On the Implementation of Global Real-Time Schedulers

Authors:
Björn B. Brandenburg;James H. Anderson
Affiliations:
-;-
Venue:
RTSS '09 Proceedings of the 2009 30th IEEE Real-Time Systems Symposium
Year:
2009

Citing 0
Cited 9

Needed foundations for assuring the desirable behavior of software-reliant systems

Proceedings of the FSE/SDP workshop on Future of software engineering research
An overview of interrupt accounting techniques for multiprocessor real-time systems

Journal of Systems Architecture: the EUROMICRO Journal
CPU scheduling and memory management for interactive real-time applications

Real-Time Systems
Swapping to reduce preemptions and migrations in EKG

ACM SIGBED Review - Work-in-Progress (WiP) Session of the 23rd Euromicro Conference on Real-Time Systems (ECRTS 2011)
RT-Xen: towards real-time hypervisor scheduling in xen

EMSOFT '11 Proceedings of the ninth ACM international conference on Embedded software
Multiprocessor extensions to real-time calculus

Real-Time Systems
An experimental comparison of different real-time schedulers on multicore systems

Journal of Systems and Software
An experimental evaluation of the scalability of real-time scheduling algorithms on large-scale multicore platforms

Journal of Experimental Algorithmics (JEA)
Implementation and evaluation of global and partitioned scheduling in a real-time OS

Real-Time Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

An empirical study of implementation tradeoffs (choice of ready queue implementation, quantum-driven vs. event driven scheduling, and interrupt handling strategy) affecting global real-time schedulers, and in particular global EDF, is presented. This study, conducted using UNC’s Linux-based LITMUSRT on Sun’s Niagara platform, suggests that implementation tradeoffs can impact schedulability as profoundly as scheduling-theoretic tradeoffs. For most of the considered workloads, implementation scalability proved to not be a key limitation of global EDF on the considered platform. Further, a combination of a parallel heap, event-driven scheduling, and dedicated interrupt handling performed best for most workloads.