EUROPEAN ORGANIZATION FOR NUCLEAR RESEARCH | |
| |
August 28th, 2002 | |
Last rev:August 28th, 2002 |
The analysis of LHC data will be performed in "Regional Computing Centres", closely integrated with each other and the CERN facility to provide as far as possible a single computing environment. The total combined cost of these facilities is expected to be several hundred million Swiss francs, with running costs in the tens of millions.
It is most likely that the centres themselves will be built from large clusters of PCs integrated with inexpensive disks, using models that have been developed in HEP over the past decade, with Linux as the operating system. However, the scale of these facilities will be very large by comparison with today's installations, and novel techniques will be required to automate the management of these clusters and the associated data. While it is hoped that appropriate tools will eventually be available from industrial sources, in the short to medium term HEP institutes will have to develop their own solutions. It is clearly of interest to LCG that the various institutes share such developments, agree wherever possible on the choice of third party tools, and standardise on the details of the Linux environment.
The Regional Centres will be integrated using Grid Middleware, initially developed by R&D projects funded through various government programmes in Europe, the United States and elsewhere. As these toolkits begin to be used to provide productive services for physics collaborations, and as the LCG global grid service takes shape it will be important that there is effective communication and collaboration between the Regional Centres to share early experiences, and agree on standards, common procedures and many practical details.
At the LCG Launching Workshop at CERN in March 2002 it was agreed to use HEPIX as the technical forum for sharing ideas and experience between the labs involved in regional centre computing, with a view to minimising the number of overlapping developments and maximising the degree of standardisation of the environment. HEPIX is an appropriate forum for this activity as it encompasses the systems and support experts from most HEP institutes, covering existing and future experiments.
The formal management of the LCG Global Grid Service will be organised separately, subject to organisational and policy decisions taken by the LCG Grid Deployment Board (GDB). The technical staff of the Regional Centres will be asked to provide input to the GDB. This will be done following the normal management structures of the Regional Centres. HEPiX is intended to be a forum for technical information exchange, not a management body of the LCG.
Converted for the web by Maria Dimou