RED behavior with different packet sizes
Stefaan De Cnodder, Omar Elloumi, Kenny Pauwels

TL;DR
This paper analyzes how RED buffer management performs with different packet sizes in TCP traffic, identifying weaknesses in existing variants and proposing settings for fairness in loss and goodput.
Contribution
It highlights flaws in two RED variants regarding packet size discrimination and proposes parameter adjustments to improve fairness across different MTUs.
Findings
The first RED variant discriminates against smaller MTUs.
The second RED variant causes high packet loss for larger MTUs.
Proper RED parameter tuning can ensure fairness in loss and goodput.
Abstract
We consider the adaptation of random early detection (RED) as a buffer management algorithm for TCP traffic in Internet gateways where different maximum transfer units (MTUs) are used. We studied the two RED variants described in [4] and point out a weakness in both. The first variant where 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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
