Abstract
In LHC Run 3 the ALICE Computing Model will change. The Grid Tiers will to a large extend be specialised for a given role. 2/3 of the reconstruction and calibration will be done at the combined online and offline O2 compute facility, 1/3 will be done by the Tier1 centres in the Grid. Additionally all Tier1 centres, as already now, will take care of archiving one copy of the raw data on tape. The Tier2 centres will only do simulation. The AODs will will be collected on specialised Analysis Facilities which shall be capable of processing 10 PB of data within 24 hours. A prototype of such an Analysis Facility has been set up at GSI based on the experiences with the local ALICE Tier2 centre which has been in production since 2002. The main components are a general purpose HPC cluster with a mounted cluster file system enhanced by Grid components like an XRootD based Storage Element and an interface for being able to receive and run dedicated Grid jobs on the Analysis Facility prototype. The necessary I/O speed as well as easy local data access is facilitated by self developed XRootD PlugIns. Performance tests with real life ALICE analysis trains suggest that the target throughput rate can be achieved.
Highlights
An upgrade of the ALICE [1] detector is currently prepared for the Run 3 period of the Large Hadron Collider (LHC) [2] at CERN starting in 2020
The Grid Tiers will to a large extend be specialised for a given role. 2/3 of the reconstruction and calibration will be done at the combined online and offline O2 compute facility, 1/3 will be done by the Tier1 centres in the Grid
A prototype of such an Analysis Facility has been set up at GSI based on the experiences with the local ALICE Tier2 centre which has been in production since 2002
Summary
An upgrade of the ALICE [1] detector is currently prepared for the Run 3 period of the Large Hadron Collider (LHC) [2] at CERN starting in 2020. The upgraded ALICE detector will produce more than 1 TByte/s of data Both collision and data rate impose new challenges onto the detector readout and compute system. In LHC Run 3 the ALICE computing model will change with the idea to minimise data movement and to optimise processing efficiency. The Tier centres are responsible of keeping together another copy of the raw data (the first copy is at CERN) and storing them on tape as long term archive. Keeping a copy of the raw data and archiving them on tape will stay a responsibility of the Tier centres. The design has been inspired by the experiences gained with the local ALICE Tier centre [4] which has been in production since 2002
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
