Improving Internet congestion control and queue management algorithms.

Abstract

With the rapid proliferation of the WWW, the Internet has seen enormous growth in both the demand for access from its users and in the demand for new services from its applications. This dissertation focuses on these two important challenges to today's Internet: supporting an explosion in the number of users and supporting a myriad of new applications which require more out of the network than the best-effort service that the Internet currently provides. The first half of this dissertation focuses on the problem of maximizing network efficiency in times of extremely heavy congestion. Over the last decade, TCP congestion control has been instrumental in allowing the network to deliver service in times of high demand. Through analysis, simulation, and experimentation, this dissertation uncovers a number of significant weaknesses in TCP's congestion control algorithm and in current active queue management mechanisms such as RED. With additional growth in demand, these weaknesses are shown to severely degrade network efficiency by driving up packet loss rates in the network. To address these shortcomings, several new queue management (Adaptive RED, BLUE) and congestion control algorithms (SUBTCP) are proposed and evaluated. These algorithms are shown to eliminate packet loss and maximize link utilization much more effectively than TCP and current active queue management algorithms can. In addition to packet loss, another problem with today's congestion control and queue management algorithms is that they only deliver applications a single service, best-effort. As the need for new services has grown, the inability to provide service differentiation across flows beyond best-effort service has become problematic. The second half addresses the problem of supporting additional services across the Internet. In particular, these chapters focus on building scalable, deployable mechanisms for supporting bandwidth guarantees across the Internet based on simple priority mechanisms as outlined by the Differentiated Services working group of the IETF. Using minor extensions to the queue management (Enhanced RED) and congestion control algorithms in place today, these mechanisms provide applications more predictable behavior out of the network and enable the deployment of a large number of bandwidth-sensitive applications.