y

Computational Grids, composed of distributed and often hetero-geneous computing resources, have become the platform-of-choice for many performance-challenged applications. Proof-of-concept imple-mentations have demonstrated that both Grids and clustered environ-ments have the potential to provide great performance benets to dis-tributed resource-intensive applications. However, at the present time, careful staging, scheduling, and/or reservation of resources is essen-tial in order for applications to achieve performance in Grid environ-ments. If Computational Grids and shared computational clusters are to achieve their full potential, it must be possible for users to achieve application performance at any given time, and when other users are present in the system. In this paper, we describe the initial development of an AppLeS (Application-Level Scheduler) for the resource selection portion of the Synthetic Aperture Radar Atlas (SARA) application, developed at JPL.We demonstrate the eectiveness of application scheduling for dis-tributed data applications such as SARA by providing a performance-eÆcient strategy for retrieving SARA data les in everyday, multiple-user Grid environments