User-Centric Monitoring and Steering of the Execution of Large Job Sets

Processing of large data sets with high through put is one of the major focus of Grid computing today. If possible, data are split up into small chunks that are processed independently. Thus, job sets of hundreds > or even thousands of individual jobs are possible. For the job submitter or the resource providers such a scenario is a nightmare currently, as it is hard to keep track of such an amount of jobs or to identify failure reasons. We present a system that will support gLite users to track and monitor their jobs and their resource usage, to nd and identify failure reasons and even to steer running applications.