Speaker
Prof.
joel snow
(Langston University)
Description
DZero uses a variety of resources on four continents to pursue a
strategy of flexibility and automation in the generation of simulation
data. This strategy provides a resilient and opportunistic system
which ensures an adequate and timely supply of simulation data to
support DZero's physics analyses. A mixture of facilities, dedicated
and opportunistic, specialized and generic, large and small, grid job
enabled and not, are used to provide a production system that has
adapted to newly developing technologies. This strategy has increased
the event production rate by a factor of seven and the data production
rate by a factor of ten in the last three years despite diminishing
manpower. Common to all production facilities is the SAM (Sequential
Access to Metadata) data-grid. Job submission to the grid uses
SAMGrid middleware which may forward jobs to the OSG, the WLCG, or
native SAMGrid sites. The distributed computing and data handling
system used by DZero will be described and the results of MC
production since the deployment of grid technologies will be
presented.
Summary
Geographically and resource diverse DZero simulation production has grown substantially in recent years. Strategy, architecture, implementation, and results will be presented.
| Presentation type (oral | poster) | oral |
|---|
Primary author
Prof.
joel snow
(Langston University)
