Congestion avoidance and control

TLDR

In October 1986, the Internet experienced its first congestion collapse, a dramatic drop in data throughput. The authors set out to investigate why bandwidth collapsed and whether 4.3BSD TCP misbehaved or could be tuned for better performance. They examined network behavior to identify the causes of the collapse. Throughput fell from 32 Kbps to 40 bps, and the study confirmed that 4.3BSD TCP misbehaved but could be tuned to improve performance.

Abstract

In October of '86, the Internet had the first of what became a series of 'congestion collapses'. During this period, the data throughput from LBL to UC Berkeley (sites separated by 400 yards and three IMP hops) dropped from 32 Kbps to 40 bps. Mike Karels1 and I were fascinated by this sudden factor-of-thousand drop in bandwidth and embarked on an investigation of why things had gotten so bad. We wondered, in particular, if the 4.3BSD (Berkeley UNIX) TCP was mis-behaving or if it could be tuned to work better under abysmal network conditions. The answer to both of these questions was "yes".