Departmental Papers (CIS)

Date of this Version

5-7-2007

Document Type

Conference Paper

Comments

Copyright 2007 IEEE. Reprinted from Proceedings of the 10th IEEE International Symposium on Object and Component-Oriented Real-Time Distributed Computing, ISORC '07, May 2007, pages 274-281.

This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Pennsylvania's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

Abstract

Embedded systems are complex as a whole but consist of smaller independent modules interacting with each other. This structure makes them amenable to compositional design. Real-time embedded systems consist of realtime workloads having deadlines. Compositional design of such systems can be done using real-time components arranged in a scheduling hierarchy. Each component consists of some real-time workload and a scheduling policy for the workload. To simplify schedulability analysis for such systems, analysis should be done compositionally using interfaces that abstract timing requirement of components. To facilitate analysis of dynamically changing systems, the framework should also support incremental analysis. In this paper, we overview our approach to compositional and incremental schedulability analysis of hierarchical real-time systems. We describe a compositional analysis technique that abstracts resource requirement of components using periodic resource models. To support incremental analysis and resource bandwidth minimization, we describe an extension to this interface model. Each extended interface consists of multiple periodic resource models for different periods. This allows the selection of a periodic model that can schedule the system using minimum bandwidth. We also account for context switch overhead of components in these extended interfaces. We then describe an associative composition technique for such interfaces, that supports incremental analysis.

Share

COinS
 

Date Posted: 22 January 2008

This document has been peer reviewed.