From the Bulletin of the Technical Committee on Operating Systems and Application Environments (TCOS), 7(4), pp.35-39.
In this paper, we assess the fitness of current models to represent the attributes underlying the distributed fault-tolerance of real-time systems. Namely, we are concerned with the correctness issues arising from the temporal properties of interprocess communication: reliable and ordered group communication, replication management protocols, time services, etc.
We are particularly concerned with best-effort or mission-critical systems, where despite the hard need to fulfil timing guarantees, this cannot be ensured at all times in a given operational envelope, mandating that the system be highly dynamic and adaptive. In the paper, we suggest quasi-synchronism as a framework to address this kind of systems. We finalize by pointing out some contributions to materialize the model.
Also available extended report (gzip postscript).