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
Transport-Layer Performance for Applications and Technologies of the Future Internet
Karlstad University, Faculty of Economic Sciences, Communication and IT, Department of Computer Science.ORCID iD: 0000-0002-8731-2482
2012 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

To provide Internet applications with good performance, the transport protocol TCP is designed to optimize the throughput of data transfers. Today, however, more and more applications rely on low latency rather than throughput. Such applications can be referred to as data-limited and are not appropriately supported by TCP. Another emerging problem is associated with the use of novel networking techniques that provide infrastructure-less networking. To improve connectivity and performance in such environments, multi-path routing is often used. This form of routing can cause packets to be reordered, which in turn hurts TCP performance.

To address timeliness issues for data-limited traffic, we propose and experimentally evaluate several transport protocol adaptations. For instance, we adapt the loss recovery mechanisms of both TCP and SCTP to perform faster loss detection for data-limited traffic, while preserving the standard behavior for regular traffic. Evaluations show that the proposed mechanisms are able to reduce loss recovery latency with 30-50%. We also suggest modifications to the TCP state caching mechanisms. The caching mechanisms are used to optimize new TCP connections based on the state of old ones, but do not work properly for data-limited flows. Additionally, we design a SCTP mechanism that reduces overhead by bundling several packets into one packet in a more timely fashion than the bundling normally used in SCTP.

To address the problem of packet reordering we perform several experimental evaluations, using TCP and state of the art reordering mitigation techniques. Although the studied mitigation techniques are quite good in helping TCP to sustain its performance during pure packet reordering events, they do not help when other impairments like packet loss are present.

Place, publisher, year, edition, pages
Karlstad: Karlstads universitet, 2012. , 30 p.
Series
Karlstad University Studies, ISSN 1403-8099 ; 2011:65
Keyword [en]
TCP, SCTP, transport protocols, loss recovery, packet reordering, congestion control, performance evaluation
National Category
Computer Systems
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:kau:diva-8920ISBN: 978-91-7063-404-8 (print)OAI: oai:DiVA.org:kau-8920DiVA: diva2:463253
Public defence
2012-02-09, 1B364 (Frödingsalen), Karlstads universitet, Karlstad, 13:15 (English)
Opponent
Supervisors
Note

Paper V was in manuscript form at the time of the defense.

Available from: 2012-01-13 Created: 2011-12-08 Last updated: 2016-10-15Bibliographically approved
List of papers
1. Loss Recovery in Short TCP/SCTP Flows
Open this publication in new window or tab >>Loss Recovery in Short TCP/SCTP Flows
2006 (English)Report (Other academic)
Abstract [en]

The Transmission Control Protocol (TCP) has been the dominant transport protocol within IP-based networks for many years, mainly due to the reliability it provide to its users and the congestion control it employs. However, as the amount of signaling traffic within IP-based networks have increased significantly in recent years, it has become clear that TCP is not suited for this kind of traffic. In order to meet the requirements of signaling traffic the Stream Control Transmission Protocol (SCTP) was developed by the Internet Engineering Task Force (IETF). SCTP is heavily influenced by TCP and is therefore similar to TCP in many ways. One example is the SCTP loss recovery and congestion control mechanisms which are almost identical to those of TCP. The primary purpose of this work is to study the performance and behavior of the TCP/SCTP loss recovery mechanisms for short flows. Using a simple client/server model, we evaluate the performance of these mechanism over a wide range of bandwidths, link delays and packet loss patterns. The experiments evaluate one TCP implementation and two SCTP implementations, and were conducted using network emulation. The experimental results show that there exist strong dependencies between the position of packet loss and the actual transmission time of the corresponding flow. In addition to these dependencies, we also found a number of implementation mistakes in the examined protocol implementations.

