Abstract
This paper defines a class of "TCP-like" transport protocols, called protocols in the TCP Paradigm. The name indicates the protocols are not TCP, but in some sense similar to it. The class includes TCP and also Tom Kelly's "Scalable TCP", and more. Most of the protocols in the class require ECN in order to become implementable. Most even require a form of ECN that allows a high rate of marked packets. The paper analyzes performance of protocols in the TCP Paradigm and indicates a subset that is likely to perform as well as, or quite possibly better than, Scalable TCP. Criteria are the ability to achieve high throughput, to maintain a steady flow if the ECN marking probability is constant, and to adapt quickly to a changing marking probability. A main conclusion is that in order to benefit from protocols in this paradigm, "source behavior" (reaction of endpoints to marked and unmarked packets) and "router behavior" (how routers choose marking probabilities) must be investigated together.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.