APPLICATIONS

The European DataGrid (EDG)1 project has taken a major step towards making the concept of a world-wide computing Grid a reality. Its latest release of middleware - the software that makes a Grid of computers work together seamlessly - will support production quality Grid computing. Markus Schulz, one of the chief software developers at CERN2, explains, "This release will take the EDG project from the laboratory bench into the real world." One of the main aims of the European DataGrid project, which started almost two years ago, is to go beyond the R&D phase and demonstrate a "production quality" computing Grid. Production quality means not just a proof of principle, but the deployment of a stable resource that European scientists can plug into and use on a regular basis. Such a Grid should give scientists unprecedented computing power to tackle major challenges, such as modelling climate change or analysing genomic data. The explicit goal of the EDG's new release of Grid middleware, which was officially made on November 11th, is to support production quality Grid computing. It builds both on software previously developed in the EDG project as well as on established open source solutions. Starting from elements of a toolkit for Grid software development known as Globus 2.2, the new release has greatly improved support for large file transfers, offering better tracking of applications as they run on the Grid and a more stable information system. Several key features for production have been added, such as simplified access to mass storage systems, an easier software installation mechanism and user friendly job submission facilities. The software is currently being installed on hundreds of computers that make up the EDG production testbed, one of the largest and most sophisticated Grid infrastructures being developed in the world. Initially limited to five European countries, the testbed has recently been enlarged to approximately 20 sites across Europe, including Poland, the Czech Republic, Spain, Portugal, Germany and the Nordic countries. Interoperability with Grid infrastructure being developed in the US has also been demonstrated, and new sites in Asia, Russia and Canada will soon be added to the testbed. Connections of the different European nodes are made possible by the EU-cofunded GEANT project, a world-leading data communications network connecting more than 30 countries across Europe at speeds of up to 10 gigabits per second. The EDG project will provide one of the first major production quality tests of this impressive network. EDG and GEANT are collaborating to address issues such as speed, reliability and monitoring capabilities raised by the applications running on the EDG testbed. The EDG production testbed will be used by scientific communities to perform research in three key areas: Genomic Exploration, Earth Observation and High Energy Physics. In the latter domain, physicists working at CERN are relying on Grid technology to solve the huge data challenge they will face when the Large Hadron Collider (LHC) - the most powerful instrument ever built to investigate the properties of matter - starts running. The LHC experiments will generate some 10 Petabytes of data each year. This is the equivalent of 16 million CD-roms, and the challenge of storing and analysing such huge amounts of data is enormous. Professor Alois Putzer, from the University of Heidelberg and responsible for the organization of the worldwide computing of the Atlas experiment on the LHC says, "We are delighted that the EDG project is already releasing production quality Grid middleware. It will allow us to start regular testing of our extreme computational requirements on a real Grid infrastructure, and could have a significant impact on how we plan our world wide distributed computing centre and the access to the data."