The Variation in RTT of Smooth TCP

Size: px
Start display at page:

Download "The Variation in RTT of Smooth TCP"

Transcription

1 The Variation in RTT of Smooth TCP Elvis Vieira and Michael Bauer University of Western Ontario Abstract Due to the way of Standard TCP is defined, it inherently provokes variation in RTT. A variation of TCP, referred to as Smooth TCP can, however, be configured to minimize such variations. In this paper, we review how Smooth TCP is defined and compare it with Standard TCP in an environment subject to packet errors. Such problems are very common in wireless networks, where sometimes Standard TCP considers a packet loss erroneously as a packet drop and as a consequence, large variations in RTT are introduced. 1. Introduction Previous work [3,4,5,6] has demonstrated the existence of design problems related to the way congestion is signaled to the TCP sender, which is done through packet drops. Indeed, packets drops should indicate to the TCP sender that there is a router queue, somewhere between the sender and the receiver, which is full. Therefore, the sender should decrease its sending rate in order to return the queue return to a normal situation. But this is not always true. A packet can be dropped for reasons other than a full queue, such as an electrical noise in the communication line. If such drops happen, there is no reason to decrease the sending rate. Consequently, the sender is penalized unnecessarily because of this signal uncertainty. Additionally, using packet drops as the main congestion indication creates another problem. Once a packet is dropped in a queue, the sender does not know immediately, but it will take a time longer than one round trip time (RTT) to find out. This temporal gap makes the TCP halve the window size, a hard penalty in high-speed networks. The signal uncertainty and temporal gap problems have, as one of their consequence, large and unnecessary variations of RTT. Our work suggests that these problems can be addressed by introducing the concept of smoothness. Briefly, a congestion control mechanism, which has this smoothness characteristic, should react to congestion signals in a less harsh way than just halving its window size, as does Standard TCP. This is because if the congestion control mechanism is smooth then there is almost no signal uncertainty and the temporal gap is minimized. Particularly, this paper describes an example of such mechanism, called Smooth TCP, and its characteristics of fairness and variation in RTT in face of packet drops is examined. The remainder of this paper is organized as follows. Section 2 discusses the motivation behind this research and some related work. Section 3 introduces a definition of smoothness, which is given in the context of four properties. Based on these properties, a set of functions that can be used to derive smooth congestion control mechanisms is given in Section 4 and introduces Smooth TCP. Section 5 reports on some simulation results comparing Standard TCP to Smooth TCP in situations in which there are packet drops. The final section provides a summary and conclusions. 2. Motivations and Related Work The work in [2] suggests that the threat to the stability of the Internet originates not from flows having alternative congestion controls, but from those not having any congestion control at all, such as largescale multicasting flows or some real-time traffic. The stability of the Internet does not require that flows decrease their sending rate by halving their window sizes, but rather that to avoid congestion collapse it is only necessary to use a lower sending rate when there is a high loss rate. Two key issues related to the TCP performance can be identified in links subjected to errors: its inability to separate the packet losses due to congestion from those due to other problems and its reliance on the timer to recover from a failed retransmission cycle. One of the effects of these issues is that spurious retransmission timeouts can reduce the performance of TCP as they can start unnecessary retransmissions of segments. These problems have been noted and addressed by others: Eifel Algorithm: In [3], Ludwig and Katz proposed an algorithm, called Eifel, to deal with spurious retransmission timeouts. It proposes an alteration in

2 TCP that uses either timestamps sent in TCP segments, or two of the reserved bits in the TCP header to determine whether there was any packet loss due to some error when an ACK arrived in the sender. Westwood TCP: In [4] and [5] Westwood TCP is introduced in which instead of dropping the window size by half of the value it was before when a packet is lost, it uses a linear decrease of the congestion window depending on the bandwidth measured on each ACK arrival. This results in a performance of up to four times that of the Standard TCP when spurious errors occur. F-RTO: The F-RTO algorithm is described in [6]. F-RTO only affects the TCP sender when there is a retransmission timeout. Otherwise it behaves as Standard TCP. A TCP-friendly mechanism is described in [2] to control unicast traffic using equation-based congestion control. This mechanism avoids reducing the sending rate to react to a single packet drop. Instead, the sender adjusts its sending rate according to the measured rate of loss events in a single round-trip time. The Family of Binomial Congestion Control Algorithms [7] also looks at the generalization of congestion control; the work in [7] was the basis for the idea of congestion control functions in the present work. 3. Smoothness A congestion control mechanism will be said to have smoothness characteristics if it has four five properties: a smooth curve, vertical smoothness, horizontal smoothness, proactive smoothness and precision property: A) Smooth Curve Property: An important characteristic of the TCP s standard congestion control algorithm is the action of halving its congestion window in face of a packet drop. This sudden decrease marks a discontinuation point on its evolution curve, given origin to a fast and large increase in the RTT. As a result, the first property required for a smooth congestion control is that its curve should not have discontinuation points or, at least they should be as few as possible. This requirement is called the smooth curve property. B) Vertical Smooth Property: Formally, the congestion control uses a function f(u) to translate events u into window sizes. When f(u) is a function of a variable where bursts with very large amplitude can occur, like RTT, this cannot be done linearly, since variations of RTT near 0 are more important or significant than variations among large values. For this reason, a hyperbolic tangent function is proposed to introduce vertical smoothness, making sure certain signals remains within a specified range. C) Horizontal Smooth Property: Sometimes, for the congestion control it is important to know the frequency of an event (or its rate) instead of its amplitude. Consequently in f(u), u should mean the rate of those events. In our work u can be the smooth average rate as described in [9] 1. D) Proactive Property: Suppose a packet is dropped at a router because its queue is full. In order for the sender to decrease its sending rate, the receiver sends duplicate acknowledgment packets, which arrive approximately 1 RTT (more precisely, 1 RTT and 3 duplicate acknowledgment arrivals ) in the sender. This relatively long time, which we refer to as a temporal gap, is one of the principal reasons TCP reacts by halving the window [10]. We can do better if other metrics are used also to signal congestion. Our work proposes the use of the following metrics: RTT ([11] details the relation between the router queue size and RTT) and ICMP-Source Quench (ICMP-SQ) Messages. Explicit Congestion Notification (ECN) [12] can be used instead of ICMP-SQ, but the latter has a smaller temporal gap since the messages are to send directly to the sender (in the opposite direction). E) Precision Property: Another problem is that a packet drop is not always the best way to signal congestion. A packet drop does not always means that the packet was discarded as a result of congestion in a router queue. For example, a packet could be dropped because of a CRC error. For that reason, we say that there is a signal uncertainty. Algorithms like Eifel [3] and F-RTO [6] eliminate some of the uncertainties, but not completely. The possibility of using ICMP-SQ messages or ECN in a proactive manner also enhances the precision of the congestion signalization. A router only sends them when the threshold of a RED queue is reached. On the other hand, RTT increases could be provoked by events other than congestion, like changes or a route table update. Therefore, RTT would not be as precise as ICMP-SQ or ECN. 4. Smooth Congestion Control Algorithms 4.1 Smooth Algorithms For our notion of smoothness, we would like to be able to make appropriate adjustments to the congestion control window. To do this, we think of the congestion window function w as being defined as a function of some set of variables p 1,..,p i,..,p n describing the network state and congestion conditions. We 1 The smooth average of n terms is u(u n )=(1- α)* u(u n-1 )+α*u n where α is ⅛ or ¼.

