Evaluation of Communication Induced Checkpointing in Resource Constrained Embedded Systems
Reconfiguration-Based Fault-Tolerance is one approach for developing dependable safety-critical embedded applications. This approach, compared to traditional hardware and software redundancy, is a promising technique that may achieve the required dependability with a significant reduction in cost in terms of size, weight, price, and power consumption. Reconfiguration necessitates using proper checkpointing protocols to support state reservation and task migration. One of the most common approaches is to use Communication Induced Checkpointing (CIC) protocols, which are well developed and understood for large parallel and information systems, but not much has been done for resource limited embedded systems. This paper implements four common CIC protocols in a resource constrained distributed embedded system with a Controller Area Network (CAN) backbone. An example feedback control system implementation is used for a case study. The four implemented protocols are described and performances are contrasted. The paper compares the protocols in terms of network bandwidth consumptions, CPU usages, checkpointing times, and checkpoint sizes in additional to the traditional measures of forced to local checkpoint rations and total number of checkpoints.