Processing in the Hybrid OLTP & OLAP Main-Memory Database System HyPer

Two emerging hardware trends have re-initiated the development of in-core database systems: ever increasing main-memory capacities and vast multi-core parallel processing power. Main-memory capacities of several TB allow to retain all transactional data of even the largest applications in-memory on one (or a few) servers. The vast computational power in combination with low data management overhead yields unprecedented transaction performance which allows to push transaction processing (away from application servers) into the database server and still “leaves room” for additional query processing directly on the transactional data. Thereby, the often postulated goal of real-time business intelligence, where decision makers have access to the latest version of the transactional state, becomes feasible. In this paper we will survey the HyPerScript transaction programming language, the mainmemory indexing technique ART, which is decisive for high transaction processing performance, and HyPer’s transaction management that allows heterogeneous workloads consisting of short pre-canned transactions, OLAP-style queries, and long interactive transactions.