Stochastic modeling of data storage systems for evaluating performance, dependability, and energy consumption
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Tipo de documento: | Tese |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFPE |
Texto Completo: | https://repositorio.ufpe.br/handle/123456789/53808 |
Resumo: | Improvements in data storage systems may be limited by the low performance of hard disk drives (HDDs) and the high cost per gigabyte of solid-state drives (SSDs). To mitigate these issues, several architectures based on hybrid storage systems have been proposed. However, energy consumption is usually neglected, and new approaches may not consider the impact on the mechanical components of HDDs, which can result in malfunctions and data loss. Similarly, the lifetime of SSDs can be reduced owing to their limited number of flash memory operations. This thesis presents an approach based on generalized stochastic Petri nets (GSPNs) to eval- uate the performance and energy consumption of homogeneous (HDD and SSD) and hybrid storage systems. Two analytical models have been proposed to represent distinct workloads and estimate throughput, energy consumption, and response time. In addition, a performability model has been conceived using the GSPN and reliability block diagram (RBD) formalisms to evaluate the impacts of failures on the performance of storage systems. Hierarchical modeling approach has been adopted, and the proposed model can estimate the availability and response time. A benchmark tool is adopted in this study to generate workloads and collect data to characterize storage devices. Simultaneously, this investigation estimates the power demand of HDDs and SSDs from measurements. The results are utilized to validate the GSPN models using statistical analysis and experiments based on industry-standard benchmarks. A design of experiment (DoE) is performed to investigate the most important factors assumed in this study. An exploratory analysis was conducted using industry datasets from Alibaba and Back- blaze to investigate the distinct effects of applications on storage failures. Results demonstrate the feasibility of the proposed models and provide important observations regarding storage solutions for different applications. |
id |
UFPE_1375d9c1d2cefb4fce805e5010bbc9b6 |
---|---|
oai_identifier_str |
oai:repositorio.ufpe.br:123456789/53808 |
network_acronym_str |
UFPE |
network_name_str |
Repositório Institucional da UFPE |
repository_id_str |
2221 |
spelling |
BORBA, Eric Rodrigueshttp://lattes.cnpq.br/3378364922278305http://lattes.cnpq.br/1233156130663707http://lattes.cnpq.br/8382158780043575TAVARES, Eduardo Antonio GuimarãesMACIEL, Paulo Romero Martins2023-11-29T18:19:25Z2023-11-29T18:19:25Z2023-07-28BORBA, Eric Rodrigues. Stochastic modeling of data storage systems for evaluating performance, dependability, and energy consumption. 2023. Tese (Doutorado em Ciência da Computação) – Universidade Federal de Pernambuco, Recife, 2023.https://repositorio.ufpe.br/handle/123456789/53808Improvements in data storage systems may be limited by the low performance of hard disk drives (HDDs) and the high cost per gigabyte of solid-state drives (SSDs). To mitigate these issues, several architectures based on hybrid storage systems have been proposed. However, energy consumption is usually neglected, and new approaches may not consider the impact on the mechanical components of HDDs, which can result in malfunctions and data loss. Similarly, the lifetime of SSDs can be reduced owing to their limited number of flash memory operations. This thesis presents an approach based on generalized stochastic Petri nets (GSPNs) to eval- uate the performance