Dell EMC big data storage has a sharper focus.
The vendor recently launched Elastic Data Platform (EDP), a series of reference architecture geared for Hadoop and related big data environments. EDP is available as direct-attached storage on PowerEdge servers, clustered Isilon scale-out NAS, or a managed service via the Dell EMC Virtustream Storage Cloud.
Financial services and health care are among the vertical industries in beta, said Matt Maccaux, who heads the global big data practiceof Dell EMC. Big data deployments have matured to the point that DevOps organizations have captured the “low-hanging fruit” of reduced data warehousing and operational gains.
“We are positioning EDP primarily at enterprises that some sort of data lake in place. They have taken all the low-hanging fruit and started to hit a wall in terms of returning value to the business. They are storing massive amounts of data and want to take advantage of the three Vs: volume, variety and velocity of data,” Maccaux said.
A big data analytics team typically has to request resources and wait for provisioning to be approved. Dell EMC’s big data system allows teams to provision resources on the fly, Maccaux said.
The Dell EMC big data hardware bundles software from BlueData Software and Blue Talon. BlueData manages the orchestration of Hadoop compute containers. The Blue Talon centralized policy engine enforces attributes-based security on individual nodes within the cluster.
PowerEdge servers with decoupled local disk storage are intended for deployments of several hundred terabytes. For larger scale-out deployments, Dell EMC recommends Isilion NAS with Hadoop Distributed File System as the underlying storage for Blue Data compute instances. EDP with Isilion includes the ability to create read-only snapshots for all users, erasure coding and automated tiering for cold, hot and warm data.
EDP in Virtustream uses underlying Dell EMC block storage. Virtustream is best known for hosting legacy applications that were not written for the cloud.