Automated testing for distributed databases with fuzzy fragment reallocation

Authors: AKHAN AKBULUT, GÖZDE KARATAŞ

Abstract: As the Internet and big data become more widespread, relational database management systems (RDBMSs) become increasingly inadequate for web applications. To provide what RDBMSs cannot, during the past 15 years distributed database systems (DDBSs) have thus emerged. However, given the complicated structure of these systems, the methods used to validate the efficiency of databases, all towards ensuring quality and security, have become diversified. In response, this paper demonstrates a system for performing automated testing with DDBSs, given that testing is significant in software verification and that accredited systems are more productive in business environments. The proposed system applies several tests to MongoDB-based NoSQL databases to evaluate their instantaneous conditions, such as average query response times and fragment utilizations, and, if necessary, suggest improvements for indexes and fragment deployment. Within this context, autogenerated data, replica, meta, system, fragment, and index tests are applied. Clearly, the system's most important feature is its fuzzy logic-enabled fragment reallocation module, which allows the creation and application of reallocation strategies that account for data changes in query frequency.

Keywords: Distributed database testing, NoSQL testing, empirical software validation, fragment reallocation, fuzzy logic, MongoDB

Full Text: PDF