Incorporating information from a cluster batch scheduler and center management software into automated log file analysis

摘要

Cluster style architectures are becoming increasingly important in the computing world. These machines have been the target of several recent attacks. In this paper, we examine how the unique characteristics of these machines, including how they are generally operated in the larger context of a computing center, can be leveraged to provide better security for these machines. We examine this by incorporating data from a batch scheduler and a user database to augment our automated log analysis using the freely available log analysis tool LoGS.