The VxRail system is assembled with proven server-node hardware that has been integrated, tested, and validated as a complete solution by Dell EMC. All the nodes in the current generation of VxRail use Intel Xeon Scalable family processors. The Intel Xeon Scalable family processors feature a multi-threaded, multi-core CPU designed to handle diverse workloads for cloud services, high-performance computing, and networking. The number of cores and memory capacity differ for each VxRail model.

Each node server includes the following technology:

• Single, dual, or quad Intel® Xeon® Scalable Gen 1 and Gen 2 processors, each with up to 28 cores per processor. Or a single 2nd Generation AMD EPYC™ processor with up to 64 cores
• Up to 24 DDR4 DIMMs, providing memory capacity ranging from 64 GB to 6,144 GB per node, depending on model
• A PCIe SAS disk-drive controller supporting 12 GB SAS speeds, if applicable
• A mirrored pair of BOSS SATA M.2 cards used to boot ESXi on the node 
• A 10/25GbE Network Daughter Card (auto-negotiable to 1 GbE)

Figure 17.          VxRail node rear view

Intel® Xeon® Scalable processor: Powerful processing for VxRail

Intel® Xeon® Scalable platforms are powerful infrastructure that represents an evolutionary leap forward in agility and scalability. Disruptive by design, it sets a new benchmark in platform convergence and capabilities across compute, storage, memory, network, and security. An innovative approach to platform design in Intel® Xeon® Scalable processors unlocks the power of scalable performance for today’s data centers and communications networks—from the smallest workloads to the most mission-critical applications. 

With up to 28 cores delivering highly enhanced per core performance, and significant increases in memory bandwidth (six memory channels) and I/O bandwidth (48 PCIe lanes), the most data-hungry, latency-sensitive applications such as in-memory databases and high-performance computing will see notable improvements that are enabled by denser compute and faster access to large data volumes. And the latest generation processors that are designated with an ‘M” can support denser memory, with up to 1536 GB per processor.

The convergence of compute, memory, network, and storage performance combined with software ecosystem optimizations make Intel® Xeon® Scalable platforms ideal for fully virtualized, software-defined data centers that dynamically self-provision resources—on-premises, through the network, and in the public cloud—based on workload needs. 

2nd Generation AMD EPYC™

2nd Gen AMD EPYC™ are a new breed of server processors which have set a higher standard for data centers. AMD has brought many first to the market with this processor generation:

• First with 7 nm technology enabling higher transistor density and energy efficiency
• First with PCIe 4.0 delivering 128 lanes to double the I/O performance over PCIe 3.0
• First with 64 cores (128 threads) in a single socket

AMD EPYC™ has been engineered for data centers that rely on CPU performance. From oil and gas exploration, to in-memory databases, to big data analytics to production rendering to standard data center applications, highly parallel workloads have more cores to work with. Traditional CPUs typically must scale up to a 2-socket server to overcome an imbalance of resources. With AMD EPYC™, 1-socket servers satisfy most workload needs, helping increase density and reduce capital, power, and cooling expenses.

PowerEdge servers are optimized for the 2nd Gen AMD EYPC processors taking advantage of the additional cores, faster and additional memory channels, and of PCIe 4.0 for faster networking. 

VxRail node storage disk drives

Storage capacity for the VxRail system is provided by drives that have been integrated, tested, and validated by Dell EMC. VxRail configurations use 2.5” form-factor SSDs, 2.5” NVMe drives, and mechanical HDDs. There is a VxRail configuration that uses 3.5” form-factor drives which also available for dense-storage requirements. Disks drives are logically organized into disk groups. Disk groups are configured in two ways:

• Hybrid configurations, which contain a single SSD flash-based disk for caching (the cache tier) and multiple HDD disks for capacity (the capacity tier)
• All-flash configurations, which contain all SAS SSD or NVMe drives for both cache and SAS or SATA SSD for capacity.

The flash drives used for caching and capacity have different endurance levels. Endurance level refers to the number of times that an entire flash disk can be written every day for a five-year period before it has to be replaced. A higher-endurance SSD is used for write caching, and capacity-optimized SSDs are used for capacity. All VxRail disk configurations use a carefully designed cache-to-capacity ratio to ensure consistent performance. Capacity SSDs are offered in both higher endurance SAS and SATA. The SATA SSDs are a lower-cost option, up to 30% per drive, and great for read or moderately intensive workloads. 

All-NVMe configurations are available in the E560N and P580N which use either Intel Optane or NVMe drives for cache, and NVMe drives for capacity. The E560N is a cost-effective 1U platform that can support a variety of workloads including data warehousing, database, and analytical workloads with its support for Nvidia T4 GPUs. The P580N is the only 4-socket VxRail offering. Combined with all-NVMe storage, it is an ideal platform for memory-intensive and compute-heavy application workloads.

VxRail hardware options

VxRail nodes can be configured with choice of processor, memory, storage (cache and capacity drives), based networking, power supply, and GPU (in the E and V Series only). Customers can be assured their VxRail is configured to best match their workload requirements in a very prescriptive manner, with millions of possible configuration combinations in the VxRail Series. Combine this with the numerous ways to scale on demand, and it is clear that VxRail provides the agility demanded by today’s modern IT. Upgrade options for VxRail include, memory, GPU, NIC cards, cache SSD, and capacity drives expand workload use case possibilities.

• GPU – VxRail supports a variety of Nvidia GPUs. Depending on the GPU model, workloads such as virtual desktop infrastructure (VDI), graphics rendering, machine learning, 3D rendering, and complex visualization computing can be suitable on a VxRail cluster.
• NIC cards – As the demand for high-bandwidth network connectivity grows, VxRail is adding higher bandwidth NIC card options. Workloads that rely on GPUs such as AI-powered business operations will drive more data transfer between nodes and clusters. 
• NVMe drives – With the economics of NVMe drives becoming more favorable, NVMe cache and capacity can be a cost-effective option for high performance compute and in-memory database workloads.
• Fiber Channel HBA – Connecting to external storage arrays can be a valuable use case for re-purposing existing investments while customers transition more toward VxRail clusters as their primary platform for virtualized workloads.