Team aoste

Members
Overall Objectives
Scientific Foundations
Application Domains
Software
New Results
Contracts and Grants with Industry
Other Grants and Activities
Dissemination
Bibliography

Section: Software

SAS

Participants : Patrick Meumeu Yomsi, Daniel de Rauglaudre [ correspondant ] , Yves Sorel.

The SAS (Simulation and Analysis of Scheduling) software implementation has started last year. It allows the user to perform the schedulability analysis of periodic otask systems [12] in the monoprocessor case. As we have shown that any periodic task is a particular periodic otask [26] , SAS thus also allows the user to perform the schedulability analysis of task systems in the monoprocessor case [25] , [14] . The main contribution, compared to other commercial and academic softwares of the same kind, is that SAS takes into account the exact preemption cost during the schedulability analysis. Now, beside the usual real-time constraints (precedence, strict periodicity, latency, etc.) and fixed-priority scheduling policies (Rate Monotonic, Deadline Monotonic, Audsley + + , User priorities) that could already be taken into account, SAS has been extended to make it possible to select dynamic scheduling policy algorithms such as Earliest Deadline First (EDF).

The resulting schedule is displayed as a typical Gantt chart with a transient and a permanent phase, or as a disk named "dameid" that clearly shows the idle slots of the processor in the permanent phase. For a schedulable task system under EDF when the exact preemtion cost is considered, the period of the permanent phase may be much longer than the classical one least commun multiple (LCM) of the periods of all tasks in the traditional scheduling theory. A specific effort has been done in SAS in order to improve the display in this case.

The classical utilization factor, the permanent exact utilization factor, the preemption cost in the permanent phase, and the worst response time for each task are displayed when the system is schedulable. In addition, another graphic, showing the response times of each task relative time, can be displayed.

The software is written in OCAML, using CAMLP5 (syntactic preprocessor) and OLIBRT (a graphic toolkit under X). Both are written by Daniel de Rauglaudre.


previous
next

Logo Inria