Realtime Data Flows

MapR radically simplifies Hadoop by making it accessible through NFS.

Other Hadoop distributions manage data slowly through a batch process. Applications must first log data to direct or network-attached storage. Data is then batch loaded into Hadoop's write-once file system. This batch process causes a significant time lag between data production by the application and analysis in a Hadoop cluster. Other Hadoop distributions are limited by the Hadoop Distributed File System (HDFS) — a system that is write-once system like a CD-ROM. HDFS prevents files from being modified once they have been written, and files cannot be read before they are closed.

In sharp contrast, MapR Direct Access™ NFS enables real-time read/write data flows via NFS. Any remote client can simply mount the cluster. Application servers can write their log files and other data directly into the cluster, rather than writing it first to direct- or network-attached storage.

Suddenly, your application can write directly into and out of Hadoop itself. That means data can be updated to enable realtime dataflows.