Fitting Schedulability Analysis Theory into Model-Driven Engineering

Abstract

The theory behind state-of-the-art schedulability analysis has reached such a level of sophistication that its complete mastering by the average industrial practitioner is practically infeasible. The centrality of automation promoted by model-driven engineering may facilitate the uptake of the front-end of the analysis theory by the industrial world. In this paper we qualitatively evaluate how current approaches to model-based schedulability analysis may employ and feed state-of-the-art analysis equations; we then illustrate a new strategy which, by way of model transformation, warrants a high degree of confidence in and permits an iterative refinement of the input to sophisticated analysis equations. We contend that model-driven engineering is well suited for fitting the most advanced analysis theories and to chart the course for future improvements in the area of model-based schedulability analysis

Rapid Model-Driven Prototyping and Verification of High-Integrity Real-Time Systems

“…Thanks to the determinism warranted by the RCM, the execution cost of the concurrent architecture is known a priori [5]. The original toolset concept includes provisions for automatically extracting worst-case execution times for the activities specified in the functional view.…”

“…Correctness by construction is achieved by combination of the metamodel ontology with validation constraints and automated transformations instructed by deterministic rules [1]. The prototype tool also features modelbased timing analysis ( [4], [5]) and automated generation of Ada 2005 source code [6].…”

A model-based approach for multiple QoS in scheduling: from models to implementation

“…In line (10) of Table 3 we analysed the timed model of the system under a non-preemptive execution policy. We used as a scheduler the 118 constraints we had synthesised for the 4-task system, see line (8). As we can see, there were indeed new bad states where deadlines are missed and we synthesised 2325 constraints for avoiding them.…”

“…Finally, compared to MDE approaches like [8] that are based on classic scheduling analyses, the general applicability of scheduler synthesis means that analysis tools do not need to be extended for each new system case that gets analysed.…”

“…Restructuring is not an easy task -not only because of the transformation steps themselves but also because it is not clear what the transformation goal should be for a given system. Indeed, software engineers are called upon to correctly identify which case among the massive (and ever-growing) body of analysed systems better fits their own system [8]. Given that systems are becoming heterogeneous, trying to continuously adapt the basic theory to accommodate each and every new sub-case is a Sisyphean task -asking software engineers to search among these cases for the one that best matches their needs is simply unrealistic.…”