Enhancing Fairness for Approximate Weighted Fair Queueing With a Single Queue

Abstract

Weighted fair queueing (WFQ) is an essential strategy for enforcing bandwidth guarantee and isolation in high-speed networks. Unfortunately, implementing the original WFQ packet scheduling algorithm on today’s commodity switch hardware is challenging due to the prohibitive complexity. Approximate WFQ packet schedulers, which work with the cheap and widely available First-In First-Out (FIFO) queues, have been proposed as an alternative in recent years. In this paper, we show that both the ideal and the approximate WFQ packet schedulers are unable to allocate bandwidths to TCP flows fairly, because of the bursty nature of the TCP traffic. Furthermore, we find that the representative approximate WFQ schedulers further degrade the scheduling fairness, due to their excessive packet drops. To address these issues, we present novel approximate WFQ packet scheduling algorithms in this paper. Our initial design, namely SQ-WFQ, imposes the minimum hardware requirement by using one single FIFO queue, and effectively reduces the excessive packet drops. Extended from SQ-WFQ, we propose the SQ-EWFQ packet scheduling algorithm. SQ-EWFQ inherits all the merits of SQ-WFQ, and is adaptive to the bursty TCP traffic by tolerating short-term packet bursts, while enforcing a long-term fairness among the TCP flows. We have implemented our proposed schedulers on commodity hardware programmable switches, and achieve line rate packet scheduling with them. Experiment results from a real-world testbed and large-scale simulations show that SQ-WFQ and SQ-EWFQ outperform the state-of-the-art approximate schedulers regarding the scheduling fairness, and SQ-EWFQ allocates bandwidths to TCP flows more fairly than SQ-WFQ and other existing solutions.