Schedulability analysis in EDF scheduler with cache memories

Cache memories can improve computer performance, but its unpredictable behaviour makes difficult to use them in hard real-time systems. Classical analysis techniques are not sufficient to accomplish schedulability analysis, and new hardware resources or complex analysis algorithms are needed. This work presents a comprehensive method to obtain predictability on the use of caches in real-time systems using an EDF scheduler. Reaching a predictable cache, schedulability analysis can be accomplished in a simple way through conventional algorithms. At the moment, this is the first approach to consider cache in this kind of scheduler. The method is based in the use of locking caches and genetic algorithms. Locking caches allows to load and lock cache contents, ensuring its remains unchanged. Genetic algorithms help to select the cache content that offers the best performance. Experimental results indicate that this scheme is fully predictable, and this predictability is reached with no performance loss for around 60% of cases.