Browsing by Author "Fohler, Gerhard"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- CIDER - envisaging a COTS communication infrastructure for evolutionary dependable real-time systemsPublication . Alves, Mário; Tovar, Eduardo; Fohler, Gerhard; Buttazzo, GiorgioIt is foreseen that future dependable real-time systems will also have to meet flexibility, adaptability and reconfigurability requirements. Considering the distributed nature of these computing systems, a communication infrastructure that permits to fulfil all those requirements is thus of major importance. Although Ethernet has been used primarily as an information network, there is a strong belief that some very recent technological advances will enable its use in dependable applications with real-time requirements. Indeed, several recently standardised mechanisms associated with Switched-Ethernet seem to be promising to enable communication infrastructures to support hard real-time, reliability and flexible distributed applications. This paper describes the motivation and the work being developed within the CIDER (Communication Infrastructure for Dependable Evolvable Real-Time Systems) project, which envisages the use of COTS Ethernet as an enabling technology for future dependable real-time systems. It is foreseen that the CIDER approach will constitute a relevant stream of research since it will bring together cutting edge research in the field of real-time and dependable distributed systems and the industrial eagerness to expand Ethernet responsabilities to support dependable real-time applications.
- A New Approach for Limited Preemptive Scheduling in Systems with Preemption OverheadPublication . Nasri, Mitra; Nelissen, Geoffrey; Fohler, GerhardThis paper considers the problem of reducing the number of preemptions in a system with periodic tasks and preemption overhead. The proposed solution is based on the key observation that for periodic task sets, the task with the smallest period plays an important role in determining the maximum interval of time during which a lower priority task can be executed without being preempted. We use this property to build a new limited preemptive scheduling algorithm, named RSLP, based on fixed-priority scheduling. In RS-LP, the length of each task’s non-preemptive region is varying during the system execution so as to keep the preemptions aligned with the releases of the highest priority task. This simple mechanism allows us to reduce the overall number of preemptions. The proposed algorithm, decides whether or not to preempt the currently executing task based on the maximum blocking tolerance of the higher priority tasks. In any case, the preemptions are authorized only at release instants of the task with the smallest period, thereby limiting the maximum number of preemptions to the number of releases of the highest priority task. Moreover, in this paper, we provide two different preemption overhead aware schedulability tests for periodic and loose-harmonic task sets (i.e., where each period is an integer multiple of the smallest period), together with a lower bound on the maximum number of preemptions. To conclude, extensive experiments comparing RS-LP with the state of the art limited preemptive scheduling algorithms are finally presented.