Hadoop distributor MapR Technologies has begun a private beta program for its offering running on the Google Compute Engine, that company’s recently announced (still in beta itself) Infrastructure-as-a-Service (IaaS) initiative.
At the announcement of GCE – which provides on-demand Linux-based compute nodes, with storage options – MapR demonstrated the integration, completing a one terabyte TeraSort job in 1 minute 20 seconds. This result was achieved on a GCE cluster with 1,256 nodes, 1,256 disks and 5,024 cores – at a cost of $16.
The integration of MapR with GCE includes a menu of MapR compute configurations where customers can store, manage and analyse large volumes of data, with payment on demand.
MapR also makes its Hadoop disribution available on Amazon Web Services, which the new Google service is set to rival.