Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Towards a Low Latency Internet: Understanding and Solutions
Karlstad University, Faculty of Health, Science and Technology (starting 2013), Department of Mathematics and Computer Science. (DISCO)ORCID iD: 0000-0003-2765-7873
2015 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Networking research and development have historically focused on increasing network throughput and path resource utilization, which particularly helped bulk applications such as file transfer and video streaming. Recent over-provisioning in the core of the Internet has facilitated the use of interactive applications like interactive web browsing, audio/video conferencing, multi- player online gaming and financial trading applications. Although the bulk applications rely on transferring data as fast as the network permits, interactive applications consume rather little bandwidth, depending instead on low latency. Recently, there has been an increasing concern in reducing latency in networking research, as the responsiveness of interactive applications directly influences the quality of experience.

To appreciate the significance of latency-sensitive applications for today's Internet, we need to understand their traffic pattern and quantify their prevalence. In this thesis, we quantify the proportion of potentially latency-sensitive traffic and its development over time. Next, we show that the flow start-up mechanism in the Internet is a major source of latency for a growing proportion of traffic, as network links get faster.

The loss recovery mechanism in the transport protocol is another major source of latency. To improve the performance of latency-sensitive applications, we propose and evaluate several modifications in TCP. We also investigate the possibility of prioritization at the transport layer to improve the loss recovery. The idea is to trade reliability for timeliness. We particularly examine the applicability of PR-SCTP with a focus on event logging. In our evaluation, the performance of PR-SCTP is largely influenced by small messages. We analyze the inefficiency in detail and propose several solutions. We particularly implement and evaluate one solution that utilizes the Non-Renegable Selective Acknowledgments (NR-SACKs) mechanism, which has been proposed for standardization in the IETF. According to the results, PR-SCTP with NR-SCAKs significantly improves the application performance in terms of low latency as compared to SCTP and TCP.

Abstract [en]

Interactive applications such as web browsing, audio/video conferencing, multi-player online gaming and financial trading applications do not benefit (much) from more bandwidth. Instead, they depend on low latency. Latency is a key determinant of user experience. An increasing concern for reducing latency is therefore currently being observed among the networking research community and industry.

In this thesis, we quantify the proportion of potentially latency-sensitive traffic and its development over time. Next, we show that the flow start-up mechanism in the Internet is a major source of latency for a growing proportion of traffic, as network links get faster.

The loss recovery mechanism in the transport protocol is another major source of latency. To improve the performance of latency-sensitive applications, we propose and evaluate several modifications in TCP. We also investigate the possibility of prioritization at the transport layer to improve the loss recovery. The idea is to trade reliability for timeliness. We particularly examine the applicability of PR-SCTP with a focus on event logging. In our evaluation, the performance of PR-SCTP is largely influenced by small messages. We analyze the inefficiency in detail and propose several solutions. We particularly implement and evaluate one solution that utilizes the Non-Renegable Selective Acknowledgments (NR-SACKs) mechanism, which has been proposed for standardization in the IETF. According to the results, PR-SCTP with NR-SCAKs significantly improves the application performance in terms of low latency as compared to SCTP and TCP.

Place, publisher, year, edition, pages
Karlstad: Karlstad University Press, 2015. , 39 p.
Series
Karlstad University Studies, ISSN 1403-8099 ; 41
Keyword [en]
latency; traffic classification; slow-start; TCP; SCTP; PR-SCTP; NR-SACKs; event logging; performance evaluation
National Category
Computer Science
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:kau:diva-37487ISBN: 978-91-7063-659-2 (print)OAI: oai:DiVA.org:kau-37487DiVA: diva2:846109
Public defence
2015-11-12, Lagerlöfsalen, 1A305, Karlstads universitet, 09:00 (English)
Opponent
Supervisors
Available from: 2015-10-16 Created: 2015-08-14 Last updated: 2015-11-12Bibliographically approved
List of papers
1. A Method for Hierarchical Clustering of Internet Traffic and its Use in Detecting Application-Limited Flows
Open this publication in new window or tab >>A Method for Hierarchical Clustering of Internet Traffic and its Use in Detecting Application-Limited Flows
Show others...
(English)Manuscript (preprint) (Other academic)
National Category
Computer Science
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-37474 (URN)
Available from: 2015-08-13 Created: 2015-08-13 Last updated: 2015-10-16Bibliographically approved
2. What Use is Top Speed without Acceleration?
Open this publication in new window or tab >>What Use is Top Speed without Acceleration?
(English)Manuscript (preprint) (Other academic)
Keyword
TCP; slow-start
National Category
Computer Science
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-37475 (URN)
Available from: 2015-08-13 Created: 2015-08-13 Last updated: 2015-10-16Bibliographically approved
3. An Evaluation of Tail Loss Recovery Mechanisms for TCP
Open this publication in new window or tab >>An Evaluation of Tail Loss Recovery Mechanisms for TCP
Show others...
2015 (English)In: Computer communication review, ISSN 0146-4833, E-ISSN 1943-5819, Vol. 45, no 1, 6-11 p.Article in journal (Refereed) Published
Abstract [en]

