Speaker
With a forward look to future evolution, discuss the issues you have encountered (or that you expect) in using the EGEE infrastructure. Wherever possible, point out the experience limitations (both in terms of existing services or missing functionality)
The Egee infrastructure is not as reliable as current batch systems. The
instablility of key elements such as resource brokers and VOMS, the
incompatibilities between software releases, constantly changing data access
policies, poor error reporting, lack of user documentation, the disconnect
betwen the user and the support, and the general high learning curve all
contribute to difficulties for the experts and failure to motivate users.
Describe the scientific/technical community and the scientific/technical activity using (planning to use) the EGEE infrastructure. A high-level description is needed (neither a detailed specialist report nor a list of references).
The BaBar experiment is a high-energy physics collaboration based at SLAC,
California, USA, with 570 members from 10 countries investigating the
properties of anti-matter. The Grid is used for simulating the experiment,
reconstructing and processing the experimental results, and analysing the
results for publication.
Report on the experience (or the proposed activity). It would be very important to mention key services which are essential for the success of your activity on the EGEE infrastructure.
In this contribution, we discuss the experience of converting pre-Grid
computing models to using the Grid; the relative costs and benefits of the Grid
to the three core tasks of simulation, central reconstruction and user analysis;
and the ability of the Grid to meet the time-critical needs of an experiment that
runs 24/7. Key to the success of the project is high throughput, high reliability,
high efficiency, low latency, good monitoring and reporting, and guaranteed
future resource use. We compare the Grid and classic batch systems against
these key metrics.
Describe the added value of the Grid for the scientific/technical activity you (plan to) do on the Grid. This should include the scale of the activity and of the potential user community and the relevance for other scientific or business applications
In 2006, the experiment required 1.4 Petabytes of storage and 5500 KSI2K of
computing power to simulate, process, reconstruct and analyse our large
dataset with low latency and high efficiency. For the last two years we have
investigated the use of the Grid as an alternative resource to achieve our
current and future goals. The main goals have been a need to double are
processing requirements while keeping manpower at current or reduced levels.