End-to-end latency characterization of task communication models for automotive systems

Abstract

Different communication models have been historically adopted in the automotive domain for allowing concurrent tasks to coordinate, interact and synchronize on a shared memory system for implementing complex functions, while ensuring data consistency and/or time determinism. To this extent, most automotive OSs provide inter-task communication and synchronization mechanisms based upon memory-sharing paradigms, where variables modified by one task may be concurrently accessed also by other tasks. A so-called “effect chain” is created when the effect of an initial event is propagated to an actuation signal through sequences of tasks writing/reading shared variables. The responsiveness, performance and stability of the control algorithms of an automotive application typically depend on the propagation delays of selected effect chains. Depending on the communication model adopted, the propagation delay of an effect chain may significantly vary, as may be the resulting overhead and memory footprint. In this paper, we explore the trade-offs between three communication models that are widely adopted for industrial automotive systems, namely, Explicit, Implicit, and Logical Execution Time (LET). A timing and schedulability analysis is provided for tasks scheduled following a mixed preemptive configuration, as specified in the AUTOSAR model. An end-to-end latency characterization is then proposed, deriving different latency metrics for effect chains under each one of the considered models. The results are compared against an industrial case study consisting of an automotive engine control system.