Amadeus

The collaboration betwen Systems Group and Amadeus has been based on the following projects:

Current:

Data Center Model

Large enterprise datacenters which have evolved over time contain a heterogeneous mix of machines, switches, and virtual networks (in contrast to more idealized, “green field” datacenters built as a single unit), and run a mix of inter-dependent services, frequently with complex constraints on placement and communication. More...


Rule Engine

In business rule engines that are accessed by thousands of clients simultaneously, retrieving rules in a timely manner is of the essence. In this project we look at problems that arise in such engines and which indexing strategies are applicable in this environment. More...


Peer-to-Peer Database Replication

When dealing with data sets that are heavily read-dominated and seldom updated it is often beneficial to cache parts of a database locally on all machines. But with an increasing number of machines scalability problems arise as the data and all its cached copies have to be updated. More...


SharedDB

SharedDB is a relational database that is designed to handle large and complex transactional and analytic workloads. On modern multicore machines, traditional databases handle such workloads by executing queries one-at-a-time on separate cores which leads to unpredictable resource contention and query interaction. More...


Past:

Crescando

Crescando is a scalable, distributed relational table implementation designed to perform large numbers of queries and updates with guaranteed access latency and data freshness. To this end, Crescando leverages a number of modern query processing techniques and hardware trends. Specifically, Crescando is based on parallel, collaborative scans in main memory and so-called "query-data" joins known from data-stream processing. More...


Global Distributed Dictionary

Snapshot Isolation is a widely adopted technique for transaction handling in database systems. This project explores the possibilities of this technique in two directions: in a distributed setting and on column stores.More...