Place, publisher, year, edition, pages
Karlstad: Karlstads universitet, 2006. 59 p.
Series
Karlstad University Studies, ISSN 1403-8099 ; 2006:71
Keyword
tcp, sctp, loss recovery, emulation, performance evaluation
National Category
Computer Systems
Identifiers
urn:nbn:se:kau:diva-725 (URN)91-7063-101-8 (ISBN)
Available from: 2007-04-13 Created: 2007-04-13 Last updated: 2014-11-21
2. Enhancing SCTP Loss Recovery: An Experimental Evaluation of Early Retransmit
Open this publication in new window or tab >>Enhancing SCTP Loss Recovery: An Experimental Evaluation of Early Retransmit
2008 (English)In: Computer Communications, ISSN 0140-3664, E-ISSN 1873-703X, Vol. 31, no 16, 3778-3788 p.Article in journal (Refereed) Published
Abstract [en]

To reduce cost and provide more flexible services, telecommunication operators are currently replacing traditional circuit-switched telephony networks with packet-switched IP networks. To support the stringent requirements of telephony signaling (SS7), the SIGTRAN working group of the IETF specified the transport protocol SCTP. SCTP was developed to overcome a number of problems that follow from using TCP for signaling transport. However, the design of SCTP was to a great extent still based on TCP, and some problems related to signaling transport were inherited. For example, the loss recovery mechanisms in SCTP are almost identical to those of TCP. This is a problem as signaling traffic has stringent requirements on timely message delivery. TCP was not designed to meet stringent requirements on timely message delivery, and therefore the loss recovery was not optimized for it. To optimize SCTP’s loss recovery for signaling traffic, we consider the loss recovery enhancement early retransmit. To make early retransmit even better suited for signaling traffic we propose a packet-based version, which was also recently included in the early retransmit specification. By experimentally evaluating this algorithm, we show that the packet-based early retransmit algorithm, in some cases, can reduce SCTP’s loss recovery time by 62%.

Place, publisher, year, edition, pages
Amsterdam: Elsevier, 2008
National Category
Computer Systems
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-2857 (URN)10.1016/j.comcom.2008.04.024 (DOI)
Available from: 2008-10-16 Created: 2008-10-16 Last updated: 2017-12-07Bibliographically approved
3. Improved Loss Detection for Signaling Traffic in SCTP
Open this publication in new window or tab >>Improved Loss Detection for Signaling Traffic in SCTP
2008 (English)In: IEEE International Conference on Communications (ICC 08), IEEE , 2008, 5886-5891 p.Conference paper, Published paper (Refereed)
Abstract [en]

The Stream Control Transmission Protocol (SCTP) was designed by the IETF as a viable solution for transportation of signaling traffic within IP-based networks. Signaling traffic is different from ordinary TCP bulk traffic in many ways. One example is that the requirement of timely delivery usually is much stricter. However, the management of the SCTP retransmission timer is not optimally designed considering this requirement. Basically, the management algorithm, unnecessarily, extends the time needed for loss detection. This paper presents a new management algorithm that is able to maintain a correct state of the retransmission timer, which eliminates this particular problem. In addition, the paper also compares the performance of the two management algorithms in an emulated signaling environment, using the lksctp implementation of SCTP. The results show that the proposed algorithm is able to provide significant reductions in loss recovery time. In some cases, the time needed to recover from packet loss is reduced with as much as 43%.

Place, publisher, year, edition, pages
IEEE, 2008
National Category
Computer Systems
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-2859 (URN)10.1109/ICC.2008.1100 (DOI)978-1-4244-2075-9 (ISBN)
Available from: 2008-10-16 Created: 2008-10-16 Last updated: 2014-11-21Bibliographically approved
4. SCTP: Designed for Timely Message Delivery?
Open this publication in new window or tab >>SCTP: Designed for Timely Message Delivery?
2011 (English)In: Telecommunications Systems, ISSN 1018-4864, E-ISSN 1572-9451, Vol. 47, no 3-4, 323-336 p.Article in journal (Refereed) Published
Abstract [en]

To reduce cost and provide more flexible services, telecommunication operators are currently replacing traditional telephony networks with IP-networks. To support the requirements of telephony signaling in IP-networks, SCTP was standardized. SCTP solves a number of problems that follows from using TCP for telephony signaling transport. However, the design of SCTP is still largely based on TCP, and most of SCTP's data transmission mechanisms are inherited from TCP. Signaling traffic has stricter requirements of timely delivery than TCP bulk traffic. However, such requirements are not supported optimally by the inherited TCP mechanisms. We therefore argue that SCTP is not fully designed for timely message delivery. In this article we present and evaluate two loss recovery adaptations that enhance the timeliness of SCTP: Early Retransmit and a modified RTO management algorithm. In addition, we evaluate an adapted Nagle-like algorithm. The results from our evaluation show a significant reduction of message delivery times. In many of the experiments, delivery times were reduced with at least 30-50%. Furthermore, in some situations, message delivery times were reduced with up to 70%, using the modified Nagle algorithm.

