Speaker
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 target of “MAssive RAy TRAcing in Fusion Plasmas” is the
Fusion Physics
scientific community. In particular, MARATRA aids those community
members who are
working in the optimization of plasma heating by electron
Bernstein waves (EBW).
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.
For porting this application onto the Grid, we relied on the
execution services
offered by FUSION VO resources and used the GridWay Metascheduler
(http://www.gridway.org/) as a Resource Broker. In particular,
its workload
management capabilities have been proved to be very valuable in
order to scale the
input data. These valuable capabilities comprehend Opportunistic
Migration (automatic
resubmission of running jobs to better resources), Performance
Slowdown Detection
(migration when a intolerable performance loss for a job, which
happens to be case in
the present application) and Fault Detection & Recovery (job
cancellation, remote
system crash or outage, network disconnection, client fault
tolerance). Also, GridWay
has been chosen because it implements the Open Grid Forum
(http://www.ogf.org/) DRMAA
Standard (http://drmaa.org/), both C and JAVA bindings, providing
compatibility of
applications with DRM systems that implement the Standard, such
as SGE, Condor, ...
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)
Basically, we found the queuing times high and, in many
occasions, many computing
resources (downtime and even DN not mapped) were not available.
Thanks to its fault
tolerance mechanisms, GridWay could handle these situations,
making its combination
with the EGEE infrastructure a very reliable one.
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
A microwave beam can be modeled as a set of rays, each one with
an independent
trajectory. The more rays that can be traced, the more accurate
the results are. A
regular case study in a cluster environment involves tracing a
factor of 10^2 rays.
The proposed optimization procedure in the case of EBW heating
needs to increase two
orders of magnitude the number of rays used in conventional ray
tracing. The
possibilities offered by a large-scale Grid infrastructure, and
in particular EGEE,
is to increase this factor to 10^3 and 10^4.