and energy consumption of homogeneous (HDD and SSD) and hybrid storage systems. Two analytical models have been proposed to represent distinct workloads and estimate throughput, energy consumption, and response time. In addition, a performability model has been conceived using the GSPN and reliability block diagram (RBD) formalisms to evaluate the impacts of failures on the performance of storage systems. Hierarchical modeling approach has been adopted, and the proposed model can estimate the availability and response time. A benchmark tool is adopted in this study to generate workloads and collect data to characterize storage devices. Simultaneously, this investigation estimates the power demand of HDDs and SSDs from measurements. The results are utilized to validate the GSPN models using statistical analysis and experiments based on industry-standard benchmarks. A design of experiment (DoE) is performed to investigate the most important factors assumed in this study. An exploratory analysis was conducted using industry datasets from Alibaba and Back- blaze to investigate the distinct effects of applications on storage failures. Results demonstrate the feasibility of the proposed models and provide important observations regarding storage solutions for different applications.CAPESCNPqO aperfeiçoamento de sistemas de armazenamento de dados pode ser limitado pelo baixo desempenho de dispositivos de disco rígido (HDDs) e pelo alto custo por gigabyte de dispos- itivos de estado sólido (SSDs). Para mitigar essas questões, diversas arquiteturas têm sido concebidas, baseadas em sistemas de armazenamento híbrido. No entanto, o consumo en- ergético é geralmente negligenciado, e novas abordagens não consideram os impactos nos componentes mecânicos de HDDs, o que pode resultar em um mau funcionamento e perda de dados. Da mesma forma, os SSDs podem ter seu tempo de vida reduzido devido ao número limitado de operações em memórias flash. Esta tese apresenta uma abordagem baseada em redes de Petri estocásticas generalizadas (GSPN) para a avaliação de desempenho e consumo energético de sistemas de armazenamento homogêneos (HDD e SSD) e híbridos. Dois mod- elos analíticos são propostos para representar diferentes cargas de trabalho e estimar vazão, consumo energético e tempo de resposta. Além disso, um modelo de performabilidade foi con- cebido utilizando os formalismos GSPN e diagrama de blocos de confiabilidade (RBD) para avaliar o impacto de falhas no desempenho de sistemas de armazenamento. Uma abordagem de modelagem hierárquica foi adotada, e o modelo pode estimar disponibilidade e tempo mé- dio de resposta. Uma ferramenta de benchmark foi adotada nesse estudo para gerar cargas de trabalho e coletar dados para a caracterização dos dispositivos de armazenamento. Simul- taneamente, esta investigação estimou a potência demandada por HDDs e SSDs por meio de medições. Os resultados foram utilizados para validar os modelos GSPN através de técnicas estatísticas e experimentos baseados em benchmarks padrões da indústria. Um planejamento de experimento (DoE) foi realizado para investigar os fatores mais impactantes assumidos nesse estudo. Uma análise exploratória foi conduzida utilizando datasets das companhias Al- ibaba e Backblaze para investigar os diferentes efeitos de aplicações na falha de dispositivos de armazenamento de dados. Os resultados demonstram a viabilidade dos modelos propostos e fornecem importantes observações em relação a soluções de armazenamento de dados para diferentes aplicações.engUniversidade Federal de PernambucoPrograma de Pos Graduacao em Ciencia da ComputacaoUFPEBrasilAttribution-NonCommercial-NoDerivs 3.0 Brazilhttp://creativecommons.org/licenses/by-nc-nd/3.0/br/info:eu-repo/semantics/openAccessRedes