Characterizing the Power Cost of Virtualization Environments

TL;DR

This paper compares the power consumption of virtual machines and containers in virtualization environments, showing containers are more energy-efficient and scale better with load, based on extensive real-world measurements.

Contribution

It provides a comprehensive empirical analysis of power costs for VMs and containers, offering models and insights into their energy efficiency in mobile networks.

Findings

Containers consume significantly less power than VMs.

Power consumption in containers increases more slowly with load.

Empirical models relate resource usage to power consumption.

Abstract

Virtualization is a key building block of next-generation mobile networks. It can be implemented through two main approaches: traditional virtual machines and lighter-weight containers. Our objective in this paper is to compare these approaches and study the power consumption they are associated with. To this end, we perform a large set of real-world measurements, using both synthetic workloads and real-world applications, and use them to model the relationship between the resource usage of the hosted application and the power consumption of both virtual machines and containers hosting it. We find that containers incur substantially lower power consumption than virtual machines, and that such consumption increases more slowly with the application load.