Clusters and Grids
 |
 |
Menu
Home
Personnel
Projects
Publications
News and Events
NEW! Blog
Job vacancies
Clusters and Grids
Access Grid
Wiki site
Publicity
Links
Contact ReSC
Search
Reading Campus Grid
A Campus Grid is in operation at the University of Reading. At present, this consists of a Condor pool of around 500 desktop Pentium IV machines (and growing) around Campus. Condor allows the spare capacity of computers to be harnessed to create a low-cost, high-throughput computing facility. Please contact resc@rdg.ac.uk if you wish to use this.
Although the worker machines in the Condor pool natively run Windows XP, CoLinux is installed as a Windows service on these machines to provide the Linux environment in which Condor runs. This means that users can run their Linux executables on the pool without the need to dual-boot the worker machines.
We anticipate that the capacity of the Campus Grid will increase to include more desktop machines and to provide access to high-end resources such as clusters around the University. We are in the process of linking the Campus Grid with the Campus Grid at the University of Oxford (OxGrid) to provide a powerful shared facility for researchers at both universities.
The Reading Campus Grid is an Affiliate of the UK National Grid Service.
See http://grid.rdg.ac.uk/condorview for usage statistics (this page is currently only available from within the University of Reading).
Clusters
ESSC has a 16-node, high performance computing (HPC) cluster with a total of 64 processors and 128 Gigabytes of RAM. More information about the ESSC Cluster can be found on the ReSC Wiki site, at http://www.resc.rdg.ac.uk/twiki/bin/view/Resc/ClusterNotes. There is also a cluster users' Wiki for sharing technical information, including a "getting started" section for beginners.
ESSC is a member of the NERC Cluster Compute Forum (CCF), formerly known as the High Performance Computing and eScience Technical Advisory Group (HPCeSTAG). The CCF brings together cluster computing specialists from Natural Environment Research Council (NERC) Surveys, research centres and collaborative research centres. The activities of the CCF include promoting and facilitating cluster computing within NERC and maximising the use of NERC's cluster resources. One way to increase cluster utilisation is to encourage NERC institutions engaged in collaborative science projects to share their clusters. Grid computing is an important tool for facilitating the sharing of distributed compute resources.
Grids
A Grid is a collection of computational resources that are connected in a way that facilitates sharing across administrative domains. Shared resources can include High Performance Computing (HPC) and High Throughput Computing (HTC) clusters, data storage facilities and scientific instruments. The Reading Campus Grid (see above) is an example of an HTC cluster. Grids facilitate the operation of Virtual Organisations that cross geographical and institutional boundaries. The National Grid Service provides facilities for sharing data and computational resources for academic institutions in the UK. The NERC Cluster Grid is an example of a compute grid, a grid designed for sharing high performance computing resources. More information about the NERC Cluster Grid can be found in the ReSC Projects section.
- Ganglia Web Frontend: Load and performance statistics
- Portal: Cluster activity reports