Speaker
Markus Schulz
(CERN)
Description
- How well do we understand our current workflows, their behaviour and resource needs?
- with respect to storage, remote access, networks, CPU, memory
- How well do we understand the behaviour of our current infrastructure?
- What can we do to improve this understanding in an experiment independent way?
- how independent can this be?
- What has been done already in experiments?
- What would be desirable? Ability to model ideas of infrastructure to understand performance, costs, etc.
- What is potentially common across experiments? What is specific?
- Can we derive a cost model for the infrastructure to explain the full costs of computing and the relative costs of each component?
