Summary: Integrating Aperiodic and Recurrent Tasks on
Fair­scheduled Multiprocessors #
Anand Srinivasan, Phil Holman, and James H. Anderson
Department of Computer Science, University of North Carolina
Chapel Hill, NC 27599­3175
E­mail: {anands,holman,anderson}@cs.unc.edu
December 2001
Abstract
We propose two server implementations for multiplexing aperiodic and recurrent (i.e., periodic, sporadic,
or ``rate­based'') real­time tasks in fair­scheduled multiprocessor systems. This is the first paper to consider
the problem of integrating support for aperiodic tasks within fair multiprocessor scheduling algorithms.
We also provide admission­control tests for the scheduling of hard aperiodic tasks (which have deadlines).
Further, we point out some of the additional complexities involved in server­based implementations on
multiprocessors and present some ways to handle them. Most of these complexities arise because of the
parallelism that exists in such systems. Finally, we provide experimental results that demonstrate the
e#ectiveness of our implementations.
# Work supported by NSF grants CCR 9732916, CCR 9972211, CCR 9988327, and ITR 0082866.

1 Introduction
There has been much recent work on scheduling techniques for multiplexing aperiodic and recurrent tasks in

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

Collections: Computer Technologies and Information Sciences