An Abstract Job Handling Grid Service for Dataset Analysis

75648-Systems for scheduling the analysis of large, remote nuclear physics datasets are being developed rapidly in many separate experiments. These separate efforts try to share implementation knowledge bases, but end up using different and non-interchangeable interfaces that require substantial expertise from users. In collaboration with the user community, this project will develop procedures for handling job requests, along with a grid service interface that allows users to submit, monitor, and control their requests. In addition, a reference implementation of a grid service for batch submission will be created by developing appropriate system-dependent sub-calls. Phase I will build a working prototype of the grid job submission service system, which will make use of, and extend as necessary, the latest working version of an abstract job-handling description language developed from within the user community. A schema for handling job control and tracking also will be developed. Commercial Applications and Other Benefits as described by the awardee: The service application could be used in various data intensive experiments, such as high-energy nuclear physics experiments, space science observations, and climate modeling. Similarly, it could be used for data processing and reduction in e-commerce and e-banking applications.