Abstract

This chapter discusses congestion control in high-speed networks with long latencies. One of the consequences of the application of control theory to TCP congestion control was the realization that TCP Reno was inherently unstable as the delay-bandwidth product of the network became large or even for very large bandwidths. As a result of this, a number of new congestion control designs were suggested with the objective of solving this problem such as High-Speed TCP (HSTCP), TCP Binary Increase Congestion control (BIC), TCP CUBIC, and Compound TCP (CTCP), which are described in this chapter. Currently, TCP CUBIC serves as the default congestion control algorithm for Linux servers and as a result is as widely deployed as TCP Reno. CTCP is used as the default option for Windows servers and is also very widely deployed. We also describe the eXpress Control Protocol (XCP) and Rate Control Protocol (RCP) algorithms that have been very influential in the design of high-speed congestion control protocols. Finally, we make connections between the algorithms in this chapter and the stability theory from Chapter 3 and give some general guidelines to be used in the design of high-speed congestion control algorithms.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

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.