Grid-enabled data access in the ATLAS Athena framework

Athena is the common framework used by the ATLAS experiment for simulation, reconstruction, and analysis. By design, Athena supports multiple persistence services, and insulates users from technology-specific persistence details. Athena users and even most Athena package developers should neither know nor care whether data come from the grid or from local filesystems, nor whether data reside in object database, in ROOT or ZEBRA files, or in ASCII files. The authors describe how Athena applications may transparently take advantage of emerging services provided by grid software today-- how data generated by Athena jobs are registered in grid replica catalogs and other collection management services, and the means by which input data are identified and located in a grid-aware collection management environment. The authors outline an evolutionary path toward incorporation of grid-based virtual data services, whereby locating data may be replaced by locating a recipe according to which that data may be generated. Several implementation scenarios, ranging from low-level grid catalog service (e.g., from Globus) through higher-level services such as the Grid Data Management Pilot (under development as part of the European DataGrid project, in collaboration with the Particle Physics Data Grid) to more conventional database services, and a common architecture to support these various scenarios, are also described