Abstract

Scientific and cultural organisations, international collaborations and projects have a need to preserve and maintain access to large volumes of digital data for several decennia. Existing systems supporting these requirements span from simple databases at libraries to complex multi-tier software environments developed by scientific communities. All communities see an increasing volume of data that must be stored efficiently and economically which today, is usually a combination of a dynamic proportion of storage on magnetic disk and on magnetic tape. The bwDataArchiv project at KIT and HLRS is developing an infrastructure for secure and reliable archival storage that functions as a uniform platform for multiple scientific domains and international projects. Access to the actual storage in the data centre is enabled through an abstracted bit-preservation layer that offers features selected for long term storage such as special metadata tags, takes into account the higher latencies of tape or cloud storage and can be used for infrastructure as a service (IaaS) offerings. At the same time access to the storage remains backward compatible for existing applications. Several projects serving different communities i.e. HPC users, libraries, archives, using the interface are presented as are the collection of requirements and the architecture of the prototype implementation.

Links and resources

Tags