Applying analytical and empirical schedulability analysis techniques to a real spacecraft flight software

Abstract

Software schedulability analysis is a crucial aspect for real-time software system verification. This paper presents a combined approach of analytical and empirical techniques for measuring task execution times and verifying the timing constraints of flight software (FSW) applications in real space projects. The proposed methodology is based on the following two main steps. Firstly, we perform an analytical verification via the response time analysis (RTA) in order to show that all the hard deadlines defined for time-critical SW tasks are met. In particular, the worst-case execution times (WCETs) of such SW tasks are measured via static code analysis. Secondly, we analyse the activities that are executed in the context of less time-critical tasks via a more empirical argumentation. The CPU load for the whole running FSW is measured in significant and time-consuming operational scenarios with the aim of proving that the CPU load requirements are fulfilled. Such approach has been applied to an industrial-sized spacecraft FSW and points out the importance of focusing on this topic in the early phases of the FSW development.