Method and system for real-time causality and root cause determination of transaction and infrastructure related events provided by multiple, heterogeneous agents

Abstract

A method is disclosed that estimates causal relationships between events based on heterogeneous monitoring data. The monitoring data consists in transaction tracing data, describing the execution performance of individual transactions, resource utilization measurements of infrastructure entities like processes or operating systems and network utilization measurement data. A topology model of the monitored environment describing its entities and the communication activities of these entities is incrementally created. The location of occurred events in the topology model is determined. The topology model is used in conjunction with a domain specific causality propagation knowledge base to calculate the possibility of causal relationships between events. Different causality determination mechanisms, based on the type of involved events are used to create graphs of causal related events. A set of root cause events, representing those events with greatest global impact on all other events in an event graph is calculated for each identified event graph.