Overview of the workshop on managing large-scale systems via the analysis of system logs and the application of machine learning techniques
暂无分享,去创建一个
These systems generate copious amounts of useful information that is used today by the system operators to perform various system management tasks. However, manually looking for anomalies in performance metrics or debugging an application using system logs can take significant amount of time. The amount of collected data is typically so large that it is often impossible for human operators to efficiently navigate it and make useful inferences about the system or what led to a particular failure.