Article

Free access

Higher response time moments for M/M/1 discriminatory processor sharing queues

Authors:

Peter HarrisonAuthors Info & Claims

VALUETOOLS'15: Proceedings of the 9th EAI International Conference on Performance Evaluation Methodologies and Tools

Pages 145 - 148

https://doi.org/10.4108/eai.14-12-2015.2262730

Published: 04 January 2016 Publication History

Abstract

Obtaining response time moments in processor sharing (PS) queues is difficult due to serving of multiple jobs. Egalitarian PS (EPS) queues are limited to one class of arriving jobs. Discriminatory PS (DPS) assigns weights to different job classes and offers more diverse modeling capabilities than EPS. It is known that response time is the representative metric for delay as specified in service level agreements (SLAs), which consider higher moments important. Hence, we build an automated numerical algorithm for calculating higher moments of response time in M/M/1-DPS queues for multiple job classes and test two different case studies.

References

[1]

E. G. Coffman Jr., R. R. Muntz, H. Trotter: Waiting Time Distributions for Processor-Sharing Systems, In Journal ACM, 17, pp. 123-130 (1970).

[2]

T. Chis: Sliding Hidden Markov Model for Evaluating Discrete Data, In Proc. EPEW (2013).

[3]

P. G. Harrison, N. M. Patel: Performance Modelling of Communication Networks and Computer Architectures, Addison-Wesley, 1 (1993).

[4]

M. A. Kjaer, M. Kihl, A. Robertsson: Response-Time Control of a Processor-Sharing System using Virtualised Server Environments, In Proc. IFAC (2008).

[5]

S. W. M. Au-Yeung, N. J. Dingle, W. J. Knottenbelt: Efficient Approximation of Response time Densities and Quantiles in Stochastic Models, In Proc. ACM WOSP (2004).

[6]

T. Chis, P. G. Harrison: Adapting Hidden Markov Models for Online Learning, In Elsevier ENTCS, 318, pp. 109-127 (2015).

[7]

J. Kim, B. Kim: Sojourn time distribution in the M/M/1 queue with discriminatory processor-sharing, In Perform. Eval., 58, pp. 341-365 (2004).

[8]

S. F. Yashkov: Processor-Sharing Queues: Some Progress In Analysis, In Queue. Sys., 2, pp. 1-17 (1987).

[9]

A. Lakhany, H. Mausser: Estimating the parameters of the General Lambda Distribution, In Algo. Research Quarterly, 3, pp. 47-58 (2000).

[10]

T. Chis, P. G. Harrison: Modeling Multi-User Behaviour in Social Networks, In Proc. IEEE MASCOTS (2014).

[11]

J. W. Roberts: A survey on statistical bandwidth sharing, In Computer Networks, 45, pp. 319-332 (2004).

[12]

G. Fayolle, R. Iasnogorodski, I. Mitrani: Sharing a Processor Among Many Job Classes, In Journal ACM, 27(3), pp. 519-532 (1980).

[13]

H. Li, M. Muskulus, L. Wolters: Modeling Job Arrivals in a data-intensive Grid, In Proc. JSSPP Workshop (2006).

[14]

T. Chis, P. G. Harrison: iSWoM: The incremental Storage Workload Model using Hidden Markov Models, In Proc. ASMTA (2013).

[15]

K. Avrachenkov, U. Ayesta, P. Brown, R. Nunez-Queija: Discriminatory Processor Sharing Revisited, In Proc. IEEE Infocom (2005).

[16]

L. Kleinrock: Time-shared systems: A theoretical treatment, In Journal ACM, 14(2), pp. 242-261 (1967).

[17]

T. Chis, P. G. Harrison: Moment-Generating Algorithm for Response Time in Processor Sharing Queueing Systems, In Proc. EPEW (2015).

Recommendations

Heavy-Traffic Analysis of a Multiple-Phase Network with Discriminatory Processor Sharing

We analyze a generalization of the discriminatory processor-sharing (DPS) queue in a heavy-traffic setting. Customers present in the system are served simultaneously at rates controlled by a vector of weights. We assume that customers have phase-type ...
Slowdown in the M/M/1 discriminatory processor-sharing queue

We consider a queue with multiple K job classes, Poisson arrivals, and exponentially distributed required service times in which a single processor serves according to the discriminatory processor-sharing (DPS) discipline. For this queue, we obtain the ...
Queues with system disasters and impatient customers when system is down

Consider a system operating as an M/M/c queue, where c =1, 1< c < , or c = . The system as a whole suffers occasionally a disastrous breakdown, upon which all present customers (waiting and served) are cleared from the system and lost. A repair ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

VALUETOOLS'15: Proceedings of the 9th EAI International Conference on Performance Evaluation Methodologies and Tools

January 2016

272 pages

ISBN:9781631900969

Editors:
William Knottenbelt
Imperial College London Department of Computing, Imperial College London, SW7 2AZ
,
Katinka Wolter
Freie Universität Berlin Takustr. 9 Raum 149 14195 Berlin
,
Ana Busic
ENS/INRIA Inria 23, avenue d'Italie CS 81321 75214 Paris Cedex 13
,
Marco Gribaudo
Politecnico di Milano Dipartimento di Elettronica, Informatica e Bioingeneria, Politecnico di Milano, Via Ponzio 34/5 - 20133 - Milano, Italy
,
Philipp Reinecke
Hewlett Packard Labs Bristol Long Down Avenue Stoke Gifford BS34 8QZ

Publisher

ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering)

Brussels, Belgium

Publication History

Published: 04 January 2016

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

0
Total Citations
46
Total Downloads

Downloads (Last 12 months)10
Downloads (Last 6 weeks)4

Reflects downloads up to 04 Feb 2025

Other Metrics

View Author Metrics

Citations

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Figures

Tables

Media

View Table of Conten