Heidelberg 2022 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
T: Fachverband Teilchenphysik
T 15: GRID Computing
T 15.1: Vortrag
Montag, 21. März 2022, 16:15–16:30, T-H28
Rucio Datamanagement: Expanding the capabilities for dealing with potentially problematic files — •Christoph Ames1, Günter Duckeck1, Rodney Walker1, and Cédric Serfon2 — 1Ludwig-Maximillians-Universität, Munich — 2Brookhaven National Laboratory
Rucio is a software framework that enables the management of large collections of data. Originally developed for the ATLAS experiment at the Large Hadron Collider (LHC), it has been expanded to encompass other scientific experiments, such as CMS and Belle II, whereby data is stored on and transferred between over 100 data centres across the world. Accessing files on these data centres doesn't always function without problems occurring, therefore dedicated services are used to track files that are being accessed or transferred. Files that cause problems are marked as suspicious by the tracking services and have to be handled by another service, the suspicious replica recoverer. The goal of this work is to expand the suspicious replica recoverer by adding more flexibility and nuance when deciding what should be done with a suspicious file. This is achieved by introducing a policy system based on file metadata, which allows each virtual organisation to individually set their own policies.