Search for: All records

The Tapis Pods service is a novel open-source API within the Tapis platform which enables researchers to seamlessly manage Kubernetes containers, volumes, networking, and security at the Texas Advanced Computing Center (TACC). This paper explores the underlying operations, technologies, and workflows of the Tapis Pods service, showcasing its implementation and effectiveness. Additionally, we discuss current and potential use cases, highlighting the service's unique features, such as management capabilities, persistent storage, sharing, and automatically encrypted networking. Initial performance measurements against local Docker containers and alternative cloud solutions demonstrate the Tapis Pods service's competitive performance, emphasizing its value as a general interface for deploying user-defined containers.  

Containerized applications have exploded in popularity in recent years, due to their ease of deployment, reproducible nature, and speed of startup. Accordingly, container orchestration tools such as Kubernetes have emerged as resource providers and users alike try to organize and scale their work across clusters of systems. This paper documents some real-world experiences of building, operating, and using self-hosted Kubernetes Linux clusters. It aims at comparisons between Kubernetes and single-node container solutions and traditional multi-user, batch queue Linux clusters. The authors of this paper have background experience first running traditional HPC Linux clusters and queuing systems like Slurm, and later virtual machines using technologies such as Openstack. Much of the experience and perspective below is informed by this perspective. We will also provide a use-case from a researcher who deployed on Kubernetes without being as opinionated about other potential choices.