Dividing point value selections for Improved Quick Processor-Demand Analysis

Fengxiang Zhang; Alan Burns

doi:10.1109/ICSTE.2010.5608891

Dividing point value selections for Improved Quick Processor-Demand Analysis

Fengxiang Zhang^*, Alan Burns

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Earliest Deadline First (EDF) is an optimal scheduling algorithm for uniprocessor real-time systems. Improved Quick Processor-demand Analysis (QPA^*) provides efficient and exact schedulability tests for EDF-scheduled systems with arbitrary relative deadlines. The values of the dividing points can significantly affect the performance of QPA ^*. In this paper, we provide an efficient approach based on experiments to find suitable values of the dividing points; we also investigate the best value of the dividing points by extensive simulations on a large number of randomly generated task sets. We show that the proposed approach can significantly reduce the required calculations to perform a dividing point's value selection.

Original language	English
Title of host publication	ICSTE 2010 - 2010 2nd International Conference on Software Technology and Engineering, Proceedings
Pages	V1-170 -V1-175
Volume	1
DOIs	https://doi.org/10.1109/ICSTE.2010.5608891
Publication status	Published - 16 Dec 2010
Event	2010 2nd International Conference on Software Technology and Engineering, ICSTE 2010 - San Juan, PR, United Kingdom Duration: 3 Oct 2010 → 5 Oct 2010

Conference

Conference	2010 2nd International Conference on Software Technology and Engineering, ICSTE 2010
Country/Territory	United Kingdom
City	San Juan, PR
Period	3/10/10 → 5/10/10

Keywords

Performance and reliability
Real-time and embedded systems
Schedulability analysis

Access to Document

10.1109/ICSTE.2010.5608891

Cite this

@inproceedings{d3a4547bbf2e4a11bddc397eb64eea70,

title = "Dividing point value selections for Improved Quick Processor-Demand Analysis",

abstract = "Earliest Deadline First (EDF) is an optimal scheduling algorithm for uniprocessor real-time systems. Improved Quick Processor-demand Analysis (QPA*) provides efficient and exact schedulability tests for EDF-scheduled systems with arbitrary relative deadlines. The values of the dividing points can significantly affect the performance of QPA *. In this paper, we provide an efficient approach based on experiments to find suitable values of the dividing points; we also investigate the best value of the dividing points by extensive simulations on a large number of randomly generated task sets. We show that the proposed approach can significantly reduce the required calculations to perform a dividing point's value selection.",

keywords = "Performance and reliability, Real-time and embedded systems, Schedulability analysis",

author = "Fengxiang Zhang and Alan Burns",

year = "2010",

month = dec,

day = "16",

doi = "10.1109/ICSTE.2010.5608891",

language = "English",

isbn = "9781424486656",

volume = "1",

pages = "V1--170 --V1--175",

booktitle = "ICSTE 2010 - 2010 2nd International Conference on Software Technology and Engineering, Proceedings",

note = "2010 2nd International Conference on Software Technology and Engineering, ICSTE 2010 ; Conference date: 03-10-2010 Through 05-10-2010",

}

Zhang, F & Burns, A 2010, Dividing point value selections for Improved Quick Processor-Demand Analysis. in ICSTE 2010 - 2010 2nd International Conference on Software Technology and Engineering, Proceedings. vol. 1, 5608891, pp. V1-170 -V1-175, 2010 2nd International Conference on Software Technology and Engineering, ICSTE 2010, San Juan, PR, United Kingdom, 3/10/10. https://doi.org/10.1109/ICSTE.2010.5608891

TY - GEN

T1 - Dividing point value selections for Improved Quick Processor-Demand Analysis

AU - Zhang, Fengxiang

AU - Burns, Alan

PY - 2010/12/16

Y1 - 2010/12/16

N2 - Earliest Deadline First (EDF) is an optimal scheduling algorithm for uniprocessor real-time systems. Improved Quick Processor-demand Analysis (QPA*) provides efficient and exact schedulability tests for EDF-scheduled systems with arbitrary relative deadlines. The values of the dividing points can significantly affect the performance of QPA *. In this paper, we provide an efficient approach based on experiments to find suitable values of the dividing points; we also investigate the best value of the dividing points by extensive simulations on a large number of randomly generated task sets. We show that the proposed approach can significantly reduce the required calculations to perform a dividing point's value selection.

AB - Earliest Deadline First (EDF) is an optimal scheduling algorithm for uniprocessor real-time systems. Improved Quick Processor-demand Analysis (QPA*) provides efficient and exact schedulability tests for EDF-scheduled systems with arbitrary relative deadlines. The values of the dividing points can significantly affect the performance of QPA *. In this paper, we provide an efficient approach based on experiments to find suitable values of the dividing points; we also investigate the best value of the dividing points by extensive simulations on a large number of randomly generated task sets. We show that the proposed approach can significantly reduce the required calculations to perform a dividing point's value selection.

KW - Performance and reliability

KW - Real-time and embedded systems

KW - Schedulability analysis

UR - http://www.scopus.com/inward/record.url?scp=78650000572&partnerID=8YFLogxK

U2 - 10.1109/ICSTE.2010.5608891

DO - 10.1109/ICSTE.2010.5608891

M3 - Conference contribution

AN - SCOPUS:78650000572

SN - 9781424486656

VL - 1

SP - V1-170 -V1-175

BT - ICSTE 2010 - 2010 2nd International Conference on Software Technology and Engineering, Proceedings

T2 - 2010 2nd International Conference on Software Technology and Engineering, ICSTE 2010

Y2 - 3 October 2010 through 5 October 2010

ER -

Dividing point value selections for Improved Quick Processor-Demand Analysis

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this