A SCALABLE APPROACH FOR PERFECT FAILURE DETECTION IN TAD ASYNCHRONOUS SYSTEMS

Abstract

Fault Detection is a fundamental issue for fault tolerance in distributed systems. Perfect failure detectors can correctly decide whether a computer has crashed. In this dissertation, we proposed a new scalable protocol for perfect failure detection in a timed asynchronous system with the hardware watchdogs. The proposed algorithm is scalable in the sense that, it allows perfect failure detection in timed asynchronous system with any number of computers which is restricted to three computer systems in the existing algorithm for perfect failure detection. The two main system model assumptions are 1) each computer can measure time intervals with a known maximum error and 2) each computer has a watchdog that crashes the computer unless the watchdog is periodically updated. The algorithm has been simulated using OMNeT++ network simulator for varying size of fully connected networks. Both the theoretical and simulation result shows the scalability of the proposed algorithm. Keywords Perfect failure detection, Scalable, crash failures, timed asynchronous system model, watchdogs