Webinar: ATLAS Compute Sites using Native Kubernetes

by Fa-Hui Lin (University of Texas at Arlington (US)), Fernando Harald Barreiro Megino (University of Texas at Arlington)

Wednesday 21 Oct 2020, 14:00 → 15:00 Europe/Zurich

https://cern.zoom.us/j/97309998917?pwd=M2liMThjNE5FbElybWVaK3JUanF4dz09 (Zoom)

Recording: YouTube

In recent years containerization has revolutionized cloud environments, providing a secure and standardized way to package and execute software. Solutions such as Kubernetes enable orchestration of containers in a cluster, including for the purpose of job scheduling.

The PanDA team has evaluated the possibility of native Kubernetes job submission in order to process ATLAS payloads and offer the possibility of immediate integration of many cloud computing providers. This model also offers a novel way to set up a lightweight ATLAS, without the need of setting up the Grid stack.

In this session we will give an overview of the lessons learned running Kubernetes sites at a couple of ATLAS grid sites, Google and Amazon. We will also demonstrate the creation of a Kubernetes batch queue and connect it to PanDA.

 

 

 

Native kubernetes batch for ATLAS.pdf