Lixia Zhang, Scott Shenker, and David Clark. Observations on the Dynamics of a Congestion Control Algorithm: The Effects of Two- Way Traffic. In ACM SIGCOMM, September 1991.  Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
First 50 documents Next 50
Evaluating and Modeling Window Synchronization in Highly.. - Jim Gast And (Correct)
....marks) to many senders. If the congestion was successfully eliminated, connections will enjoy a long loss free period and will grow their cWnd using additive increase. If the connections grow and shrink their cWnd in synchrony, the global synchronization is referred to as window synchronization [8]. The most significant effort to reduce oscillations caused by synchronization is Random Early Detection (RED) 9] RED tries to break the deterministic cycle by detecting incipient congestion and dropping (or marking) packets probabilistically. On slow links, this effectively eliminates global ....
L. Zhang, S. Shenkar, and D. Clark, "Observations on the dynamics of a congestion control algorithm: The effects of two-way traffic," in Proceedings of ACM SIGCOMM, 1991.
Analysis of two competing TCP/IP connections - Altman, Jimenez, Nunez-Queija (2002) (5 citations) (Correct)
....achieved by a TCP connection is inversely proportional to RTT with 1 # 2, where RTT is the two way propagation delay of the connection. However, it turns out that in practice this assumption does not hold, except for drop tail buffers and connections with similar round trip times (RTTs) [15]. Indeed, traces in [1] e.g. Fig. 5) show that the synchronization assumption is invalid for asymmetric connections using a drop tail buffer. In preparing [5] the authors have also observed through simulations (using the ns simulator) that there is no synchronization between losses when the RED ....
L. Zhang, S. Shenker, D.D. Clark, Observations on the dynamics of a congestion control algorithm: the effects of two-way traffic, Proceedings of ACM SIGCOMM, 1991.
A Comparison of TCP Automatic Tuning Techniques for.. - Eric Weigle Ehw (2002) (5 citations) (Correct)
....flow. Unidirectional Transfers: Although TCP is inherently a full duplex protocol, the majority of traffic generally flows in one direction. TCP protocol dynamics do not significantly differ between one flow with bidirectional traffic and two unidirectional flows sending in opposite directions [12]. Loss: Our WAN emulator is configured to emulate no loss (although loss may still occur due to sender receiver buffer overruns) All experiments are intended to be the best case scenario. The artificial inclusion of loss adds nothing to the discussion, as congestion control for TCP Reno SACK ....
Lixia Zhang, Scott Shenker, and David D. Clark, "Observations on the Dynamics of a Congestion Control Algorithm: The Effects of Two-Way Traffic," in Proceedings of ACM SigComm 1991.
On Randomizing the Sending Times in TCP and other.. - Chandrayana.. (Correct)
.... have been known to suffer from a number of phenomena which limit their effectiveness and degrade performance, the primary amongst them being: synchronization of congestion windows (or correspondingly the loss instances) causing alternate overloading and underloading of the bottleneck [12] 14] [15]; phase effects wherein a certain section of flows face recurrent losses [6] unfairness to flows with higher RTTs [5] delays and losses due to the bursty nature of TCP traffic [15] 2] In this paper we look at a comprehensive solution to all these issues by randomizing the packet ....
.... correspondingly the loss instances) causing alternate overloading and underloading of the bottleneck [12] 14] 15] phase effects wherein a certain section of flows face recurrent losses [6] unfairness to flows with higher RTTs [5] delays and losses due to the bursty nature of TCP traffic [15], 2] In this paper we look at a comprehensive solution to all these issues by randomizing the packet transmission times in TCP flows. Synchronization of windows and loss events for flows sharing common links causes alternating periods of overload and underload thereby leading to inefficient ....
[Article contains additional citation context not shown here]
L. Zhang, S. Shenker, and D. Clark, "Observations on the dynamics of a congestion control algorithm: The effects of two-way traffic, " Proc. of ACM SIGCOMM, , Zurich, Switzerland, Sept. 1991.
Limiting Model of ECN/RED under a Large Number of.. - Tinnakornsrisuphap, La (2003) (Correct)
....a connection all arrive only in a single timeslot, rather than being spread out throughout a round trip. Such simplification can be justified by the following: i) In the Internet, most of the packet arrivals at a bottleneck are usually compressed together due to the ACK compression phenomenon [9], which leads to bursty arrivals at the bottlenecks. Hence, modeling the packet arrivals over a RTT as a batch arrival in a single timeslot tends to be more accurate than modeling them as smooth arrivals throughout the RTT. ii) Aggregating a round trip worth of packet arrivals into a single ....
