The Hadoop Loader enables users to routinely populate Hadoop Distributed File Systems with huge volumes of corporate data. The Hadoop Loader tracks, accelerates, and automates direct two-way data transfers between a Hadoop cluster and mainframe, Linux, Unix, Windows and other Hadoop clusters.
The direct data transfer function reduces processing time and lowers operating costs by eliminating the need for interim file copies, thereby reducing storage requirements on both ends of the transfer. Mainframe datasets and entire databases can be moved without landing first on the Hadoop server.
Customers adopting this solution will have an easy upgrade path to Parallel Data Mover release 7.