Automatisation de la structuration des logs pour le Cloud Computing

TL;DR

This paper evaluates two log-structuring solutions for cloud computing, focusing on how parameterization and preprocessing affect automation efficiency and effectiveness in handling large log volumes.

Contribution

It provides an analysis of the impact of parameterization and preprocessing on the performance of log-structuring methods in cloud environments.

Findings

Preprocessing significantly influences method effectiveness.

Parameter tuning is crucial for optimizing performance.

Automation challenges are linked to human-dependent steps.

Abstract

Logs are a fundamental component of modern computer systems. They enable the analysis and monitoring teams to understand any abnormal or malicious behavior that may have occurred. The continuous increase in the volume of logs generated by these systems made it unsuitable for manual inspection and represents a real challenge with regard to process automation. In order to process these data, several log-structuring solutions have been developed. In this article, we analyze the capabilities of two solutions in order to meet the challenges of Cloud Computing in terms of efficiency and effectiveness. Our work focuses on the impact of parameterization and preprocessing on the performance of these methods -- two important steps as they require human intervention, which is incompatible with with the automation of the log-structuring process.