Virtual data in CMS production
Initial applications of the GriPhyN Chimera Virtual Data System have been performed within the context of CMS Production of Monte Carlo Simulated Data. The GriPhyN Chimera system consists of four primary components: (1) a Virtual Data Language, which is used to describe virtual data products, (2) a Virtual Data Catalog, which is used to store virtual data entries, (3) an Abstract Planner, which resolves all dependencies of a particular virtual data product and forms a location and existence independent plan, (4) a Concrete Planner, which maps an abstract, logical plan onto concrete, physical grid resources accounting for staging in/out files and publishing results to a replica location service. A CMS Workflow Planner, MCRunJob, is used to generate virtual data products using the Virtual Data Language. Subsequently, a prototype workflow manager, known as WorkRunner, is used to schedule the instantiation of virtual data products across a grid.
- Research Organization:
- Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
- Sponsoring Organization:
- USDOE Office of Energy Research (ER) (US)
- DOE Contract Number:
- AC02-76CH03000
- OSTI ID:
- 828651
- Report Number(s):
- FERMILAB-Conf-03/485-CD; TRN: US0404057
- Resource Relation:
- Conference: CHEP 03, La Jolla, CA (US), 03/24/2003--03/28/2003; Other Information: PBD: 26 Aug 2004
- Country of Publication:
- United States
- Language:
- English
Similar Records
Using Grid for the BABAR Experiment
Swift : fast, reliable, loosely coupled parallel computation.