TCP veno: End-to-end congestion control over heterogeneous networks

The success of the Internet can be attributed directly to the large number of useful applications running on it. TCP/IP has been the underlying communication protocols enabling these applications. Despite the widespread deployment of the protocols, TCP/IP continues to be a hot research topic among R&D teams in the academia as well as the industry. Much of the recent work has been centered on adapting the protocols for use in wireless environments because of its ease of deployment, convenience to users, and high bandwidth brought about by maturing of advanced technologies (e.g., 3G and IEEE802.11 LAN). The next big wave—mobile Internet, in which wireless will play a necessary part of the Internet infrastructure—is around the comer.; The original TCP design assumes packet loss is always induced by congestion. This assumption can lead to significant performance degradation in wireless networks where random loss due to environmental noise is rampant. The detrimental effect of random loss on TCP performance is a well-known outstanding problem that remains to be unsolved. This dissertation proposes and studies a novel end-to-end congestion control mechanism called TCP Veno that is able to deal with random loss effectively.; Veno differs from the conventional TCP in a major way: it monitors the congestion level using an end-to-end estimation algorithm and uses that knowledge to refine the congestion control algorithm of TCP. Specifically, (1) it refines the multiplicative decrease algorithm of Reno by setting the congestion threshold—a key control parameter in TCP—according to the perceived congestion level of the network instead of a fixed drop factor when packet loss is detected; (2) it refines the linear increase algorithm by attempting to stay longer in an operating region in which the bandwidth is fully utilized.; Extensive network testbed experiments and live Internet measurements 1 have been conducted and they consistently show that Veno can achieve significant performance improvement over Reno in many different scenarios. Throughput improvement of as high as 56% is typical in the wireless setting with random loss. Detailed investigation indicates that the improvements are brought about without any harms to concurrently running Reno connections: that is, Veno connections achieve higher throughput by using bandwidth that will not be used by Reno connections anyway. In addition to wireless networks, Veno can also achieve better improvement relative to Reno in high-latency networks (e.g., networks including satellite links) and asymmetric networks (e.g., networks with ADSL access link).; Very importantly, TCP Veno only involves modification at the sender without requiring changes of the receiver protocol stack or intermediate router nodes. Because of that, it can be easily deployed. The operator of a Web server, for example, can replace its protocol stack with Veno without requiring all its clients to do anything.; Our comprehensive study leads us to the conclusions that Veno (1) can achieve better performance than Reno in randon-loss, high-latency, and asymmetric environments; (2) can co-exist with concurrent Reno connections without degrading the performance of Reno connections; and (3) can be deployed easily with only minor modifications of the sender-side algorithm.; A project called GIMe (Global Internet Measurement environments) has been launched to measure TCP Veno performance in a large scale.; 1TCP Veno has been implemented in NetBSD1.0, and its enhanced version with selective acknowledgement (SACK) option was implemented in NetBSD1.1, seeing http://www.broadband.ie.cuhk.edu.hk site for details.