de computadoresAvaliação de desempenhoStochastic modeling of data storage systems for evaluating performance, dependability, and energy consumptioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisdoutoradoreponame:Repositório Institucional da UFPEinstname:Universidade Federal de Pernambuco (UFPE)instacron:UFPEORIGINALTESE Eric Rodrigues Borba.pdfTESE Eric Rodrigues Borba.pdfapplication/pdf3015692https://repositorio.ufpe.br/bitstream/123456789/53808/1/TESE%20Eric%20Rodrigues%20Borba.pdfa1c7102e077dc63976f4b86d1b6da98cMD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8811https://repositorio.ufpe.br/bitstream/123456789/53808/2/license_rdfe39d27027a6cc9cb039ad269a5db8e34MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-82362https://repositorio.ufpe.br/bitstream/123456789/53808/3/license.txt5e89a1613ddc8510c6576f4b23a78973MD53TEXTTESE Eric Rodrigues Borba.pdf.txtTESE Eric Rodrigues Borba.pdf.txtExtracted texttext/plain296505https://repositorio.ufpe.br/bitstream/123456789/53808/4/TESE%20Eric%20Rodrigues%20Borba.pdf.txt8cf51670969e4aec99efd07bba8cea0cMD54THUMBNAILTESE Eric Rodrigues Borba.pdf.jpgTESE Eric Rodrigues Borba.pdf.jpgGenerated Thumbnailimage/jpeg1255https://repositorio.ufpe.br/bitstream/123456789/53808/5/TESE%20Eric%20Rodrigues%20Borba.pdf.jpgf4a8036240a949366e9c041dd856c301MD55123456789/538082024-01-05 02:23:18.989oai:repositorio.ufpe.br:123456789/53808VGVybW8gZGUgRGVww7NzaXRvIExlZ2FsIGUgQXV0b3JpemHDp8OjbyBwYXJhIFB1YmxpY2l6YcOnw6NvIGRlIERvY3VtZW50b3Mgbm8gUmVwb3NpdMOzcmlvIERpZ2l0YWwgZGEgVUZQRQoKCkRlY2xhcm8gZXN0YXIgY2llbnRlIGRlIHF1ZSBlc3RlIFRlcm1vIGRlIERlcMOzc2l0byBMZWdhbCBlIEF1dG9yaXphw6fDo28gdGVtIG8gb2JqZXRpdm8gZGUgZGl2dWxnYcOnw6NvIGRvcyBkb2N1bWVudG9zIGRlcG9zaXRhZG9zIG5vIFJlcG9zaXTDs3JpbyBEaWdpdGFsIGRhIFVGUEUgZSBkZWNsYXJvIHF1ZToKCkkgLSBvcyBkYWRvcyBwcmVlbmNoaWRvcyBubyBmb3JtdWzDoXJpbyBkZSBkZXDDs3NpdG8gc8OjbyB2ZXJkYWRlaXJvcyBlIGF1dMOqbnRpY29zOwoKSUkgLSAgbyBjb250ZcO6ZG8gZGlzcG9uaWJpbGl6YWRvIMOpIGRlIHJlc3BvbnNhYmlsaWRhZGUgZGUgc3VhIGF1dG9yaWE7CgpJSUkgLSBvIGNvbnRlw7pkbyDDqSBvcmlnaW5hbCwgZSBzZSBvIHRyYWJhbGhvIGUvb3UgcGFsYXZyYXMgZGUgb3V0cmFzIHBlc3NvYXMgZm9yYW0gdXRpbGl6YWRvcywgZXN0YXMgZm9yYW0gZGV2aWRhbWVudGUgcmVjb25oZWNpZGFzOwoKSVYgLSBxdWFuZG8gdHJhdGFyLXNlIGRlIG9icmEgY29sZXRpdmEgKG1haXMgZGUgdW0gYXV0b3IpOiB0b2RvcyBvcyBhdXRvcmVzIGVzdMOjbyBjaWVudGVzIGRvIGRlcMOzc2l0byBlIGRlIGFjb3JkbyBjb20gZXN0ZSB0ZXJtbzsKClYgLSBxdWFuZG8gdHJhdGFyLXNlIGRlIFRyYWJhbGhvIGRlIENvbmNsdXPDo28gZGUgQ3Vyc28sIERpc3NlcnRhw6fDo28gb3UgVGVzZTogbyBhcnF1aXZvIGRlcG9zaXRhZG8gY29ycmVzcG9uZGUgw6AgdmVyc8OjbyBmaW5hbCBkbyB0cmFiYWxobzsKClZJIC0gcXVhbmRvIHRyYXRhci1zZSBkZSBUcmFiYWxobyBkZSBDb25jbHVzw6NvIGRlIEN1cnNvLCBEaXNzZXJ0YcOnw6NvIG91IFRlc2U6IGVzdG91IGNpZW50ZSBkZSBxdWUgYSBhbHRlcmHDp8OjbyBkYSBtb2RhbGlkYWRlIGRlIGFjZXNzbyBhbyBkb2N1bWVudG8gYXDDs3MgbyBkZXDDs3NpdG8gZSBhbnRlcyBkZSBmaW5kYXIgbyBwZXLDrW9kbyBkZSBlbWJhcmdvLCBxdWFuZG8gZm9yIGVzY29saGlkbyBhY2Vzc28gcmVzdHJpdG8sIHNlcsOhIHBlcm1pdGlkYSBtZWRpYW50ZSBzb2xpY2l0YcOnw6NvIGRvIChhKSBhdXRvciAoYSkgYW8gU2lzdGVtYSBJbnRlZ3JhZG8gZGUgQmlibGlvdGVjYXMgZGEgVUZQRSAoU0lCL1VGUEUpLgoKIApQYXJhIHRyYWJhbGhvcyBlbSBBY2Vzc28gQWJlcnRvOgoKTmEgcXVhbGlkYWRlIGRlIHRpdHVsYXIgZG9zIGRpcmVpdG9zIGF1dG9yYWlzIGRlIGF1dG9yIHF1ZSByZWNhZW0gc29icmUgZXN0ZSBkb2N1bWVudG8sIGZ1bmRhbWVudGFkbyBuYSBMZWkgZGUgRGlyZWl0byBBdXRvcmFsIG5vIDkuNjEwLCBkZSAxOSBkZSBmZXZlcmVpcm8gZGUgMTk5OCwgYXJ0LiAyOSwgaW5jaXNvIElJSSwgYXV0b3Jpem8gYSBVbml2ZXJzaWRhZGUgRmVkZXJhbCBkZSBQZXJuYW1idWNvIGEgZGlzcG9uaWJpbGl6YXIgZ3JhdHVpdGFtZW50ZSwgc2VtIHJlc3NhcmNpbWVudG8gZG9zIGRpcmVpdG9zIGF1dG9yYWlzLCBwYXJhIGZpbnMgZGUgbGVpdHVyYSwgaW1wcmVzc8OjbyBlL291IGRvd25sb2FkIChhcXVpc2nDp8OjbykgYXRyYXbDqXMgZG8gc2l0ZSBkbyBSZXBvc2l0w7NyaW8gRGlnaXRhbCBkYSBVRlBFIG5vIGVuZGVyZcOnbyBodHRwOi8vd3d3LnJlcG9zaXRvcmlvLnVmcGUuYnIsIGEgcGFydGlyIGRhIGRhdGEgZGUgZGVww7NzaXRvLgoKIApQYXJhIHRyYWJhbGhvcyBlbSBBY2Vzc28gUmVzdHJpdG86CgpOYSBxdWFsaWRhZGUgZGUgdGl0dWxhciBkb3MgZGlyZWl0b3MgYXV0b3JhaXMgZGUgYXV0b3IgcXVlIHJlY2FlbSBzb2JyZSBlc3RlIGRvY3VtZW50bywgZnVuZGFtZW50YWRvIG5hIExlaSBkZSBEaXJlaXRvIEF1dG9yYWwgbm8gOS42MTAgZGUgMTkgZGUgZmV2ZXJlaXJvIGRlIDE5OTgsIGFydC4gMjksIGluY2lzbyBJSUksIGF1dG9yaXpvIGEgVW5pdmVyc2lkYWRlIEZlZGVyYWwgZGUgUGVybmFtYnVjbyBhIGRpc3BvbmliaWxpemFyIGdyYXR1aXRhbWVudGUsIHNlbSByZXNzYXJjaW1lbnRvIGRvcyBkaXJlaXRvcyBhdXRvcmFpcywgcGFyYSBmaW5zIGRlIGxlaXR1cmEsIGltcHJlc3PDo28gZS9vdSBkb3dubG9hZCAoYXF1aXNpw6fDo28pIGF0cmF2w6lzIGRvIHNpdGUgZG8gUmVwb3NpdMOzcmlvIERpZ2l0YWwgZGEgVUZQRSBubyBlbmRlcmXDp28gaHR0cDovL3d3dy5yZXBvc2l0b3Jpby51ZnBlLmJyLCBxdWFuZG8gZmluZGFyIG8gcGVyw61vZG8gZGUgZW1iYXJnbyBjb25kaXplbnRlIGFvIHRpcG8gZGUgZG9jdW1lbnRvLCBjb25mb3JtZSBpbmRpY2FkbyBubyBjYW1wbyBEYXRhIGRlIEVtYmFyZ28uCg==Repositório InstitucionalPUBhttps://repositorio.ufpe.br/oai/requestattena@ufpe.bropendoar:22212024-01-05T05:23:18Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE)false |
dc.title.pt_BR.fl_str_mv |
Stochastic modeling of data storage systems for evaluating performance, dependability, and energy consumption |
title |
Stochastic modeling of data storage systems for evaluating performance, dependability, and energy consumption |
spellingShingle |
Stochastic modeling of data storage systems for evaluating performance, dependability, and energy consumption BORBA, Eric Rodrigues Redes de computadores Avaliação de desempenho |
title_short |
Stochastic modeling of data storage systems for evaluating performance, dependability, and energy consumption |
title_full |
Stochastic modeling of data storage systems for evaluating performance, dependability, and energy consumption |
title_fullStr |
Stochastic modeling of data storage systems for evaluating performance, dependability, and energy consumption |
title_full_unstemmed |
Stochastic modeling of data storage systems for evaluating performance, dependability, and energy consumption |
title_sort |
Stochastic modeling of data storage systems for evaluating performance, dependability, and energy consumption |
author |
BORBA, Eric Rodrigues |
author_facet |
BORBA, Eric Rodrigues |
author_role |
author |
dc.contributor.authorLattes.pt_BR.fl_str_mv |
http://lattes.cnpq.br/3378364922278305 |
dc.contributor.advisorLattes.pt_BR.fl_str_mv |
http://lattes.cnpq.br/1233156130663707 |
dc.contributor.advisor-coLattes.pt_BR.fl_str_mv |
http://lattes.cnpq.br/8382158780043575 |
dc.contributor.author.fl_str_mv |
BORBA, Eric Rodrigues |
dc.contributor.advisor1.fl_str_mv |
TAVARES, Eduardo Antonio Guimarães |
dc.contributor.advisor-co1.fl_str_mv |
MACIEL, Paulo Romero Martins |
contributor_str_mv |
TAVARES, Eduardo Antonio Guimarães MACIEL, Paulo Romero Martins |
dc.subject.por.fl_str_mv |
Redes de computadores Avaliação de desempenho |
topic |
Redes de computadores Avaliação de desempenho |
description |
Improvements in data storage systems may be limited by the low performance of hard disk drives (HDDs) and the high cost per gigabyte of solid-state drives (SSDs). To mitigate these issues, several architectures based on hybrid storage systems have been proposed. However, energy consumption is usually neglected, and new approaches may not consider the impact on the mechanical components of HDDs, which can result in malfunctions and data loss. Similarly, the lifetime of SSDs can be reduced owing to their limited number of flash memory operations. This thesis presents an approach based on generalized stochastic Petri nets (GSPNs) to eval- uate the performance and energy consumption of homogeneous (HDD and SSD) and hybrid storage systems. Two analytical models have been proposed to represent