BAcK to Curriculum
:: Distributed Computing Grid Experiences in CMS Data Challenge

Alessandra Fanfani
Dept. of Physics and INFN, Bologna

The Compact Muon Solenoid experiment (CMS) is one of the four High Energy Physics experiments that will collect data at the Large Hadron Collider (LHC) being build at CERN. The CMS collaboration is currently taking part in computing intensive Monte Carlo simulation studies of the detector. CMS has a long term need to perform large-scale simulation efforts, in which physics events are generated and their manifestations in the CMS detector are simulated.
The challenge for the CMS computing infrastructure is to cope with the very large computational and data access requirements. The size of the resources required, the complexity of the software and the physical distribution of the CMS collaboration naturally imply a distributed computing and data access solution.
The Grid paradigm is one of the most promising solutions to be investigated, and CMS is collaborating with many Grid projects with the aim of understanding how the Grid can be useful for CMS and how CMS software needs to be adapted to use Grid functionalities.
The preparation and building of the Computing System able to treat the data being collected pass through sequentially planned steps of increasing complexities (data and physics challenges).
Data Challenge for CMS during the year 2004 was planned to reach a complexity scale equal to about 25% of that foreseen for LHC initial running.
The goal of the challenge was to run CMS reconstruction for sustained period at 25Hz input rate, distribute the data to the CMS Tier-1 centers and analyze them at remote sites. To achieve the challenge CMS undertook a large simulated event production in advance. Grid environments developed in Europe by the LHC Computing Grid (LCG) in Europe and in the US with Grid2003 were utilized to complete the aspects of the challenge.
A description of the experiences, successes and lessons learned from experiences with grid infrastructure is presented.

Slides: [ppt|pdf]