Interactive applications do not require more bandwidth to go faster. Instead, they require less latency. Unfortunately, the current design of transport protocols such as TCP limits possible latency reductions. In this paper we evaluate and compare different loss recovery enhancements to fight tail loss latency. The two recently proposed mechanisms "RTO Restart" (RTOR) and "Tail Loss Probe" (TLP) as well as a new mechanism that applies the logic of RTOR to the TLP timer management (TLPR) are considered. The results show that the relative performance of RTOR and TLP when tail loss occurs is scenario dependent, but with TLP having potentially larger gains. The TLPR mechanism reaps the benefits of both approaches and in most scenarios it shows the best performance.

Place, publisher, year, edition, pages
USA: ACM Special Interest Group on Computer Science Education, 2015
Keyword
TCP; Congestion Control; Latency; Packet Loss; Recovery
National Category
Computer Science
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-34860 (URN)10.1145/2717646.2717648 (DOI)000354951000002 ()
Available from: 2015-01-01 Created: 2015-01-01 Last updated: 2017-12-05Bibliographically approved
4. Priority Based Delivery of PR-SCTP Messages in a Syslog Context
Open this publication in new window or tab >>Priority Based Delivery of PR-SCTP Messages in a Syslog Context
2011 (English)In: Access networks, Springer, 2011, 299-310 p.Conference paper, Published paper (Refereed)
Abstract [en]

Unquestionably, syslog provides the most popular and easily manageable computer system logging environment. In a computer network, syslog messages are used for several purposes such as for optimizing system performance, logging user's actions and investigating malicious activities. Due to all these essential utilities, a competent transport service for syslog messages becomes important. Most of the current syslog implementations use either the unreliable UDP protocol or the more costly reliable TCP protocol. Neither of these protocols can provide both timeliness and reliability, while transporting inherently prioritized syslog messages in a congested network. In this paper, we both propose and evaluate the use of PR-SCTP, an existing partial reliability extension of the SCTP transport protocol, as a candidate transport service for the next generation syslog standard. In our emulation based experimental results, PR-SCTP shows better performance than TOP in terms of average delay for message transfer. Furthermore, PR-SCTP exhibits less average packet loss than UDP. In both cases, PR-SCTP exploits priority properties of syslog messages during loss recovery.

Place, publisher, year, edition, pages
Springer, 2011
Series
Lecture Notes of the Institute for Computer Sciences Social Informatics and Telecommunications Engineering, ISSN 1867-8211 ; 63
Keyword
Syslog, PR-SCTP, performance evaluations, transport service
National Category
Computer Science
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-10295 (URN)000307264600023 ()978-3-642-20930-7 (ISBN)
Conference
5th Annual International ICST Conference on Access Networks (AccessNets 2010), NOV 03-05, 2010, Budapest, HUNGARY
Available from: 2012-02-08 Created: 2012-02-08 Last updated: 2017-12-06Bibliographically approved
5. Syslog Performance: Data Modeling and Transport
Open this publication in new window or tab >>Syslog Performance: Data Modeling and Transport
2011 (English)In: Proceedings of the 3rd International Workshop on Security and Communication Networks (IWSCN 2011), Norway: IEEE Press, 2011, 31-37 p.Conference paper, Published paper (Refereed)
Abstract [en]

Syslog is one of the basic methods for event logging in computer networks. Log messages that are generated by syslog can be used for a number of purposes, including optimizing system performance, system auditing, and investigating malicious activities in a computer network. Considering all these attractive uses, both timeliness and reliability is needed when syslog messages are transported over a network. The unreliable transport protocol UDP was specified in the original syslog specification; later a reliable transport service based on TCP was also proposed. However, TCP is a costly alternative in terms of delay. In our previous work, we introduced the partially reliable extension of SCTP, PR-SCTP, as a transport service for syslog, trading reliability against timeliness by prioritizing syslog messages. In this work, we first model syslog data using real syslog traces from an operational network. The model is then used as input in the performance evaluation of PR-SCTP. In the experiments, real congestion is introduced in the network by running several competing flows. Although PR-SCTP clearly outperformed TCP and SCTP in our previous work, our present evaluations show that PR-SCTP performance is largely influenced by the syslog data size characteristics

