In recent years, Cloud computing has become a very attractive paradigm and popular model for accessing distributed resources. The Cloud has emerged as the next big trend after the so-called Grid computing approach. The burst of platforms and projects providing Cloud resources and interfaces at the very same time that Grid projects are entering a production phase in their life cycle has, however, raised the question of the best approach to handling distributed resources. Especially, are Cloud resources scaling at the levels shown by Grids? Are they performing at the same level? Can they be compared? What are their overhead on the IT teams and infrastructure? Since its first use of Cloud resources on Amazon EC2 in 2008/2009 using a Nimbus/EC2
interface, the STAR experiment software team has tested and experimented with many novel approaches: from a traditional native EC2 approach to the Virtual Organization Cluster (VOC) at Clemson university and Condor/VM on the GLOW resources, STAR has ramped up the job scale step by step to achieve stable operation at the 1,000 jobs level. This paper presents an overview of our findings and reports on practical usage of truly opportunistic use of resources.

Submitted: SciDAC 2010 proceedings.
Status: Paper published as part of the SciDAC 2010 proceedings.