A modeling framework for infrastructure planning of Workflow-as-a-Service environments
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Tipo de documento: | Tese |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFPE |
Texto Completo: | https://repositorio.ufpe.br/handle/123456789/35378 |
Resumo: | Given the characteristics of dynamic provisioning and the illusion of unlimited resources, “the cloud” is becoming a popular alternative for running scientific workflows. In a cloud system for processing workflow applications, the performance of the system is heavily influenced by two factors: the scheduling strategy and failure of components. Failures in a cloud system can simultaneously affect several users and depreciate the number of available computing resources. A bad scheduling strategy can increase the expected makespan and the idle time of physical machines. In this work, we propose a modeling framework, and a set of formal models and methods for supporting the infrastructure planning of Workflow-as-a-Service clouds. This modeling framework supports the tasks of: i) planning the deployment of workflow applications in computational clouds in order to maximize performance and reliability metrics; ii) planning the redundancy arrangements in the cloud infrastructure in order to reduce the acquisition cost while satisfying availability requirements; iii) identifying availability bottlenecks and enabling the prioritization of critical components for improvement. We conducted three case studies in order to illustrate and validate the proposed modeling framework. The first case study employs a comprehensive hierarchical availability model using RBD and DRBD models and applied sensitivity analysis methods in order to find the most influential parameters. The second case study extends the previous one by modeling a cloud infrastructure as an instance of the redundancy allocation problem (RAP). To minimize the acquisition cost while maximizing the availability of the system, we proposed the combined use of a local-search algorithm and the bisection method. In the last case study, we optimize the scheduling of scientific cloud workflows. This case study comprises the use of a metaheuristic algorithm coupled with a performability model that provides the fitnesses of the explored solutions. The experimental results obtained in all case studies have proven the framework effectiveness on aiding planning infrastructures tasks, allowing cloud providers to maximize resource utilization, reduce operational costs, and ensure SLA requirements. |
id |
UFPE_2b65aaaea0d2513e6a98a4f116c5c304 |
---|---|
oai_identifier_str |
oai:repositorio.ufpe.br:123456789/35378 |
network_acronym_str |
UFPE |
network_name_str |
Repositório Institucional da UFPE |
repository_id_str |
2221 |
spelling |
OLIVEIRA, Danilo Mendonçahttp://lattes.cnpq.br/8973700908236602http://lattes.cnpq.br/8382158780043575MACIEL, Paulo Romero Martins2019-11-29T19:02:15Z2019-11-29T19:02:15Z2019-02-15OLIVEIRA, Danilo Mendonça. A modeling framework for infrastructure planning of Workflow-as-a-Service environments. 2019. Tese (Doutorado em Ciência da Computação) – Universidade Federal de Pernambuco, Recife, 2019.https://repositorio.ufpe.br/handle/123456789/35378Given the characteristics of dynamic provisioning and the illusion of unlimited resources, “the cloud” is becoming a popular alternative for running scientific workflows. In a cloud system for processing workflow applications, the performance of the system is heavily influenced by two factors: the scheduling strategy and failure of components. Failures in a cloud system can simultaneously affect several users and depreciate the number of available computing resources. A bad scheduling strategy can increase the expected makespan and the idle time of physical machines. In this work, we propose a modeling framework, and a set of formal models and methods for supporting the infrastructure planning of Workflow-as-a-Service clouds. This modeling framework supports the tasks of: i) planning the deployment of workflow applications in computational clouds in order to maximize performance and reliability metrics; ii) planning the redundancy arrangements in the cloud infrastructure in order to reduce the acquisition cost while satisfying availability requirements; iii) identifying availability bottlenecks and enabling the prioritization of critical components for improvement. We conducted three case studies in order to illustrate and validate the proposed modeling framework. The first case study employs a comprehensive hierarchical availability model using RBD and DRBD models and applied sensitivity analysis methods in order to find the most influential parameters. The second case study extends the previous one by modeling a cloud infrastructure as an instance of the redundancy allocation problem (RAP). To minimize the acquisition cost while maximizing the availability of the system, we proposed the combined use of a local-search algorithm and the