BRAIN. Broad Research in Artificial Intelligence and Neuroscience-Stable Modeling on Resource Usage Parameters of MapReduce Application

<p>Currently, Hadoop MapReduce framework has been applied to many productive fields to<br> analyze big data. MapReduce applications based on the MapReduce programming model are used<br> to generate and process such huge data. Due to various computational purpose, MapReduce<br> applications have different resource requirements. For specific applications, the resource bottleneck<br> of the cloud computing platform must inevitably impact its executive performance. Therefore,<br> identification of the bottleneck about the allocated resource for MapReduce applications is crucially<br> needed from the viewpoint of either cloud operators or program developers. In this paper, we model<br> the relationship of resource usage parameters of MapReduce applications using multiple linear<br> regression methods and investigate the minimum sampling time for stable modeling. Based on the<br> analysis, we propose the approach which can be used to build stable performance model to expose<br> the bottleneck resource of Hadoop platform and give the effective optimization suggestion.