Linked Data Partitioning for RDF Processing on Apache Spark

RDF models are widely used in the web of data due to their flexibility and similarity to graph patterns. Because of growing use of RDFs, their volumes and contents are increasing. Therefore, processing of such amount of data on a single machine is not efficient enough, because of the response time and limited hardware resources. As a result, to process this data model, cluster processing is introduced. One of these cluster processing tools is Apache Hadoop. Because of using too much of hard disks, the response time is usually unacceptable. In this paper, according to this problem, we use Apache Spark for rapid processing of RDF data models. One key feature of Apache Spark is using main memory instead of hard disk, so the speed of data processing is improved. In continues, we will run SQL query on RDF data which partitioned on the cluster.