research-article

A QoE Perspective on Sizing Network Buffers

Authors:

Oliver Hohlfeld,

Anja Feldmann, and

Paul BarfordAuthors Info & Claims

IMC '14: Proceedings of the 2014 Conference on Internet Measurement Conference

November 2014

Pages 333 - 346

https://doi.org/10.1145/2663716.2663730

Published: 05 November 2014 Publication History

Abstract

Despite decades of operational experience and focused research efforts, standards for sizing and configuring buffers in network systems remain controversial. An extreme example of this is the recent claim that excessive buffering (i.e., bufferbloat) can severely impact Internet services. In this paper, we systematically examine the implications of buffer sizing choices from the perspective of factors impacting end user experience. To assess user perception of application quality under various buffer sizing schemes we employ Quality of Experience (QoE) metrics. We evaluate these metrics over a wide range of end-user applications (e.g., web browsing, VoIP, and RTP video streaming) and workloads in two realistic testbeds emulating access and backbone networks. The main finding of our extensive evaluations is that network workload, rather than buffer size, is the primary determinant of end user QoE. Our results also highlight the relatively narrow conditions under which bufferbloat seriously degrades QoE, i.e., when buffers are oversized and sustainably filled.

References

[1]

Bufferbloat. http://www.bufferbloat.net/.

[2]

ITU-T Recommendation P.862: Perceptual Evaluation of Speech Quality (PESQ): An Objective Method for End-To-End Speech Quality Assessment of Narrow-Band Telephone Networks and Speech Codecs, 2001.

[3]

ITU-T Recommendation G.107: The E-Model, a computational model for use in transmission planning, 2003.

[4]

ITU-T Rec. P.862 annex a: Reference implementations and conformance testing for ITU-T Recs P.862, P.862.1 a. P.862.2, 2005.

[5]

ITU-T Recommendation G.1030: estimating end-to-end performance in IP networks for data applications, 2005.

[6]

Bufferbloat: What's wrong with the internet? Queue, 9(12):10:10--10:20, Dec. 2011.

Digital Library

[7]

Qualinet white paper on definitions of Quality of Experience. European Network on Quality of Experience in Multimedia Systems and Services (COST Action IC 1003), Patrick Le Callet, Sebastian Möller and Andrew Perkis, eds., Version 1.1, June 2012.

[8]

M. Allman. Comments on bufferbloat. ACM CCR, 43(1):31--37, Jan. 2013.

Digital Library

[9]

G. Appenzeller, I. Keslassy, and N. McKeown. Sizing router buffers. In ACM SIGCOMM, 2004.

Digital Library

[10]

N. Barakat and T. E. Darcie. Delay characterization of cable access networks. IEEE Communications Letters, 11(4):357--359, 2007.

[11]

N. Beheshti, Y. Ganjali, M. Ghobadi, N. McKeown, and G. Salmon. Experimental study of router buffer sizing. In ACM IMC, 2008.

Digital Library

[12]

C. Chirichella and D. Rossi. To the moon and back: are Internet bufferbloat delays really that large. In IEEE INFOCOM TMA Workshop, 2013.

[13]

M. Dischinger, A. Haeberlen, K. P. Gummadi, and S. Saroiu. Characterizing residential broadband networks. In ACM IMC, 2007.

Digital Library

[14]

S. Egger, T. Hossfeld, R. Schatz, and M. Fiedler. Tutorial: Waiting Times in Quality of Experience for Web based Services. In IEEE QoMEX, 2012.

[15]

S. Egger, P. Reichl, T. Hosfeld, and R. Schatz. "time is bandwidth?" narrowing the gap between subjective time perception and Quality of Experience. In IEEE ICC, 2012.

[16]

S. Egger, R. Schatz, K. Schoenenberg, A. Raake, and G. Kubin. Same but different? - using speech signal features for comparing conversational voip quality studies. In IEEE ICC, 2012.

[17]

M. Enachescu, Y. Ganjali, A. Goel, N. McKeown, and T. Roughgarden. Routers with very small buffers. In IEEE INFOCOM, 2006.

