You are required to read and agree to the below before accessing a full-text version of an article in the IDE article repository.
The full-text document you are about to access is subject to national and international copyright laws. In most cases (but not necessarily all) the consequence is that personal use is allowed given that the copyright owner is duly acknowledged and respected. All other use (typically) require an explicit permission (often in writing) by the copyright owner.
For the reports in this repository we specifically note that
- the use of articles under IEEE copyright is governed by the IEEE copyright policy (available at http://www.ieee.org/web/publications/rights/copyrightpolicy.html)
- the use of articles under ACM copyright is governed by the ACM copyright policy (available at http://www.acm.org/pubs/copyright_policy/)
- technical reports and other articles issued by M‰lardalen University is free for personal use. For other use, the explicit consent of the authors is required
- in other cases, please contact the copyright owner for detailed information
By accepting I agree to acknowledge and respect the rights of the copyright owner of the document I am about to access.
If you are in doubt, feel free to contact webmaster@ide.mdh.se
Tighter Response-Times for Tasks with Offsets
Publication Type:
Conference/Workshop Paper
Venue:
Real-time and Embedded Computing Systems and Applications Conference (RTCSA)
Publisher:
Springer-Verlag
Abstract
We present an improvement to the analysis methods for calculating approximate response times for tasks with offsets. Our improvement calculates tighter (i.e. lower) response-times than does earlier approximation methods, and simulations show that the method, under certain conditions, calculates the exact worst-case response time.
We reveal, and exploit, a misconception in previous methods concerning the interference a higher priority task poses on a lower priority task. In this paper we show how the generally accepted concept of ``released for execution'' interference produces unnecessary pessimistic response times for the approximate response time analysis (RTA), presented by Tindell and Palencia Gutierrez et al. This concept of interference does not cause any pessimism in response-time analysis for tasks without offsets (neither in the exact analysis with offsets), and has thus remained undetected over the years.
Instead, we propose the concept of ``imposed'' interference, which more accurately captures the interference a task causes a lower priority task. We provide formal proofs that ``imposed'' interference is never higher than ``released for execution'' interference and that it never underestimates the interference caused by higher priority tasks. We also show, by simulations on randomly generated task sets, that our improvement results in response times that outperform previous approximate methods. A typical improvement results in about 12% better admission probability (more than 30% under certain circumstances can be obtained).
Bibtex
@inproceedings{Maki-Turja622,
author = {Jukka M{\"a}ki-Turja and Mikael Sj{\"o}din},
title = {Tighter Response-Times for Tasks with Offsets},
month = {August},
year = {2004},
booktitle = {Real-time and Embedded Computing Systems and Applications Conference (RTCSA)},
publisher = {Springer-Verlag},
url = {http://www.es.mdu.se/publications/622-}
}