Speaker
Laurence Field
(CERN)
Description
The adoption of cloud technologies by the LHC experiments is currently focused on IaaS, more specifically the ability to dynamically create virtual machines on demand.
This talk provides an overview of how this alternative approach for resource provision fits into the existing workflows used by the experiments.
It shows that in order to fully exploit this approach, solutions are required in the areas of image management, capacity management, monitoring, accounting, pilot job frameworks and supporting services.
Each of those areas is covered in more detail to explain the various architectural choices and the rational for the decisions made.
Finally, a general overview of the state of adoption within each experiment is given that describes the ongoing integration with their individual frameworks.
Author
Laurence Field
(CERN)
