DIRAC: Workload Management System

The Workload Management System is the core component of the DIRAC distributed MC production and analysis grid environment of the CERN LHCb experiment. This paper discusses the architecture, implementation and performance of this system. The WMS is a community scheduler, realizing a pull paradigm, pa...

Descripción completa

Detalles Bibliográficos
Autores principales: Garonne, V, Tsaregorodtsev, A Yu, Stokes-Rees, I
Lenguaje:eng
Publicado: CERN 2004
Materias:
Detectors and Experimental Techniques
Computing and Computers
Acceso en línea:https://dx.doi.org/10.5170/CERN-2005-002.1041
http://cds.cern.ch/record/798910
_version_ 1780904715380326400
author Garonne, V
Tsaregorodtsev, A Yu
Stokes-Rees, I
author_facet Garonne, V
Tsaregorodtsev, A Yu
Stokes-Rees, I
author_sort Garonne, V
collection CERN
description The Workload Management System is the core component of the DIRAC distributed MC production and analysis grid environment of the CERN LHCb experiment. This paper discusses the architecture, implementation and performance of this system. The WMS is a community scheduler, realizing a pull paradigm, particulary for the high troughput computing context. It has recently been used for an intensive physics simulation production involving more than 60 sites, 65 TB of data, and over 1000-GHz processor-years.
id cern-798910
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2004
publisher CERN
record_format invenio
spelling cern-7989102019-09-30T06:29:59Zdoi:10.5170/CERN-2005-002.1041http://cds.cern.ch/record/798910engGaronne, VTsaregorodtsev, A YuStokes-Rees, IDIRAC: Workload Management SystemDetectors and Experimental TechniquesComputing and ComputersThe Workload Management System is the core component of the DIRAC distributed MC production and analysis grid environment of the CERN LHCb experiment. This paper discusses the architecture, implementation and performance of this system. The WMS is a community scheduler, realizing a pull paradigm, particulary for the high troughput computing context. It has recently been used for an intensive physics simulation production involving more than 60 sites, 65 TB of data, and over 1000-GHz processor-years.CERNLHCb-PROC-2004-023LHCb-2004-084oai:cds.cern.ch:7989102004-10-19
spellingShingle Detectors and Experimental Techniques
Computing and Computers
Garonne, V
Tsaregorodtsev, A Yu
Stokes-Rees, I
DIRAC: Workload Management System
title DIRAC: Workload Management System
title_full DIRAC: Workload Management System
title_fullStr DIRAC: Workload Management System
title_full_unstemmed DIRAC: Workload Management System
title_short DIRAC: Workload Management System
title_sort dirac: workload management system
topic Detectors and Experimental Techniques
Computing and Computers
url https://dx.doi.org/10.5170/CERN-2005-002.1041
http://cds.cern.ch/record/798910
work_keys_str_mv AT garonnev diracworkloadmanagementsystem
AT tsaregorodtsevayu diracworkloadmanagementsystem
AT stokesreesi diracworkloadmanagementsystem

Ejemplares similares