Performance and impact of dynamic data placement in ATLAS

Mostrar otras versiones (1)

For high-throughput computing the efficient use of distributed computing resources relies on an evenly distributed workload, which in turn requires wide availability of input data that is used in physics analysis. In ATLAS, the dynamic data placement agent C3PO was implemented in the ATLAS distribut...

Descripción completa

Detalles Bibliográficos
Autores principales: Maier, Thomas, Beermann, Thomas Alfons, Duckeck, Guenter, Lassnig, Mario, Legger, Federica, Vukotic, Ilija, Magoni, Matteo
Lenguaje:eng
Publicado: 2018
Materias:
Particle Physics - Experiment
Acceso en línea:https://dx.doi.org/10.1051/epjconf/201921404025
http://cds.cern.ch/record/2644708
_version_ 1780960398547091456
author Maier, Thomas
Beermann, Thomas Alfons
Duckeck, Guenter
Lassnig, Mario
Legger, Federica
Vukotic, Ilija
Magoni, Matteo
author_facet Maier, Thomas
Beermann, Thomas Alfons
Duckeck, Guenter
Lassnig, Mario
Legger, Federica
Vukotic, Ilija
Magoni, Matteo
author_sort Maier, Thomas
collection CERN
description For high-throughput computing the efficient use of distributed computing resources relies on an evenly distributed workload, which in turn requires wide availability of input data that is used in physics analysis. In ATLAS, the dynamic data placement agent C3PO was implemented in the ATLAS distributed data management system Rucio which identifies popular data and creates additional, transient replicas to make data more widely and more reliably available. This proceedings presents studies on the performance of C3PO and the impact it has on throughput rates of distributed computing in ATLAS. Furthermore, results of a study on popularity prediction using machine learning techniques are presented.
id cern-2644708
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2018
record_format invenio
spelling cern-26447082022-08-10T12:23:24Zdoi:10.1051/epjconf/201921404025http://cds.cern.ch/record/2644708engMaier, ThomasBeermann, Thomas AlfonsDuckeck, GuenterLassnig, MarioLegger, FedericaVukotic, IlijaMagoni, MatteoPerformance and impact of dynamic data placement in ATLASParticle Physics - ExperimentFor high-throughput computing the efficient use of distributed computing resources relies on an evenly distributed workload, which in turn requires wide availability of input data that is used in physics analysis. In ATLAS, the dynamic data placement agent C3PO was implemented in the ATLAS distributed data management system Rucio which identifies popular data and creates additional, transient replicas to make data more widely and more reliably available. This proceedings presents studies on the performance of C3PO and the impact it has on throughput rates of distributed computing in ATLAS. Furthermore, results of a study on popularity prediction using machine learning techniques are presented.ATL-SOFT-PROC-2018-010oai:cds.cern.ch:26447082018-10-24
spellingShingle Particle Physics - Experiment
Maier, Thomas
Beermann, Thomas Alfons
Duckeck, Guenter
Lassnig, Mario
Legger, Federica
Vukotic, Ilija
Magoni, Matteo
Performance and impact of dynamic data placement in ATLAS
title Performance and impact of dynamic data placement in ATLAS
title_full Performance and impact of dynamic data placement in ATLAS
title_fullStr Performance and impact of dynamic data placement in ATLAS
title_full_unstemmed Performance and impact of dynamic data placement in ATLAS
title_short Performance and impact of dynamic data placement in ATLAS
title_sort performance and impact of dynamic data placement in atlas
topic Particle Physics - Experiment
url https://dx.doi.org/10.1051/epjconf/201921404025
http://cds.cern.ch/record/2644708
work_keys_str_mv AT maierthomas performanceandimpactofdynamicdataplacementinatlas
AT beermannthomasalfons performanceandimpactofdynamicdataplacementinatlas
AT duckeckguenter performanceandimpactofdynamicdataplacementinatlas
AT lassnigmario performanceandimpactofdynamicdataplacementinatlas
AT leggerfederica performanceandimpactofdynamicdataplacementinatlas
AT vukoticilija performanceandimpactofdynamicdataplacementinatlas
AT magonimatteo performanceandimpactofdynamicdataplacementinatlas

Ejemplares similares