A Programmable Packet Scheduling Method Based on Traffic Rate
Liangliang Kang, Le Tian, Yuxiang Hu · 2024
Network congestion results in high queuing delays and increased flow completion time, significantly deteriorating the quality of network services. To mitigate network congestion, this paper proposes an active queue management scheme based on traffic rate control (Traffic Rate Control based AQM, TRC-AQM), operating entirely on the modern programmable switch. TRC-AQM monitors packets' enqueuing time to predict the congestion status of a switch and uses a sliding window to calculate the relative rank of the arrival packet. Based on the congestion status and relative rank, the arrival packet is either dropped or enqueued, mitigating network congestion while providing differentiated quality of service. Experimental results show that, for flows sharing a single queue, TRC-AQM can effectively alleviate congestion, and stabilize the queue length to a very low level while maintaining high link utilization, leading to a highly reduced flow completion time for flows with high priority.