Baler: deterministic, lossless log message clustering tool
Baler: deterministic, lossless log message clustering tool
复制标题
Baler：确定性、无损日志消息聚类工具
DOI：
10.1007/s00450-011-0155-3
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
C. Leangsuksun
中科院分区：
文献类型：
--
作者：
Narate Taerat;J. Brandt;A. Gentile;M. Wong;C. Leangsuksun
随着组成系统的组件数量的增加，HPC系统的故障率持续增加。系统日志是可用于分析系统故障及其根本原因的有价值的信息源之一。但是，系统日志文件通常太大且太复杂，无法手动分析。有一些现有的日志聚类工具，试图帮助分析师在探索这些日志，但他们无法满足我们的需求，可扩展性，可用性和质量的结果。因此，我们开发了一个日志聚类工具，以更好地满足这些需求。在本文中，我们提出了我们的新方法和初步的实验结果。
The rate of failures in HPC systems continues to increase as the number of components comprising the systems increases. System logs are one of the valuable information sources that can be used to analyze system failures and their root causes. However, system log files are usually too large and complex to analyze manually. There are some existing log clustering tools that seek to help analysts in exploring these logs, however they fail to satisfy our needs with respect to scalability, usability and quality of results. Thus, we have developed a log clustering tool to better address these needs. In this paper we present our novel approach and initial experimental results.