Keyword
SCTP, TCP, loss recovery, nagle, network emulation
National Category
Computer Systems
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-2860 (URN)10.1007/s11235-010-9321-3 (DOI)000291242600012 ()
Available from: 2008-11-25 Created: 2008-10-16 Last updated: 2017-12-07Bibliographically approved
5. Enhanced Metric Caching for Short TCP Flows
Open this publication in new window or tab >>Enhanced Metric Caching for Short TCP Flows
2012 (English)In: Proceedings of the IEEE International Conference on Communications (ICC 2012), IEEE Press, 2012, 1209-1213 p.Conference paper, Published paper (Refereed)
Abstract [en]

Internet-based applications that require low latency are becoming more common. Such applications typically generate traffic consisting of short, or bursty, TCP flows. As TCP, instead, is designed to optimize the throughput of long bulk flows there is an apparent mismatch. To overcome this, a lot of research has recently focused on optimizing TCP for short flows as well. In this paper, we identify a performance problem for short flows caused by the metric caching conducted by the TCP control block interdependence mechanisms. Using this metric caching, a single packet loss can potentially ruin the performance for all future flows to the same destination by making them start in congestion avoidance instead of slow-start. To solve this, we propose an enhanced selective caching mechanism for short flows. To illustrate the usefulness of our approach, we implement it in both Linux and FreeBSD and experimentally evaluate it in a real test-bed. The experiments show that the selective caching approach is able to reduce the average transmission time of short flows by up to 40%.

Place, publisher, year, edition, pages
IEEE Press, 2012
Keyword
TCP, Caching, TCBI, sharing, short flows, congestion control
National Category
Communication Systems
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-13632 (URN)10.1109/ICC.2012.6364516 (DOI)000312855701103 ()978-1-4577-2051-2 (ISBN)978-1-4577-2052-9 (ISBN)
Conference
IEEE International Conference on Communications (ICC 2012), June 2012, Ottawa, Canada
Available from: 2012-06-13 Created: 2012-06-13 Last updated: 2016-10-15Bibliographically approved
6. Recent Trends in TCP Packet-Level Characteristics
Open this publication in new window or tab >>Recent Trends in TCP Packet-Level Characteristics
2011 (English)In: Proceedings of the 7th International Conference on Networking and Services (ICNS), Venice/Mestre, Italy: IARIA , 2011, 179-195 p.Conference paper, Published paper (Refereed)
Abstract [en]

Up-to-date TCP traffic characteristics are essential for research and development of protocols and applications. This paper presents recent trends observed in 70 measurements on backbone links from 2006 and 2009. First, we provide general characteristics such as packet size distributions and TCP option usage. We confirm previous observations such as the dominance of TCP as transport and higher utilization of TCP options. Next, we look at out-of-sequence (OOS) TCP segments. OOS segments often have negative effects on TCP performance, and therefore require special consideration. While the total fraction of OOS segments is stable in our measurements, we observe a significant decrease in OOS due to packet reordering (from 22.5% to 5.2% of all OOS segments). We verify that this development is a general trend in our measurements and not caused by single hosts/networks or special temporal events. Our findings are surprising as many researchers previously have speculated in an increased amount of reordering.

Place, publisher, year, edition, pages
Venice/Mestre, Italy: IARIA, 2011
Keyword
traffic measurement; TCP; reordering
National Category
Computer Systems
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-8878 (URN)978-1-61208-133-5 (ISBN)
Conference
The 7th International Conference on Networking and Services (ICNS), Venice/Mestre, Italy, May 2011
Available from: 2011-12-07 Created: 2011-12-07 Last updated: 2014-11-21Bibliographically approved
7. Packet Reordering in TCP
Open this publication in new window or tab >>Packet Reordering in TCP
2011 (English)In: Proceedings of the IEEE GLOBECOM Workshop CCNet, IEEE Press, 2011, 136-141 p.Conference paper, Published paper (Refereed)
Abstract [en]

Packet reordering is now considered naturally prevalent within complex networks like the Internet. When packets are reordered, the performance of transport protocols like TCP is severely hurt. To overcome performance issues a number of mitigations have been proposed. While evaluations have shown the success of such mitigations, most have not considered realistic scenarios where other impairments are present. Furthermore, most studies only evaluate the performance of long-lived TCP flows, although short-lived flows are the most common. In this paper we evaluate Linux's built-in reordering mitigations and the TCP-NCR proposal using real protocol implementations. The results show that Linux and TCP-NCR are able to provide good protection against reordering when no other impairments are present. For flows that also experience packet loss, the performance is dominated by the negative effect of these losses. Results also indicate that short-lived flows are sensitive to how reordering mitigation is conducted. Linux was able to improve the performance of short flows slightly, while TCP-NCR performed worse than TCP without reordering protection.