distinct workloads and estimate throughput, energy consumption, and response time. In addition, a performability model has been conceived using the GSPN and reliability block diagram (RBD) formalisms to evaluate the impacts of failures on the performance of storage systems. Hierarchical modeling approach has been adopted, and the proposed model can estimate the availability and response time. A benchmark tool is adopted in this study to generate workloads and collect data to characterize storage devices. Simultaneously, this investigation estimates the power demand of HDDs and SSDs from measurements. The results are utilized to validate the GSPN models using statistical analysis and experiments based on industry-standard benchmarks. A design of experiment (DoE) is performed to investigate the most important factors assumed in this study. An exploratory analysis was conducted using industry datasets from Alibaba and Back- blaze to investigate the distinct effects of applications on storage failures. Results demonstrate the feasibility of the proposed models and provide important observations regarding storage solutions for different applications. |
publishDate |
2023 |
dc.date.accessioned.fl_str_mv |
2023-11-29T18:19:25Z |
dc.date.available.fl_str_mv |
2023-11-29T18:19:25Z |
dc.date.issued.fl_str_mv |
2023-07-28 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
BORBA, Eric Rodrigues. Stochastic modeling of data storage systems for evaluating performance, dependability, and energy consumption. 2023. Tese (Doutorado em Ciência da Computação) – Universidade Federal de Pernambuco, Recife, 2023. |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufpe.br/handle/123456789/53808 |
identifier_str_mv |
BORBA, Eric Rodrigues. Stochastic modeling of data storage systems for evaluating performance, dependability, and energy consumption. 2023. Tese (Doutorado em Ciência da Computação) – Universidade Federal de Pernambuco, Recife, 2023. |
url |
https://repositorio.ufpe.br/handle/123456789/53808 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
Attribution-NonCommercial-NoDerivs 3.0 Brazil http://creativecommons.org/licenses/by-nc-nd/3.0/br/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Attribution-NonCommercial-NoDerivs 3.0 Brazil http://creativecommons.org/licenses/by-nc-nd/3.0/br/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de Pernambuco |
dc.publisher.program.fl_str_mv |
Programa de Pos Graduacao em Ciencia da Computacao |
dc.publisher.initials.fl_str_mv |
UFPE |
dc.publisher.country.fl_str_mv |
Brasil |
publisher.none.fl_str_mv |
Universidade Federal de Pernambuco |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFPE instname:Universidade Federal de Pernambuco (UFPE) instacron:UFPE |
instname_str |
Universidade Federal de Pernambuco (UFPE) |
instacron_str |
UFPE |
institution |
UFPE |
reponame_str |
Repositório Institucional da UFPE |
collection |
Repositório Institucional da UFPE |
bitstream.url.fl_str_mv |
https://repositorio.ufpe.br/bitstream/123456789/53808/1/TESE%20Eric%20Rodrigues%20Borba.pdf https://repositorio.ufpe.br/bitstream/123456789/53808/2/license_rdf https://repositorio.ufpe.br/bitstream/123456789/53808/3/license.txt https://repositorio.ufpe.br/bitstream/123456789/53808/4/TESE%20Eric%20Rodrigues%20Borba.pdf.txt https://repositorio.ufpe.br/bitstream/123456789/53808/5/TESE%20Eric%20Rodrigues%20Borba.pdf.jpg |
bitstream.checksum.fl_str_mv |
a1c7102e077dc63976f4b86d1b6da98c e39d27027a6cc9cb039ad269a5db8e34 5e89a1613ddc8510c6576f4b23a78973 8cf51670969e4aec99efd07bba8cea0c f4a8036240a949366e9c041dd856c301 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE) |
repository.mail.fl_str_mv |
attena@ufpe.br |
_version_ |
1802310610362302464 |