3 elaborate on which variables shortly. Most importantly we are interested in changes dw in w, that is an increment or decrement to the existing window size depending on changes in some measured attributes, say p 1,..,p i,..,p n., of TCP behavior. This allows formulating the increment (or decrement) D as: (1) D = dp dp i... + dp n p1 pi p n As per our discussion of smoothness previously, we assume that each partial derivative is of the form: = A p + C tanh( B (p M )) p i p i p i i (2) p i i Eq. (1) defines a family of functions. When such a family includes only smooth functions, we call it a Family of Smooth Congestion Control Algorithms (or briefly, Smooth Algorithms). 4.2 Fairness In order to enforce Smooth TCP connections to share the same bandwidth approximately equally, the following idea, inspired from Standard TCP, is used in the extension to add fairness: Let us call D the increment given by Eq. (1). Then the final value dw added to w should be: dw =D/w if D > 0 or, (3) dw =D * w if D < 0 Consequently, having n connections sharing different window sizes, after a certain amount of dp i variations, they will have approximately the same window size. This guarantees that those connections having the largest window sizes suffer the smallest window increments. On the other hand, Eq. (3) multiplies the decrement (D < 0) by the current window. This guarantees that connections having the smallest window sizes suffer the smallest decrements. 5. Smooth TCP We can then introduce the form of the functions for the partial derivatives that define the particular instance of Smooth Algorithms called Smooth TCP: D = dj + dx δ j δ x + df δ f + de δ e + dq δ q (4) where j is the variation in RTT (as per above), x is the variation in the number of timeout retransmits, f is variation in the number of fast retransmits, e is the variation of ECN acknowledgments packets and q is the variation in the number of ICMP-SQ messages. Then, the individual partial derivatives are: j = A j + C j tanh( B j ( j + M j )) = A x + C x tanh( B x ( x + M x )) x = A f + C f tanh( B f ( f + M f )) f = A e + C e tanh( B e ( e + M e )) e = A q + C q tanh( B q ( q + M q )) q (5) Hence, Smooth TCP is defined as a family of functions where any instance can be a function of 5 metrics, at most. If the corresponding coefficient A pi or C pi and B pi are different from zero in Eq. (7), then the corresponding metric p i effectively collaborate to final value of dw The Stable State When the network does not suffer any alteration of state, such as adding or removing new TCP connections or other types of flows, each Smooth TCP connection converges to particular window size. This happens because all variables involved in Eq. (14) do not suffer any alteration, that is, dj=dx=df=de=dq=0. So the corresponding window increment dw is zero. If all Smooth TCP connections reach the convergence situation, they can end up having different window size. These values for the window size will not be modified unless some event provokes some change in the network. Having different window sizes in the convergence situation results in different bandwidths for each Smooth TCP connections. 5.2 Fairness Factor Smooth TCP also needs a mechanism to enable it to get out of the stable state and continue its search for a shared bandwidth, which is approximately the same as the other Smooth TCP connections (having the same origin and destination). Adding a new increment κ that is not dependent on any increment of the variables in Eq(14) does the trick: dw = D / w ; if D > 0 (6) dw = D w ; if D 0 where D = δ j dj + dx δ x + df δ f + dq δ q + τ 2 In this case, we are going to call p i as a control metric.

4 Consequently, when any dp i is zeroed, dw = κ. Although not totally correct, κ is called fairness factor. 6. Simulations 6.1 Simulations with Standard TCP Using these equations and algorithms, we explored Smooth TCP in the situation shown in Figure 1 using coefficients given by Table 1. Those coefficients not indicated by Table 1, are assumed be 0.0. In Figure 1, the links between the router and the server are 100 Mbps with latency of 1 ms. The links between the router and the two clients are 0.5 Mbps with latency of 100ms. Modified RED queues were implemented in each connection from the router to the clients in order to send ICMP-SQ messages when the average queue size reaches 3 packets, or to drop a packet (as soon as the average queue size reaches 9 packets). Server1 opens k connections with Client1 and Server2 also opens k connections with Client2. So the total number of connections is 2*k. In each connection, an FTP is started to run continuously (without stopping). Only in the link between router and client1 is provoked a packet drop in a random time after 100s of simulation (assuring the finishing of the Smooth TCP slow-start). 0.5 server router client1 100 RTT Variation 0.5 Figure 1 - Simulated Environment Fast ICMP-SQ Retransmit A r =0.0 A f =0.0 A q =0.0 B r =45.02 B f =4.952 B q = C r =0.025 C f =0.025 C q =0.025 M r =0.0 M f =0.0 M q =0.0 client2 Table 1 Coefficient of Smooth TCP connections Figure 2 and 3 depicts the behavior of Standard TCP and Smooth TCP, respectively, in a situation where there is a packet drop, which is provoked by some other cause than a queue full. Figure 2 - Behavior of Standard TCP These figures show the results of simulating of 180s of Standard TCP and Smoot TCP connections for k=2. The main results can be enumerated as follows: 1) Congestion window: For Standard TCP the congestion window varies quite irregularly. In contrast, Smooth TCP tends to find a stable window size independently of the occurrence of the packet drop. 2) Variation in RTT: With Standard TCP the RTT varies quite a bit, broadly between 0.3s and 0.5s. The RTT in Smooth TCP, however, suffers few and small variations, with the biggest variation occurring when just after the packet drop occurs. This provokes a huge variation because of the way RTT is measured (using TCP timestamp option). After this, however, the RTT for Smooth TCP is very steady around 0.4s. 3) Throughput and Fairness: Standard TCP demonstrates good fairness, as shown in Figure 2, in looking at the throughput. Three connections transfer almost the same amount of data, while the one that suffers a packet drop transfers somewhat less. Figure 3 shows that with fair factor = 0.001, Smooth TCP presents a fairness almost identical to TCP. In general, the fairness of Smooth TCP improves if κ is increased, while it decreases if κ is decreased. However, increasing κ, it also will increase the variation in RTT. 4) ICMP-SQ Messages: For both Standard TCP and Smooth TCP the ICMP-SQ messages increase as the number of the number of connections increases. This is expected since the average queue size increases as the number of connections increases. 6.2 Simulations with Smooth TCP The behavior of Smooth TCP is illustrated in Figure 3.

5 Figure 3 - Behavior of Smooth TCP 7. Final Considerations A new requirement for a congestion control mechanisms for TCP and an instance of such a mechanism was proposed. This mechanism was motivated by the desire to reduce the temporal gap and to improve the precision of congestion signals. Throughout simulations, we concluded that prioritizing the fairness characteristic generally penalizes the low RTT variation of Smooth TCP and vice-versa. It is important because Smooth TCP can be configured to filter the variation in RTT other than due to packet drops. But this filter capacity is limited by how fair Smooth TCP needs to be. Some conclusions of this work are also valid for Standard TCP. For example, much of the RTT variations in Standard TCP are due to its necessity to keep increasing slowly its window. So when a window is reached that provokes a packet drop, TCP can have notion of how much bandwidth it can take. However it is a mechanism that increases the variation of RTT. TCP Westwood: Analytic Model and Performance Evaluation, Proceedings of IEEE Globecom 2001, San Antonio, Texas, Nov, 2001, pp [6] P. Sarolahti, M. Kojo and K. Raatikainen. F-RTO: an enhanced recovery algorithm for TCP retransmission timeouts, ACM SIGCOMM 03 Computer Communication Review, Vol 33-2, ACM Press, 2003, pp [7] D. Bansal and H. Balakrishnam. TCP-Friendly Congestion Control for Real-time Streaming Applications, Technical Report, MIT-LCS-TR-806, M.I.T Laboratory for Computer Science, Cambridge, MA, May, [8] S. Floyd. RFC3649: High-Speed TCP for Large Congestion Windows, Network Working Group, IETF, Dec., [9] V. Paxson and M. Allman. RFC2988: Computing TCP's Retransmission Timer, Network Working Group, IETF, Nov., [10] V. Jacobson. Congestion Avoidance and Control, ACM SIGCOMM 88 Computer Communication Review, ACM Press, 1988, pp [11] G. Appenzeller, I. Keslassy and N. McKeown. Sizing Router Buffers, ACM SIGCOMM 04 Computer Communication Review, 2004, pp [12] K. Ramakrishnan, S. Floyd and D. Black. RFC3168: The Addition of Explicit Congestion Notification (ECN) to IP, Network Working Group, IETF, Sep., [13] Elvis Vieira and Michael Bauer. Smoothness Properties in Congestion Control for TCP, 3 rd International Conference on Computing Communications and Control Technologies, Austin, Texas, Jul, 2005 (to appear). References [1] J. Nagle. RFC0896: Congestion Control in IP/TCP Internetworks, Network Working Group, IETF, Jan., [2] S. Floyd, M. Handley, J. Padhye and J. Widmer. Equation-Based Cong. Control for Unicast Applications: the Extended Version, Technical Report, TR , ICSI, Berkeley, CA, Mar., [3] R. Ludwig and R. Katz. The Eifel Algorithm: Making TCP Robust Against Spurious Retransmissions, Vol 30-1, Jan., 2000, pp [4] M. Gerla, M. Sanadidi, R. Wang, A. Zanella, C. Casetti, S. Mascolo. TCP Westwood: Congestion Window Control Using Bandwidth Estimation, Proc. of IEEE Globecom 2001, Vol 3, San Antonio, Texas, Nov., 2001, pp [5] Zanella, G. Procissi, M. Gerla, and M. Y. Sanadidi.

Open Box Protocol (OBP)

Open Box Protocol (OBP) Open Box Protocol (OBP) Paulo Loureiro 1, Saverio Mascolo 2, Edmundo Monteiro 3 1 Polytechnic Institute of Leiria, Leiria, Portugal, loureiro.pjg@gmail.pt 2 Politecnico di Bari, Bari, Italy, saverio.mascolo@gmail.com

More information

Lecture 21: Congestion Control" CSE 123: Computer Networks Alex C. Snoeren

Lecture 21: Congestion Control CSE 123: Computer Networks Alex C. Snoeren Lecture 21: Congestion Control" CSE 123: Computer Networks Alex C. Snoeren Lecture 21 Overview" How fast should a sending host transmit data? Not to fast, not to slow, just right Should not be faster than

More information

Investigating the Use of Synchronized Clocks in TCP Congestion Control

Investigating the Use of Synchronized Clocks in TCP Congestion Control Investigating the Use of Synchronized Clocks in TCP Congestion Control Michele Weigle Dissertation Defense May 14, 2003 Advisor: Kevin Jeffay Research Question Can the use of exact timing information improve

More information

Congestion Control End Hosts. CSE 561 Lecture 7, Spring David Wetherall. How fast should the sender transmit data?

Congestion Control End Hosts. CSE 561 Lecture 7, Spring David Wetherall. How fast should the sender transmit data? Congestion Control End Hosts CSE 51 Lecture 7, Spring. David Wetherall Today s question How fast should the sender transmit data? Not tooslow Not toofast Just right Should not be faster than the receiver

More information

CC-SCTP: Chunk Checksum of SCTP for Enhancement of Throughput in Wireless Network Environments

CC-SCTP: Chunk Checksum of SCTP for Enhancement of Throughput in Wireless Network Environments CC-SCTP: Chunk Checksum of SCTP for Enhancement of Throughput in Wireless Network Environments Stream Control Transmission Protocol (SCTP) uses the 32-bit checksum in the common header, by which a corrupted

More information

A Survey of Recent Developments of TCP. Sally Floyd ACIRI (AT&T Center for Internet Research at ICSI) October 17, 2001

A Survey of Recent Developments of TCP. Sally Floyd ACIRI (AT&T Center for Internet Research at ICSI) October 17, 2001 A Survey of Recent Developments of TCP Sally Floyd ACIRI (AT&T Center for Internet Research at ICSI) October 17, 2001 IEEE Annual Computer Communications Workshop 1 An overview of this session: This talk:

More information

CS519: Computer Networks. Lecture 5, Part 4: Mar 29, 2004 Transport: TCP congestion control

CS519: Computer Networks. Lecture 5, Part 4: Mar 29, 2004 Transport: TCP congestion control : Computer Networks Lecture 5, Part 4: Mar 29, 2004 Transport: TCP congestion control TCP performance We ve seen how TCP the protocol works Sequencing, receive window, connection setup and teardown And

More information

ROBUST TCP: AN IMPROVEMENT ON TCP PROTOCOL

ROBUST TCP: AN IMPROVEMENT ON TCP PROTOCOL ROBUST TCP: AN IMPROVEMENT ON TCP PROTOCOL SEIFEDDINE KADRY 1, ISSA KAMAR 1, ALI KALAKECH 2, MOHAMAD SMAILI 1 1 Lebanese University - Faculty of Science, Lebanon 1 Lebanese University - Faculty of Business,

