Extended group communication algorithm for updating distributed programs

Large-scale distributed systems are not always stable because the environments and the user requirements are changeable. The author has discussed the receptive platform to make distributed systems flexible and reliable. In order to achieve the receptive platform, it is essential to discuss how to update the distributed programs. Since conventional updating methods require that multiple processes be suspended simultaneously, the availability of the system becomes lower. A new method called the dynamic updating has been proposed. The key idea is that multiple versions of processes are allowed to co-exist temporarily while the old-version processes are not used anymore. If such protocol errors as the unspecified receptions and the dead-locks caused by the co-existence occurs, the suspended old-version processes are restarted from the consistent state. An algorithm, has been designed for treating the unspecified receptions. This paper proposes an extended group communication algorithm that can detect and resolve the deadlocks. By using the algorithm, the dynamic updating can be applied to more general distributed application programs