[18]

J. Gettys. IW10 considered harmful. IETF Internet-Draft, 2011.

[19]

J. Gettys and K. Nichols. Bufferbloat: Dark buffers in the internet. ACM Queue, 9:40:40--40:54, Nov. 2011.

Digital Library

[20]

Y. Gu, D. F. Towsley, C. V. Hollot, and H. Zhang. Congestion control for small buffer high speed networks. In IEEE INFOCOM, 2007.

Digital Library

[21]

D. Guse, S. Egger, A. Raake, and S. Möller. Web-QoE under real-world distractions: Two test cases. In IEEE QoMEX, 2014.

[22]

K. L. Haiqing Jiang, Yaogong Wang and I. Rhee. Tackling bufferbloat in 3G/4G networks. In ACM IMC, 2012.

Digital Library

[23]

M. Heusse, S. A. Merritt, T. X. Brown, and A. Duda. Two-way TCP connections: old problem, new insight. ACM CCR, 41(2):6--15, 2011.

Digital Library

[24]

O. Hohlfeld, B. Balarajah, S. Benner, A. Raake, and F. Ciucu. On revealing the ARQ mechanism of MSTV. In IEEE ICC, 2011.

[25]

V. Jacobson. Modified TCP congestion control algorithm. End2end-interest mailing list, Apr. 1990.

[26]

N. Kitawaki and K. Itoh. Pure delay effects on speech quality in telecommunications. IEEE Journal on Selected Areas in Communications, 9(4):586--593, 1991.

Digital Library

[27]

J. Korhonen and J. You. Peak signal-to-noise radio revised: Is simple beautiful? In IEEE QoMEX, 2012.

[28]

C. Kreibich, N. Weaver, B. Nechaev, and V. Paxson. Netalyzr: Illuminating the edge network. In ACM IMC, 2010.

Digital Library

[29]

A. Lakshmikantha, C. Beck, and R. Srikant. Impact of file arrivals and departures on buffer sizing in core routers. IEEE/ACM ToN, 19(2):347--358, Apr. 2011.

Digital Library

[30]

J. Martin, J. Westall, T. Shaw, G. White, R. Woundy, J. Finkelstein, and G. Hart. Cable modem buffer management in docsis networks. In IEEE conference on Sarnoff, 2010.

Digital Library

[31]

S. Möller, W.-Y. Chan, N. Côté, T. H. Falk, A. Raake, and M. Wältermann. Speech quality estimation: Models and trends. IEEE Signal Process. Mag., 28(6):18--28, 2011.

[32]

K. Nichols and V. Jacobson. Controlling queue delay. ACM Queue, 10(5), May 2012.

Digital Library

[33]

R. S. Prasad, C. Dovrolis, and M. Thottan. Router buffer sizing for tcp traffic and the role of the output/input capacity ratio. IEEE/ACM ToN, 17(5):1645--1658, Oct. 2009.

Digital Library

[34]

A. Raake. Predicting speech quality under random packet loss: Individual impairment and additivity with other network impairments. Acta Acustia, 90:1061--1083, 2004.

[35]

B. Sat and B. W. Wah. Analyzing voice quality in popular voip applications. IEEE MultiMedia, 16(1):46--59, 2009.

Digital Library

[36]

L. Sequeira et al. The influence of the buffer size in packet loss for competing multimedia and bursty traffic. In SPECTS, 2013.

[37]

J. Sommers, P. Barford, A. Greenberg, and W. Willinger. An SLA perspective on the router buffer sizing problem. SIGMETRICS Perf. Eval. Review, 35:40--51, March 2008.

Digital Library

[38]

J. Sommers, H. Kim, and P. Barford. Harpoon: a flow-level traffic generator for router and network tests. SIGMETRICS Perf. Eval. Review, 32(1):392--392, June 2004.

Digital Library

[39]

D. Strohmeier, S. Jumisko-Pyykko, and A. Raake. Toward task-dependent evaluation of web-QoE: Free exploration vs. "who ate what?". In IEEE Globecom Workshops, 2012.

[40]

D. Strohmeier, M. Mikkola, and A. Raake. The importance of task completion times for modeling web-QoE of consecutive web page requests. In IEEE QoMEX, 2013.