Place, publisher, year, edition, pages
Norway: IEEE Press, 2011
National Category
Computer Science
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-10922 (URN)
Conference
The 3rd International Workshop on Security and Communication Networks (IWSCN 2011), May 18-20, Gjøvik, Norway
Available from: 2012-02-08 Created: 2012-02-08 Last updated: 2017-12-06Bibliographically approved
6. On the Effectiveness of PR-SCTP in Networks with Competing Traffic
Open this publication in new window or tab >>On the Effectiveness of PR-SCTP in Networks with Competing Traffic
2011 (English)In: 2011 IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS (ISCC), Corfu, Greece: IEEE conference proceedings, 2011Conference paper, Published paper (Refereed)
Abstract [en]

PR-SCTP is an extension to SCTP for partial reliability that enables a content sensitive transport service where the reliability of messages can be individually controlled. In previous work, PR-SCTP has been applied for prioritization of messages and trading of reliability against timeliness for applications such as real time video streaming, IPTV transmission, SIP signaling, and syslog. As compared to TCP, it has been shown to provide significant reductions in message transfer delay and gains in application performance. Much of the previous work has, however, considered artificial loss scenarios without competing traffic. Experiments presented in this paper show that although PR-SCTP clearly outperforms TCP in artificial loss scenarios, the performance gain is not as evident in scenarios where PR-SCTP shares a bottleneck link with competing traffic. Our analysis shows that inefficiencies in the \emph{forward\_tsn} mechanism of PR-SCTP, overhead due to small messages, and a higher loss rate per byte encountered by PR-SCTP are contributing factors to the reduced performance when network resources are shared. Finally, a proposal for a more efficient \emph{forward\_tsn} mechanism is introduced

Place, publisher, year, edition, pages
Corfu, Greece: IEEE conference proceedings, 2011
Series
IEEE Symposium on Computers and Communications ISCC
National Category
Computer Science Telecommunications
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-10925 (URN)000298614900157 ()
Conference
The IEEE symposium on Computers and Communications (ISCC 2011), Corfu, GREECE, Date: JUN 28-JUL 01, 2011
Available from: 2012-02-08 Created: 2012-02-08 Last updated: 2016-08-12Bibliographically approved
7. Performance Analysis and Improvement of PR-SCTP for Small Messages
Open this publication in new window or tab >>Performance Analysis and Improvement of PR-SCTP for Small Messages
2013 (English)In: Computer Networks, ISSN 1389-1286, Vol. 57, no 18, 3967-3986 p.Article in journal (Refereed) Published
Abstract [en]

PR-SCTP, a partially reliable extension of SCTP, provides a flexible QoS trade-off between timeliness and reliability for application traffic. However, the performance of PR-SCTP can be reduced due to certain traffic characteristics and network scenarios. Previously, we proposed a NR-SACK based optimization for PR-SCTP. In this work we extensively evaluate and analyze the performance of PR-SCTP with NR-SACKs using different network scenarios. Moreover, we compare the performance of our NR-SACK based PR-SCTP with existing transport protocols for syslog traffic. In the evaluation, we use real syslog traces from an operational syslog system. The results indicate that NR-SACKs based PR-SCTP significantly improves the overall message transfer delay as compared to SCTP and TCP.

Place, publisher, year, edition, pages
Elsevier: , 2013
Keyword
SCTP, PR-SCTP, NR-SACKs, event logging, performance evaluation
National Category
Computer Science
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-14674 (URN)10.1016/j.comnet.2013.09.018 (DOI)000328011900016 ()
Available from: 2012-09-06 Created: 2012-09-06 Last updated: 2017-12-06Bibliographically approved

Open Access in DiVA

Rajiullah 2015_41(483 kB)237 downloads
File information
File name FULLTEXT01.pdfFile size 483 kBChecksum SHA-512
831b08aacef16bf7022121c0657e99112293fc755c54d97ce20ef288f59488b99ac407d3f819984cbb0488cb8c1e837c6b1ed3fa5f633c1fb577755e23c0f30d
Type fulltextMimetype application/pdf

Authority records BETA

Rajiullah, Mohammad

Search in DiVA

By author/editor
Rajiullah, Mohammad
By organisation
Department of Mathematics and Computer Science
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 237 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 1277 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf