Speaker
Paul Nilsson
(UT-Arlington)
Description
The PanDA software provides a highly performant distributed production and
distributed analysis system. It is the first system in the ATLAS experiment to use a
pilot based late job delivery technique. In this talk, we will describe the
architecture of the pilot system used in Panda. Unique features have been implemented
for high reliability automation in a distributed environment. Performance of Panda
will be analyzed from one and half year of experience of performing distributed
computing on the OSG infrastructure. Experience with pilot delivery mechanism using
CondorG, and a GlideIn factory developed under OSG will be described.
| Submitted on behalf of Collaboration (ex, BaBar, ATLAS) | ATLAS |
|---|
Primary author
Paul Nilsson
(UT-Arlington)
