The High Performance Computing Centre (HLRS) is a research and service institution affiliated to the University of Stuttgart (USTUTT). It is one of the three national supercomputing centres in Germany and is offering services to academic users and industry.
The part of the site dedicated to ECO2Clouds site USTUTT-HLRS runs OpenNebula 3.6 in a dedicated version derived for BonFIRE.
Hypervisor used: Worker nodes operate XEN 3.1.2
Image management: Block devices managed using a modified version of the LVM manager provided by OpenNebula
Image storage: Images stored using the “raw” format
OpenNebula scheduler configuration
- t (seconds between two scheduling actions): 10
- m (max number of VMs managed in each scheduling action ): 300
- d (max number of VMs dispatched in each scheduling action): 30
- h (max number of VMs dispatched to a given host in each scheduling action): 2
USTUTT-HLRS provides 17 dedicated worker nodes with different hardware combinations:
8 nodes: 2x Dual Core Intel Xeon @ 2.66 GHz, 8GB RAM
1 node: Dual Core AMD Opteron @ 2 GHz, 4GB RAM
6 nodes: 2x Dual Core Intel Xeon @ 3.2 GHZ, 2GB RAM
2 nodes: 4x AMD Opteron 12 Core @ 2.6GHz, 196GB RAM
These 17 host types of various architectures offer users many various capabilities to run their case studies. Every node type can be accessed directly during the creation of a virtual computing resource. For a better overview of all available resources, USTUTT-HLRS provides a current summary of the worker nodes at http://nebulosus.rus.uni-stuttgart.de/one-status.txt. In addition, a storage server with a total amount of 12 TB disk space supplies the case studies requiring shared data storage. All these nodes are connected via Gigabit Ethernet network interconnections.
USTUTT-HLRS provides 36 on-request nodes distributed on two Christmann RECSs with additional fields of application:
18 nodes: Intel i7-610E Dual Core, 4 GB RAM
6 nodes: Intel Core i7 Quad Core @ 2.1 GHz, 8 GB RAM
6 nodes: AMD Atom, 2 GB RAM
6 nodes: AMD T56N Dual Core, 2 GB RAM
These nodes feature specific functionalities for green IT-related research like measuring power consumption or energy efficiency. They are not part of the permanent infrastructure; access to these nodes needs to be reserved and requires an installation process of at least one working day.