Penalty Shaper to Enforce Assured Service for TCP Flows

Dairaine²,

Jourjon

2006

Telecommun Syst

Self Cite

This study addresses the end-to-end congestion control support over the DiffServ Assured Forwarding (AF) class. The resulting Assured Service (AS) provides a minimum level of throughput guarantee. In this context, this article describes a new end-to-end mechanism for continuous transfer based on TCP-Friendly Rate Control (TFRC). The proposed approach modifies TFRC to take into account the QoS negotiated. This mechanism, named gTFRC, is able to reach the minimum throughput guarantee whatever the flow's RTT and target rate. Simulation measurements and implementation over a real QoS testbed demonstrate the efficiency of this mechanism either in over-provisioned or exactly-provisioned network. In addition, we show that the gTFRC mechanism can be used in the same DiffServ/AF class with TCP or TFRC flows.

Section: Tcp Over Diffserv/af Classmentioning

confidence: 98%

gTFRC, a TCP friendly QoS-aware rate control for DiffServ Assured Service

Dairaine²,

Jourjon

2006

Telecommun Syst

Self Cite

“…As for TCP in the AF class [11], the TFRC mechanism is not aware that the loss was of an out-of-profile packet and that it should not decrease its actual sending rate below the target rate. For TCP, the solution was to introduce a conditioner able to better mark the TCP flows by taking into account the sporadic nature of the TCP flows [12], [13]. But the proposed conditioners are not all really efficient in certain network conditions, such as long RTTs, and are sometimes complex to use.…”

Section: A Problem Statementmentioning

confidence: 98%

Implementation and performance analysis of a QoS-aware TFRC mechanism

Jourjon

2006 14th IEEE International Conference on Networks

Dairaine³

et al. 2006

Self Cite

This paper deals with the improvement of transport protocol behaviour over the DiffServ Assured Forwarding (AF) class. The Assured Service (AS) provides a minimum throughput guarantee that classical congestion control mechanisms, like window-based in TCP or equation-based in TCP-Friendly Rate Control (TFRC), are not able to use efficiently. In response, this paper proposes a performance analysis of a QoS aware congestion control mechanism, named gTFRC, which improves the delivery of continuous streams. The gTFRC (guaranteed TFRC) mechanism has been integrated into an Enhanced Transport Protocol (ETP) that allows protocol mechanisms to be dynamically managed and controlled. After comparing a ns-2 simulation and our implementation of the basic TFRC mechanism, we show that ETP/gTFRC extension is able to reach a minimum throughput guarantee whatever the flow's RTT and target rate (TR) and the network provisioning conditions1.

“…Finally, as opposed to the marking strategy adopted by new conditioners, we have proposed a delay based shaper [26]. This shaper applies a delay penalty to a flow if there are outprofile packets losses in the network and if it outperforms its target rate.…”

Section: B Aimd Penalty Shapermentioning

confidence: 99%

TCP throughput guarantee in the DiffServ Assured Forwarding service: what about the results?

Anelli

2008

Ann. Telecommun.

Self Cite

International audienceSince the proposition of quality of service (QoS) architectures by the Internet Engineering Task Force (IETF), the interaction between TCP and the QoS services has been intensively studied. This paper proposes to look forward to the results obtained in terms of TCP throughput guarantee in the DiffServ assured forwarding (DiffServ/AF) service and to present an overview of the different proposals to solve the problem. It has been demonstrated that the standardized IETF DiffServ conditioners such as the token bucket color marker and the time sliding window color maker were not good TCP traffic descriptors. Starting with this point, several propositions have been made, and most of them present new marking schemes in order to replace or improve the traditional token bucket color marker. The main problem is that TCP congestion control is not designed to work with the AF service. Indeed, both mechanisms are antagonists. TCP has the property to share in a fair manner the bottleneck bandwidth between flows while DiffServ network provides a level of service that is controllable and predictable. In this paper, we build a classification of all the propositions made during the past few years and compare them. As a result, we will see that these conditioning schemes can be separated into three sets of action levels and that the conditioning at the network edge level is the most accepted one. We conclude that the problem is still unsolved and that TCP, conditioned or not conditioned, remains inappropriate for the DiffServ/AF service