Cache Related Pre-emption Delays in Hierarchical Scheduling

Abstract — Hierarchical scheduling provides a means of composing multiple real-time applications onto a single processor such that the temporal requirements of each application are met. This has become a popular technique in industry as it allows applications from multiple vendors as well as legacy applications to co-exist in isolation on the same platform. However, performance enhancing features such as caches mean that one application can interfere with another by evicting blocks from cache that were in use by another application, violating the requirement of temporal isolation. In this paper, we present analysis that bounds the additional delay due to blocks being evicted from cache by other applications in a system using hierarchical scheduling when using either a local FP or EDF scheduler. EXTENDED VERSION This paper forms an extended version of “Accounting for Cache Related Pre-emption Delays in Hierarchical Scheduling” (Lunniss et al. 2014a) which was published in RTNS 2014. The main additional contributions are as follows: The introduction of new CRPD analysis for hierarchical scheduling with a local EDF scheduler (section VII) Extending the evaluation with results for EDF and with some additional evaluations to explain the differences in the results obtained using a local FP scheduler vs a local EDF scheduler Note: Preliminary results for the EDF extension were presented in a workshop paper “Accounting for Cache Related Pre-emption Delays in Hierarchical Scheduling with Local EDF Scheduler ” (Lunniss et al. 2014b) at the JRWRTC at RTNS 2014