Summary: Fair Scheduling of Dynamic Task Systems on
Multiprocessors #
Anand Srinivsan and James H. Anderson
Department of Computer Science, University of North Carolina
Chapel Hill, NC 27599­3175 USA
Abstract
In dynamic real­time task systems, tasks that are subject to deadlines are al­
lowed to join and leave the system. In previous work, Stoica et al. and Baruah et al.
presented conditions under which such joins and leaves may occur in fair­scheduled
uniprocessor systems without causing missed deadlines. In this paper, we extend
their work by considering fair­scheduled multiprocessors. We show that their con­
ditions are su#cient on M processors, under any deadline­based Pfair scheduling
algorithm, if the utilization of every subset of M - 1 tasks is at most one. Further,
for the general case in which task utilizations are not restricted in this way, we
derive su#cient join/leave conditions for the PD 2 Pfair algorithm. We also show
that, in general, these conditions cannot be improved upon without causing missed
deadlines.
Key words: Dynamic task systems, Pfairness, multiprocessor, real­time scheduling
1 Introduction
In many real­time systems, the set of runnable tasks may change dynamically.

Source: Anderson, James - Department of Computer Science, University of North Carolina at Chapel Hill

Collections: Computer Technologies and Information Sciences