Cargando…

Benchmarking cloud resources for HEP

In a commercial cloud environment, exhaustive resource profiling is beneficial to cope with the intrinsic variability of the virtualised environment, allowing to promptly identify performance degradation. In the context of its commercial cloud initiatives, CERN has acquired extensive experience in b...

Descripción completa

Detalles Bibliográficos
Autores principales: Alef, M, Cordeiro, C, De Salvo, A, Di Girolamo, A, Field, L, Giordano, D, Guerri, M, Schiavi, F C, Wiebalck, A
Lenguaje:eng
Publicado: 2017
Materias:
Acceso en línea:https://dx.doi.org/10.1088/1742-6596/898/9/092056
http://cds.cern.ch/record/2298175
_version_ 1780956989853007872
author Alef, M
Cordeiro, C
De Salvo, A
Di Girolamo, A
Field, L
Giordano, D
Guerri, M
Schiavi, F C
Wiebalck, A
author_facet Alef, M
Cordeiro, C
De Salvo, A
Di Girolamo, A
Field, L
Giordano, D
Guerri, M
Schiavi, F C
Wiebalck, A
author_sort Alef, M
collection CERN
description In a commercial cloud environment, exhaustive resource profiling is beneficial to cope with the intrinsic variability of the virtualised environment, allowing to promptly identify performance degradation. In the context of its commercial cloud initiatives, CERN has acquired extensive experience in benchmarking commercial cloud resources. Ultimately, this activity provides information on the actual delivered performance of invoiced resources. In this report we discuss the experience acquired and the results collected using several fast benchmark applications adopted by the HEP community. These benchmarks span from open-source benchmarks to specific user applications and synthetic benchmarks. The workflow put in place to collect and analyse performance metrics is also described.
id oai-inspirehep.net-1638221
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2017
record_format invenio
spelling oai-inspirehep.net-16382212021-02-09T10:05:19Zdoi:10.1088/1742-6596/898/9/092056http://cds.cern.ch/record/2298175engAlef, MCordeiro, CDe Salvo, ADi Girolamo, AField, LGiordano, DGuerri, MSchiavi, F CWiebalck, ABenchmarking cloud resources for HEPComputing and ComputersIn a commercial cloud environment, exhaustive resource profiling is beneficial to cope with the intrinsic variability of the virtualised environment, allowing to promptly identify performance degradation. In the context of its commercial cloud initiatives, CERN has acquired extensive experience in benchmarking commercial cloud resources. Ultimately, this activity provides information on the actual delivered performance of invoiced resources. In this report we discuss the experience acquired and the results collected using several fast benchmark applications adopted by the HEP community. These benchmarks span from open-source benchmarks to specific user applications and synthetic benchmarks. The workflow put in place to collect and analyse performance metrics is also described.oai:inspirehep.net:16382212017
spellingShingle Computing and Computers
Alef, M
Cordeiro, C
De Salvo, A
Di Girolamo, A
Field, L
Giordano, D
Guerri, M
Schiavi, F C
Wiebalck, A
Benchmarking cloud resources for HEP
title Benchmarking cloud resources for HEP
title_full Benchmarking cloud resources for HEP
title_fullStr Benchmarking cloud resources for HEP
title_full_unstemmed Benchmarking cloud resources for HEP
title_short Benchmarking cloud resources for HEP
title_sort benchmarking cloud resources for hep
topic Computing and Computers
url https://dx.doi.org/10.1088/1742-6596/898/9/092056
http://cds.cern.ch/record/2298175
work_keys_str_mv AT alefm benchmarkingcloudresourcesforhep
AT cordeiroc benchmarkingcloudresourcesforhep
AT desalvoa benchmarkingcloudresourcesforhep
AT digirolamoa benchmarkingcloudresourcesforhep
AT fieldl benchmarkingcloudresourcesforhep
AT giordanod benchmarkingcloudresourcesforhep
AT guerrim benchmarkingcloudresourcesforhep
AT schiavifc benchmarkingcloudresourcesforhep
AT wiebalcka benchmarkingcloudresourcesforhep