Congestion Control in High-Speed Networks
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 ...
Get Internet Congestion Control now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
