Dirk Duellmann, deputy leader of the data and storage services group in the IT department at CERN, will discuss the large scale (100 PB) data management and analysis infrastructure for physics data at the Large Hadron Collider (LHC).
He will compare the established scientific workflow with more recent deployments of hadoop ecosystem components at CERN, which are rapidly gaining popularity for computing infrastructure analytics / optimisation studies and as an alternative to traditional database deployments. The presentation will conclude with an outlook on how big data analysis experience from scientific and mainstream applications may further complement each other.
