Diagnosis system for automatic detection of deadlock in asynchronous concurrent distributed computing systems: using timed Petri net with stacks

Abstract

The authors show how to use the timed Petri net with stacks (TPNS-net) to describe asynchronous concurrent distributed computing systems (DCS) which are based on the environment of loosely coupled computing systems. They also present methods for detecting types of DCS deadlocks such as cycle waiting, hold and wait, and exclusive access. It is shown that TPNS-net permits a process to request more than one resource at a time, express the dynamic state of the system, and increase the system parallelism.<>