A Common Programming Interface for Managed Heterogeneous Data Analysis

The widespread success of data analysis in a growing number of application domains has lead to the development of a variety of purpose build data processing systems. Today, many organizations operate whole fleets of different data related systems. Although this differentiation has good reasons there is also a growing need to create holistic perspectives that cut across the borders of individual systems. Application experts that want to create such perspectives are confronted with a variety of programming interfaces, data formats, and the task to combine available systems in an efficient manner. These issues are generally unrelated to the application domain and require a specialized set of skills. As a consequence, development is slowed down and made more expensive which stifles exploration and innovation. In addition, the direct use of specialized system interfaces can couple application code to specific processing systems. In this dissertation, we propose the data processing platform DataCalc which presents users with a unified application oriented programming interface and which automatically executes this interface in an efficient manner on a variety of processing systems. DataCalc offers a managed environment for data analyses that enables domain experts to concentrate on their application logic and decouples code from specific processing technology. The basis of this managed processing environment are the high-level domain oriented program representation DCIL and a flexible and extensible cost based optimization component. In addition to traditional up-front optimization, the optimizer also supports dynamic re-optimization of partially executed DCIL programs. This enables the system to benefit from dynamic information that only becomes available during execution of queries. DataCalc assigns workloads to available processing systems using a fine grained task scheduling model to enable efficient exploitation of available resources. In the second part of the dissertation we present a prototypical implementation of the DataCalc platform which includes connectors for the relational DBMS PostgreSQL, the document store MongoDB, the graph database Neo4j, and for the custom build PyProc processing system. For the evaluation of this prototype we have implemented an extended application scenario. Our experiments demonstrate that DataCalc is able to find and execute efficient execution strategies that minimize cross system data movement. The system achieves much better results than a naive implementation and it comes close to the performance of a hand-optimized solution. Based on these findings we are confident to conclude that the DataCalc platform architecture provides an excellent environment for cross domain data analysis on a heterogeneous federated processing architecture