Delay-based congestion avoidance for TCP

Martin, Jim; Nilsson, Arne A.; Rhee, Injong

doi:10.1109/tnet.2003.813038

Cited by 109 publications

(63 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, we focus on evaluating and improving congestion prediction from end-hosts. We show that such congestion prediction is more accurate than characterized by studies in [21,26]. While it is possible to further improve the prediction ability of end-host based congestion estimators, it may not be possible to entirely eliminate the noise/uncertainty in the signal.…”

Section: Sigcomm'07mentioning

confidence: 76%

“…We refer to the work in this area as end-host delay-based congestion avoidance. Some of the representative schemes in this area are CARD [17], TRI-S [29], DUAL [30], Vegas [7], and CIM [21].…”

Section: Sigcomm'07mentioning

confidence: 99%

“…Comparatively, updating the TCP stack at end-hosts is a relatively easier task. But end-host delay-based schemes have been assailed by doubts about the accuracy and effectiveness of congestion prediction at end-hosts [21,24,26].…”

Section: Sigcomm'07mentioning

confidence: 99%

“…In Vegas [7], the authors propose comparing the achieved throughput to the expected throughput based on the minimum observed RTT for predicting congestion. In CIM [21], the authors propose comparing the moving average of a small number of RTT samples to the moving average of a large number of RTT samples for determining if there is any congestion. In TCP-BFA [3], the authors propose monitoring the variance of the RTT for preventing the bottleneck link from filling up.…”

Section: Overview Of Related Workmentioning

confidence: 99%

“…Several other studies [6,21,24,26] have focused on understanding whether delay-based congestion prediction can reliably work in the real Internet. Some of the issues raised by these studies are unique to end-host based mechanisms, while others have received similar attention in router based schemes.…”

Section: Overview Of Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Emulating AQM from end hosts

Bhandarkar

Reddy

Zhang

et al. 2007

SIGCOMM Comput. Commun. Rev.

View full text Add to dashboard Cite

In this paper, we show that end-host based congestion prediction is more accurate than previously characterized. However, it may not be possible to entirely eliminate the uncertainties in congestion prediction. To address these uncertainties, we propose Probabilistic Early Response TCP (PERT). PERT emulates the behavior of AQM/ECN, in the congestion response function of end-hosts. We present fluid-flow analysis of PERT/RED and PERT/PI, versions of PERT that emulate router-based RED and PI controllers. Our analysis shows that PERT/RED has better stability behavior than router-based RED. We also present results from ns-2 simulations to show the practical feasibility of PERT. The scheme presented here is general and can be used for emulating other AQM algorithms.

show abstract

Section: Sigcomm'07mentioning

confidence: 76%

Section: Sigcomm'07mentioning

confidence: 99%

Section: Sigcomm'07mentioning

confidence: 99%

Section: Overview Of Related Workmentioning

confidence: 99%

Section: Overview Of Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Emulating AQM from end hosts

Bhandarkar

Reddy

Zhang

et al. 2007

SIGCOMM Comput. Commun. Rev.

View full text Add to dashboard Cite

show abstract

Adaptive Transmission Control Protocol‐trunking flow control mechanism for supporting proxy‐assisted video on demand system

Tong

2011

Int J Communication

View full text Add to dashboard Cite

SUMMARY Video streaming has been challenged by the best‐effort service inherently provided by the Internet. Transmission Control Protocol (TCP) is sensitive to traffic congestion, and current TCP is insufficient to offer stable and high throughput bandwidth for video transmissions. Although many investigations have been proposed to deal with the inefficient problem of TCP protocol, such as Stream Control Transmission Protocol, these mechanisms and protocols are still not well employed by current Internet and used by Hypertext Transfer Protocol (HTTP). Adaptive TCP‐trunking flow control (ATCP+), which is a segment‐based flow control scheme built upon TCP protocol, is proposed in the paper. ATCP+ dynamically adjusts the transmitted segment size and makes multiple TCP connections be trunked together based on network condition, in order to optimize all TCP connection throughputs efficiently. The proposed scheme is implemented through HTTP 1.1. Experiments show that the proposed method can achieve stable throughput for smooth multimedia presentation on numerous network states, and the scheme can be handily applied on general web servers. Lastly, ATCP+ presents a cost‐effective video streaming solution in real deployment. Copyright © 2011 John Wiley & Sons, Ltd.

show abstract

Potential performance bottleneck in Linux TCP

Crawford

2007

Int J Communication

View full text Add to dashboard Cite

TCP is the most widely used transport protocol on the Internet today. Over the years, especially recently, due to requirements of high bandwidth transmission, various approaches have been proposed to improve TCP performance. The Linux 2.6 kernel is now preemptible. It can be interrupted mid-task, making the system more responsive and interactive. However, we have noticed that Linux kernel preemption can interact badly with the performance of the networking subsystem. In this paper we investigate the performance bottleneck in Linux TCP. We systematically describe the trip of a TCP packet from its ingress into a Linux network end system to its final delivery to the application; we study the performance bottleneck in Linux TCP through mathematical modeling and practical experiments; finally we propose and test one possible solution to resolve this performance bottleneck in Linux TCP.

show abstract

Delay-based congestion avoidance for TCP

Cited by 109 publications

References 31 publications

Emulating AQM from end hosts

Emulating AQM from end hosts

Adaptive Transmission Control Protocol‐trunking flow control mechanism for supporting proxy‐assisted video on demand system

Potential performance bottleneck in Linux TCP

Contact Info

Product

Resources

About