Vast Data Universal Storage Platform Ceres With Nvidia BlueField DPUs and Ruler-Based Hyperscale SSDs

VAST Data, Inc. announced support for a next-gen storage platform concept called Ceres.

Enabled by the company’s Universal Storage data platform, Ceres is built leveraging hardware technologies including Nvidia BlueField DPUs and ruler-based hyperscale SSDs that improve performance, simplify serviceability and reduce data center costs.

Ceres platform
Click to enlarge

Designed by the company and industry partners to advance storage into the AI era, Ceres brings speed, resilience, modularity and data center efficiency. It furthers the firm’s mission to equip enterprises and service providers with capabilities that have otherwise been the exclusive domain of largest hyperscale cloud providers.

These hardware platforms, powered by the company’s Universal Storage software, enables customers to adopt technologies providing the following benefits:

• Increased performance, better power and space efficiencies. Leveraging Nvidia BlueField technology, which combines network and NVMe device management services into a low-power ARM-based SoC, DPUs make it possible to build NVMe enclosures without the need for large and power-hungry x86 processors. Transitioning NVMeoF services from x86 servers to BlueField DPUs makes it possible to achieve a 1U form factor capable of delivering over 60GB/s of performance per enclosure for data-intensive applications, all while consuming less power. The firm’s DASE architecture is positioned to leverage DPU-based systems by decoupling storage processing from the flash layer.

• Dense flash capacity configurations. Ceres evolves beyond the classic SSD form-factor and instead features ruler-based, high-density SSDs. Ruler-based flash drives will, over time, pack more flash capacity compared to traditional NVMe drives because of their larger surface area and airflow-friendly design. At launch, the firm has partnered with Solidigm to certify its 15TB and 30TB E1.L SSDs (long ruler format), packing up to 675TB of raw flash in 1U of rack space. With the company’s Data’s Similarity-based data reduction algorithms, Ceres can manage nearly 2PB of effective capacity per enclosure at an average 3:1 data reduction ratio. Additionally, write shaping techniques extend QLC and penta level cell (PLC) flash endurance, while erasure coding also shortens the time to rebuild high-capacity storage devices.

• Simplified serviceability for disaggregated storage clusters. Ceres was engineered to solve a number of problems that customers have faced when dealing with high-density storage systems, including:

  • Eliminating the need to slide systems in and out of racks, and the need for cable management, by making the system fully front and rear serviceable

  • Reducing the upfront hardware costs with a minimum capacity entry point of 338TB, while supporting seamless cluster scaling to hundreds of petabytes

  • Improving rack-scale resilience with less hardware required for customers that choose to enable full-enclosure failover in Universal Storage clusters

  • Allowing customers to mix and match Ceres with previous generations of VAST-supported hardware to enable the infinite cluster lifecycle

In addition to storage-side DPUs, the company is collaborating with Nvidia on new storage services to enable zero-trust security and offload functionality with client-side DPUs, such as those introduced in the recently announced Nvidia DGX SuperPOD configurations. This platform design will initially be manufactured by the firm’s design partners such as AIC, Inc. (for commercial applications) and Mercury Systems (for rugged/defense applications) and will serve as the data capacity building blocks of the Universal Storage clusters.

Vast Nvidia Ceres DGX Racks

Nvidia DGX SuperPOD architecture featuring Universal Storage
The company is in the process of certifying Ceres for Nvidia DGX SuperPOD. This later is engineered for large-scale AI workloads, bringing together performance storage and networking to provide customers with a turnkey AI data center solution for enterprises.

With Ceres, Nvidia customers can enjoy the simplicity of a NAS solution with virtually limitless levels of scale and performance via a system architecture that improves storage resiliency, proven by the firm’s 99.9999% availability track record across exabytes of production data. With all-flash performance and archive storage economics, the company will make it easy for DGX SuperPOD customers to scale their AI training infrastructure to support exabytes of data, without the burden of performance and capacity tradeoffs imposed by legacy tiered storage architectures.

The Universal Storage certification for Nvidia DGX SuperPOD is slated for availability in 3Q22.

Ceres server room mix

Early Ceres adoption
Ceres has already been chosen by organizations with some of the world’s largest computing environments. To date, the firm has received software orders to support over 170Ps of data capacity to be deployed on Ceres platforms.

“A year ago, we shared our vision for hyperscale data infrastructure to the industry, and we’ve been amazed by the collaboration and support for this vision that has come back from industry partners. While explosive data growth continues to overwhelm organizations that are increasingly challenged to find value in vast reserves of data, Ceres enables customers to realize a future of at-scale AI and analytics on all of their data as they build to Nvidia DGX SuperPOD scale and beyond,” said Jeff Denworth, co-founder and CMO, VAST Data.

“Enterprises around the world are using AI to transform their data into insights and services that boost customer satisfaction, increase operational efficiency and bring new products to market,” said Charlie Boyle, VP and GM, DGX systems, Nvidia Corp. “Nvidia DGX SuperPOD and Nvidia BlueField DPUs, paired with the VAST Ceres platform, offer customers the option to integrate the world’s leading AI infrastructure with high-performance NAS storage certified to meet the demands of advanced AI workloads.”

Resources
Blog: Building The Storage Ecosystem For Hyperscale
Blog: When Simplicity Pairs With Scale: VAST-Powered NVIDIA DGX SuperPOD to Unite NAS With Advanced AI