   |  |
Computing Technical Design Report
| | |
Computing Technical Design Report
Simulated data are assumed to be produced in the external Tier-2 facilities. Once produced, the simulated data must be available for the whole collaboration on an essentially 24/7 basis, as for real data. This requirement suggests that the simulated data should be stored at the Tier-1 facilities unless the lower tiers can guarantee the required level of access. However, it is assumed that all of the required derived datasets (ESD, AOD and TAG) are produced together at the same site, and then transported to their eventual storage location.
If the produced simulated data are to be shipped to the local storage site, this would contribute to the required connectivity to the regional Tier-1. If it is not shipped offsite, the bandwidth must also support the replication offsite on demand when the simulated data are analysed, or else the local facility must also support (and be credited for) the processing of ATLAS analysis jobs from all regions. The relative merits of moving jobs to the data or data to the jobs are a key issue in the Grid, and the optimal strategy depends on the requested data volume, the CPU requirement of the job and the available network interconnect. In general, all the factors tend to suggest that the storage and analysis of simulated data are best handled through the Tier-1 facilities by default, although some larger Tier-2 facilities may wish to share this load, with appropriate credit.
In addition to the official datasets that are officially requested by ATLAS and available to all, there will be additional samples that will be generated locally to test and optimize the simulation procedures and support local analyses. These only enter in the Computing Model in terms of their resource requirements, and are accounted in the resource requirements per user in the Section 2.3 .
| | |
Copyright © CERN 2005