How network asymmetry affects TCP

Several emerging wireline and wireless access network technologies exhibit asymmetry in their network characteristics. For instance, cable modem networks exhibit significant bandwidth asymmetry, while packet radio networks exhibit media access asymmetry. A high degree of asymmetry can have an adverse effect on the performance of feedback-based transport protocols. We study the effects of bandwidth and media access asymmetry on the performance of the TCP protocol. We identify the fundamental reasons for the mismatch between TCP and asymmetric networks, and then present several techniques to address this problem     

The impact of multihop wireless channel on TCP performance

This paper studies TCP performance in a stationary multihop wireless network using IEEE 802.11 for channel access control. We first show that, given a specific network topology and flow patterns, there exists an optimal window size W* at which TCP achieves the highest throughput via maximum spatial reuse of the shared wireless channel. However, TCP grows its window size much larger than W* leading to throughput reduction. We then explain the TCP throughput decrease using our observations and analysis of the packet loss in an overloaded multihop wireless network. We find out that the network overload is typically first signified by packet drops due to wireless link-layer contention, rather than buffer overflow-induced losses observed in the wired Internet. As the offered load increases, the probability of packet drops due to link contention also increases, and eventually saturates. Unfortunately the link-layer drop probability is insufficient to keep the TCP window size around W'*. We model and analyze the link contention behavior, based on which we propose link RED that fine-tunes the link-layer packet dropping probability to stabilize the TCP window size around W*. We further devise adaptive pacing to better coordinate channel access along the packet forwarding path. Our simulations demonstrate 5 to 30 percent improvement of TCP throughput using the proposed two techniques.     

数据包大小对TCP流性能的影响

在互联网时代,如何提高网络通信质量一直是研究热点,当前网络通信大部分数据流都采用TCP流。对于TCP流性能的影响因素如丢包、时延已有大量研究,但是数据包大小对其的影响却罕有涉及。另一方面,网络通信的质量很大程度上取决于路由器的性能,而路由器的性能又很大程度上取决于路由器的缓存设置。因此本文从数据包大小这一新的切入点入手,研究在不同的路由器缓存下,其对TCP流性能的影响。论文介绍了TCP协议、路由器缓存、数据包等相关概念,提出了实验方案的网络拓扑模型,选择了NS2平台进行网络仿真。在实验中,我们通过改变数据包大小和路由器缓存容量,得到了对应的实验数据并进行了分析整理,总结出了TCP流吞吐量和丢包率在数据包大小改变时的变化规律,即丢包率随数据包大小的增加呈线性增长,路由器缓存越小丢包率越大;TCP流的吞吐量随数据包大小的增加缓慢变大,路由器缓存达到一定值后不再成为瓶颈因素。     

The effect of correlated errors on the performance of TCP

Wireless channels are known to introduce correlated bursts of errors at the physical layer. Although these errors affect the performance at all layers of a protocol stack, their precise impact, especially at the higher layers, is not completely understood. We study the effect of error correlations on the throughput of a single transport control protocol (TCP) Tahoe connection. We find that TCP Tahoe performs better in the presence of clustered errors. This suggests that techniques that reduce channel memory may be undesirable     

The effect of Mobile IP handoffs on the performance of TCP

Mobile IP is a standard for handling routing for hosts that have moved from their home network. This paper studies the costs of the Mobile IP handoff that occurs when a mobile host moves between networks. Experiments were carried out with Mobile IP and TCP over varying network conditions to observe the effect of handoffs on the transmission. This paper shows that although Mobile IP may be appropriate for current applications, its long handoff periods make it unsuitable for the future.     

