Speaker
Description
German computing sites play a vital role in the Large Hadron Collider (LHC) job processing and data storage as part of the Worldwide LHC Computing Grid (WLCG). The storage and computing contributions of university-based Tier-2 centres in Germany are transitioning to the Helmholtz Centres and National High Performance Computing (NHR) sites, respectively, to meet the growing data and computational demands of the High-Luminosity LHC (HL-LHC). This transition requires scalable strategies for data storage, data distribution, and their integration with computing centres.
Research towards this transition is conducted in Goettingen, where both the WLCG Tier-2 GoeGrid and the NHR HPC cluster Emmy are located. GoeGrid contributes to the ATLAS Collaboration computational tasks and data storage. Its batch system is extended with containers, allowing Emmy nodes to act as virtual worker nodes for LHC job processing.
Since large local mass storage is not planned at NHR centres for WLCG operations, alternative storage stolutions are being evaluated. Three approaches are currently investigated: pre-caching with a small storage instance of the order of 100 TB at GoeGrid, direct data access via WAN to the Helmholtz Centres DESY and GridKa and a satellite dCache storage instance of DESY deployed at Emmy. The latter is being implemented within the FUSE project, while the tests of the first two strategies have been already started within the FIDIUM project. Their performance has been benchmarked on Emmy using the current ATLAS workflow management system.
While results are promising, ongoing studies aim to identify potential bottlenecks in order to ensure scalability and applicability at other computing centres without large local storage. The concepts, performance results, and limitations of the storage strategies are presented, providing insights into future LHC computing and data management.