When it comes to data storage, is there a solution that offers optimal performance, security, resilience and governance at minimal costs without trade-offs?

IBM Storage seeks to meet these objectives through its Fusion technology and a storage virtualization layer that eliminate the hassle of query engines having to deal with all kinds of diverse storage on-premises, in the cloud or at the edge, since consistent storage is provided, according to Vincent Hsu (pictured), vice president, fellow, chief technology officer and vice president of IBM Storage at IBM Corp.

“The IBM storage technology is going to leverage the hyper cloud scale object storage, be able to scale from edge to on-prem to the cloud and provide the most efficient store for the persistent storage,” he said. “What we do is provide a storage virtualization layer that is able to present a consistent storage to the query engines. But in the backend, we’ll be able to virtualize the very different type of storage HDFS files and objects.”

Hsu spoke with theCUBE industry analyst Dave Vellante at IBM Storage Summit, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed how IBM offers consistent storage for optimal query engine performance. (* Disclosure below.)

IBM watsonx.data is a game-changer

IBM’s new watsonx.data has incorporated more innovations and supports multiple engines. As a result, enterprises are provided with consistent performance, given that they can query any data anywhere at any given time, according to Hsu.

“Let me just focus on watsonx.data; I mean the data management piece of it,” he noted. “It has three salient points. Number one is it supports multi engines. The second one is IBM watsonx.data is supporting the Open Data format [which] allows different kinds of platforms to share data. The third one is the building metadata management and data governance to allow us to be able to truly harvest the insight of the data, be able to truly manage this very diverse data.”

When tackling data problems, a holistic approach is needed to deal with structured, semi-structured and unstructured data for various reasons, such as compliance and security. IBM comes in handy by offering governed data sharing, according to Hsu.

“IBM Storage has a capability to cross through all the unstructured data,” he stated. “For IBM technology, you can see a single pane of glass to see the distribution of all the data, and then you can apply the policy on those data to allow us to be able to perform some particular function — for example, remove the PIIs or the hate speech information from the raw data sources.”

IBM has mastered the art of improving query performance by caching and changing the data format from its original form to an open data format, which is more efficient, according to Hsu.

It’s important for storage technology to “be able to detect what is the right data and be able to cache those data from the remote data sources and cache the local NVMe drives to provide the very high performance,” he said. “In the lab, we have seen that seven to 10x performance improvement by doing this caching.”

Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of the IBM Storage Summit:

(* Disclosure: TheCUBE is a paid media partner for the IBM Storage Summit. Neither IBM Corp., the sponsor of theCUBE’s event coverage, nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE