Parts | Days | Selection | Search | Updates | Downloads | Help

T: Fachverband Teilchenphysik

T 76: Grid-Computing I

T 76.2: Talk

Wednesday, March 30, 2011, 17:05–17:20, 30.23: 2-1

The Consistency Service of the ATLAS Distributed Data Management system — •Cédric Serfon, Philippe Calfayan, Günter Duckeck, Johannes Ebke, Johannes Elmsheuser, Federica Legger, Christoph Mitterer, Dorothee Schaile, and Rodney Walker — LMU Munich

With the continuously increasing volume of data (More than 50 PB) produced by ATLAS and stored on the WLCG sites, the probability of data corruption or data losses (for instance due to hardware failure) is increasing. With the current size of the disks, a pool crash that cannot be recovered typically represents O(10000) files. It is therefore important to have an automated service to recover these file losses : this is the role of the Consistency Service. This service is used by various ATLAS tools (Analysis tools, Production tools, DQ2 Site Services...) or by site administrators that report corrupted or lost files. It automatically recovers lost files or corrects the errors reported and informs the users in case of irrecoverable file loss.