Infrastructure for Private Cloud Takes a Big, Bold Step Beyond Hyperconverged Systems

Datrium is taking private cloud infrastructure beyond hyperconvergence with its DVX Rackscale System, for improved performance at a fraction of traditional total cost of ownership (TCO). Unlike hyperconverged infrastructure, it is open to including existing customer servers while still offering a full turnkey infrastructure experience.

Datrium DVX vs. HCI Vendors

Datrium announced today how it’s taking the $11.3 billion converged systems market in 2016 per IDC[i] and a hyperconverged market predicted to grow to almost $5 billion by 2019 according to Gartner[ii] a step further, with its DVX Rackscale System making infrastructure for the private cloud effortless. It’s a first-of-its-kind turnkey scale-out system, showcasing why Open Convergence is moving data centers beyond hyperconvergence in a big way.

“There are two standard reactions to private cloud infrastructure modernization as the public cloud grows,” says Brian Biles, CEO, Datrium. “Either you can freeze your SAN the way people have done with mainframes —​ with the occasional component upgrade but without helping Opex — or you can focus on Opex improvement.  The latter will drive you to convergence and commodity systems.”

"There are two standard reactions to private cloud infrastructure modernization as the public cloud grows. Either you can freeze your SAN the way people have done with mainframes — with the occasional component upgrade but without helping Opex — or you can focus on Opex improvement. The latter will drive you to convergence and commodity systems."

Brian Biles, CEO, Datrium

With the introduction of DVX Rackscale Systems, both Open Convergence and hyperconverged infrastructures (HCI) offer converged clusters of compute and storage using commodity hardware. However, DVX brings a host of capabilities not offered by a hyperconverged infrastructure (HCI).

There are more differences to consider, but DVX is like a host-based scale-out flash system integrated with one of the world’s leading cloud data management platforms for persistence. 

Just two node types required
In HCI, all hosts can write to all hosts in a cluster. This makes configuration a very deliberate exercise. In DVX, there are two node types: a Compute Node and a Data Node. The Compute Node is where performance happens, and it writes to Data Nodes for persistence. Compute Node performance is isolated from other Compute Nodes, so when one is down for maintenance, it doesn’t affect the others. Data Nodes just persist data and coordinate, so they have redundant hardware, batteries for RAM power protection, etc.

If the goal is to be as effortless as possible, clear node roles, as is the case with hyperscale clouds — and DVX — is just simpler.

[i] Source:  IDC Worldwide Quarterly Converged Systems Tracker, March 23, 2017.

[ii] Source:  “Gartner Says Hyperconverged Integrated Systems will be Mainstream in Five Years.”


Datrium is the leader in Open Convergence for private clouds. Datrium converges storage and compute across primary application and data management workloads — modeled on public cloud IaaS versus traditional converged infrastructure or hyper-convergence — for vastly simpler performance, predictability and protection. For more information, visit

Datrium and the Datrium logo are trademarks of Datrium, Inc. All other trademarks are the property of their respective owners.

Press Contacts

Media Contact | April Burghardt | +1 (646) 246-0484 |

Source: Datrium, Inc.


Categories: Cloud computing, Data Storage and Warehousing, Information Systems

Tags: cloud infrastructure, hyperconverged, open convergence, private cloud