Abstract

Predicted task resource usage provides a basis for developing two centralized load-sharing policies: MinQ and MinResp. Trace-driven simulations are used to compare MinQ and MinResp against Centex, an efficient centralized scheme. Experimental results show that the use of prediction makes MinQ and MinResp significantly less sensitive to the status update rate than Centex. Consequently, the proposed algorithms perform better than Centex at slower update rates and are capable of handling larger workloads. The prediction-based policies are also highly effective for load-sharing in environments with widely varying CPU requirements. Using a real trace file, with an equal number of large and small tasks, MinResp consistently produced mean response times that were 9% to 35% lower than those of Centex.

Original languageEnglish (US)
Title of host publicationProceedings of the Hawaii International Conference on System Science
EditorsBruce D. Shriver
PublisherPubl by Western Periodicals Co
Pages921-927
Number of pages7
ISBN (Print)0818619120
StatePublished - 1989
EventProceedings of the Twenty-Second Annual Hawaii International Conference on System Sciences: Software Track - Kailua-Kona, Hawaii, USA
Duration: Jan 3 1989Jan 6 1989

Publication series

NameProceedings of the Hawaii International Conference on System Science
Volume2
ISSN (Print)0073-1129

Other

OtherProceedings of the Twenty-Second Annual Hawaii International Conference on System Sciences: Software Track
CityKailua-Kona, Hawaii, USA
Period1/3/891/6/89

ASJC Scopus subject areas

  • General Computer Science

Fingerprint

Dive into the research topics of 'Load sharing based on task resource prediction'. Together they form a unique fingerprint.

Cite this