More information

TCP Flavors Simulation Evaluations over Noisy Environment

TCP Flavors Simulation Evaluations over Noisy Environment International Journal of Information Engineering and Applications 2018; 1(1): 11-17 http://www.aascit.org/journal/information TCP Flavors Simulation Evaluations over Noisy Environment Elsadig Gamaleldeen

More information

CSE 123A Computer Networks

CSE 123A Computer Networks CSE 123A Computer Networks Winter 2005 Lecture 14 Congestion Control Some images courtesy David Wetherall Animations by Nick McKeown and Guido Appenzeller The bad news and the good news The bad news: new

More information

A Report on Some Recent Developments in TCP Congestion Control

A Report on Some Recent Developments in TCP Congestion Control A Report on Some Recent Developments in TCP Congestion Control Sally Floyd June 5, 2000 Abstract This paper discusses several changes either proposed or in progress for TCP congestion control. The changes

More information

Considering Spurious Timeout in Proxy for Improving TCP Performance in Wireless Networks

Considering Spurious Timeout in Proxy for Improving TCP Performance in Wireless Networks Considering Spurious Timeout in Proxy for Improving TCP Performance in Wireless Networks YuChul Kim Telecommunication R&D Center, Samsung Electronics,Co., Ltd yuchul.kim@samsung.com DongHo Cho Communication

More information

image 3.8 KB Figure 1.6: Example Web Page

image 3.8 KB Figure 1.6: Example Web Page image. KB image 1 KB Figure 1.: Example Web Page and is buffered at a router, it must wait for all previously queued packets to be transmitted first. The longer the queue (i.e., the more packets in the

More information

Equation-Based Congestion Control for Unicast Applications. Outline. Introduction. But don t we need TCP? TFRC Goals

Equation-Based Congestion Control for Unicast Applications. Outline. Introduction. But don t we need TCP? TFRC Goals Equation-Based Congestion Control for Unicast Applications Sally Floyd, Mark Handley AT&T Center for Internet Research (ACIRI) Jitendra Padhye Umass Amherst Jorg Widmer International Computer Science Institute

More information

Evaluating the Eifel Algorithm for TCP in a GPRS Network

Evaluating the Eifel Algorithm for TCP in a GPRS Network Evaluating the Eifel Algorithm for TCP in a GPRS Network Andrei Gurtov University of Helsinki Finland e-mail: Andrei.Gurtov@cs.Helsinki.FI Reiner Ludwig Ericsson Research Germany e-mail: Reiner.Ludwig@Ericsson.com

More information

Lecture 14: Congestion Control"

Lecture 14: Congestion Control Lecture 14: Congestion Control" CSE 222A: Computer Communication Networks George Porter Thanks: Amin Vahdat, Dina Katabi and Alex C. Snoeren Lecture 14 Overview" TCP congestion control review Dukkipati

More information

A Report on Some Recent Developments in TCP Congestion Control

A Report on Some Recent Developments in TCP Congestion Control A Report on Some Recent Developments in TCP Congestion Control Sally Floyd October 9, To appear in IEEE Communications Magazine, April Abstract This paper discusses several changes to TCP s congestion

More information

MaVIS: Media-aware Video Streaming Mechanism

MaVIS: Media-aware Video Streaming Mechanism MaVIS: Media-aware Video Streaming Mechanism Sunhun Lee and Kwangsue Chung School of Electronics Engineering, Kwangwoon University, Korea sunlee@adamskwackr and kchung@kwackr Abstract Existing streaming

More information

RD-TCP: Reorder Detecting TCP

RD-TCP: Reorder Detecting TCP RD-TCP: Reorder Detecting TCP Arjuna Sathiaseelan and Tomasz Radzik Department of Computer Science, King s College London, Strand, London WC2R 2LS {arjuna,radzik}@dcs.kcl.ac.uk Abstract. Numerous studies

More information

Network Management & Monitoring

Network Management & Monitoring Network Management & Monitoring Network Delay These materials are licensed under the Creative Commons Attribution-Noncommercial 3.0 Unported license (http://creativecommons.org/licenses/by-nc/3.0/) End-to-end

More information

Buffer Requirements for Zero Loss Flow Control with Explicit Congestion Notification. Chunlei Liu Raj Jain

Buffer Requirements for Zero Loss Flow Control with Explicit Congestion Notification. Chunlei Liu Raj Jain Buffer Requirements for Zero Loss Flow Control with Explicit Congestion Notification Chunlei Liu Raj Jain Department of Computer and Information Science The Ohio State University, Columbus, OH 432-277

More information

The Present and Future of Congestion Control. Mark Handley

The Present and Future of Congestion Control. Mark Handley The Present and Future of Congestion Control Mark Handley Outline Purpose of congestion control The Present: TCP s congestion control algorithm (AIMD) TCP-friendly congestion control for multimedia Datagram

More information

TCP based Receiver Assistant Congestion Control

TCP based Receiver Assistant Congestion Control International Conference on Multidisciplinary Research & Practice P a g e 219 TCP based Receiver Assistant Congestion Control Hardik K. Molia Master of Computer Engineering, Department of Computer Engineering

More information

TCP Congestion Control in Wired and Wireless networks

TCP Congestion Control in Wired and Wireless networks TCP Congestion Control in Wired and Wireless networks Mohamadreza Najiminaini (mna28@cs.sfu.ca) Term Project ENSC 835 Spring 2008 Supervised by Dr. Ljiljana Trajkovic School of Engineering and Science

More information

Page 1. Review: Internet Protocol Stack. Transport Layer Services. Design Issue EEC173B/ECS152C. Review: TCP

Page 1. Review: Internet Protocol Stack. Transport Layer Services. Design Issue EEC173B/ECS152C. Review: TCP EEC7B/ECS5C Review: Internet Protocol Stack Review: TCP Application Telnet FTP HTTP Transport Network Link Physical bits on wire TCP LAN IP UDP Packet radio Transport Layer Services Design Issue Underlying

More information

Recap. More TCP. Congestion avoidance. TCP timers. TCP lifeline. Application Presentation Session Transport Network Data Link Physical

Recap. More TCP. Congestion avoidance. TCP timers. TCP lifeline. Application Presentation Session Transport Network Data Link Physical Recap ½ congestion window ½ congestion window More TCP Congestion avoidance TCP timers TCP lifeline Application Presentation Session Transport Network Data Link Physical 1 Congestion Control vs Avoidance

More information

Experimental Study of TCP Congestion Control Algorithms

Experimental Study of TCP Congestion Control Algorithms www..org 161 Experimental Study of TCP Congestion Control Algorithms Kulvinder Singh Asst. Professor, Department of Computer Science & Engineering, Vaish College of Engineering, Rohtak, Haryana, India

