Automating Multi-Tenancy Performance Evaluation on Edge Compute Nodes

TL;DR

This paper presents an automated benchmarking framework to evaluate how multi-tenancy affects performance and energy efficiency on Edge computing nodes, simplifying complex testing processes.

Contribution

The authors introduce a comprehensive auto-benchmarking framework with monitoring and integration capabilities for diverse workloads in Edge environments.

Findings

Multi-tenancy impacts performance variably across hardware configurations.

Workload co-location strategies can mitigate performance degradation.

The framework enables efficient analysis of multi-tenancy effects.

Abstract

Edge Computing emerges as a promising alternative of Cloud Computing, with scalable compute resources and services deployed in the path between IoT devices and Cloud. Since virtualization techniques can be applied on Edge compute nodes, administrators can share their Edge infrastructures among multiple users, providing the so-called multi-tenancy. Even though multi-tenancy is unavoidable, it raises concerns about security and performance degradation due to resource contention in Edge Computing. For that, administrators need to deploy services with non-antagonizing profiles and explore workload co-location scenarios to enhance performance and energy consumption. Achieving this, however, requires extensive configuration, deployment, iterative testing, and analysis, an effort-intensive and time-consuming process. To address this challenge, we introduce an auto-benchmarking framework designed to streamline the analysis of multi-tenancy performance in Edge environments. Our framework includes a built-in monitoring stack and integrates with widely used benchmarking workloads, such as streaming analytics, database operations, machine learning applications, and component-based stress testing. We perform a case-driven analysis and provide valuable insights into the impact of multi-tenancy on Edge environments with different hardware configurations and diverse workloads. Finally, the implementation of our framework, along with the containerized workloads used for experimentation, is publicly available.