一种基于模糊推理的Hadoop异构机群自动配置工具

以运行Hadoop云计算软件平台的异构机群中服务器的硬件指标作为模糊输入,设计了一种自动配置本地服务器的工具.该工具改变了传统云计算平台下的配置方法,以服务器运行历史数据作为参考,引入异构配置方法,通过对异构机群特性的分析,实现对机群的自动配置.仿真实验证明,在保证机群高效的基础上,该工具降低了云计算异构机群的维护成本,具有较高的通用性和可扩展性,对一般的云计算平台也具有参考价值.

An auto-configuration tool for heterogeneous Hadoop cluster

The rapid development of cloud computing makes the heterogeneous cluster a hot research topic. One of the urgent problems in this field is how to configure the cloud computing software platform running on a heterogeneous cluster. We propose a new tool, which can configure each local server automatically according to its hardware parameters in a Hadoop cluster and configures each server individually by analyzing the heterogeneous features and the running history of the Hadoop cluster instead of the traditional uniform way. The simulation and experiment results show that this tool can obviously reduce the maintenance cost without any degradation of system performance and improve performance compared to the manual optimization. It is believed that this method is general and extensible and should be valuable for other cloud computing platforms.