Optimizing TCP forwarder performance

A TCP forwarder is a network node that establishes and forwards data between a pair of TCP connections. An example of a TCP forwarder is a firewall that places a proxy between a TCP connection to an external host and a TCP connection to an internal host, controlling access to a resource on the internal host. Once the proxy approves the access, it simply forwards data from one connection to the other. We use the term TCP forwarding to describe indirect TCP communication via a proxy in general. This paper characterizes the behavior of TCP forwarding, and illustrates the role TCP forwarding plays in common network services like firewalls and HTTP proxies. We then introduce an optimization technique, called connection splicing, that can be applied to a TCP forwarder, and report the results of a performance study designed to evaluate its impact. Connection splicing improves TCP forwarding performance by a factor of two to four, making it competitive with IP router performance on the same hardware     

Reducing the impact of false time out on TCP performance in TCP over OBS networks

Random burst contention losses plague the performance of Optical Burst Switched networks. Such random losses occur even in low load network condition due to the analogous behavior of wavelength and routing algorithms. Since a burst may carry many packets from many TCP sources, its loss can trick the TCP sources to conclude/infer that the underlying (optical) network is congested. Accordingly, TCP reduces sending rate and switches over to either fast retransmission or slow start state. This reaction by TCP is uncalled-for in TCP over OBS networks as the optical network may not be congested during such random burst contention losses. Hence, these losses are to be addressed in order to improve the performance of TCP over OBS networks. Existing work in the literature achieves the above laid objective at the cost of violating the semantics of OBS and/or TCP. Several other works make delay inducing assumptions. In our work, we introduce a new layer, called Adaptation Layer, in between TCP and OBS layers. This layer uses burst retransmission to mitigate the effect of burst loss due to contention on TCP by leveraging the difference between round trip times of TCP and OBS. We achieve our objective with the added advantage of maintaining the semantics of the layers intact.     

TCP performance issues over wireless links

This article discusses the problems arising when the TCP/IP protocol suite is used to provide Internet connectivity over existing and emerging wireless links. Due to the strong drive toward wireless Internet access through mobile terminals, these problems must be carefully studied in order to build improved systems. We review wireless link characteristics using wireless LANs and cellular communications systems as examples. We then outline the performance problems of the TCP/IP protocol suite when employed over those links, such as degraded TCP performance due to mistaking wireless errors for congestion. We present various proposals for solving these problems and examine their benefits and limitations. Finally, we consider the future evolution of wireless systems and the challenges that emerging systems will impose on the Internet protocol suite     

Potential performance bottleneck in Linux TCP

Transmission control protocol (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 modelling and practical experiments; finally, we propose and test one possible solution to resolve this performance bottleneck in Linux TCP. Copyright © 2007 John Wiley & Sons, Ltd.     

Improving TCP performance in mobile networks

In this letter, a new transport layer mechanism is proposed to improve the performance of transport control protocol (TCP) in mobile networks. The proposed mechanism is comprised of two parts: a loss classifier (LC) and a congestion window extrapolator (CWE). Based on LC, the cause of packet loss during roaming is determined. If the loss is considered to be caused by congestion in the wireline, the congestion window is halved; otherwise, the packet is considered to be lost in the last hop, the wireless portion, and the sender adjusts the size of the congestion window based on CWE. We conduct simulations to evaluate the performance of the proposed mechanism. The results show that our mechanism significantly improves TCP performance as compared with existing solutions for mobile networks.     

A detailed experimental performance evaluation on TCP over UBR

The ATM service category UBR is intended for non-real-time applications that do not require guaranteed QoS commitments. With additional, relatively inexpensive control functions such as packet discard schemes, UBR could become a cost-effective alternative for the transmission of data traffic, offering a straightforward and flexible solution as opposed to nrt-VBR and GFR that applies stricter traffic specifications as well as ABR with its sophisticated and complex rate-control protocol. This paper presents the results obtained from a comprehensive set of experiments with TCP over UBR, comprising measurements taken on different protocol layers. The goal is to experimentally investigate the performance of UBR to carry TCP traffic, to evaluate the performance gain achievable by packet discard schemes and TCP parameter tuning, to study the influence of the TCP implementation, and in a final step, to relate the measurements to simulation results. This revised version was published online in August 2006 with corrections to the Cover Date.     

