umu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Principles and performance characteristics of algorithms for live VM migration
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. (grid and cloud computing)
SAP Research CEC Belfast.
SAP Research CEC Belfast.
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. (grid and cloud computing)
Visa övriga samt affilieringar
2015 (Engelska)Ingår i: ACM SIGOPS Operating Systems Review, Vol. 49, nr 1, s. 142-155Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

Since first demonstrated by Clark et al. in 2005, live migration of virtual machines has both become a standard feature of hypervisors and created an active field of research. However, the rich ongoing research in live migration focusmainly on performance improvements to well-known techniques, most of them being variations of the Clark approach. In order to advance live migration beyond incremental performance improvements, it is important to gain a deeper understanding of the live migration problem itself and its underlying principles.

To address this issue, this contribution takes a step back and investigates the essential characteristics of live migration. The paper identifies five fundamental properties of live migration and uses these to investigate, categorize, and compare three approaches to live migration: precopy, postcopy and hybrid. The evaluated algorithms include well-known techniques derived from that of Clark as well as novel RDMA in-kernel approaches. Our analysis of the fundamental properties of the algorithms is validated by a set of experiments. In these, we migrate virtual machines with large memory sizes hosting workloads with high page dirtying rates to expose differences and limitations of the different approaches. Finally, we provide guidelines for which approach to use in different scenarios.

Ort, förlag, år, upplaga, sidor
New York, NY, USA: Association for Computing Machinery (ACM), 2015. Vol. 49, nr 1, s. 142-155
Nyckelord [en]
platform virtualization, virtual machine monitors, performance evaluation
Nationell ämneskategori
Datavetenskap (datalogi)
Forskningsämne
data- och systemvetenskap
Identifikatorer
URN: urn:nbn:se:umu:diva-100352DOI: 10.1145/2723872.2723894OAI: oai:DiVA.org:umu-100352DiVA, id: diva2:791686
Forskningsfinansiär
EU, FP7, Sjunde ramprogrammet, 215605EU, FP7, Sjunde ramprogrammet, 257115eSSENCE - An eScience CollaborationTillgänglig från: 2015-03-02 Skapad: 2015-03-02 Senast uppdaterad: 2018-06-07Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltexthttp://dl.acm.org/citation.cfm?doid=2723872.2723894

Personposter BETA

Svärd, PetterTordsson, JohanElmroth, Erik

Sök vidare i DiVA

Av författaren/redaktören
Svärd, PetterTordsson, JohanElmroth, Erik
Av organisationen
Institutionen för datavetenskap
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 572 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf