Jukka Kommeri

Improving Energy-Efficiency of Grid Computing Clusters

Electricity is a significant cost in high performance computing. It can easily exceed the cost of hardware during hardware lifetime. We have studied energy efficiency in a grid computing cluster and noticed that optimising the system configuration can both decrease energy consumption per job and increase throughput. The goal with the proposed saving scheme was that it is easy to implement in normal HPC clusters. Our tests showed that the savings can be up to 25%. The tests were done with real-life high-energy physics jobs.

Practical cloud evaluation from a nordic eScience user perspective

In this paper, we describe the findings of the NEON project - a cross-Nordic - Sweden, Norway, Denmark, Finland and Iceland - project evaluating the usefulness of private versus public cloud services for HPC users. Our findings are briefly that private cloud technology is not mature enough yet to provide a transparent user experience. It is expected that this will be the case mid 2012. The cost efficiency of both public and private cloud should be continuously monitored as there is a strong downward trend. This conclusion is supported by NEON experimenting as well as larger initiatives e.g. StratusLab reports. Public cloud technology is mature enough but lacks certain features that will be necessary to include cloud resources in a transparent manner in a national infrastructure like the Norwegian NOTUR (www.notur.no) case, e.g. with respect to quota management. These features are expected to emerge in 2011 via third party management software and in the best of breed public cloud services. Public clouds are competitive in the low end for non-HPC jobs (low memory, low number of cores) on price. A significant fraction (ca. 20%) of the jobs running on the current Nordic supercomputer infrastructure are potentially suitable for cloud-like technology. This holds in particular for singlethreaded or single-node jobs with small/medium memory requirements and non-intensive I/O. There is a backlog of real supercomputer jobs that suffers from the non-HPC jobs on the supercomputer infrastructure. Off-loading these non-HPC jobs to a public cloud would effectively add supercomputing capacity. Another finding is that available storage capacity is not accessible in a user-friendly way; most storage clouds are only accessible via programmable interfaces. A number of experiments and piloting are presented to support these claims.

The Effect of Network Performance on High Energy Physics Computing

High Energy Physics (HEP) data analysis consists of simulating and analysing events in particle physics. In order to understand physics phenomena, one must collect and go through a very large quantity of data generated by particle accelerators and software simulations. This data analysis can be done using the cloud computing paradigm in distributed computing environment where data and computation can be located in different, geographically distant, data centres. This adds complexity and overhead to networking. In this paper, we study how the networking solution and its performance affects the efficiency and energy consumption of HEP computing. Our results indicate that higher latency both prolongs the processing time and increases the