The impact of NRZ data asymmetry on the performance of a spacetelemetry system

The author derives an expression for the power spectral density of an asymmetric nonreturn-to-zero (NRZ) data stream. This formula is used to investigate how the data bandwidth varies with data asymmetry. The threshold levels of undesired spectral components that fall into the carrier tracking loop bandwidth are determined by examining the derived spectral density. Based on this formula, a simple technique is developed for the computation of bit signal-to-noise ratio (SNR) degradation due to data asymmetry. The telemetry bit SNR degradations derived using this technique are compared with the results obtained previously by M.K. Simon et al. (1978) and with measurements by the electronic systems test laboratory (ESTL) at the Lyndon B. Johnson Space Center     

TCP/IP performance over satellite links

Achieving high data rates using TCP/IP over satellite networks can be difficult. This article explains some of the reasons TCP/IP has difficulty with satellite links. We present solutions to some problems, and describe the state of the research on some the unsolved problems     

TCP traffic performance improving in LTE-A networks

This paper presents a novel way to improve Transmission Control Protocol (TCP) performance of the users at the edge areas of the macro cells in Long Term Evolution Advanced (LTE-A) systems. Previous works on improving wireless TCP performance are reviewed and current considerations on TCP in LTE-A are explained. However, those solutions are neither too complex nor limited to some presuppositions which are too restricting for the deployment of LTE-A networks. In this paper a substituted TCP acknowledgement transmission scheme based on Automatic Repeat reQuest (ARQ) information in layer 2 is proposed. The simulation result shows that the proposed method can reduce the delay and improve the throughput of the edging users of the cell, as well as reducing radio resources in LTE-A macro cells.     

Improving performance of TCP over mobile wireless networks

Mobile IP is a network layer protocol for handling mobility of hosts in the Internet. However, mobile IP handoff causes degradation of TCP performance. Hence, there is a need for improving performance of TCP over mobile IP in wireless mobile networks. We propose an approach which handles losses due to both wireless link errors and host mobility. To handle losses due to host mobility, a method for seamless handoff is proposed. Empirical results show that the scheme provides substantial improvement of performance.

光突发交换网络的动态TCP特性研究

通过仿真研究了动态业务竞争环境下,不同TCP版本在OBS网络中的传输性能。研究中,以TCP在OBS网络中传送一个固定大小的文件所需的时间作为性能指标,此外,详细分析了突发丢失的内部机制和造成不同TCP版本性能差异的原因。结果表明,TCP SACK性能最好。     

ABR performance in presence of bursty TCP traffic

The available bit rate (ABR) service class is a solution for the integration of data traffic in asynchronous transfer mode networks. Many algorithms have been proposed to implement ABR services. The authors present simulation results showing poor performance by a common ABR algorithm when supporting TCP bursty traffic. As a solution to this problem, the authors propose time averaging of the parameters calculated by the ABR algorithms     

Dispersion and asymmetry effects of ADI-FDTD

In this paper, a generalized derivation of the alternating direction implicit finite-difference time-domain algorithm based on operator splitting is proposed. The formulation follows the notation of the finite integration technique. A straightforward proof of stability is given and the numerical dispersion formula is presented and verified by numerical experiments. As an additional parasitic effect, the asymmetric behavior of the algorithm even for exactly symmetric setups is revealed. Both the dispersion error and the asymmetry error are discussed in terms of the applicability of ADI for low-frequency problems.     

Enhancing TCP performance with a load-adaptive RED mechanism

This paper describes a technique for enhancing the effectiveness of RED by dynamically changing the threshold settings as the number of connections (and system load) changes. Using this technique, routers and switches can effectively control packet losses and TCP timeouts while maintaining high link utilization. Copyright © 2001 John Wiley & Sons, Ltd.