SearcharxivSearch

arXiv subjects

S. Fantinel

Publications and source records attributed to S. Fantinel.

2 recordsLinked to original sources

Running CMS software on GRID Testbeds

Starting in the middle of November 2002, the CMS experiment undertook an evaluation of the European DataGrid Project (EDG) middleware using its event simulation programs. A joint CMS-EDG task force performed a "stress test" by submitting a large number of jobs to many distributed sites. The EDG testbed was complemented with additional CMS-dedicated resources. A total of ~ 10000 jobs consisting of two different computational types were submitted from four different locations in Europe over a period of about one month. Nine sites were active, providing integrated resources of more than 500 CPUs and about 5 TB of disk space (with the additional use of two Mass Storage Systems). Descriptions of the adopted procedures, the problems encountered and the corresponding solutions are reported. Results and evaluations of the test, both from the CMS and the EDG perspectives, are described.

physics.comp-ph

A monitoring tool for a GRID operation center

WorldGRID is an intercontinental testbed spanning Europe and the US integrating architecturally different Grid implementations based on the Globus toolkit. The WorldGRID testbed has been successfully demonstrated during the WorldGRID demos at SuperComputing 2002 (Baltimore) and IST2002 (Copenhagen) where real HEP application jobs were transparently submitted from US and Europe using "native" mechanisms and run where resources were available, independently of their location. To monitor the behavior and performance of such testbed and spot problems as soon as they arise, DataTAG has developed the EDT-Monitor tool based on the Nagios package that allows for Virtual Organization centric views of the Grid through dynamic geographical maps. The tool has been used to spot several problems during the WorldGRID operations, such as malfunctioning Resource Brokers or Information Servers, sites not correctly configured, job dispatching problems, etc. In this paper we give an overview of the package, its features and scalability solutions and we report on the experience acquired and the benefit that a GRID operation center would gain from such a tool.

cs.DC