The time-triggered router for CAN has as its goal to improves the dependability, performance and timeliness of CAN communication. The configuration of the CAN router includes knowledge about the permitted behavior of nodes in the time and value domains. Based on this configuration the CAN router performs fault isolation, diagnosis, message multicasting and message transformations. This paper presents architectural elements and algorithms for the modification of the router configuration at run-time. The router is realized as a Multi-Processor-System-on-a-Chip (MPSoC) and contains a dedicated hardware core for controlling the reconfiguration process. The configuration information is transferred to the cores responsible for the individual CAN segments through a time-triggered network-on-a-chip. We provide a solution for assured reconfiguration with predictable timing and continuity of service during the reconfiguration. An experimental evaluation demonstrates the bounded time for reconfiguration, as well as the seamless and consistent switching to new configurations.
I. INTRODUCTIONDynamic reconfiguration occurs when the configuration of an application is modified while it is running. Dynamic configuration enables a system to dynamically adapt to changes in the environment and to changes in resource demands or resource availability (e.g., power, time/scheduling, communication bandwidth, memory). Dynamic configuration enables better resource utilization, improved dependability, and the enabling of power-aware system behavior. In a distributed system where node computers are interconnected by a communication network, dynamic configuration involves changes in the use of computational resources (i.e., the allocation of functions to node computers) and changes in the use of communication resources (i.e., the use of communication network for interaction between node computers).This paper investigates the adoption of a new configuration of the communication resources for a Controller Area Network (CAN) [7] based on a router. As presented in previous work [8], [11], a time-triggered router for CAN exploits a priori knowledge about the communication behavior of nodes in order to improve the dependability, performance and composability in CAN-based systems. The disadvantage of this approach is that a given configuration of the router restricts modifications of the system such as the replacement, addition or removal of nodes and messages.Therefore, the goal is to modify at run-time the router's a priori knowledge about the communication behavior of nodes such as the temporal properties of messages (e.g., maximum and minimum interarrival times), valid identifiers, recipients