Testbed Monitoring Kaushik De Univ. of Texas at Arlington U.S. ATLAS Grid Workshop Boston, June 2002
Overview Monitoring is critically important in distributed Grid computing check system health, debug problems discover resources using static data job scheduling and resource allocation decisions using dynamic data Testbed monitoring priorities Site configuration Software installation Application monitoring Grid status/operations monitoring Also need Data for job scheduling Visualization
Back End Publishing MDS information Non-MDS back ends Good progress! Glue schema - BNL & UTA Pippy - Pacman information service provider BNL ACAS schema Hierarchical GIIS server Non-MDS back ends iPerf Netlogger Prophesy Ganglia Good progress!
Middle (archiving) MySQL RRD Work needed GridView BNL ACAS Network What to store? Replication?
Front End MDS based Non-MDS Work needed GridView Gridsearcher Perl? Cricket Ganglia Work needed Urgently for SC2002! Graphs, maps, drill-down… Need visualization volunteers!