Computing grid ready for Large Hadron Collider restart
1 min read
The massive compute power needed to support the experiments at the Large Hadron Collider (LHC ) has passed all tests mimicking the load when the world's most powerful particle accelerator finally restarts later this year.
After months of preparation and two intensive weeks of continual operation, the Worldwide LHC Computing Grid (wLCG) says it has demonstrated that it is ready to support the massive growth in LHC users once data taking commences.
wLCG combines the IT power of more than 140 computer centres – the result of collaboration between 33 countries. The UK features very strongly throughout – contributing 21 of these sites and a staggering 15,000 computers. UK facilities are all managed by GridPP, funded by the Science and Technology Facilities Council (STFC).
While there have been several large-scale data-processing tests in recent years, the latest exercise, codenamed STEP'09, was the first full demonstration involving all key elements, from data taking at CERN through to analysis of data at the individual sites worldwide.
GridPP reports that the main ATLAS experiment alone successfully ran close to 1 million analysis jobs and achieving 6Gbps of grid traffic over long periods – yes, that's the equivalent of a DVD worth of data every second.
"Unlike previous challenges, which were dedicated testing periods, STEP'09 was a production activity that closely matches the types of workload that we can expect during LHC data taking. It was a demonstration not only of the readiness of experiments, sites and services but also the operations and support procedures and infrastructures," comments Ian Bird, leader of the wLCG project.