More information

Page 1. Review: Internet Protocol Stack. Transport Layer Services EEC173B/ECS152C. Review: TCP. Transport Layer: Connectionless Service

Page 1. Review: Internet Protocol Stack. Transport Layer Services EEC173B/ECS152C. Review: TCP. Transport Layer: Connectionless Service EEC7B/ECS5C Review: Internet Protocol Stack Review: TCP Application Telnet FTP HTTP Transport Network Link Physical bits on wire TCP LAN IP UDP Packet radio Do you remember the various mechanisms we have

More information

ADVANCED COMPUTER NETWORKS

ADVANCED COMPUTER NETWORKS ADVANCED COMPUTER NETWORKS Congestion Control and Avoidance 1 Lecture-6 Instructor : Mazhar Hussain CONGESTION CONTROL When one part of the subnet (e.g. one or more routers in an area) becomes overloaded,

More information

Congestion Control in Communication Networks

Congestion Control in Communication Networks Congestion Control in Communication Networks Introduction Congestion occurs when number of packets transmitted approaches network capacity Objective of congestion control: keep number of packets below

More information

IIP Wireless. Presentation Outline

IIP Wireless. Presentation Outline IIP Wireless Improving Internet Protocols for Wireless Links Markku Kojo Department of Computer Science www.cs cs.helsinki.fi/research/.fi/research/iwtcp/ 1 Presentation Outline Project Project Summary

More information

RED behavior with different packet sizes

RED behavior with different packet sizes RED behavior with different packet sizes Stefaan De Cnodder, Omar Elloumi *, Kenny Pauwels Traffic and Routing Technologies project Alcatel Corporate Research Center, Francis Wellesplein, 1-18 Antwerp,

More information

cs/ee 143 Communication Networks

cs/ee 143 Communication Networks cs/ee 143 Communication Networks Chapter 4 Transport Text: Walrand & Parakh, 2010 Steven Low CMS, EE, Caltech Recap: Internet overview Some basic mechanisms n Packet switching n Addressing n Routing o

More information

8. TCP Congestion Control

8. TCP Congestion Control 8. TCP Congestion Control 1 TCP Congestion Control Slow-start increase Multiplicative decrease Congestion avoidance Measurement of variation Exponential timer backoff 2002 Yanghee Choi 2 Congestion Control

More information

AN IMPROVED STEP IN MULTICAST CONGESTION CONTROL OF COMPUTER NETWORKS

AN IMPROVED STEP IN MULTICAST CONGESTION CONTROL OF COMPUTER NETWORKS AN IMPROVED STEP IN MULTICAST CONGESTION CONTROL OF COMPUTER NETWORKS Shaikh Shariful Habib Assistant Professor, Computer Science & Engineering department International Islamic University Chittagong Bangladesh

More information

Congestion Control. Daniel Zappala. CS 460 Computer Networking Brigham Young University

Congestion Control. Daniel Zappala. CS 460 Computer Networking Brigham Young University Congestion Control Daniel Zappala CS 460 Computer Networking Brigham Young University 2/25 Congestion Control how do you send as fast as possible, without overwhelming the network? challenges the fastest

More information

Transmission Control Protocol (TCP)

Transmission Control Protocol (TCP) TETCOS Transmission Control Protocol (TCP) Comparison of TCP Congestion Control Algorithms using NetSim @2017 Tetcos. This document is protected by copyright, all rights reserved Table of Contents 1. Abstract....

More information

A SURVEY ON VIDEO STREAMING OVER MULTIMEDIA NETWORKS USING TCP

A SURVEY ON VIDEO STREAMING OVER MULTIMEDIA NETWORKS USING TCP A SURVEY ON VIDEO STREAMING OVER MULTIMEDIA NETWORKS USING TCP U.RAHAMATHUNNISA 1, DR.R.SARAVANAN 2, 1 Assistant Professor, SITE, VIT university, Vellore. 2 Sr. Professor, SITE, VIT university, Vellore

More information

TCP Congestion Control

TCP Congestion Control TCP Congestion Control What is Congestion The number of packets transmitted on the network is greater than the capacity of the network Causes router buffers (finite size) to fill up packets start getting

More information

TCP Congestion Control

TCP Congestion Control What is Congestion TCP Congestion Control The number of packets transmitted on the network is greater than the capacity of the network Causes router buffers (finite size) to fill up packets start getting

More information

Performance Evaluation of TCP Westwood. Summary

Performance Evaluation of TCP Westwood. Summary Summary This project looks at a fairly new Transmission Control Protocol flavour, TCP Westwood and aims to investigate how this flavour of TCP differs from other flavours of the protocol, especially TCP

More information

Impact of transmission errors on TCP performance. Outline. Random Errors

Impact of transmission errors on TCP performance. Outline. Random Errors Impact of transmission errors on TCP performance 1 Outline Impact of transmission errors on TCP performance Approaches to improve TCP performance Classification Discussion of selected approaches 2 Random

More information

CS419: Computer Networks. Lecture 10, Part 3: Apr 13, 2005 Transport: TCP performance

CS419: Computer Networks. Lecture 10, Part 3: Apr 13, 2005 Transport: TCP performance : Computer Networks Lecture 10, Part 3: Apr 13, 2005 Transport: TCP performance TCP performance We ve seen how TCP the protocol works But there are a lot of tricks required to make it work well Indeed,

More information

ENRICHMENT OF SACK TCP PERFORMANCE BY DELAYING FAST RECOVERY Mr. R. D. Mehta 1, Dr. C. H. Vithalani 2, Dr. N. N. Jani 3

ENRICHMENT OF SACK TCP PERFORMANCE BY DELAYING FAST RECOVERY Mr. R. D. Mehta 1, Dr. C. H. Vithalani 2, Dr. N. N. Jani 3 Research Article ENRICHMENT OF SACK TCP PERFORMANCE BY DELAYING FAST RECOVERY Mr. R. D. Mehta 1, Dr. C. H. Vithalani 2, Dr. N. N. Jani 3 Address for Correspondence 1 Asst. Professor, Department of Electronics

More information

Transmission Control Protocol. ITS 413 Internet Technologies and Applications

Transmission Control Protocol. ITS 413 Internet Technologies and Applications Transmission Control Protocol ITS 413 Internet Technologies and Applications Contents Overview of TCP (Review) TCP and Congestion Control The Causes of Congestion Approaches to Congestion Control TCP Congestion

More information

TCP Congestion Control

TCP Congestion Control 6.033, Spring 2014 TCP Congestion Control Dina Katabi & Sam Madden nms.csail.mit.edu/~dina Sharing the Internet How do you manage resources in a huge system like the Internet, where users with different

