Optimising task layout to increase schedulability via reduced cache related pre-emption delays
Proceedings of the 20th International Conference on Real-Time and Network Systems
Proceedings of the 21st International conference on Real-Time Networks and Systems
Approximation scheme for real-time tasks under fixed-priority scheduling with deferred preemption
Proceedings of the 21st International conference on Real-Time Networks and Systems
Limited preemptive scheduling of non-independent task sets
Proceedings of the Eleventh ACM International Conference on Embedded Software
A review of fixed priority and EDF scheduling for hard real-time uniprocessor systems
ACM SIGBED Review - Special Issue on the 3rd Embedded Operating System Workshop (EWiLi 2013)
Hi-index | 0.00 |
A central issue for verifying the schedulability of hard real-time systems is the correct evaluation of task execution times. These values are significantly influenced by the preemption overhead, which mainly includes the cache related delays and the context switch times introduced by each preemption. Since such an overhead significantly depends on the particular point in the code where preemption takes place, this paper proposes a method for placing suitable preemption points in each task in order to maximize the chances of finding a schedulable solution. In a previous work, we presented a method for the optimal selection of preemption points under the restrictive assumption of a fixed preemption cost, identical for each preemption point. In this paper, we remove such an assumption, exploring a more realistic and complex scenario where the preemption cost varies throughout the task code. Instead of modeling the problem with an integer programming formulation, with exponential worst-case complexity, we derive an optimal algorithm that has a linear time and space complexity. This somewhat surprising result allows selecting the best preemption points even in complex scenarios with a large number of potential preemption locations. Experimental results are also presented to show the effectiveness of the proposed approach in increasing the system schedulability.