L. Zhang, S. Shenker, and D. Clark. Observations on the dynamics of a congestion control algorithm: The effects of two-way traffic. In Proceedings of ACM SIGCOMM, pages 133--147, September 1991.
On Reducing the Degree of Second-Order Scaling in.. - Sikdar.. (Correct)
....buffer management policy to reduce correlated losses (and consequently timeouts) in TCP flows. The second technique is to eliminate the inherent burstiness and back to back packet transmissions in TCP flows. One of the reasons behind this behavior is the phenomenon of ACK compression in TCP flows [26]. ACK compression has also been suggested as a possible cause of the fractal nature of network traffic in [6] We look at the impact of reducing the effects of ACK compression and burstiness of TCP sources through TCP pacing [26] on the second order scaling of traffic. Our results show that both ....
.... this behavior is the phenomenon of ACK compression in TCP flows [26] ACK compression has also been suggested as a possible cause of the fractal nature of network traffic in [6] We look at the impact of reducing the effects of ACK compression and burstiness of TCP sources through TCP pacing [26] on the second order scaling of traffic. Our results show that both these techniques are very successful in reducing the scaling exponents and burstiness in traffic. While these techniques are aimed at TCP s contribution to traffic scaling, we also show that these techniques are also effective ....
[Article contains additional citation context not shown here]
L. Zhang, S. Shenker, and D. Clark, "Observations on the dynamics of a congestion control algorithm: The effects of two-way traffic," Proceedings of ACM SIGCOMM, pp. 133-147, Zurich, Switzerland, September 1991.
Improving the Adaptability of AQM Algorithms to Traffic Load.. - Zhi Li Zhongwei (2003) Self-citation (Zhang) (Correct)
No context found.
L. Zhang, S. Shenker, and D. Clark, "Observations on the dynamics of a congestion control algorithm: The effects of twoway traffic," in SIGCOMM, 1991, pp. 133--147. [Online]. Available: citeseer.nj.nec.com/zhang91observations.html
Decoupling Congestion Control and Bandwidth Allocation Policy.. - Katabi Self-citation (Clark) (Correct)
....variety of scenarios. In particular, we simulate capacities in [1.5 Mb s, 4 Gb s] propagation delays in [10 ms, 1. 4 sec] number of long lived sources in [1, 1000] and arrival rates of Web like flows in [10 sec, 1000 sec] We also simulate 2 way traffic (with the resulting Ack compression [80]) and dynamic environments with arrivals and departures of short Web like flows. In all of these simulations, we set = 0:4 and = 0:226 showing the applicability of the results in Theorem 1. Ack compression refers to the phenomenon in which multiple Acks arrive at the sender back to back, ....
S. S. L. Zhang and D. Clark. Observations on the dynamics of a congestion control algorithm: The effects of two-way traffic. ACM SIGCOMM 91, 1991. 129
Notes on Burst Mitigation for Transport Protocols - Mark Allman Icsi (Correct)
No context found.
Lixia Zhang, Scott Shenker, and David Clark. Observations on the Dynamics of a Congestion Control Algorithm: The Effects of Two- Way Traffic. In ACM SIGCOMM, September 1991.
A Survey on Improving TCP Performance over Wireless Networks - Chen, Zhai, Wang, Fang (2005) (Correct)
No context found.
L. Zhang, S. Shenker and D. Clark, "Observations on the dynamics of a congestion control algorithm: the effects of two-way traffic," Proceedings of ACM SIGCOMM'91, Sep. 1991.
Notes on Burst Mitigation for Transport Protocols - Mark Allman Icsi (2004) (Correct)
No context found.
Lixia Zhang, Scott Shenker, and David Clark. Observations on the Dynamics of a Congestion Control Algorithm: The Effects of Two- Way Traffic. In ACM SIGCOMM, September 1991.
Time for a TCP Benchmark Suite? - David Wei Pei (Correct)
No context found.
ZHANG, L., SHENKER, S., AND CLARK, D. D. Observations on the dynamics of a congestion control algorithm: the effects of twoway traffic. In SIGCOMM '91: Proceedings of the conference on Communications architecture & protocols (New York, NY, USA, 1991), ACM Press, pp. 133--147.
