.png){kind=icon}
.png){kind=icon}
Return
Improving flow fairness in non-programmable networks using P4-programmable Data Planes
.png){kind=icon}
PRE
AI
DOI：10.1016/j.comnet.2025.111339.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper presents a system that leverages P4-programmable Data Planes (PDPs) to achieve flow separation in non-programmable networks, enhancing fairness and performance for TCP flows with varying Round-Trip Times (RTTs). The system passively taps into traffic at the physical layer, sending a copy to a PDP for real-time flow identification, RTT computation, and classification. Using the Jenks natural breaks algorithm, the system classifies flows based on their RTTs and allocates them to distinct queues within non-programmable routers. The paper demonstrates improvements in fairness, bandwidth distribution, and reduced latency through a series of experiments, including tests on long-flow fairness, adaptability to changing network conditions, bufferbloat prevention, and Flow Completion Time (FCT). Additionally, the system is extended to mitigate UDP abuses, preventing it from monopolizing network resources. Limitations such as memory constraints on programmable switches and computational overhead are also discussed, along with potential areas for optimization. Experimental results show that the proposed system improves average fairness by up to 15% compared to a single-queue baseline approach. Furthermore, results show a reduction in average FCTs by approximately 20% for large TCP flows. These efficiency gains underscore the system's potential for mitigating RTT unfairness, reducing latency, and enhancing overall throughput independently of the Congestion Control Algorithm (CCA) in mixed-traffic network environments.
Keywords:
Programmable Data Plane (PDP)
Transmission Control Protocol (TCP)
Congestion Control Algorithm (CCA)
P4
Bandwidth and Round-trip Time (BBR)
Journal
IF:
4.6
Papers:
1.5K
Citations:
1.6W