Abstract
Throughout the first half of LHC Run 2, ATLAS cloud computing has undergone a period of consolidation, characterized by building upon previously established systems, with the aim of reducing operational effort, improving robustness, and reaching higher scale. This paper describes the current state of ATLAS cloud computing. Cloud activities are converging on a common contextualization approach for virtual machines, and cloud resources are sharing monitoring and service discovery components. We describe the integration of Vacuum resources, streamlined usage of the Simulation at Point 1 cloud for offline processing, extreme scaling on Amazon compute resources, and procurement of commercial cloud capacity in Europe. Finally, building on the previously established monitoring infrastructure, we have deployed a real-time monitoring and alerting platform which coalesces data from multiple sources, provides flexible visualization via customizable dashboards, and issues alerts and carries out corrective actions in response to problems.
Highlights
The Sim@P1 project enables the ATLAS HighLevel Trigger farm to be used for offline production activities
In 2016, the virtual machine (VM) definition for the Vacuum platform[2] was rewritten from scratch to use the industrystandard cloudinit format for contextualization. This allowed common elements of the contextualization recipe used across cloud platforms in ATLAS to be consolidated
The benchmarking suite is being used by ATLAS to quantify the performance of every VM on several clouds, in HS06equivalent units
Summary
Ryan P Taylor,[1] Cristovao Jose Domingues Cordeiro,[2] Domenico Giordano,[2] Alessandro Di Girolamo,[2] John Hover,[3] Tomas Kouba,[4] Peter Love,[5] Andrew McNab,[6] Jaroslava Schovancova[2] and Randall Sobie,[1] on behalf of the ATLAS Collaboration
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have