NPi-Cluster: a Low Power Energy-Proportional Computing Cluster Architecture

Detalhes bibliográficos
Autor(a) principal: Filho, Sebastião Emidio Alves
Data de Publicação: 2017
Outros Autores: Burlamaqui, Aquiles Medeiros Filgueira, Aroca, Rafael Vidal, Gonçalves, Luiz Marcos Garcia
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UFRN
Texto Completo: https://repositorio.ufrn.br/handle/123456789/48874
Resumo: This paper presents the NPi-Cluster, an energy proportional computing cluster that automatically powers ON or OFF the number of running machines according to the actual processing demand. A theoretical model is proposed, discussed, and implemented on a cluster composed of Raspberry Pi computer boards designed and built in order to test the proposed system architecture. Experimental results show adequate performance of the proposed platform when compared with other web servers running on traditional server architectures, but with considerably less power consumption. The power consumption of the entire cluster is about 14 W when running at maximum performance. In this situation, the system is able to handle more than 450 simultaneous requests, with about 1000 transactions per second, making it possible to be used as a server capable of handling real web workloads with acceptable quality of service. When the requests demand is reduced to a minimum, the power consumption is dynamically reduced until less than 2 W. Additionally, the proposed cluster architecture also provides high availability by reducing single points of failure on the system
id UFRN_fbd64a305859a750bd5740e1a53550f5
oai_identifier_str oai:https://repositorio.ufrn.br:123456789/48874
network_acronym_str UFRN
network_name_str Repositório Institucional da UFRN
repository_id_str
spelling Filho, Sebastião Emidio AlvesBurlamaqui, Aquiles Medeiros FilgueiraAroca, Rafael VidalGonçalves, Luiz Marcos Garcia2022-07-29T15:37:06Z2022-07-29T15:37:06Z2017-08-09ALVES FILHO, Sebastiao Emidio; BURLAMAQUI, Aquiles Medeiros Filgueira; AROCA, Rafael Vidal; GONCALVES, Luiz Marcos Garcia. NPi-Cluster: a low power energy-proportional computing cluster architecture. Ieee Access, [s.l.], v. 5, p. 16297-16313, 2017. Institute of Electrical and Electronics Engineers (IEEE). http://dx.doi.org/10.1109/access.2017.2728720. Disponível em: https://ieeexplore.ieee.org/document/8004443. Acesso em: 27 jul. 2020.1678-765Xhttps://repositorio.ufrn.br/handle/123456789/48874This paper presents the NPi-Cluster, an energy proportional computing cluster that automatically powers ON or OFF the number of running machines according to the actual processing demand. A theoretical model is proposed, discussed, and implemented on a cluster composed of Raspberry Pi computer boards designed and built in order to test the proposed system architecture. Experimental results show adequate performance of the proposed platform when compared with other web servers running on traditional server architectures, but with considerably less power consumption. The power consumption of the entire cluster is about 14 W when running at maximum performance. In this situation, the system is able to handle more than 450 simultaneous requests, with about 1000 transactions per second, making it possible to be used as a server capable of handling real web workloads with acceptable quality of service. When the requests demand is reduced to a minimum, the power consumption is dynamically reduced until less than 2 W. Additionally, the proposed cluster architecture also provides high availability by reducing single points of failure on the systemThis paper presents the NPi-Cluster, an energy proportional computing cluster that automatically powers ON or OFF the number of running machines according to the actual processing demand. A theoretical model is proposed, discussed, and implemented on a cluster composed of Raspberry Pi computer boards designed and built in order to test the proposed system architecture. Experimental results show adequate performance of the proposed platform when compared with other web servers running on traditional server architectures, but with considerably less power consumption. The power consumption of the entire cluster is about 14 W when running at maximum performance. In this situation, the system is able to handle more than 450 simultaneous requests, with about 1000 transactions per second, making it possible to be used as a server capable of handling real web workloads with acceptable quality of service. When the requests demand is reduced to a minimum, the power consumption is dynamically reduced until less than 2 W. Additionally, the proposed cluster architecture also provides high availability by reducing single points of failure on the systemInstitute of Electrical and Electronics EngineersAttribution 3.0 Brazilhttp://creativecommons.org/licenses/by/3.0/br/info:eu-repo/semantics/openAccessEnergy efficiencyScalabilityQuality of serviceDistributed computingLow power electronicsNPi-Cluster: a Low Power Energy-Proportional Computing Cluster Architectureinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleengreponame:Repositório Institucional da UFRNinstname:Universidade Federal do Rio Grande do Norte (UFRN)instacron:UFRNORIGINALNPi_Cluster_ALowPower_BULAMARQUI_2017.pdfNPi_Cluster_ALowPower_BULAMARQUI_2017.pdfArtigoapplication/pdf7327866https://repositorio.ufrn.br/bitstream/123456789/48874/1/NPi_Cluster_ALowPower_BULAMARQUI_2017.pdfc79052c71ac2d67812fbecaaad20911cMD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8914https://repositorio.ufrn.br/bitstream/123456789/48874/2/license_rdf4d2950bda3d176f570a9f8b328dfbbefMD52LICENSElicense.txtlicense.txttext/plain; charset=utf-81484https://repositorio.ufrn.br/bitstream/123456789/48874/3/license.txte9597aa2854d128fd968be5edc8a28d9MD53123456789/488742022-07-29 12:37:08.677oai:https://repositorio.ufrn.br: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Repositório de PublicaçõesPUBhttp://repositorio.ufrn.br/oai/opendoar:2022-07-29T15:37:08Repositório Institucional da UFRN - Universidade Federal do Rio Grande do Norte (UFRN)false
