Hadoop is a distributed batch processing infrastructure which is currentlybeing used for big data management. The foundation of Hadoop consists of HadoopDistributed File System or HDFS. HDFS presents a client server architecturecomprised of a NameNode and many DataNodes. The NameNode stores the metadatafor the DataNodes and DataNode stores application data. The NameNode holds filesystem metadata in memory, and thus the limit to the number of files in a filesystem is governed by the amount of memory on the NameNode. Thus when thememory on NameNode is full there is no further chance of increasing the clustercapacity. In this paper we have used the concept of cache memory for handlingthe issue of NameNode scalability. The focus of this paper is to highlight ourapproach that tries to enhance the current architecture and ensure thatNameNode does not reach its threshold value soon.
展开▼
