SpatialHadoop: towards flexible and scalable spatial processing using mapreduce

Recently, MapReduce frameworks, e.g., Hadoop, have been used extensively in different applications that include tera-byte sorting, machine learning, and graph processing. With the huge volumes of spatial data coming from different sources, there is an increasing demand to exploit the efficiency of Hadoop, coupled with the flexibility of the MapReduce framework, in spatial data processing. However, Hadoop falls short in supporting spatial data efficiently as the core is unaware of spatial data properties. This paper describes SpatialHadoop; a full-edged MapReduce framework with native support for spatial data. SpatialHadoop is a comprehensive extension to Hadoop that injects spatial data awareness in each Hadoop layer, namely, the language, storage, MapReduce, and operations layers. In the language layer, SpatialHadoop adds a simple and ex- pressive high level language for spatial data types and operations. In the storage layer, SpatialHadoop adapts traditional spatial index structures, Grid, R-tree and R+-tree, to form a two-level spatial index. SpatialHadoop enriches the MapReduce layer by two new components, SpatialFileSplitter and SpatialRecordReader, for efficient and scalable spatial data processing. In the operations layer, SpatialHadoop is already equipped with a dozen of operations, including range query, kNN, and spatial join. The flexibility and open source nature of SpatialHadoop allows more spatial operations to be implemented efficiently using MapReduce. Extensive experiments on a real system prototype and real datasets show that SpatialHadoop achieves orders of magnitude better performance than Hadoop for spatial data processing.