More information

Reliable Transport II: TCP and Congestion Control

Reliable Transport II: TCP and Congestion Control Reliable Transport II: TCP and Congestion Control Stefano Vissicchio UCL Computer Science COMP0023 Recap: Last Lecture Transport Concepts Layering context Transport goals Transport mechanisms and design

More information

F-RTO: An Enhanced Recovery Algorithm for TCP Retransmission Timeouts

F-RTO: An Enhanced Recovery Algorithm for TCP Retransmission Timeouts F-RTO: An Enhanced Recovery Algorithm for TCP Retransmission Timeouts Pasi Sarolahti Nokia Research Center pasi.sarolahti@nokia.com Markku Kojo, Kimmo Raatikainen University of Helsinki Department of Computer

More information

UNIT IV -- TRANSPORT LAYER

UNIT IV -- TRANSPORT LAYER UNIT IV -- TRANSPORT LAYER TABLE OF CONTENTS 4.1. Transport layer. 02 4.2. Reliable delivery service. 03 4.3. Congestion control. 05 4.4. Connection establishment.. 07 4.5. Flow control 09 4.6. Transmission

More information

Problems and Solutions for the TCP Slow-Start Process

Problems and Solutions for the TCP Slow-Start Process Problems and Solutions for the TCP Slow-Start Process K.L. Eddie Law, Wing-Chung Hung The Edward S. Rogers Sr. Department of Electrical and Computer Engineering University of Toronto Abstract--In this

More information

Performance Evaluation of SCTP with Adaptive Multistreaming over LEO Satellite Networks

Performance Evaluation of SCTP with Adaptive Multistreaming over LEO Satellite Networks Performance Evaluation of SCTP with Adaptive Multistreaming over LEO Satellite Networks Hiroshi Tsunoda, Nei Kato, Abbas Jamalipour, and Yoshiaki Nemoto Graduate School of Information Sciences, Tohoku

More information

CS321: Computer Networks Congestion Control in TCP

CS321: Computer Networks Congestion Control in TCP CS321: Computer Networks Congestion Control in TCP Dr. Manas Khatua Assistant Professor Dept. of CSE IIT Jodhpur E-mail: manaskhatua@iitj.ac.in Causes and Cost of Congestion Scenario-1: Two Senders, a

More information

Outline Computer Networking. TCP slow start. TCP modeling. TCP details AIMD. Congestion Avoidance. Lecture 18 TCP Performance Peter Steenkiste

Outline Computer Networking. TCP slow start. TCP modeling. TCP details AIMD. Congestion Avoidance. Lecture 18 TCP Performance Peter Steenkiste Outline 15-441 Computer Networking Lecture 18 TCP Performance Peter Steenkiste Fall 2010 www.cs.cmu.edu/~prs/15-441-f10 TCP congestion avoidance TCP slow start TCP modeling TCP details 2 AIMD Distributed,

More information

Improved Selective Acknowledgment Scheme for TCP

Improved Selective Acknowledgment Scheme for TCP Improved Selective Acknowledgment Scheme for TCP Rajkumar Kettimuthu and William Allcock Argonne National Laboratory, Globus Alliance Argonne, IL 60439, USA kettimut, allcock @mcs.anl.gov Abstract A selective

More information

Request for Comments: S. Floyd ICSI K. Ramakrishnan AT&T Labs Research June 2009

Request for Comments: S. Floyd ICSI K. Ramakrishnan AT&T Labs Research June 2009 Network Working Group Request for Comments: 5562 Category: Experimental A. Kuzmanovic A. Mondal Northwestern University S. Floyd ICSI K. Ramakrishnan AT&T Labs Research June 2009 Adding Explicit Congestion

More information

DualRTT: Enhancing TCP Performance During Delay Spikes

DualRTT: Enhancing TCP Performance During Delay Spikes DualRTT: Enhancing TCP Performance During Delay Spikes Ph.D. School of Computer Science University of Oklahoma. Email: atiq@ieee.org Web: www.cs.ou.edu/~atiq Presentation at Tohoku University, Sendai,

More information

CS644 Advanced Networks

CS644 Advanced Networks What we know so far CS644 Advanced Networks Lecture 6 Beyond TCP Congestion Control Andreas Terzis TCP Congestion control based on AIMD window adjustment [Jac88] Saved Internet from congestion collapse

More information

Revisiting TCP Congestion Events Detection

Revisiting TCP Congestion Events Detection Revisiting TCP Congestion Events Detection Pascal Anelli, Fanilo Harivelo Université de la Réunion LIM - France firstname.lastname@univ-reunion.fr Emmanuel Lochin, Dino Lopez CNRS ; LAAS ; Université de

More information

Communication Networks

Communication Networks Communication Networks Spring 2018 Laurent Vanbever nsg.ee.ethz.ch ETH Zürich (D-ITET) April 30 2018 Materials inspired from Scott Shenker & Jennifer Rexford Last week on Communication Networks We started

More information

Enhancing TCP Throughput over Lossy Links Using ECN-Capable Capable RED Gateways

Enhancing TCP Throughput over Lossy Links Using ECN-Capable Capable RED Gateways Enhancing TCP Throughput over Lossy Links Using ECN-Capable Capable RED Gateways Haowei Bai Honeywell Aerospace Mohammed Atiquzzaman School of Computer Science University of Oklahoma 1 Outline Introduction

More information

Chapter 3. Wireless Access of Internet Using TCP/IP A Survey of Issues and Recommendations 3.1 INTRODUCTION

Chapter 3. Wireless Access of Internet Using TCP/IP A Survey of Issues and Recommendations 3.1 INTRODUCTION Chapter 3 Wireless Access of Internet Using TCP/IP A Survey of Issues and Recommendations Sridhar Komandur, Spencer Dawkins and Jogen Pathak Cynela Networks, Inc 3.1 INTRODUCTION The Internet has many

More information

TCP so far Computer Networking Outline. How Was TCP Able to Evolve

TCP so far Computer Networking Outline. How Was TCP Able to Evolve TCP so far 15-441 15-441 Computer Networking 15-641 Lecture 14: TCP Performance & Future Peter Steenkiste Fall 2016 www.cs.cmu.edu/~prs/15-441-f16 Reliable byte stream protocol Connection establishments

More information

6.033 Spring 2015 Lecture #11: Transport Layer Congestion Control Hari Balakrishnan Scribed by Qian Long

6.033 Spring 2015 Lecture #11: Transport Layer Congestion Control Hari Balakrishnan Scribed by Qian Long 6.033 Spring 2015 Lecture #11: Transport Layer Congestion Control Hari Balakrishnan Scribed by Qian Long Please read Chapter 19 of the 6.02 book for background, especially on acknowledgments (ACKs), timers,

