System Level LET: Mastering Cause-Effect Chains in Distributed Systems

Abstract

Cause-effect chains are omnipresent in automotive and other distributed software, where sensor data is first collected and then processed in order to control actuators. It is challenging to find a correct implementation which respects all latency and precedence constraints of the numerous cause-effect chains contained in the software and which is at the same time robust towards software updates and changes. The Logical Execution Time (LET) programming model has proven to be a very promising solution featuring determinism in time and data flow as well as composability, but it is inherently limited to the scope of an electronic control unit (ECU) due to strict requirements w.r.t. clock synchronization and zero-time communication. In this paper, we present and evaluate a new concept, called System Level LET, which generalizes LET and extends it to the scope of the entire, distributed system while preserving determinism in time and data flow as well as composability. System Level LET has relaxed synchronization requirements, is independent of scheduling policies and can be combined with different communication semantics.