Distributed system fault root cause tracing method based on knowledge graph technology

Abstract

The invention discloses a distributed system fault root cause tracing method based on a knowledge graph technology. The method is used for solving the problem that large distributed system fault root cause tracing is difficult. The distributed system fault root cause tracing task is used for finding out a root cause causing a system fault. According to the method, a fault knowledge graph is constructed for each type of faults in a distributed system, events are generated from historical fault data by using a template technology in the construction process, then a fault propagation graph is constructed by using a relationship between learning events of a machine learning model, and finally, a merging algorithm is used to extract a common structure of the fault propagation graphs of the same type of faults to generate a fault knowledge graph. When a fault occurs, the fault knowledge graph most similar to the real-time fault propagation graph is obtained by constructing and calculating the real-time fault propagation graph and the similarity between the real-time fault propagation graph and the fault knowledge graph, so that the root cause of the system fault is obtained according to the fault root cause marked by the fault knowledge graph.

Description

technical field [0001] The invention belongs to the field of knowledge graphs, and in particular relates to a root cause tracing method for distributed system faults based on knowledge graph technology. Background technique [0002] With the rapid development of virtualization technology, distributed systems are becoming larger and more complex. Due to the complex network topology of the distributed system, the urgent time to repair faults, and the scarcity of high-level distributed system operation and maintenance personnel, when the system fails, it is difficult for the operation and maintenance personnel to find the root cause in a short time, and the system will be in an unstable state. stable state. It is an urgent problem to find out the root cause of large-scale distributed system failures in time and ensure the safe and stable operation of the system. In recent years, more and more researchers have begun to pay attention to these problems. The methods based on depe...

AI Technical Summary

Problems solved by technology

However, these methods have two limitations: 1. They have not studied how to use the hidden explicit knowledge in historical data to guide the current root cause analysis; 2. They cannot fully explain the fault triggering path at the event level

[0003] The fault propagation path contains a lot of fault information, and different devices and different propagation sequences on the propagation path will lead to different faults

Images