As high energy physicist by education, I am since more than two decades involved in the design, development and deployment of large scale distributed data handling systems, raging from object and relational databases to distributed storage clusters.
Data and Analysis Preservation
Data Center Analysis
Since WLCG went into stable operation, I spend a fraction my time with the statistical analysis of CERN computer center metrics in order to help optimising the efficiency of scientific analysis workflows.
Recent analysis areas included:
- analysis of storage media failure rates in a population of 90k disk units
- interaction between storage and CPU efficiency
- quantification of WAN latency impact on specific science workflows
Currently, I lead the Scientific computing Collaborations (SC) group in CERN’s IT department which hosts the Worldwide LHC Computing Grid (WLCG) project office and operations coordination and is actively involved in software and infrastructure optimisation.
- 1995 PhD degree in physics, University of Hamburg
- 1990 Diplom degree in physics, University of Hamburg
- 1986 Physics and computer science studies at University of Muenster and Hamburg
Other Roles and Memberships
- IT department representative in CERN’s Open Data Policy working group
- Part-time lecturer for Advanced Data Analysis at University of Lausanne
- Leader of the LHC Computing Grid (WLCG) project for persistency framework development
- Leader of the WLCG Distributed Database Deployment project
- Organiser of XLDB Europe 2013 and session organiser XLDB Europe 2017
- Program comittee chair of Computing in High Energy Physic (CHEP) 2012
- Invited reviewer at ESA (2001), NIF(2011) and LHC experiment (ATLAS, LHCb, CMS) project reviews
- Ph.D project supervisior or Ph.D thesis supervisor at (Univ. Vienna (2001), Univ. Paris (2006) and Braunschweig Univ. of Technology)
- CERN Summer Student Lecture Program Committee (2007-2013), responsible for computing related lectures
- ACM member
- Frequent reviewer of storage related publications
- Invited speaker at DevDays 2017 (Vilnius), CRUNCH 2016 (Budapest), UseR 2016 (Stanford), Apache BigData 2015 (Budapest), GOTO 2012 (Aarhus)
- Invited as external expert to ISAT Storage Meeting 2016 (New York), ReThink Big, Roadmap for European Technologies for Big Data, project meetings (2015)
- Invited lecturer representing the LHC Computing Grid at the first CERN – Thailand Computing School, Bangkok, Thailand 2010.
- Back-end storage - use as a true archive, WLCG Data & Storage Management Jamboree, Amsterdam, June 2010
- Invited CHEP plenary, Distributed Data and Meta Data Management, CHEP 2009, Prague, Czech Republic
- Petabyte Scale Data Management for LHC, Workshop on Data Storage, ESRF Grenoble, June 2008
- Presented CERN’s grid and database activities in a keynote talk by Intel CEO Paul Otellini at the Oracle Open World Conference 2007
- Lecturer at the 1998, 2001 and 2004 CERN School of Computing
- DEXA 2000 - paper on File replica consistency in a Grid environment, 2000
- Invited Talk about ODBMS Data Stores in HEP at the 2000 OMG ObjectWorld conference in Frankfurt, Germany
- Invited tutorial on Petabyte Object Databases at the 1999 ACM SIGMOD/PODS conference - Philadelphia, USA
- An up-to-date list can be otained from Inspire.
- A older (status 2016) PDF version is available here.
- There are also a few links / references at my ResearchGate entry.