The Fermilab HEP Cloud Facility will enable experiments to perform the full spectrum of computing tasks, including data-intensive simulation and reconstruction, at production scale irrespective of whether the resources are local, remote, or both. This will enable the facility to respond to demand peaks without local over-provisioning, using a more cost-effective mix of local and remote resources.
The current architecture and design overview document is available here.
A VO submits workflows to the Facility as a series of jobs. Once the jobs are authorized for facility access, the Decision Engine queries the Facility interfaces for the jobs and their associated manifests. Based on the information obtained from the manifests, the Decision Engine determines suitable types of resources for the jobs.
The following is an example deployment of the HEP cloud facility at Fermilab.