From the Application to the CPU: Holistic Resource Management for Modern Database Management Systems
Stefan Noll, Norman May, Alexander Böhm, Jan Mühlig, Jens Teubner
Bulletin of the Technical Committee on Data Engineering, IEEE Computer Society, March 2019 (Online First)
With their capability to perform both high-speed transactional processing and complex analytical work-loads on the same dataset and at the same time, Operational Analytics Database Management Systemsgive enormous flexibility to application developers. Particularly, they allow for the development ofnew classes of enterprise applications by giving analytical insights into operational data sets in realtime. From a database system point of view though, these applications are very demanding, as theyexhibit a highly diverse combination of different query workloads with inhomogeneous performance andlatency requirements. In this article, we discuss the practical implications and challenges for databasearchitects and system designers. We propose solutions that—by sharing semantics between the appli-cation, the database system, the operating system, and the hardware—allow to manage complex andresource-intensive workloads in an efficient and holistic way