基于机器学习的日志函数自动识别方法
随着软件规模的不断增长,日志在故障检测中发挥着愈加重要的作用。然而,目前软件日志缺乏统一标准,常受开发人员个人习惯影响,为大规模系统中日志的自动化分析带来了挑战。其中,日志函数的识别作为日志分析的前提条件,对分析结果有着直接影响。提出了一种基于机器学习的方法以支持日志自动识别。通过系统分析广泛使用的大规模开源软件,总结出日志函数编写的主要形式,并提取不同形式间的共性特征,进而基于机器学习实现了自动日志识别工具iLog。实验显示,使用iLog识别的日志函数能力平均为使用特定关键字的76倍,十折交叉验证得到iLog的分析结果的F-Score为0.93。...
Saved in:
Published in | 计算机工程与科学 Vol. 39; no. 1; pp. 111 - 117 |
---|---|
Main Author | |
Format | Journal Article |
Language | Chinese |
Published |
国防科学技术大学计算机学院,湖南长沙,410073
2017
|
Subjects | |
Online Access | Get full text |
ISSN | 1007-130X |
DOI | 10.3969/j.issn.1007-130X.2017.01.015 |
Cover
Loading…
Summary: | 随着软件规模的不断增长,日志在故障检测中发挥着愈加重要的作用。然而,目前软件日志缺乏统一标准,常受开发人员个人习惯影响,为大规模系统中日志的自动化分析带来了挑战。其中,日志函数的识别作为日志分析的前提条件,对分析结果有着直接影响。提出了一种基于机器学习的方法以支持日志自动识别。通过系统分析广泛使用的大规模开源软件,总结出日志函数编写的主要形式,并提取不同形式间的共性特征,进而基于机器学习实现了自动日志识别工具iLog。实验显示,使用iLog识别的日志函数能力平均为使用特定关键字的76倍,十折交叉验证得到iLog的分析结果的F-Score为0.93。 |
---|---|
Bibliography: | JIA Zhou-yang, LIAO Xiang-ke, LIU Xiao-dong, LI Shan-shan, ZHOU Shu-lin, XIE Xin-wei (College of Computer, National University of Defense Technology,Changsha 410073,China) 43-1258/TP With software scaling up continuously, logging mechanism has become an indispensable part in failure diagnosis area. A pretty similar symptom may be caused by various software bugs, and the most obvious evidence is always logging messages. Meanwhile, the development of most pieces of large-scale software is affected by developers' personal habits rather than being guided by certain conventional specification, so log-related analysis suffers in large-scale software. The recognition of logging function plays a precondition role in log analysis and affects the results of log analysis directly. We propose a machine learning method to fill the gap that logging function recognition has not been paid attention by most existing log-related works. Learning from widely-used software, we summary three logging functions, extract five common fe |
ISSN: | 1007-130X |
DOI: | 10.3969/j.issn.1007-130X.2017.01.015 |