Rumble: data independence when data is in a mess
This paper introduces Rumble, an engine that executes JSONiq queries on large, heterogenous and nested collections of JSON objects, leveraging the parallel capabilities of Spark so as to provide a high degree of data independence. The design is based on two key insights: (i) how to map JSONiq expressions to Spark transformations on RDDs and (ii) how to map JSONiq FLWOR clauses to Spark SQL on DataFrames. We have developed a working implementation of these mappings showing that JSONiq can efficiently run on Spark to query billions of objects into, at least, the TB range. The JSONiq code is concise in comparison to Spark's host languages while seamlessly supporting the nested, heterogeneous datasets that Spark SQL does not. The ability to process this kind of input, commonly found, is paramount for data cleaning and curation. The experimental analysis indicates that there is no excessive performance loss, occasionally even a gain, over Spark SQL for structured data, and a performance gain over PySpark. This demonstrates that a language such as JSONiq is a simple and viable approach to large-scale querying of denormalized, heterogeneous, arborescent datasets, in the same way as SQL can be leveraged for structured datasets. The results also illustrate that Codd's concept of data independence makes as much sense for heterogeneous, nested datasets as it does on highly structured tables.
READ FULL TEXT