We propose a lightweight fault-tolerant multicast and membership service for real-time process groups which may exchange periodic and aperiodic messages. The service supports bounded-time message transport, atomicity, and order for multicasts within a group of communicating processes in the presence of processor crashes and communication failures. It guarantees agreement on membership among the communicating processors, and ensures that membership changes (e.g., resulting from processor joins or departures) are atomic and ordered with respect to multicast messages. We provide the flexibility of an event-triggered approach with the fast message delivery time of time-triggered protocols, such as TTP [14], where messages are delivered to the application immediately upon reception. This is achieved withoutcompromisingagreement, order andatomicity properties. In addition to the design and details of the algorithm, we describe our implementationof the protocol using the x-Kernel protocol ar...
Tarek F. Abdelzaher, Anees Shaikh, Farnam Jahanian