Background
As the cloud computing paradigm is getting more and more momentum, it is of paramount interest for cloud service providers to offer a well-integrated set of services across the cloud service stack (Software as a Service, Platform as a Service, Infrastructure as a Service). This not only holds for commercial environments but also for academia. Typical examples of such a services are the Apache Hadoop library and the Apache Cassandra database. Together with the Leibniz Supercomputing Centre we are evaluating adequate service sets using a test cloud based on OpenNebula.
Objectives
In this thesis we are focusing on the Apache Cassandra database. The objectives of this thesis are fourfold. Firstly, install and configure Cassandra on the LRZ OpenNebula test cloud. In particular, interface Cassandra with the LRZ Secure Identity Management (SIM) and Hadoop. Secondly, specify a set of benchmarks to compare Cassandra with mySQL (or any other relational database). Thirdly, run the benchmarks. Finally, based on the benchmark results, identify bottlenecks and propose solutions to bridge these gaps.
Assigner:
Prof. Dr. D. Kranzlmüller
Requirements:
Basics in databases, Linux
Duration: according to study guidelines
Number of Students: 1
Supervisors:
Dr. Michael Schiffers, Oettingenstr. 67, Raum E 003 (Erdgeschoß), Tel. 2180-9164
Dr. Helmut Heller, LRZ
Dr. Matteo Lanati, LRZ