Last update: Apr 1, 2000
Speaker: Julian BunnThe GIOD (Globally Interconnected Object Databases) Project, a joint effort between Caltech and CERN, funded by Hewlett Packard Corporation, has investigated the use of WAN-distributed Object Databases and Mass Storage systems for LHC data. A prototype small-scale LHC data analysis center has been constructed using computing resources at Caltech’s Centre for Advanced Computing Research. These resources include a 256 CPU HP Exemplar of ~4600 SPECfp95, a 600 TByte High Performance Storage System (HPSS), and local/wide area links based on OC3 ATM. Using the Exemplar, a large number of fully simulated CMS events were produced, and used to populate an object database with a complete schema for raw, reconstructed and analysis objects. The reconstruction software used for this task was based on early codes developed in preparation for the current CMS reconstruction program, ORCA. Simple analysis software was then developed in Java, and integrated with SLAC’s Java Analysis Studio tool. An event viewer was constructed with the Java 3D API. Using this suite of software, tests were made in collaboration with researchers at FNAL and SDSC, that focused on distributed access to the database by numerous clients, and measurements of peak bandwidths were made and interpreted.
In this paper, the most significant findings from the GIOD Project are presented. The goals of the follow-on project “GIOD II” are described, and put in context with other current activities at Caltech in this area. These include the DoE-funded “Particle Physics Data Grid”, the NSF-funded “Accessing Large Data Archives in Astronomy and Particle Physics” project, and continuing work on the MONARC project.
|| | Home | Bulletins | Committees | Scientific Program | Docs by topics | Social Event | Conference Location | Secretariat |