dc.title.pt_BR.fl_str_mv NPi-Cluster: a Low Power Energy-Proportional Computing Cluster Architecture
title NPi-Cluster: a Low Power Energy-Proportional Computing Cluster Architecture
spellingShingle NPi-Cluster: a Low Power Energy-Proportional Computing Cluster Architecture
Filho, Sebastião Emidio Alves
Energy efficiency
Scalability
Quality of service
Distributed computing
Low power electronics
title_short NPi-Cluster: a Low Power Energy-Proportional Computing Cluster Architecture
title_full NPi-Cluster: a Low Power Energy-Proportional Computing Cluster Architecture
title_fullStr NPi-Cluster: a Low Power Energy-Proportional Computing Cluster Architecture
title_full_unstemmed NPi-Cluster: a Low Power Energy-Proportional Computing Cluster Architecture
title_sort NPi-Cluster: a Low Power Energy-Proportional Computing Cluster Architecture
author Filho, Sebastião Emidio Alves
author_facet Filho, Sebastião Emidio Alves
Burlamaqui, Aquiles Medeiros Filgueira
Aroca, Rafael Vidal
Gonçalves, Luiz Marcos Garcia
author_role author
author2 Burlamaqui, Aquiles Medeiros Filgueira
Aroca, Rafael Vidal
Gonçalves, Luiz Marcos Garcia
author2_role author
author
author
dc.contributor.author.fl_str_mv Filho, Sebastião Emidio Alves
Burlamaqui, Aquiles Medeiros Filgueira
Aroca, Rafael Vidal
Gonçalves, Luiz Marcos Garcia
dc.subject.por.fl_str_mv Energy efficiency
Scalability
Quality of service
Distributed computing
Low power electronics
topic Energy efficiency
Scalability
Quality of service
Distributed computing
Low power electronics
description This paper presents the NPi-Cluster, an energy proportional computing cluster that automatically powers ON or OFF the number of running machines according to the actual processing demand. A theoretical model is proposed, discussed, and implemented on a cluster composed of Raspberry Pi computer boards designed and built in order to test the proposed system architecture. Experimental results show adequate performance of the proposed platform when compared with other web servers running on traditional server architectures, but with considerably less power consumption. The power consumption of the entire cluster is about 14 W when running at maximum performance. In this situation, the system is able to handle more than 450 simultaneous requests, with about 1000 transactions per second, making it possible to be used as a server capable of handling real web workloads with acceptable quality of service. When the requests demand is reduced to a minimum, the power consumption is dynamically reduced until less than 2 W. Additionally, the proposed cluster architecture also provides high availability by reducing single points of failure on the system
publishDate 2017
dc.date.issued.fl_str_mv 2017-08-09
dc.date.accessioned.fl_str_mv 2022-07-29T15:37:06Z
dc.date.available.fl_str_mv 2022-07-29T15:37:06Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.citation.fl_str_mv ALVES FILHO, Sebastiao Emidio; BURLAMAQUI, Aquiles Medeiros Filgueira; AROCA, Rafael Vidal; GONCALVES, Luiz Marcos Garcia. NPi-Cluster: a low power energy-proportional computing cluster architecture. Ieee Access, [s.l.], v. 5, p. 16297-16313, 2017. Institute of Electrical and Electronics Engineers (IEEE). http://dx.doi.org/10.1109/access.2017.2728720. Disponível em: https://ieeexplore.ieee.org/document/8004443. Acesso em: 27 jul. 2020.
dc.identifier.uri.fl_str_mv https://repositorio.ufrn.br/handle/123456789/48874
dc.identifier.issn.none.fl_str_mv 1678-765X
identifier_str_mv ALVES FILHO, Sebastiao Emidio; BURLAMAQUI, Aquiles Medeiros Filgueira; AROCA, Rafael Vidal; GONCALVES, Luiz Marcos Garcia. NPi-Cluster: a low power energy-proportional computing cluster architecture. Ieee Access, [s.l.], v. 5, p. 16297-16313, 2017. Institute of Electrical and Electronics Engineers (IEEE). http://dx.doi.org/10.1109/access.2017.2728720. Disponível em: https://ieeexplore.ieee.org/document/8004443. Acesso em: 27 jul. 2020.
1678-765X
url https://repositorio.ufrn.br/handle/123456789/48874
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv Attribution 3.0 Brazil
http://creativecommons.org/licenses/by/3.0/br/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution 3.0 Brazil
http://creativecommons.org/licenses/by/3.0/br/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
dc.source.none.fl_str_mv reponame:Repositório Institucional da UFRN
instname:Universidade Federal do Rio Grande do Norte (UFRN)
instacron:UFRN
instname_str Universidade Federal do Rio Grande do Norte (UFRN)
instacron_str UFRN
institution UFRN
reponame_str Repositório Institucional da UFRN
collection Repositório Institucional da UFRN
bitstream.url.fl_str_mv https://repositorio.ufrn.br/bitstream/123456789/48874/1/NPi_Cluster_ALowPower_BULAMARQUI_2017.pdf
https://repositorio.ufrn.br/bitstream/123456789/48874/2/license_rdf
https://repositorio.ufrn.br/bitstream/123456789/48874/3/license.txt
bitstream.checksum.fl_str_mv c79052c71ac2d67812fbecaaad20911c
4d2950bda3d176f570a9f8b328dfbbef
e9597aa2854d128fd968be5edc8a28d9
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
repository.name.fl_str_mv Repositório Institucional da UFRN - Universidade Federal do Rio Grande do Norte (UFRN)
repository.mail.fl_str_mv
_version_ 1802117785583616000

Registros relacionados