Atlas Tier 3

ATLAS has built a powerful system for computing activities on top of three major grid infrastructures. As expected, with data finally arriving physicists need dedicated resources for analysis activities. In contrast to the existing grid infrastructure, there is a strong need to provide users with data control and high-performance (quasi) interactive data access. The ATLAS Tier3 solution is targeted to provide efficient and manageable analysis computing at each member institution. For most of sites only a small fraction of a physicist or student can be diverted for computing support. Transformative technologies have been chosen and integrated with the existing ATLAS tools. The result is a site which is substantially simpler to maintain and which is essentially operated by client tools and extensive use of caching technologies. Most promising new technologies we are using are: xroot and Lustre (distributed storage); CVMFS (experiment software distribution and condition files). We believe that this experience has a value to guide even the evolution of the entire computing system of HEP experiments.