Publication: Visual Analysis Application for the Error Messages Clustering Framework
Дата
2021
Авторы
Journal Title
Journal ISSN
Volume Title
Издатель
Аннотация
© 2020 Elsevier B.V.. All rights reserved.The framework for clustering of error messages, ClusterLogs, was developed as a flexible and modular tool for the needs of large-scale distributed computing infrastructures. Various types of failures are being constantly registered during the execution of millions of computing operations daily. Monitoring systems are faced with a challenging task of the analysis of considerable amount of multi-sourced error messages. It is critical to present the information about errors to human experts in a way that makes them able to analyze it. ClusterLogs is a pipeline of methods that allows the discovering of common patterns in error messages and group similar messages for further analysis. This pipeline is able to cluster heterogeneous messages without any prior knowledge about textual pattern and can be executed in a fully automated way. In this work we describe a visual analytics web application that provides the analyst with the visual means of setting up clustering pipeline parameters and facilitates the interpretation and validation of the clustering results.
Описание
Ключевые слова
Цитирование
Grin, D. Visual Analysis Application for the Error Messages Clustering Framework / Grin, D., Grigorieva, M., Artamonov, A. // Procedia Computer Science. - 2021. - 190. - P. 274-283. - 10.1016/j.procs.2021.06.037