Open Compute Project: Toshiba Announcing Availability of KumoScale NVMe-oF Shared Accelerated Storage Software

At the 2018 Open Compute Project (OCP) U.S. Summit, Toshiba Memory America, Inc. (TMA), U.S.-based subsidiary of Toshiba Memory Corporation, announced the availability of KumoScale, its NVMe-oF (NVM Express over Fabrics) shared accelerated storage software.

Click to enlarge

Provider of NVMe SSDs, technology and software, the company is committed to helping cloud data center customers maximize flash and compute resources. The introduction of KumoScale software enables the use of NVMe-oF to make flash storage accessible over a data center network, providing a simple and flexible abstraction of physical disks into a pool of block storage, all while preserving the performance of direct-attached NVMe SSDs.

“The cloud was built on DAS SSDs due to their low cost and ease of deployment,” noted Steve Fingerhut, SVP and GM, SSD and cloud software business units, TMA. “However, customers are finding the fixed nature of DAS inhibits the flexibility promised by the adoption of containers and orchestration frameworks. With the availability of KumoScale software, these cloud data centers can scale and provision server and flash storage independently to accommodate unexpected and peak workloads. This increases data center efficiency and gives the agility needed to respond to new revenue opportunities.“

The availability of KumoScale opens up a range of possibilities for the company’s customers – including Lenovo.

“Toshiba is an important strategic partner for Lenovo’s servers and storage offerings,” said Chris Verne, executive director, data center group, Lenovo. “We’ve recently collaborated on the KumoScale software solution, demonstrating its ability to work on Lenovo’s platforms. We see the Toshiba software solution as a key innovation for future NVMe-oF offerings that enable increased flexibility and efficiency.“

The technology behind KumoScale was first introduced by the company last year and subsequently certified as the only NVMe-oF-compliant storage target software by the University of New Hampshire InterOperability Laboratory, a testing and certification lab for NVMe technology and software.

KumoScale software manages all system functionality, enabling the creation of networked storage nodes that can be immediately deployed at scale – delivering improved utilization of NVMe SSDs by allowing them to be shared. Additionally, KumoScale paves the way to more efficient use of compute nodes via dynamic orchestration and enables performance storage for container orchestration frameworks such as Kubernetes – and can be adapted to in-house developed provisioning systems.

Commenting on KumoScale’s ability to enable improved server and SSD capacity utilization while lending revenue agility, Eric Burgener, research VP, storage in enterprise platforms, storage and network infrastructure group, IDC, noted: “For many cloud deployments, CPU and storage bottlenecks have hampered performance and storage scalability. Toshiba’s KumoScale software provides increased efficiencies in CapEx and application flexibility. New cloud-based architectures running real-time analytics, financial applications and NoSQL databases can leverage disaggregated NVMe-oF to alleviate these bottlenecks – and gain the full benefit of containerized, orchestrated environments.”

In collaboration with Portworx, Inc., a cloud native storage management solution for Kubernetes, KumoScale provides a solution for making containerized big data, fast data and machine learning workloads easier to manage and higher performing. Portworx provides Kubernetes storage that is dynamically provisioned, highly available, automatically backed-up and enables multi-cloud workflows. Running Portworx volumes on top of KumoScale’s target namespaces enables the raw performance of NVMe to be efficiently and flexibly configured under the leading orchestration framework – which is an industry first.

“The joint TMA and Portworx solution represents the first standards-compliant integration of Kubernetes container orchestration with an NVMe-oF storage target,” noted Eric Han, VP, product management, Portworx. “The ability to run containerized workloads in a fully automated manner with the performance of NVMe-oF will enable a new level of performance and elasticity for data center scale container users.“

TMA and Portworx will jointly demonstrate KumoScale at OCP at the San Jose Convention Center from March 20-21.