More information

A NEW CONGESTION MANAGEMENT MECHANISM FOR NEXT GENERATION ROUTERS

A NEW CONGESTION MANAGEMENT MECHANISM FOR NEXT GENERATION ROUTERS Journal of Engineering Science and Technology Vol. 3, No. 3 (2008) 265-271 School of Engineering, Taylor s University College A NEW CONGESTION MANAGEMENT MECHANISM FOR NEXT GENERATION ROUTERS MOHAMMED

More information

Experimental Analysis of TCP Behaviors against Bursty Packet Losses Caused by Transmission Interruption

Experimental Analysis of TCP Behaviors against Bursty Packet Losses Caused by Transmission Interruption Experimental Analysis of TCP Behaviors against Bursty Packet Losses Caused by Transmission Interruption Weikai Wang, Celimuge Wu, Satoshi Ohzahata, Toshihiko Kato Graduate School of Information Systems

More information

Mobile Communications Chapter 9: Mobile Transport Layer

Mobile Communications Chapter 9: Mobile Transport Layer Prof. Dr.-Ing Jochen H. Schiller Inst. of Computer Science Freie Universität Berlin Germany Mobile Communications Chapter 9: Mobile Transport Layer Motivation, TCP-mechanisms Classical approaches (Indirect

More information

Congestion Control in TCP

Congestion Control in TCP Congestion Control in TCP Antonio Carzaniga Faculty of Informatics University of Lugano November 11, 2014 Outline Intro to congestion control Input rate vs. output throughput Congestion window Congestion

More information

CS 5520/ECE 5590NA: Network Architecture I Spring Lecture 13: UDP and TCP

CS 5520/ECE 5590NA: Network Architecture I Spring Lecture 13: UDP and TCP CS 5520/ECE 5590NA: Network Architecture I Spring 2008 Lecture 13: UDP and TCP Most recent lectures discussed mechanisms to make better use of the IP address space, Internet control messages, and layering

More information

WB-RTO: A Window-Based Retransmission Timeout for TCP

WB-RTO: A Window-Based Retransmission Timeout for TCP WB-RTO: A Window-Based Retransmission Timeout for TCP Ioannis Psaras and Vassilis Tsaoussidis Dept. of Electrical and Computer Engineering Demokritos University of Thrace Xanthi, Greece Email: {ipsaras,

More information

Receiver-initiated Sending-rate Control based on Data Receive Rate for Ad Hoc Networks connected to Internet

Receiver-initiated Sending-rate Control based on Data Receive Rate for Ad Hoc Networks connected to Internet Receiver-initiated Sending-rate Control based on Data Receive Rate for Ad Hoc Networks connected to Internet Akihisa Kojima and Susumu Ishihara Graduate School of Engineering, Shizuoka University Graduate

More information

Sally Floyd, Mark Handley, and Jitendra Padhye. Sept. 4-6, 2000

Sally Floyd, Mark Handley, and Jitendra Padhye. Sept. 4-6, 2000 A Comparison of Equation-Based and AIMD Congestion Control Sally Floyd, Mark Handley, and Jitendra Padhye Sept. 4-6, 2 Workshop on the Modeling of Congestion Control Algorithms Paris 1 Why look at non-tcp

More information

Congestion control in TCP

Congestion control in TCP Congestion control in TCP If the transport entities on many machines send too many packets into the network too quickly, the network will become congested, with performance degraded as packets are delayed

More information

Transport Protocols & TCP TCP

Transport Protocols & TCP TCP Transport Protocols & TCP CSE 3213 Fall 2007 13 November 2007 1 TCP Services Flow control Connection establishment and termination Congestion control 2 1 TCP Services Transmission Control Protocol (RFC

More information

TCP Enhancements in Linux. Pasi Sarolahti. Berkeley Summer School Outline

TCP Enhancements in Linux. Pasi Sarolahti. Berkeley Summer School Outline TCP Enhancements in Linux Pasi Sarolahti Berkeley Summer School 6.6.2002 Outline TCP details per IETF RFC s Pitfalls in the specifications Linux TCP congestion control engine Features Discussion on performance

More information

15-744: Computer Networking TCP

15-744: Computer Networking TCP 15-744: Computer Networking TCP Congestion Control Congestion Control Assigned Reading [Jacobson and Karels] Congestion Avoidance and Control [TFRC] Equation-Based Congestion Control for Unicast Applications

More information

Improving Reliable Transport and Handoff Performance in Cellular Wireless Networks

Improving Reliable Transport and Handoff Performance in Cellular Wireless Networks Improving Reliable Transport and Handoff Performance in Cellular Wireless Networks H. Balakrishnan, S. Seshan, and R. H. Katz ACM Wireless Networks Vol. 1, No. 4, pp. 469-482 Dec. 1995 P. 1 Introduction

More information

TCP. CSU CS557, Spring 2018 Instructor: Lorenzo De Carli (Slides by Christos Papadopoulos, remixed by Lorenzo De Carli)

TCP. CSU CS557, Spring 2018 Instructor: Lorenzo De Carli (Slides by Christos Papadopoulos, remixed by Lorenzo De Carli) TCP CSU CS557, Spring 2018 Instructor: Lorenzo De Carli (Slides by Christos Papadopoulos, remixed by Lorenzo De Carli) 1 Sources Fall and Stevens, TCP/IP Illustrated Vol. 1, 2nd edition Congestion Avoidance

More information

Transport Protocols and TCP: Review

Transport Protocols and TCP: Review Transport Protocols and TCP: Review CSE 6590 Fall 2010 Department of Computer Science & Engineering York University 1 19 September 2010 1 Connection Establishment and Termination 2 2 1 Connection Establishment

More information

TCP Congestion Control 65KB W

TCP Congestion Control 65KB W TCP Congestion Control 65KB W TO 3DA 3DA TO 0.5 0.5 0.5 0.5 3 3 1 SS SS CA SS CA TCP s Congestion Window Maintenance TCP maintains a congestion window (cwnd), based on packets Sender s window is limited

More information

Communications Software. CSE 123b. CSE 123b. Spring Lecture 3: Reliable Communications. Stefan Savage. Some slides couresty David Wetherall

Communications Software. CSE 123b. CSE 123b. Spring Lecture 3: Reliable Communications. Stefan Savage. Some slides couresty David Wetherall CSE 123b CSE 123b Communications Software Spring 2002 Lecture 3: Reliable Communications Stefan Savage Some slides couresty David Wetherall Administrativa Home page is up and working http://www-cse.ucsd.edu/classes/sp02/cse123b/

