear in Ann. Appl. Prob. Google Scholar