Blog

Archive for June, 2010

Configuration Management with Puppet and Coupling it to Kickstart

Friday, June 18th, 2010

Here is the presentation of Valeri Markushin (PSI) on “Configuration management with puppet and coupling it to kickstart at PSI” he had at the last hpc-ch forum on Operating Systems for HPC and Installation Methods.

The goals of this talk are to discuss the OS deployment and management tools used at PSI, to outline main arguments and facts (contact me for details) and to show some PSI customization features.

Topics

  • Scientific Linux
  • Kickstart Installation
  • Puppet Management
  • Enhancing your Linux distribution

Slides (PDF) of the presentation »

Experiences with the Rocks Distribution for Cluster Deployment

Thursday, June 17th, 2010

Dorian Krause (USI) presented at the last hpc-ch forum on “Operating Systems for HPC and Installation Methods” about “Experiences with the Rocks Distribution for Cluster Deployment“.

Presentation (PDF) »

Overview of OS, Installation Procedures and Monitoring at CSCS

Wednesday, June 16th, 2010

Here are the slides of Peter Öttl and Fotis Georgatos (CSCS) for their presentation  “An overview of operating systems, installation procedures and monitoring at CSCS” for the last hpc-ch forum on Operating Systems for HPC and Installation Methods.

Outline:

  • Operating Systems for the Swiss WLCG Tier-2
  • Installation Methods Chosen
  • Configuration Management
  • Monitoring Tools

Slides (PDF) of the presentation »

ETH Zurich: Social Supercomputing Is Now

Tuesday, June 15th, 2010

(from ACM TechNew)

ETH Zurich scientists working on the FuturIcT project plan to use the world’s largest supercomputers to simulate life on Earth, including the financial system, economies, and whole societies. The ETH researchers, working under the Competence Center for Coping with Crises in Complex Socio-Economic Systems, are analyzing huge amounts of financial data to detect dangerous bubbles in stock and housing markets, potential bankruptcy cascades in networks of companies, or similar vulnerabilities in other complex networks such as communication networks or the Internet. The FutureIcT project aims to bring different kinds of research together to simulate the entire globe, including the diverse interactions of social systems and of the economy with the environment. The FutureIcT project also aims to analyze data on social, economic, and environmental processes by augmenting the results of field studies and laboratory experiments. “Such observatories would detect advance warning signs of many different kinds of emerging problems, including large-scale congestion, financial instabilities, the spreading of diseases, environmental change, resource shortages, and social conflicts,” says ETH’s Dirk Helbing.


View Full Article »

Clusters Management with AutoYaST

Monday, June 14th, 2010

Here are the slides of Jacques Menu on “AutoYaST and Installation of central services clusters” presented at the last hpc-ch forum.

The agenda of the presentation is:

  • YaST possibilities
  • Novell registration
  • System patch
  • Installation of software supplied by Novell
  • Installation server 8
  • Compute nodes installation strategy 8
  • Compute nodes boot order 9
  • PXE boot configuration files 10
  • AutoYaST control files 15
  • Node-specific settings 19
  • “chroot-scripts” section
  • “init-scripts” section
  • Specific software installation scripts
  • SSH matters
  • Conclusion

Slides as PDF »