GridPP3 project resources at Royal Holloway, University of London

点击翻译按钮获取中文摘要

'The Grid' is the next leap in computer interconnectivity. The Internet and the World Wide Web are increasingly an integral part of people's lives, helping the world share information and transfer data quickly and easily. In the same way as we now share files and facts over the global network of computers, in the future the Grid will let us share other things, such as processing power and storage space. The Grid is a practical solution to the problems of storing and processing the large quantities of data that will be produced by industry and the scientific communities over the next decade. Particle physicists are waiting for 2007 when a new particle accelerator opens in the world's largest particle physics laboratory, CERN. The Large Hadron Collider (LHC) will be the most powerful instrument ever built to investigate fundamental physics. Once this is fully functional the amount of data being produced will be massive. All this will be too much for one institution to handle so they need to share resources i.e. to use distributed computing. The Grid is built on the same Internet infrastructure as the web, but uses different tools. Middleware is one of these tools. In a stand alone computer the resources allocated to each job are managed by the operating system e.g. Windows, Linux, Unix, Mac OS X. Middleware is like the operating system of a Grid, allowing users to access resources without searching for them manually. GridPP has developed middleware for the Grid, in collaboration with other international projects. Due to GridPP's open source policy, the middleware can evolve and be improved by the people who use it. Distributed computing has been available to scientists for some time but, in general, the use of different sites has to be negotiated by each scientist individually. They need a separate account on each system and jobs have to be submitted and results collected back by hand. Current distributed computing means the user has a lot of work to do to get their results. This is where the idea of Grid computing comes in. Middleware lets users simply submit jobs to the Grid without having to know where the data is or where the jobs will run. The software can run the job where the data is, or move the data to where there is CPU power available. Using the Grid and middleware, all the user has to do is submit a job and pick up the results. Acting as the gatekeeper and matchmaker for the Grid, middleware monitors the Grid, decides where to send computing jobs, manages users, data and storage. It will check the identity of the user through the use of digital certificates. A digital certificate is a file stored securely on a user's computer which allows the Grid to correctly identify a user. The certificates are given to a user by the Certification Authority, with numerous steps to ensure the person applying is who they say they are. The middleware automatically extracts the users' identity from their digital certificate and uses this to log them in. This means users don't have to remember user names and passwords to log onto the Grid, they're automatically logged on using their Grid certificate. After this seamless identification process the middleware will find the most convenient and efficient places for the job to be run and organise efficient access to the relevant scientific data. It deals with authentication to the different sites being used, runs the jobs, keeps track of progress, lets the user know when the work is complete and transfers the result back.