Container-level Energy Observability in Kubernetes Clusters

2025-04-14

AI Summary

Existing container-level energy monitoring in Kubernetes clusters suffers from insufficient accuracy, hindering application refactoring and deployment optimization. Method: This paper first conducts a systematic evaluation of Kepler—the dominant energy estimation tool—revealing significant measurement bias. To address this, we propose KubeWatt, a lightweight, high-accuracy container power tracking framework. KubeWatt integrates RAPL hardware performance counters, eBPF kernel probes, cgroup-based resource isolation, and time-synchronization calibration to enable fine-grained, low-overhead, dynamic power attribution at the container level. Contribution/Results: Experiments show that under identical conditions, KubeWatt reduces the mean absolute error (MAE) of container-level energy estimation to below 3.8%, a 62% improvement over Kepler. This accuracy meets the stringent requirements for energy-efficiency optimization decisions in production Kubernetes environments.

Technology Category

• Machine Learning: Hardware-aware ML
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Plan Execution and Monitoring

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Kubernetes has been for a number of years the default cloud orchestrator solution across multiple application and research domains. As such, optimizing the energy efficiency of Kubernetes-deployed workloads is of primary interest towards controlling operational expenses by reducing energy consumption at data center level and allocated resources at application level. A lot of research in this direction aims on reducing the total energy usage of Kubernetes clusters without establishing an understanding of their workloads, i.e. the applications deployed on the cluster. This means that there are untapped potential improvements in energy efficiency that can be achieved through, for example, application refactoring or deployment optimization. For all these cases a prerequisite is establishing fine-grained observability down to the level of individual containers and their power draw over time. A state-of-the-art tool approved by the Cloud-Native Computing Foundation, Kepler, aims to provide this functionality, but has not been assessed for its accuracy and therefore fitness for purpose. In this work we start by developing an experimental procedure to this goal, and we conclude that the reported energy usage metrics provided by Kepler are not at a satisfactory level. As a reaction to this, we develop KubeWatt as an alternative to Kepler for specific use case scenarios, and demonstrate its higher accuracy through the same experimental procedure as we used for Kepler.

Problem

• Assessing energy observability accuracy in Kubernetes containers
• Improving energy efficiency via container-level monitoring
• Developing KubeWatt as a more accurate alternative to Kepler

Innovation

• Container-level energy monitoring in Kubernetes
• Developed KubeWatt for higher accuracy
• Assessed Kepler's energy metrics inadequacy