[41]

L. Sun. Speech Quality Prediction for Voice over Internet Protocol Networks. PhD thesis, Univ. of Plymouth, 2004.

[42]

S. Sundaresan, W. de Donato, N. Feamster, R. Teixeira, S. Crawford, and A. Pescapè. Measuring home broadband performance. Commun. ACM, 55(11):100--109, Nov. 2012.

Digital Library

[43]

Q. H. Thu and M. Ghanbari. Scope of validity of PSNR in image/video quality assessment. Electronics Letters, 44(13):800--801, June 2008.

[44]

C. Villamizar and C. Song. High performance tcp in ansnet. ACM CCR, 24(5):45--60, Oct. 1994.

Digital Library

[45]

A. Vishwanath, V. Sivaraman, and M. Thottan. Perspectives on router buffer sizing: recent results and open problems. ACM CCR, 39(2):34--39, Mar. 2009.

Digital Library

[46]

M. Wang and Y. Ganjali. The effects of fairness in buffer sizing. In IFIP-TC6 conference on Ad Hoc and sensor networks, wireless networks, next generation internet, 2007.

Digital Library

[47]

Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli. Image quality assessment: From error visibility to structural similarity. IEEE Trans. on Image Processing, 13:600--612, 2004.

Digital Library

[48]

Z. Wang, L. Lu, and A. Bovik. Video quality assessment based on structural distortion measurement. Signal Processing: Image Communication, 19(1), Jan. 2004.

[49]

T. Zinner, O. Abboud, O. Hohlfeld, T. Hossfeld, and P. Tran-Gia. Towards QoE management for scalable video streaming. In 21st ITC-SS, 2010.

Cited By

Choi SChoi SLee GYoon SBahk S(2024)Deep Reinforcement Learning for Scalable Dynamic Bandwidth Allocation in RAN Slicing With Highly Mobile UsersIEEE Transactions on Vehicular Technology10.1109/TVT.2023.330241673:1(576-590)Online publication date: Jan-2024
https://doi.org/10.1109/TVT.2023.3302416
Kfoury ECrichigno JBou-Harb E(2024)P4BS: Leveraging Passive Measurements From P4 Switches to Dynamically Modify a Router’s Buffer SizeIEEE Transactions on Network and Service Management10.1109/TNSM.2023.330633521:1(1082-1099)Online publication date: Feb-2024
https://doi.org/10.1109/TNSM.2023.3306335
Shah ABran JZarifis KBedi H(2022)SSQoE: Measuring Video QoE from the Server-Side at a Global Multi-tenant CDNPassive and Active Measurement10.1007/978-3-030-98785-5_27(600-625)Online publication date: 22-Mar-2022
https://doi.org/10.1007/978-3-030-98785-5_27
Show More Cited By

Index Terms

A QoE Perspective on Sizing Network Buffers
1. Networks
  1. Network components
  2. Network types
    1. Public Internet

Recommendations

Sizing router buffers

All Internet routers contain buffers to hold packets during times of congestion. Today, the size of the buffers is determined by the dynamics of TCP's congestion control algorithm. In particular, the goal is to make sure that when a link is congested, ...
Read More
Sizing router buffers
SIGCOMM '04: Proceedings of the 2004 conference on Applications, technologies, architectures, and protocols for computer communications

All Internet routers contain buffers to hold packets during times of congestion. Today, the size of the buffers is determined by the dynamics of TCP's congestion control algorithm. In particular, the goal is to make sure that when a link is congested, ...
Read More
Simulation studies on router buffer sizing for short-lived and pacing TCP flows

Traditionally, the size of router buffers is determined by the bandwidth-delay product discipline (normal discipline), which is the product of the link bandwidth and average round-trip time (RTT) of flows passing through the router. However, recent ...
Read More

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

IMC '14: Proceedings of the 2014 Conference on Internet Measurement Conference

November 2014

524 pages

ISBN:9781450332132

DOI:10.1145/2663716

General Chair:
Carey Williamson
University of Calgary, Canada
,
Program Chairs:
Aditya Akella
University of Wisconsin - Madison, USA
,
Nina Taft
Google, USA

Copyright © 2014 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

SIGMETRICS: ACM Special Interest Group on Measurement and Evaluation
SIGCOMM: ACM Special Interest Group on Data Communication
USENIX Assoc: USENIX Assoc

