Fault-tolerant real-time communication in distributed computing systems

An increasing number of applications require packets to be delivered reliably within prespecified delay bounds. It is shown how this can be achieved by using real-time channels that make soft reservation of network resources to ensure the timely delivery of real-time packets. Algorithms are presented for the establishment of real-time channels, and it is shown how the basic real-time channels can be enhanced to be fault tolerant using the multiple paths between a pair of communicating nodes. The contribution of the former is a tighter schedulability condition that makes more efficient use of network resources than other existing approaches, and the contribution of the latter is a significant improvement in fault tolerance over the basic real-time channel, which is inherently susceptible to component failures.<>