Do Data Center Network Metrics Predict Application-Facing Performance?

TL;DR

This paper demonstrates that easily measurable network telemetry metrics can effectively predict application-facing performance in large-scale data center networks, aiding network design and operation decisions.

Contribution

It introduces a large-scale measurement approach and predictive models linking network metrics to application performance, highlighting the variability of predictors and model types.

Findings

Network telemetry metrics correlate with application performance.

Simple linear models often outperform complex models.

No single network metric is universally the best predictor.

Abstract

Applications that run in large-scale data center networks (DCNs) rely on the DCN's ability to deliver application requests in a performant manner. DCNs expose a complex design and operational space, and network designers and operators care how different options along this space affect application performance. One might run controlled experiments and measure the corresponding application-facing performance, but such experiments become progressively infeasible at a large scale, and simulations risk yielding inaccurate or incomplete results. Instead, we show that we can predict application-facing performance through more easily measured network metrics. For example, network telemetry metrics (e.g., link utilization) can predict application-facing metrics (e.g., transfer latency). Through large-scale measurements of production networks, we study the correlation between the two types of metrics, and construct predictive, interpretable models that serve as a suggestive guideline to network designers and operators. We show that no single network metric is universally the best predictor (even though some prior work has focused on a single predictor). We found that simple linear models often have the lowest error, while queueing-based models are better in a few cases.