Speaker
Dr
Patricia Mendez Lorenzo
(CERN IT/PSS)
Description
The EGEE infrastructure is a key part of the computing environment for the
simulation, processing and analysis of the data of the Large Hadron Collider (LHC)
experiments (ALICE, ATLAS, CMS and LHCb). The example of the LHC experiments
illustrates well the motivation behind Grid technology. The LHC accelerator will
start operation in 2007, and the total data volume per experiment is estimated to
be
a few PB/year at the beginning of the machine’s operations, leading to a total
yearly production of several hundred PB for all four experiments around 2012. The
processing of this data will require large computational, storage and associated
human resources for operation and support. It was not considered feasible to fund
all of the resources at one site, and so it was agreed that the LCG computing
service would be implemented as a geographically distributed Computational Data
Grid. This means, the service will use computational and storage resources,
installed at a large number of computing sites in many different countries,
interconnected by fast networks. At the moment, the EGEE infrastructure counts 160
sites, distributed over more than 30 countries. These sites hold 15000 CPUs and
about 9PB of storage capability.
The Grid middleware will hide much of the complexity of this environment from the
user, organizing all the resources in a coherent virtual computer centre.
The computational and storage capability of the Grid is attracting other research
communities and we would like to discuss the general patterns observed in
supporting
new applications, porting their application onto the EGEE infrastructure.
In this talk we present our experiences in the porting of three different
applications inside the Grid like Geant4, UNOSAT and others.
Geant4 is a toolkit for the Monte Carlo simulation of the interaction of particles
with matter. It is applied to a wide field of research including high energy
physics
and nuclear experiments, medical, accelerator and space physics studies. ATLAS,
CMS,
LHCb, Babar, and HARP are actively using Geant4 in production.
UNOSAT is a United Nations initiative to provide the humanitarian community with
access to satellite imaginary and Geographic System services. UNOSAT is implemented
by the UN Institute for Training and Research (UNITAR) and manager by the UN Office
for Project Services (UNOPS). In addition, partners from public and private
organizations constitute the UNOSAT consortium. Among these partners, CERN
participates actively providing the computational and storage resources needed for
their images analysis.
During the gridification of the UNOSAT project, the collaboration with the
developers of the ARDA group to adapt the AMGA software to the UNOSAT expectations
was extremely important. The satellite images provided by UNOSAT have been stored
in
Storage Systems at CERN and registered inside the LCG Catalog (LFC). The files so
registered have been identified with an easy to remember Logical File Name (LFN).
The LFC Catalog is then able to map these LFN to the physical location of the
files.
Due to the UNOSAT infrastructure, their users will provide as input information the
coordinates of each image. AMGA is able to map these coordinates (considered
metadata information) to the corresponding LFN of the files registered inside the
Grid. Then the LFC will find the physical location of the images.
A successful model to guarantee a smooth and efficient entrance in the Grid
environment is to identify an expert support to work with the new community. This
person will assist them during the implementation and execution of their
applications inside the Grid. He will also be the Virtual Organization (VO) contact
person with the EGEE sites. This person will work together with the EGEE deployment
team and with the responsible of the sites to set the services needed by the
experiment or community, observing also the relevant security and access policies.
Once these new communities attain a good level of maturity and confidence, a VO
Manager would be identified in the users community.
This talk will report a number of concrete examples and it will try to summarize
the
main lessons. We believe that this should be extremely interesting for new
communities in order to early identify possible problems and prepare the
appropriate
solutions. In addition, this support scheme would also be very interesting as a
model, for example, for local application support in EGEE II.
Author
Dr
Patricia Mendez Lorenzo
(CERN IT/PSS)
