Active Data Repositories are data stores that are located close to computational or visualisation resources such that high performance access to data is enabled (in terms of high bandwidth and/or high IOPS rates). Active data repositories should be used for storing temporary slave replica of large data objects, for improving access performance, with the master copy of the data kept in an Archival Data Repository. These repositories are typically implemented as parallel file systems (like GPFS or Lustre) and accessible via a POSIX interface.