Global states monitoring algorithm for distributed system

Abstract

AbstractIn distributed systems, there are not only synchronization errors which stop the system but also errors in which each process behaves according to its process definition, yet the system as a whole behaves differently from the requirements. Since many synchronization errors cannot be detected by locally monitoring the state of each process, monitoring system global states is required. Stable global states are the global states with all channels empty, and monitoring them is known to be important for detecting loss of synchronization in distributed systems, i.e., the presence of unintended global states or the absence of intended ones.This paper describes a method of monitoring stable global states during the operation of distributed systems. This paper first clarifies the lower bound of control information, which each process should record for detection of stable global states, under the assumption that all control information is piggybacked with ordinary system messages. A stable global state monitoring algorithm is then presented, whose control information is minimum and which has minimum‐order complexity.