Analyzing DCTCP and Cubic Buffer Sharing under Diverse Router Configurations

TL;DR

This paper investigates how different router buffer configurations affect the performance and fairness of DCTCP and Cubic traffic in data centers, using extensive simulations and a machine learning model to optimize buffer settings.

Contribution

It provides a measurement-driven analysis of buffer sharing impacts on DCTCP and Cubic, and introduces a ML model for tuning buffer configurations in data centers.

Findings

Buffer configurations significantly influence DCTCP and Cubic performance.

The ML model accurately predicts traffic behavior under various settings.

Optimized buffer tuning improves fairness and throughput in data center networks.

Abstract

In this work, we look at the impact of router configurations on DCTCP and Cubic traffic when both algorithms share router buffers in the data center. Modern data centers host traffic with mixed congestion controls, including DCTCP and Cubic traffic. Both DCTCP and Cubic in the data center can compete with each other and potentially starve and/or be unfair to each other when sharing buffer space in the data center. This happens since both algorithms are at odds with each other in terms of buffer utilization paradigms where DCTCP attempts to limit buffer utilization while Cubic generally fills buffers to obtain high throughput. As a result, we propose methods for a measurement-driven analysis of DCTCP and Cubic performance when sharing buffers in data center routers via simulation. We run around 10000 simulation experiments with unique router configurations and network conditions. Afterwards, we present a generalizable ML model to capture the effect that different buffer settings have on DCTCP and Cubic streaming traffic in the data center. Finally, we suggest that this model can be used to tune buffer settings in the data center.