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 05 November 2014

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Deutsche Forschungsgemeinschaft
Telekom Innovation Laboratories

Conference

IMC '14

Sponsor:

SIGMETRICS
SIGCOMM
USENIX Assoc

IMC '14: Internet Measurement Conference

November 5 - 7, 2014

BC, Vancouver, Canada

Acceptance Rates

IMC '14 Paper Acceptance Rate 32 of 103 submissions, 31%;

Overall Acceptance Rate 277 of 1,083 submissions, 26%

Upcoming Conference

IMC '24

Sponsor:
sigcomm
sigcomm

ACM Internet Measurement Conference

November 4 - 6, 2024

Madrid , AA , Spain

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

21
Total Citations
View Citations
340
Total Downloads

Downloads (Last 12 months)30
Downloads (Last 6 weeks)2

Other Metrics

View Author Metrics

Citations

Cited By

Choi SChoi SLee GYoon SBahk S(2024)Deep Reinforcement Learning for Scalable Dynamic Bandwidth Allocation in RAN Slicing With Highly Mobile UsersIEEE Transactions on Vehicular Technology10.1109/TVT.2023.330241673:1(576-590)Online publication date: Jan-2024
https://doi.org/10.1109/TVT.2023.3302416
Kfoury ECrichigno JBou-Harb E(2024)P4BS: Leveraging Passive Measurements From P4 Switches to Dynamically Modify a Router’s Buffer SizeIEEE Transactions on Network and Service Management10.1109/TNSM.2023.330633521:1(1082-1099)Online publication date: Feb-2024
https://doi.org/10.1109/TNSM.2023.3306335
Shah ABran JZarifis KBedi H(2022)SSQoE: Measuring Video QoE from the Server-Side at a Global Multi-tenant CDNPassive and Active Measurement10.1007/978-3-030-98785-5_27(600-625)Online publication date: 22-Mar-2022
https://doi.org/10.1007/978-3-030-98785-5_27
Vargas SDrucker RRenganathan ABalasubramanian AGandhi A(2021)BBR Bufferbloat in DASH VideoProceedings of the Web Conference 202110.1145/3442381.3450061(329-341)Online publication date: 19-Apr-2021
https://dl.acm.org/doi/10.1145/3442381.3450061
Spang BArslan SMcKeown N(2021)Updating the theory of buffer sizingPerformance Evaluation10.1016/j.peva.2021.102232151:COnline publication date: 1-Nov-2021
https://dl.acm.org/doi/10.1016/j.peva.2021.102232
Ruth JKunze IHohlfeld O(2019)An Empirical View on Content Provider Fairness2019 Network Traffic Measurement and Analysis Conference (TMA)10.23919/TMA.2019.8784684(177-184)Online publication date: Jun-2019
https://doi.org/10.23919/TMA.2019.8784684
Spang BWalsh BHuang TRusnock TLawrence JMcKeown N(2019)Buffer sizing and Video QoE Measurements at NetflixProceedings of the 2019 Workshop on Buffer Sizing10.1145/3375235.3375241(1-7)Online publication date: 2-Dec-2019
https://dl.acm.org/doi/10.1145/3375235.3375241
Wang YZheng JTan LTian C(2019)Joint Optimization on Bandwidth Allocation and Route Selection in QoE-Aware Traffic EngineeringIEEE Access10.1109/ACCESS.2018.28862407(3314-3319)Online publication date: 2019
https://doi.org/10.1109/ACCESS.2018.2886240
Milanesio MCallegari CMichiardi P(2019)Network level perspective in web sessions troubleshootingInternational Journal of Communication Systems10.1002/dac.390832:6Online publication date: 29-Jan-2019
https://doi.org/10.1002/dac.3908
Zhang YGao CGuo YBian KJin XYang ZSong LCheng JTuo HLi X(2018)Proactive Video Push for Optimizing Bandwidth Consumption in Hybrid CDN-P2P VoD SystemsIEEE INFOCOM 2018 - IEEE Conference on Computer Communications10.1109/INFOCOM.2018.8485962(2555-2563)Online publication date: Apr-2018
https://doi.org/10.1109/INFOCOM.2018.8485962
Show More Cited By

View Options

Get Access

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

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents