Data Center Strategy: All-Flash NVMe Architecture Solutions

Posted on June 6, 2021 by rawee.k

The challenge to meet the performance demands of on-prem data center applications and services – including high-performance computing (HPC), cloud computing, SQL/NoSQL databases, virtualization (VMs/containers), AI/ML and data analytics – has forced organizations to explore an all-flash NVMe solution. Generally, IT departments migrate to NVMe from traditional SATA or SAS storage in the data center, to focus on cloud and mission-critical applications that require high-performance, low latency. Unfortunately, while cloud hyperscalers have heavily-adopted NVMe but traditional IT departments are still largely using SSDs with SATA and SAS interfaces.

Is now the time for to replace legacy storage with NVMe SSDs and NVMe over Fabrics (NVMe-oF) technologies? First, let’s examine how you can achieve improved performance and efficiency by sharing your NVMe investment across servers.

Researching flash-based solutions to achieve new levels of performance and efficiency? Here’s what data center administrators need to know to evaluate NVMe flash storage solutions. Questions? Drop us an email at

NVMe Solution Architecture

To enable a performance-built, end-to-end NVMe solution, there’s three components to consider: SSDs, controller, and network fabric.

NVMe Solid Stage Drives (SSDs) – Flash-based NVMe SSDs, such as those from Western Digital, are designed to allow consistent response time with low latencies, and storage capacities ranging from 1.6TB to 15.36TB. Additionally, they utilize dual-ports, so users have redundant ports to all resources, ideal for highly-available architectures.

NVMe Controller – Designed to take full advantage of flash storage performance, NVMe assumes flash memory – not spinning disk – is the storage target. Developed in early 2008 as a much more efficient (and faster) protocol, NVMe provides a divided 12-lane I/O highway versus the two-lane country road of SAS and SATA.

With more I/O lanes and native PCIe interconnect to communicate directly with CPUs and DRAM, NVMe SSDs deliver higher-performance and more throughput without the bottlenecks of SAS or SATA controllers. From Western Digital’s vertically-integrated NVMe RapidFlex controller, firmware and 96-layer 3D TLC NAND technology, NVMe SSD users experience sub-500 nanosecond latency for projected platform performance of up to 13 million IOPS when used in six-controller configurations.


Traditional NVMe Use-Case – The data center adoption of NVMe by users is often to directly connect an NVMe SSD within a rackmount server. For example, within a hyperconverged (HCI) system, any NVMe SSDs would be silo’d within a single HCI enclosure. However, this creates a situation where NVMe is underutilized, as the flash device is not accessible by other systems beyond the server to which it is attached.

The option to connect a high-density all-NVMe network expansion device would give your Business a more efficient way to use flash storage. But is that possible?

Introducing NVMe over Fabrics – Previously, the challenge with using NVMe is that other servers cannot benefit from flash storage. However, the NVMe protocol is not limited to connecting flash drives: it may also be used as a networking protocol. When used in this context, NVMe-oF enables any-to-any connections. This is to distinguish it from a network, which may restrict the possible connections possible.

With an NVMe “fabric”, any server can access any NVMe SSD without dedicated connections. Now, data center users can easily deploy highly-dense, high-performance NVMe SSDs over their network with latencies that obliterate DAS with legacy SATA or SAS interfaces. Simply connect the fabric-based JBOF (Just a Bunch of Flash) expansion enclosure to the network switch, to make it accessible by any server.

Next, how do you get all the performance potential out of an all-flash NVMe architecture solution with NVMe over Fabrics?

Choosing an all-flash NVMe Architecture Solution

Low latency or high transfer rates are of little benefit if they swamp the target application. While these systems generate IOPS approaching the millions, the reality is that there are very few workloads that require more than the performance of these systems. However, there is an emerging class of workloads that can take advantage of all the performance and low latency of an end-to-end NVMe system.

If you’d like to learn more about how to maximize your data center infrastructure by up to 90% while minimizing its footprint, give us a call at (888) 828-7646, email us at or book a time calendar to speak. We’ve helped organizations of all sizes deploy composable solutions for just about every IT budget.