MapR Makes Hadoop More Dependable

MapR is the first, and only, distribution for Apache Hadoop to eliminate single points of failure and incorporate features such as Mirroring, Snapshots and Distributed HA.

MapR provides fully configurable snapshots to enable point-in-time recovery. Recovery is as simple as a drag-and-drop copy of selected files.

MapR Mirroring provides business continuity and performance options within a cluster, across clusters or between two data centers.

Distributed Namenode HA™ eliminates single points of failure and provides unlimited scalability. MapR also provides JobTracker HA to prevent lost jobs, and Multi-node NFS High Availability to ensure dependable data access and loading of MapR clusters.

	High Availability		Mirroring
	Cloud		Snapshots

MapR enables you to share Hadoop safely with multiple jobs. We protect the core system by isolating it from user jobs. That means a runaway job can’t bring down your entire cluster. Safely sharing the cluster also means higher utilization. Setting quotas for users and then tracking capacity usage is made easy whether you are managing one node or thousands.