Bandwidth Estimation Schemes for TCP over Wireless Networks - Capone, Fratta, Martignon (2004) (1 citation) (Correct)
No context found.
L. Zhang, S. Shenker, and D. Clark, "Observations on the Dynamics of a Congestion Control Algorithm: The Effects of Two-Way Traffic," Proc. SIGCOMM Symp. Comm. Architectures and Protocols, pp. 133-147, Sept. 1991.
TCP with Bandwidth Estimation over Wireless Networks - Martignon, Capone (2002) (Correct)
No context found.
L.Zhang, S.Shenker, and D.Clark. Observations on the Dynamics of a Congestion Control Algorithm: The Effects of Two-Way Traffic. In Proceedings of SIGCOMM'91 Symposium on Communications Architectures and Protocols, pages 133--147, Zurich, September 1991.
Low-Rate TCP-Targeted Denial of Service Attacks (The Shrew .. - Kuzmanovic, Knightly (2003) (3 citations) (Correct)
No context found.
L. Zhang, S. Shenker, and D. Clark. Observation on the dynamics of a congestion control algorithm: The effects of two-way traffic. In Proceedings of ACM SIGCOMM'91, Zurich, Switzerland, September 1991.
The origin of TCP traffic burstiness in some time scales - Jiang, Dovrolis (2004) (Correct)
No context found.
L. Zhang, S. Shenker, and D. D. Clark, "Observations on the Dynamics of a Congestion Control Algorithm," in Proceedings of ACM SIGCOMM, Sept. 1991.
Proxy-based Flow Aggregation for Enhanced TCP over GPRS - Chakravorty, Katti.. (2003) (Correct)
No context found.
L. Zhang, S. Shenker and D. Clark, "Observations on the Dynamics of a Congestion Control Algorithm: The Effects of Two-Way Traffic", In Proceedings of ACM SIGCOMM 1991.
Addressing the Challenges of Reliable Data Transfer over.. - Chakravorty (2003) (Correct)
No context found.
L. Zhang, S. Shenker, D. Clark, "Observations on the Dynamics of a Congestion Control Algorithm: The Effects of Two-Way Traffic", In Proceedings of ACM SIGCOMM, 1991.
Robust TCP Congestion Recovery - Haining Wang And (Correct)
No context found.
L. Zhang, S. Shenker, and D. Clark, "Observations on the Dynamics of a Congestion Control Algorithm: The E#ects of Two Way Tra#c", Proceedings of ACM SIGCOMM'91, Zurich, Switzerland, September 1991.
Unknown - The Erica And (Correct)
No context found.
Lixia Zhang, Scott Shenker, and D.D.Clark. Observations on the dynamics of a congestion control algorithm: The effects of two-way traffic. In Proceedings of the ACM SIGCOMM, August 1991. 431
Analysis of Two Competing TCP/IP Connections - Altman, Jimenez, Nunez-Queija (2002) (5 citations) (Correct)
No context found.
L. Zhang, S. Shenker, and D.D. Clark, "Observations on the Dynamics of a Congestion Control Algorithm: The Effects of Two-Way Traffic", ACM SIGCOMM, Sep 1991.
Unknown - Survey Of Atm (Correct)
No context found.
Lixia Zhang, Scott Shenker, and D.D.Clark. Observations on the dynamics of a congestion control algorithm: The effects of two-way traffic. In Proceedings of the ACM SIGCOMM, August 1991. 431
Traffic Management for the Available Bit Rate (ABR) Service in .. - Kalyanaraman (1997) (3 citations) (Correct)
No context found.
Lixia Zhang, Scott Shenker, and D.D.Clark. Observations on the dynamics of a congestion control algorithm: The effects of two-way traffic. In Proceedings of the ACM SIGCOMM, August 1991. 429
A Non-Feedback Congestion Control Framework for High-Speed Data.. - Kim (1995) (6 citations) (Correct)
No context found.
L. Zhang, S. Shenker, and D.D. Clark. Observations on the Dynamics of a Congestion Control Algorithm: the Effects of Two-Way Traffic. In Proceedings of ACM SIGCOMM, August 1991. 99
Some Observations on the Effect of Route Fluctuation and.. - Ulka Ranadive And (2001) (Correct)
No context found.
L. Zhang, S. Shenker and D. D. Clark, "Observations on the dynamics of a congestion control algorithm: The effects of two-way traffic," Proc. SIGCOMM'91,
First 50 documents Next 50
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC