The Limited-Preemption Uniprocessor Scheduling of Sporadic Task Systems

Authors:
Sanjoy Baruah
Affiliations:
University of North Carolina, Chapel Hill
Venue:
ECRTS '05 Proceedings of the 17th Euromicro Conference on Real-Time Systems
Year:
2005

Citing 0
Cited 10

Analysis on quantum-based fixed priority scheduling of real-time tasks

Proceedings of the 3rd International Conference on Ubiquitous Information Management and Communication
An implementation of the earliest deadline first algorithm in Linux

Proceedings of the 2009 ACM symposium on Applied Computing
Worst-case response time analysis of real-time tasks under fixed-priority scheduling with deferred preemption

Real-Time Systems
Improving task responsiveness with limited preemptions

ETFA'09 Proceedings of the 14th IEEE international conference on Emerging technologies & factory automation
Dynamic alteration schemes of real-time schedules for I/O device energy efficiency

ACM Transactions on Embedded Computing Systems (TECS)
Schedulability analysis of non-preemptive recurring real-time tasks

IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
Feasibility analysis under fixed priority scheduling with limited preemptions

Real-Time Systems
Partially non-preemptive dual priority multiprocessor scheduling

OPODIS'11 Proceedings of the 15th international conference on Principles of Distributed Systems
Limited preemptive scheduling of non-independent task sets

Proceedings of the Eleventh ACM International Conference on Embedded Software
A review of fixed priority and EDF scheduling for hard real-time uniprocessor systems

ACM SIGBED Review - Special Issue on the 3rd Embedded Operating System Workshop (EWiLi 2013)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Although preemptive uniprocessor scheduling algorithms are ableto successfully schedule some systems that cannot be scheduledby any non-preemptive scheduling algorithm, the run-time overheadassociated with implementing preemptive algorithms is often higherthan for non-preemptive algorithms.In choosing between preemptiveand non-preeemptive scheduling algorithms and uniprocessors, thetradeoff is therefore between enhanced feasibility on the one hand,and increased overheads on the other.Hybrid Scheduling schemesare proposed and evaluated here:these schemes permit preemptionwhere necessary for feasibility, but attempt to avoid unnecessarypreemptions during run-time.This is done by determining, for eachtask in the system, the longest amount of time for which the task mayexecute non-preemptively without compromising the feasibility of thesystem.