• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2012, Vol. 34 ›› Issue (10): 73-77.

• 论文 • 上一篇    下一篇

基于服务器集群的云监控系统设计与实现

沈 青,董 波,肖德宝   

  1. (华中师范大学计算机科学系,湖北 武汉 430079)
  • 收稿日期:2012-04-25 修回日期:2012-07-10 出版日期:2012-10-25 发布日期:2012-10-25

Design and Implementation of Cloud Monitoring System Based on Server Clusters

SHEN Qing,DONG Bo,XIAO Debao   

  1. (Department of Computer Science,China Central China Normal University,Wuhan 430079,China)
  • Received:2012-04-25 Revised:2012-07-10 Online:2012-10-25 Published:2012-10-25

摘要:

为了应对数据延时和IT资源分散状况,越来越多的公司正将服务器和应用程序从远程分支机构撤回到数据中心集中管理,这就使得数据中心的IT资源越来越多,数据中心越来越趋于大型化,管理对象不仅包括传统的小型机、服务器、数据库和各种应用,还包括更多的存储设备、刀片服务器、虚拟机、云计算等,传统的网络管理和监控面临巨大挑战。本文阐述在复杂的网络环境下如何对服务器集群进行全面的监控和高效的管理,重点对数据中心的大规模多类型服务器监控告警技术进行研究。云监控管理系统主要包括高效的数据采集和海量数据处理两大部分,可实现对1 000~10 000台服务器的有效管理和全面监控,目前已实现对Windows、Linux、Unix、IBM、Solaris类型主机和mySQL、SQLserver、Oracle、Apache、Tomcat、IIS、网站监测等应用的监控。

关键词: 服务器集群, 云监控, 海量数据处理

Abstract:

In order to solve the problems of data delay and distributed IT resources, more and more companies put the server and the application from the remote branches to the data center in order to do centralized management. This leads to more and more IT resources in the data center, and the scale of the data center tends to be larger. The data center manages not only the traditional minicomputers, servers, databases and various applications, but also storage equipments, blades servers, virtualization and cloud computing. In this way, the traditional network management and monitoring faces great challenges. This paper describes the comprehensive monitoring and efficient management of server clusters in complex network environments, and focuses on the research of monitoring largescale and multitype data in the data center. The cloud monitoring and management system is made up with data collection and massive data monitoring, It can achieve effective management and comprehensive monitoring of 1 000~10 000 servers. Currently, it can monitor five categories of hosts, for instance, Windows, Linux, Unix, IBM, and Solaris, and seven kinds of applications, such as mySQL, SQLServer, Oracle, Aapache, Tomcat, IIS, site monitoring, etc.

Key words: server clusters;cloud monitoring;massive data processing