bisection method. In the last case study, we optimize the scheduling of scientific cloud workflows. This case study comprises the use of a metaheuristic algorithm coupled with a performability model that provides the fitnesses of the explored solutions. The experimental results obtained in all case studies have proven the framework effectiveness on aiding planning infrastructures tasks, allowing cloud providers to maximize resource utilization, reduce operational costs, and ensure SLA requirements.Considerando as características de provisionamento dinâmico e a ilusão de recursos ilimitados, nuvens computacionais estão se tornando uma alternativa popular para executar workflows científicos. Numa nuvem computacional para processamento de workflows, o desempenho do sistema é altamente influenciado por dois fatores: a estratégia de escalonamento e falhas de componentes. Falhas numa nuvem podem afetar vários usuários simultaneamente e diminuir o número de recursos computacionais disponíveis. Uma estratégia de escalonamento ruim pode aumentar o makespan e diminuir a utilização das máquinas físicas. Neste trabalho, nós propomos um framework de modelagem e um conjunto de modelos formais e métodos para auxiliar o planejamento de infraestrutura de nuvens do tipo Workflow-as-a-Service. Este framework de modelagem provê auxílio às tarefas de: i) planejar a implantação de aplicações de workflow em nuvens computacionais a fim de maximizar métricas de desempenho e confiabilidade; ii) planejar os arranjos de redundância na infraestrutura de nuvem a fim de reduzir o gasto de aquisição e, ao mesmo tempo, garantir requisitos de disponibilidade; iii) identificar gargalos de disponibilidade e habilitar a priorização dos componentes mais críticos. Nós conduzimos três estudos de caso a fim de ilustrar e validar o framework de modelagem proposto. O primeiro estudo de caso emprega um modelo hierárquico de disponibilidade usando modelos RBD e DRBD e aplica métodos de análise de sensibilidade para detectar os parâmetros mais influentes na métrica considerada. O segundo estudo de caso extende o anterior, ao modelar a infraestrutura de nuvem como um problema de alocação de redundância (RAP - redundancy allocation problem). Para minimizar o custo de aquisição enquanto a disponibilidade é maximizada, nós combinamos o método de busca local com o algoritmo de bisecção. No último estudo de caso, nós propomos um método para a otimização do escalonamento de workflows em nuvem. Este estudo de caso adota um algoritmo meta-heurístico acoplado a um modelo de performabilidade que provê a função fitness das soluções exploradas. Os resultados experimentais obtidos nos estudos de caso demonstram a eficácia do framework em auxiliar tarefas de planejamento de infraestrutura, permitindo que provedores de nuvem maximizem a utilização de recursos, reduzam custos operacionais, e garantam requisitos de SLA.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/openAccessAvaliação de desempenhoComputação em nuvemOtimização combinatóriaA modeling framework for infrastructure planning of Workflow-as-a-Service environmentsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisdoutoradoreponame:Repositório Institucional da UFPEinstname:Universidade Federal de Pernambuco (UFPE)instacron:UFPECC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8811https://repositorio.ufpe.br/bitstream/123456789/35378/2/license_rdfe39d27027a6cc9cb039ad269a5db8e34MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-81748https://repositorio.ufpe.br/bitstream/123456789/35378/3/license.txt8a4605be74aa9ea9d79846c1fba20a33MD53ORIGINALTESE Danilo Mendonça Oliveira.pdfTESE Danilo Mendonça Oliveira.pdfapplication/pdf2940334https://repositorio.ufpe.br/bitstream/123456789/35378/1/TESE%20Danilo%20Mendon%c3%a7a%20Oliveira.pdf3ad65b06ae10836d7971bf929c2527bdMD51TEXTTESE Danilo Mendonça Oliveira.pdf.txtTESE Danilo Mendonça Oliveira.pdf.txtExtracted texttext/plain278356https://repositorio.ufpe.br/bitstream/123456789/35378/4/TESE%20Danilo%20Mendon%c3%a7a%20Oliveira.pdf.txtcf38280c64de0bc6e017e268eaf1e4cfMD54THUMBNAILTESE Danilo Mendonça Oliveira.pdf.jpgTESE Danilo Mendonça Oliveira.pdf.jpgGenerated Thumbnailimage/jpeg1198https://repositorio.ufpe.br/bitstream/123456789/35378/5/TESE%20Danilo%20Mendon%c3%a7a%20Oliveira.pdf.jpg89253f8545f277c7f27c4c1782dbaa94MD55123456789/353782019-11-30 02:11:07.85oai:repositorio.ufpe.br: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Repositório InstitucionalPUBhttps://repositorio.ufpe.br/oai/requestattena@ufpe.bropendoar:22212019-11-30T05:11:07Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE)false |
dc.title.pt_BR.fl_str_mv |
A modeling framework for infrastructure planning of Workflow-as-a-Service environments |
title |
A modeling framework for infrastructure planning of Workflow-as-a-Service environments |
spellingShingle |
A modeling framework for infrastructure planning of Workflow-as-a-Service environments OLIVEIRA, Danilo Mendonça Avaliação de desempenho Computação em nuvem Otimização combinatória |
