DRST: a Non-Intrusive Framework for Performance Analysis in Softwarized Networks

TL;DR

This paper introduces DRST, a lightweight, non-intrusive framework that uses hardware features and machine learning to accurately infer network performance and detect bottlenecks in NFV environments without direct traffic analysis.

Contribution

The paper presents DRST, a novel framework that leverages hardware features and adaptive ML techniques for performance inference in NFV, reducing system overhead and complexity.

Findings

DRST achieves high accuracy in performance inference across diverse NFV scenarios.

It operates with minimal interference and no need for traffic models or VNF-specific tuning.

DRST effectively detects runtime bottlenecks and adapts to system drift.

Abstract

The last decade has witnessed the proliferation of network function virtualization (NFV) in the telco industry, thanks to its unparalleled flexibility, scalability, and cost-effectiveness. However, as the NFV infrastructure is shared by virtual network functions (VNFs), sporadic resource contentions are inevitable. Such contention makes it extremely challenging to guarantee the performance of the provisioned network services, especially in high-speed regimes (e.g., Gigabit Ethernet). Existing solutions typically rely on direct traffic analysis (e.g., packet- or flow-level measurements) to detect performance degradation and identify bottlenecks, which is not always applicable due to significant integration overhead and system-level constraints. This paper complements existing solutions with a lightweight, non-intrusive framework for online performance inference that easily adapts to drift (i.e., a change over time of the actual state of our system). Instead of direct data-plane collection, we reuse hardware features in the underlying NFV infrastructure, introducing negligible interference in the data-plane. Our Drift-Resilient and Self-Tuning (DRST) framework can be integrated into existing NFV systems with minimal engineering effort and operate without the need for predefined traffic models or VNF-specific customization. DRST is deployed via a lightweight MLOps pipeline that automates the adaptation under runtime drift. We show how DRST can deliver accurate performance inference or diagnose run-time bottlenecks, as demonstrated through a comprehensive evaluation across diverse NFV scenarios.