Effect of Different Packet Sizes on RED Performance.pdf

Effect of different packet sizes on RED performance Stefaan De Cnodder, Omar Elloumi, Kenny Pauwels Traffic and Routing Technologies project Alcatel Corporate Research Center, Francis Wellesplein, 1 - 2018 Antwerp, Belgium Abstract We consider the adaptation of random early detection (RED) as an active queue management algorithm for TCP traffic in Internet gateways where different maximum transfer units (MTUs) are used. We studied the two RED variants described in [1] and point out a weakness in both. The first variant where the drop probability is independent from the packet size discriminates connections with smaller MTUs. The second variant results in a very high Packet Loss Ratio (PLR), and as a consequence low goodput, for connections with higher MTUs. We show that fairness in terms of loss and goodput can be supplied through an appropriate setting of the RED algorithm. Index Terms: RED, TCP, fairness, active queue management. I Introduction The random early detection (RED) algorithm is becoming a de-facto standard for congestion avoidance in the Internet and other packet switched networks. As a consequence of the incremental deployment of RED, several algorithms based on RED have been and are still being proposed to improve its performance. RFC2309 [2] states that RED should be used as the default mechanism for managing queues in routers unless there are good reasons to use another mechanism. To this end, strong recommendations for testing, standardization and widespread deployment of active queue management in routers, to improve the performance of today’s Internet are made. How does RED operate? In order to allow transient bursts, RED randomly drops pa