title_short |
A modeling framework for infrastructure planning of Workflow-as-a-Service environments |
title_full |
A modeling framework for infrastructure planning of Workflow-as-a-Service environments |
title_fullStr |
A modeling framework for infrastructure planning of Workflow-as-a-Service environments |
title_full_unstemmed |
A modeling framework for infrastructure planning of Workflow-as-a-Service environments |
title_sort |
A modeling framework for infrastructure planning of Workflow-as-a-Service environments |
author |
OLIVEIRA, Danilo Mendonça |
author_facet |
OLIVEIRA, Danilo Mendonça |
author_role |
author |
dc.contributor.authorLattes.pt_BR.fl_str_mv |
http://lattes.cnpq.br/8973700908236602 |
dc.contributor.advisorLattes.pt_BR.fl_str_mv |
http://lattes.cnpq.br/8382158780043575 |
dc.contributor.author.fl_str_mv |
OLIVEIRA, Danilo Mendonça |
dc.contributor.advisor1.fl_str_mv |
MACIEL, Paulo Romero Martins |
contributor_str_mv |
MACIEL, Paulo Romero Martins |
dc.subject.por.fl_str_mv |
Avaliação de desempenho Computação em nuvem Otimização combinatória |
topic |
Avaliação de desempenho Computação em nuvem Otimização combinatória |
description |
Given the characteristics of dynamic provisioning and the illusion of unlimited resources, “the cloud” is becoming a popular alternative for running scientific workflows. In a cloud system for processing workflow applications, the performance of the system is heavily influenced by two factors: the scheduling strategy and failure of components. Failures in a cloud system can simultaneously affect several users and depreciate the number of available computing resources. A bad scheduling strategy can increase the expected makespan and the idle time of physical machines. In this work, we propose a modeling framework, and a set of formal models and methods for supporting the infrastructure planning of Workflow-as-a-Service clouds. This modeling framework supports the tasks of: i) planning the deployment of workflow applications in computational clouds in order to maximize performance and reliability metrics; ii) planning the redundancy arrangements in the cloud infrastructure in order to reduce the acquisition cost while satisfying availability requirements; iii) identifying availability bottlenecks and enabling the prioritization of critical components for improvement. We conducted three case studies in order to illustrate and validate the proposed modeling framework. The first case study employs a comprehensive hierarchical availability model using RBD and DRBD models and applied sensitivity analysis methods in order to find the most influential parameters. The second case study extends the previous one by modeling a cloud infrastructure as an instance of the redundancy allocation problem (RAP). To minimize the acquisition cost while maximizing the availability of the system, we proposed the combined use of a local-search algorithm and the bisection method. In the last case study, we optimize the scheduling of scientific cloud workflows. This case study comprises the use of a metaheuristic algorithm coupled with a performability model that provides the fitnesses of the explored solutions. The experimental results obtained in all case studies have proven the framework effectiveness on aiding planning infrastructures tasks, allowing cloud providers to maximize resource utilization, reduce operational costs, and ensure SLA requirements. |
publishDate |
2019 |
dc.date.accessioned.fl_str_mv |
2019-11-29T19:02:15Z |
dc.date.available.fl_str_mv |
2019-11-29T19:02:15Z |
dc.date.issued.fl_str_mv |
2019-02-15 |
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 |
OLIVEIRA, Danilo Mendonça. A modeling framework for infrastructure planning of Workflow-as-a-Service environments. 2019. Tese (Doutorado em Ciência da Computação) – Universidade Federal de Pernambuco, Recife, 2019. |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufpe.br/handle/123456789/35378 |
identifier_str_mv |
OLIVEIRA, Danilo Mendonça. A modeling framework for infrastructure planning of Workflow-as-a-Service environments. 2019. Tese (Doutorado em Ciência da Computação) – Universidade Federal de Pernambuco, Recife, 2019. |
url |
https://repositorio.ufpe.br/handle/123456789/35378 |
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/123456789/35378/2/license_rdf https://repositorio.ufpe.br/bitstream/123456789/35378/3/license.txt https://repositorio.ufpe.br/bitstream/123456789/35378/1/TESE%20Danilo%20Mendon%c3%a7a%20Oliveira.pdf https://repositorio.ufpe.br/bitstream/123456789/35378/4/TESE%20Danilo%20Mendon%c3%a7a%20Oliveira.pdf.txt https://repositorio.ufpe.br/bitstream/123456789/35378/5/TESE%20Danilo%20Mendon%c3%a7a%20Oliveira.pdf.jpg |
bitstream.checksum.fl_str_mv |
e39d27027a6cc9cb039ad269a5db8e34 8a4605be74aa9ea9d79846c1fba20a33 3ad65b06ae10836d7971bf929c2527bd cf38280c64de0bc6e017e268eaf1e4cf 89253f8545f277c7f27c4c1782dbaa94 |
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_ |
1802310772251951104 |