安全管理平台中基于云计算的日志分析系统设计  

Design of Log Analysis System Based on Cloud Computing in Security Management Platform

作　　者：陈洁 于永刚 刘明恒 潘盛合 徐克付[2] 

机构地区：[1]中国移动(深圳)有限公司,广东深圳518048 [2]中国科学院信息工程研究所,北京100093

出　　处：《计算机工程》2015年第2期21-25,共5页Computer Engineering

基　　金：国家自然科学基金资助项目(61003295)

摘　　要：安全管理平台(SMP)是实现安全管理工作常态化运行的技术支撑平台,在实际应用中需要实时处理来自安全设备所产生的海量日志信息。为解决现有SMP中海量日志查询效率低下的问题,设计基于云计算的SMP日志存储分析系统。基于Hive的任务转化模式,利用Hadoop架构的分布式文件系统和MapReduce并行编程模型,实现海量SMP日志的有效存储与查询。实验结果表明,与基于关系数据的多表关联查询方法相比,该系统使得SMP日志的平均查询效率提高约90%,并能加快SMP集中管控的整体响应速度。With the development of cloud computing,massive data can be very easy to be stored and managed.Security Management Platform（SMP） is a support platform which realizes security management normalized operation.In a real application,this platform needs to process the massive information which generates from security device in real time.Considering the problem of low query efficiency,an efficient log analysis system based on the cloud computing for SMP is presented.It introduces the Hadoop distributed system infrastructure,and in the meantime,based on the study of transformation mission of the Hive,Hadoop Distributed File System（HDFS） and Map Reduce are applied to effective storage and query of massive log.Experimental results show that,using proposed system can obtain a general increase in the query performance by about 90%compared with the existing Oracle storage method,and it can also further improve response speed of the SMP.

关 键 词：安全管理平台 云计算 Hadoop架构 海量日志 并行处理 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]