More information

Cross-layer TCP Performance Analysis in IEEE Vehicular Environments

Cross-layer TCP Performance Analysis in IEEE Vehicular Environments 24 Telfor Journal, Vol. 6, No. 1, 214. Cross-layer TCP Performance Analysis in IEEE 82.11 Vehicular Environments Toni Janevski, Senior Member, IEEE, and Ivan Petrov 1 Abstract In this paper we provide

More information

CS268: Beyond TCP Congestion Control

CS268: Beyond TCP Congestion Control TCP Problems CS68: Beyond TCP Congestion Control Ion Stoica February 9, 004 When TCP congestion control was originally designed in 1988: - Key applications: FTP, E-mail - Maximum link bandwidth: 10Mb/s

More information

Congestion Control in TCP

Congestion Control in TCP Congestion Control in TCP Antonio Carzaniga Faculty of Informatics University of Lugano May 6, 2005 Outline Intro to congestion control Input rate vs. output throughput Congestion window Congestion avoidance

More information

TCP-DCR: Making TCP Robust to Non-Congestion Events

TCP-DCR: Making TCP Robust to Non-Congestion Events TCP-DCR: Making TCP Robust to Non-Congestion Events Sumitha Bhandarkar and A. L. Narasimha Reddy Dept. of Electrical Engineering Texas A & M University sumitha,reddy @ee.tamu.edu Abstract. In this paper,

More information

ISSN: Index Terms Wireless networks, non - congestion events, packet reordering, spurious timeouts, reduce retransmissions.

ISSN: Index Terms Wireless networks, non - congestion events, packet reordering, spurious timeouts, reduce retransmissions. ISSN:2320-0790 A New TCP Algorithm to reduce the number of retransmissions in Wireless Networks A Beulah, R Nita Marie Ann Assistant Professsor, SSN College of Engineering, Chennai PG Scholar, SSN College

More information

Chapter 24 Congestion Control and Quality of Service 24.1

Chapter 24 Congestion Control and Quality of Service 24.1 Chapter 24 Congestion Control and Quality of Service 24.1 Copyright The McGraw-Hill Companies, Inc. Permission required for reproduction or display. 24-1 DATA TRAFFIC The main focus of congestion control

More information

Wireless TCP Performance Issues

Wireless TCP Performance Issues Wireless TCP Performance Issues Issues, transport layer protocols Set up and maintain end-to-end connections Reliable end-to-end delivery of data Flow control Congestion control Udp? Assume TCP for the

More information

Congestion Avoidance and Control. Rohan Tabish and Zane Ma

Congestion Avoidance and Control. Rohan Tabish and Zane Ma Congestion Avoidance and Control Rohan Tabish and Zane Ma TCP is self-clocking Self-clocking systems should be robust Congestion collapse Internet had first of what became a series of congestion collapses

More information

Flow and Congestion Control

Flow and Congestion Control CE443 Computer Networks Flow and Congestion Control Behnam Momeni Computer Engineering Department Sharif University of Technology Acknowledgments: Lecture slides are from Computer networks course thought

More information

Reliable Transport II: TCP and Congestion Control

Reliable Transport II: TCP and Congestion Control Reliable Transport II: TCP and Congestion Control Brad Karp UCL Computer Science CS 3035/GZ01 31 st October 2013 Outline Slow Start AIMD Congestion control Throughput, loss, and RTT equation Connection

More information

THE TCP specification that specifies the first original

THE TCP specification that specifies the first original 1 Median Filtering Simulation of Bursty Traffic Auc Fai Chan, John Leis Faculty of Engineering and Surveying University of Southern Queensland Toowoomba Queensland 4350 Abstract The estimation of Retransmission

More information

Goals of Today s Lecture! Congestion Control! Course So Far.! Congestion Control Overview! It s Not Just The Sender & Receiver! Congestion is Natural!

Goals of Today s Lecture! Congestion Control! Course So Far.! Congestion Control Overview! It s Not Just The Sender & Receiver! Congestion is Natural! Goals of Today s Lecture! Congestion Control! EE 22: Intro to Communication Networks Fall 200 (MW 4-5:30 in 0 Barker) Scott Shenker TAs: Sameer Agarwal, Sara Alspaugh, Igor Ganichev, Prayag Narula http://inst.eecs.berkeley.edu/~ee22/

More information

Making TCP Robust Against Delay Spikes

Making TCP Robust Against Delay Spikes University of Helsinki Department of Computer Science Series of Publications C, No. C-1-3 Making TCP Robust Against Delay Spikes Andrei Gurtov Helsinki, November 1 Report C-1-3 University of Helsinki Department

More information

Transport Layer PREPARED BY AHMED ABDEL-RAOUF

Transport Layer PREPARED BY AHMED ABDEL-RAOUF Transport Layer PREPARED BY AHMED ABDEL-RAOUF TCP Flow Control TCP Flow Control 32 bits source port # dest port # head len sequence number acknowledgement number not used U A P R S F checksum Receive window

More information

Random Early Detection (RED) gateways. Sally Floyd CS 268: Computer Networks

Random Early Detection (RED) gateways. Sally Floyd CS 268: Computer Networks Random Early Detection (RED) gateways Sally Floyd CS 268: Computer Networks floyd@eelblgov March 20, 1995 1 The Environment Feedback-based transport protocols (eg, TCP) Problems with current Drop-Tail

More information

Performance Analysis of TCP Variants

Performance Analysis of TCP Variants 102 Performance Analysis of TCP Variants Abhishek Sawarkar Northeastern University, MA 02115 Himanshu Saraswat PES MCOE,Pune-411005 Abstract The widely used TCP protocol was developed to provide reliable

More information

Advanced Computer Networks

Advanced Computer Networks Advanced Computer Networks Congestion control in TCP Contents Principles TCP congestion control states Congestion Fast Recovery TCP friendly applications Prof. Andrzej Duda duda@imag.fr http://duda.imag.fr

More information

Improving the Performance of Interactive TCP Applications using End-point Based and Network Level Techniques

Improving the Performance of Interactive TCP Applications using End-point Based and Network Level Techniques Improving the Performance of Interactive TCP Applications using End-point Based and Network Level Techniques Varun G Menon Assistant Professor Department of Computer Science and Engineering M.E.T S School

More information

TCP in Asymmetric Environments

TCP in Asymmetric Environments TCP in Asymmetric Environments KReSIT, IIT Bombay Vijay T. Raisinghani TCP in Asymmetric Environments 1 TCP Overview Four congestion control algorithms Slow start Congestion avoidance Fast retransmit Fast

More information

Intro to LAN/WAN. Transport Layer

Intro to LAN/WAN. Transport Layer Intro to LAN/WAN Transport Layer Transport Layer Topics Introduction (6.1) Elements of Transport Protocols (6.2) Internet Transport Protocols: TDP (6.5) Internet Transport Protocols: UDP (6.4) socket interface

More information