Termination detection in a very general distributed computing model

Abstract

Termination detection constitutes one of the basic problems of distributed computing, and many distributed algorithms have been proposed to solve it, but all these algorithms consider a very simple model for the underlying application programs: for processes of such programs, nondeterministic constructs are allowed, but each 'receive' statement (request) concerns only one message at a time. A more realistic and very general model of distributed computing is first presented, allowing a request to be atomic on several messages and to obey AND/OR/AND-OR/k-out-of-n/etc. request types. Within this framework, two definitions of termination are proposed and discussed. Then, accordingly, two distributed algorithms for detecting these terminations are presented and evaluated; they differ in the information they use and in the time they need to claim termination.<>