Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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
Disallowing Same-program Co-schedules to Improve Efficiency in Quad-core Servers
University West, Department of Engineering Science, Division of Computer, Electrical and Surveying Engineering.ORCID iD: 0000-0001-7232-0079
University West, Department of Engineering Science, Division of Computer, Electrical and Surveying Engineering.ORCID iD: 0000-0003-0589-8086
2017 (English)Conference paper, Presentation (Other academic)
Abstract [en]

Programs running on different cores in a multicore serverare often forced to share resources like off-chip memory,caches, I/O devices, etc. This resource sharing often leadsto degraded performance, a slowdown, for the programsthat share the resources. A job scheduler can improve performance by co-scheduling programs that use different resources on the same server. The most common approachto solve this co-scheduling problem has been to make jobschedulers resource aware, finding ways to characterize andquantify a program’s resource usage. We have earlier suggested a simple, program and resource agnostic, scheme asa stepping stone to solving this problem: Avoid TerribleTwins, i.e., avoid co-schedules that contain several instancesfrom the same program. This scheme showed promising results when applied to dual-core servers. In this paper, weextend the analysis and evaluation to also cover quad-coreservers. We present a probabilistic model and empirical datathat show that execution slowdowns get worse as the numberof instances of the same program increases. Our schedulingsimulations show that if all co-schedules containing multiple instances of the same program are removed, the averageslowdown is decreased from 54% to 46% and that the worstcase slowdown is decreased from 173% to 108%.

Place, publisher, year, edition, pages
2017.
Keyword [en]
Co-scheduling; Same Process;Scheduling; Allocation; Multicore; Slowdown; Cluster; Cloud
National Category
Engineering and Technology Computer Systems
Research subject
ENGINEERING, Computer engineering
Identifiers
URN: urn:nbn:se:hv:diva-10620OAI: oai:DiVA.org:hv-10620DiVA: diva2:1066747
Conference
HIPEAC 2017, 2st COSH Workshop on Co-Scheduling of HPC Applications
Available from: 2017-01-19 Created: 2017-01-19 Last updated: 2017-04-07Bibliographically approved

Open Access in DiVA

No full text

Search in DiVA

By author/editor
De Blanche, AndreasLundqvist, Thomas
By organisation
Division of Computer, Electrical and Surveying Engineering
Engineering and TechnologyComputer Systems

Search outside of DiVA

GoogleGoogle Scholar

Total: 34 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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