Towards a common environment for learning scheduling algorithms
Renato Luiz Cunha, Luiz Chaimowicz
MASCOTS 2020
On-premise research environments often face the challenge of managing a diverse range of platforms and execution environments, including Kubernetes, HPC job scheduling systems, and more. While ClusterAPI and Metal3 have simplified the provisioning and management of Kubernetes clusters on bare metal, managing non-Kubernetes nodes requires additional infrastructure management tools, introducing redundancy and complexity.
What if we could bridge this gap?
In this session, we'll explore the possibilities of extending ClusterAPI to manage non-Kubernetes hosts at scale, leveraging the Virtual Kubelet project to unlock this capability. We'll discuss the opportunities and challenges of this approach and present a Proof of Concept that showcases how ClusterAPI Bootstrap Provider using Virtual Kubelet can unify the management of diverse environments and use cases.
Renato Luiz Cunha, Luiz Chaimowicz
MASCOTS 2020
S. Hung, S. Mochizuki, et al.
VLSI Technology and Circuits 2025
Pritish Parida, Shurong Tian, et al.
ITherm 2024
Ilias Iliadis
CTRQ 2022