Measuring the Performance of Schedulability Tests
Real-Time Systems
Procrastination for leakage-aware rate-monotonic scheduling on a dynamic voltage scaling processor
Proceedings of the 2006 ACM SIGPLAN/SIGBED conference on Language, compilers, and tool support for embedded systems
Schedulability issues for EDZL scheduling on real-time multiprocessor systems
Information Processing Letters
Stochastic Analysis of Expected Schedulability for Real-Time Tasks on a Single Computing System
DS-RT '08 Proceedings of the 2008 12th IEEE/ACM International Symposium on Distributed Simulation and Real-Time Applications
Reliability comparison of schedulability test in ubiquitous computing
UIC'11 Proceedings of the 8th international conference on Ubiquitous intelligence and computing
| Hi-index | 14.98 |
Utilization bound is a well-known concept introduced in the seminal paper of Liu and Layland (1973), which provides a simple and practical way to test the schedulability of a real-time task set. The original utilization bound for the fixed-priority scheduler was given as a function of the number of tasks in the periodic task set. In this paper, we define the utilization bound as a function of the information about the task set. By making use of more than just the number of tasks, better utilization bound over the Liu and Layland bound can be achieved. We investigate in particular the bound given a set of periods for which it is still unknown if there is a polynomial algorithm for the exact bound. By investigating the relationships among the periods, we derive algorithms that yield better bounds than the Liu and Layland bound and the harmonic chain bound. Randomly generated task sets are tested against different bound algorithms. We also give a more intuitive proof of the harmonic chain bound and derive a computationally simpler algorithm.