Place, publisher, year, edition, pages
IEEE Press, 2011
National Category
Computer Systems
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-8880 (URN)000304097200026 ()978-1-4673-0038-4 (ISBN)978-1-4673-0039-1 (ISBN)
Conference
The IEEE GLOBECOM Workshop CCNet, Houston, USA, December 2011
Available from: 2011-12-07 Created: 2011-12-07 Last updated: 2016-10-15Bibliographically approved
8. Impact of Multi-path Routing on TCP Performance
Open this publication in new window or tab >>Impact of Multi-path Routing on TCP Performance
Show others...
2012 (English)In: 2012 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM 2012), Washington, DC: IEEE Press, 2012, 1-3 p.Conference paper, Published paper (Refereed)
Abstract [en]

Routing packets over multiple disjoint paths towards a destination can increase network utilization by load-balancing the traffic over the network. The drawback of load-balancing is that different paths might have different delay properties, causing packets to be reordered. This can reduce TCP performance significantly, as reordering is interpreted as a sign of congestion. Packet reordering can be avoided by letting the network layer route strictly on flow-level. This will, however, also limit the ability to achieve optimal network throughput. There are also several proposals that try to mitigate the effects of reordering at the transport layer. In this paper, we perform an initial evaluation of such TCP reordering mitigations in multi-radio multi-channel wireless mesh networks when using multi-path routing. We evaluate two TCP reordering mitigation techniques implemented in the Linux kernel. The transport layer mitigations are compared using different multi-path routing strategies. Our findings show that, in general, flow-level routing gives the best TCP performance and that transport layer reordering mitigations only marginally can improve performance.

Place, publisher, year, edition, pages
Washington, DC: IEEE Press, 2012
Keyword
TCP, reordering, wireless mesh networks, multi-channel, multi-radio, multi-path
National Category
Communication Systems
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-13633 (URN)10.1109/WoWMoM.2012.6263723 (DOI)978-1-4673-1238-7 (ISBN)
Conference
The 13th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM 2012), June 2012, San Francisco, USA
Available from: 2012-06-13 Created: 2012-06-13 Last updated: 2017-12-06Bibliographically approved
9. Emulation Support for Advanced Packet Reordering Models
Open this publication in new window or tab >>Emulation Support for Advanced Packet Reordering Models
2010 (English)In: 2010 IEEE International Conference on Communications, Cape Town, South Africa: IEEE Communications Society, 2010Conference paper, Published paper (Refereed)
Abstract [en]

From being regarded as a pathological event, packet reordering is now considered to be naturally prevalent within the Internet. When packets are reordered, the performance of transport protocols like TCP can be severely hurt. To overcome performance problems a number of mitigations have been proposed. Common for most proposals is, however, the lack of evaluations using real protocol implementations and good models of packet reordering. In this paper we highlight the need for detailed reordering models, and implement support for such models in the KauNet network emulator. To demonstrate the importance of using detailed models we present an experimental example.

Place, publisher, year, edition, pages
Cape Town, South Africa: IEEE Communications Society, 2010
National Category
Computer Science
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-9697 (URN)10.1109/ICC.2010.5501900 (DOI)978-1-4244-6404-3 (ISBN)
Conference
IEEE International Conference on Communications (ICC)
Available from: 2012-02-08 Created: 2012-02-08 Last updated: 2014-11-21Bibliographically approved

Open Access in DiVA

Transport-Layer Performance(308 kB)1030 downloads
File information
File name FULLTEXT01.pdfFile size 308 kBChecksum SHA-512
877cdfdf91ca9aa96d8910df4c0f83f3750797c74298d53aca5772e63fc806fa2037f22b55a9ba4c5ac00d61ae240c856cf96852babb4c525cfd0a93fdc11e02
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Hurtig, Per
By organisation
Department of Computer Science
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 1030 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: 442 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