Studying network protocols and distributed applications in real networks can be difficult due to the need for complex topologies, hard to find physical channels (e.g., satellite channels), and conditions beyond the control of a researcher (e.g., queue sizes). Network emulators can provide a controlled and reproducible environment for network testing. This paper discusses ONE, a network emulator we have written and tested. 1 Introduction Network emulators, like network simulators, allow researchers to create network topologies and conditions that are difficult to achieve in a reproducible manner on production networks. Studying network protocols and distributed applications in the relatively simplistic environment that simulators and emulators furnish can be helpful when investigating subtle network and protocol interactions. In addition, these environments can provide access to network environments that are not easily found in the production Internet, such as satellite links. Network ...

this report are those of the author(s) and should not be interpreted as representing the official policies, either expressed or implied, of the Defense Advanced Research Projects Agency, RADC, or the U.S. Government. Computer facilities were provided in part by NSF grant CCR-8811954.

In this paper we examine the performance implications of providing reliability in conjunction with multicast transport over a high speed wide area network. We use a block based acknowledgement and selective retransmission protocol to evaluate the impact of the loss rate and the multicast tree topology on the achievable throughput. Our results show that even when the buffer overflow probability at switches and receivers is low, the cumulative loss probability seen by a source may be quite high. We also demonstrate that the average throughput increases significantly if the transport protocol delivers packets to the application layer outof -sequence. We investigate the scaling properties of the error control mechanism and show that the multicast tree topology that results in minimum transfer time is not necessarily the same as the one constructed using minimal bandwidth or shortest path algorithms. 1 Introduction Applications involving multi-user interaction are expected to consume a si...

We propose a flow-control scheme for multicast 1 ABR services in ATM networks. At the heart of the proposed scheme is an optimal second-order rate control algorithm, called the #-control,designedto deal with the variation in RM-cell round-trip time (RTT) resulting from dynamic drift of the bottleneck in a multicast tree. Applying two-dimensional rate control, the proposed scheme makes the rate process converge to the available bandwidth of the connection's most congested link sensed by the traffic source. It also confines the buffer occupancy to a target regime bounded by a finite buffer capacity as the system enters the equilibrium state. It works well irrespective of the topology of the multicast tree. Using the fluid analysis, we model the proposed scheme and analyze the system dynamics for multicast ABR traffic. We study the convergence properties and derive the optimal-control conditions for the #-control. The analytical results show that the scheme is stable and efficient in the sense that both the source rate and bottleneck queue length rapidly converge to a small neighborhood of the designated operating point. We present simulation results which verify the analytical observations. The simulation experiments also demonstrate the superiority of the proposed scheme to the other schemes in dealing with RM-cell RTT and link-bandwidth variations, achieving fairness in both buffer and bandwidth occupancies, and enhancing average throughput.

Abstract—We propose an efficient flow and error control scheme for highthroughput transport protocols by using a second-order rate control, called the-control, and a new sliding-window scheme for error control. The-control minimizes the packet retransmissions by adjusting the rate-gain parameter to the variations in the number and round-trip times (RTTs) of cross-traffic flows that share the bottleneck. Using selective retransmission, the sliding-window scheme guarantees lossless transmission. By applying the-control, the proposed scheme can drive the flow-controlled system to a retransmission-less equilibrium state. Using the fluid analysis, we establish the flow-control system model, obtain the greatest lower bound for the target buffer occupancy, and derive closed-form expressions for packet losses, loss rate, and link-transmission efficiency. We prove that the-control is feasible and optimal linear control in terms of efficiency and fairness. Also presented are the extensive simulation results that confirm the analytical results, and demonstrate the superiority of the proposed scheme to others in dealing with the variations of cross-traffic flows sharing the same bottleneck and their RTTs, controlling packet losses/retransmissions, and achieving buffer-usage fairness as well as high throughput. Index Terms—High-throughput transport protocol, second-order rate control, decoupled flow and error control, Internet, TCP/IP, TCP-Friendly. I.

This report presents the initial design of a testbed for developing routing algorithms for large dynamic computer networks.

Abstract not found

: : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 11 CHAPTER 1: Introduction : : : : : : : : : : : : : : : : : : : : : : : : : : : : 12 1.1 Computer Networks : : : : : : : : : : : : : : : : : : : : : : : : : : : : 12 1.2 Congestion : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 15 1.3 Protocols : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 17 1.4 Dissertation Outline : : : : : : : : : : : : : : : : : : : : : : : : : : : 18 CHAPTER 2: Simulator and Visualization Tools : : : : : : : : : : : : : : : : 20 2.1 The x-Kernel : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 20 2.1.1 Protocol Objects : : : : : : : : : : : : : : : : : : : : : : : : 22 2.1.2 Session Objects : : : : : : : : : : : : : : : : : : : : : : : : : 23 2.1.3 Message Objects : : : : : : : : : : : : : : : : : : : : : : : : : 24 2.1.4 Support Routines : : : : : : : : : : : : : : : : : : : : : : : : 24 2.1.5 x-Kernel Modifications to Support the Simulato...

this report are those of the author(s) and should not be interpreted as representing the official policies, either expressed or implied, of the Defense Advanced Research Projects Agency, RADC, or the U.S. Government. Computer facilities were provided in part by NSF grant CCR8811954. MaRS-Version 1.0 Programmer's Manual July 1, 1991 Contents

this report are those of the author(s) and should not be interpreted as representing the official policies, either expressed or implied, of the Defense Advanced Research Projects Agency, RADC, or the U.S. Government. Computer facilities were provided in part by NSF grant CCR-8811954.