umu.sePublications
3940414243444542 of 244
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Containerization for HPC in the Cloud: Docker vs Singularity - A Comparative Performance Benchmark
Umeå University, Faculty of Science and Technology, Department of Computing Science.
2018 (English)Independent thesis Basic level (degree of Bachelor of Fine Arts), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

In recent years, ‘containerization’, also known as ‘light-weight virtualization’, has arguably been one of the dominating buzzwords, both in industry and academic research. While scalability has been the main drivingforce in industry, reproducibility is often stated as the main benefit of containers in scientific High Performance Computing (HPC). Docker is currently the most widely deployed framework, ideally suited for microservice architecture. Singularity is a framework that aims to provide mobility of compute with a focus on bare-metal HPC cluster systems.

In earlier studies the performance of different light-weight virtualization frameworks when deployed on bare metal HPC systems has been evaluated and Singularity was mostly found to be superior to others in it’s application niche. However, performing HPC applications in the cloud has recently become a viable alternative to dedicated bare-metal HPC clusters. This results in running light-weight virtualization frameworks on virtual machines.

The aim of this study was to benchmark the performance of Singularity when run on virtual machines in the cloud compared to a setup using’Docker’. Adhering to earlier studies, performance metrics for compute, I/O, memory, and network through put/latency were established.

Place, publisher, year, edition, pages
2018. , p. 35
Series
UMNAD ; 1160
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:umu:diva-155291OAI: oai:DiVA.org:umu-155291DiVA, id: diva2:1277794
Educational program
Bachelor of Science Programme in Computing Science
Supervisors
Examiners
Available from: 2019-01-11 Created: 2019-01-11 Last updated: 2019-01-11Bibliographically approved

Open Access in DiVA

fulltext(252 kB)6 downloads
File information
File name FULLTEXT01.pdfFile size 252 kBChecksum SHA-512
679260f733b21eb651e1fa113480d1af109d4e0bf642ffed2bf2c0944a338948f2ce29ae19ca0342188adeba8c44b098b15082614ee56dc44d839d77acb0b631
Type fulltextMimetype application/pdf

By organisation
Department of Computing Science
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 6 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 16 hits
3940414243444542 of 244
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf