Form Factor Fun with Dell EMC vSAN Ready Nodes
Mon, 20 Dec 2021 13:00:54 -0000|
Read Time: 0 minutes
Form Factor Fun with Dell EMC vSAN Ready Nodes
When thinking of a VMware vSAN-based integrated solution, it is clear that the virtualization layer is a key technology piece. That virtualization layer abstracts the classical hardware domains, compute, storage, and network, to present users with a consolidated view of their data center hardware resources through the vSphere abstractions.
Even still, the underlying hardware plays a main role. It is responsible for the specific characteristics of its processors, memory, IO devices, and storage, and also for the available form factors in which that set of hardware resources can be installed and deployed.
Having a rack mount, tower, modular, and ruggedized servers to deploy a vSAN Ready Node environment offers robust choices to adapt infrastructure to customer business needs.
VMware with vSAN can host almost any existing workload today. This ability gets a boost when the underlying platform is also capable of showing different forms, sizes, and infrastructure offerings, such as those in the Dell EMC PowerEdge portfolio.
Some of the most common data center choices are the types of servers that can be installed within a rack: rackmount and blade servers. These server types achieve optimal space and power utilization when compute density is a desired goal—a key design criteria for many facilities.
The range of rack mount and composable infrastructure available in the Dell EMC vSAN Ready Node family is extensive, at 14 different server types. This wide range of options allows customer to find the perfect resource fit for their specific workload demands. It’s likely that the compute, storage, and network mix they are looking for can be found in the exact requested proportions among the 14 server platforms.
This range of options also enables an important price flexibility, as customers can choose the most affordable options to suit their needs.
Even platform homogeneity represents an operational savings opportunity. Many companies have gone through infrastructure standardization campaigns to explore the benefits of sizing, designing, operating, servicing, and lifecycle managing the most homogeneous server platform possible. The broader the server offering is, the greater the chance that the bare metal deployments need alignment with the VMware-based infrastructure.
The rack mount format offers servers ranging from 1 to 2U, and from one to four sockets. Rack servers can include up to 112 Intel Xeon Scalable processors, 6 TB of RAM, and 24 direct-attach NVMe drives, and in the PowerEdge R840 in just 2Us.
The full rack mount and composable portfolio looks like this:
With 5G and edge becoming mainstream, they have enabled new business opportunities from next-generation applications and services. There is an increasing need for businesses to have IT resources as close as possible to the data creation place.
But the edge is a place with some inherent constraints in space, power, and cooling, coupled with limited bandwidth and limited IT staff. There are two great choices for this challenging space among the Dell EMC vSAN Ready Node portfolio:
- Dell EMC XR2 vSAN Ready Node: Built for rugged environments, this option is able to operate in temperatures up to 45⁰C and avoid thermal damage up to 55⁰C with high shock, vibration, dust, humidity, and electromagnetic interference (EMI). With a minimal footprint of 1U and short depth, this option is ideal for space-constrained installations.
- Dell EMC T340 and T350 vSAN Ready Nodes: With the T350 vSAN Ready Node coming soon, these reliable platforms in a tower form factor represent a great choice for edge locations because they allow customers to build a scalable IT platform by starting small, with an affordable investment. To address the demands and typical constraints of edge locations, including space constraints, communications constraints, and minimal staff at edge locations, the T340 and T350 provide a cyber-resilient architecture that includes reduced server size, thermal efficiency technologies, and advanced security features.
Finally, the PowerEdge MX kinetic infrastructure is a rack-based modular chassis uniquely designed to support new processor technologies, storage types, and fabric advances. These capabilities provide the foundation for software-defined environments.
PowerEdge MX7000 hosts elastic compute and storage resources connected by a Smart I/O fabric in a flexible 7U modular enclosure, able to hold two and four sockets in its compute sleds.
The Dell EMC MX750c vSAN Ready Node is one of the latest additions to the MX ecosystem, supporting up to two 3rd Generation Intel Xeon Scalable Processors (Ice Lake), 32x DIMMs, and PCIe Gen4, which enables faster NVMe drives and NICs.
The MX750c adds a flexible building block to the Dell EMC vSAN Ready Node family that helps to reduce deployment risks with certified configurations and to improve storage efficiencies that can help when building the vSAN clusters.
Dell EMC MX750c vSAN Ready Nodes offer the platform flexibility that allows customers to add resources as business peaks demand.
In conclusion, having a wide range of available form factors is a crucial aspect for any infrastructure offering, allowing customers to choose the best platform for each business case.
Dell EMC vSAN Ready Nodes delivers some of the best of breed rack mount, blade, and tower server options to deploy a vSAN cluster. For more information, see the vSAN Ready Nodes InfoHub site.
Author: Iñigo Olcoz, Senior Principal Engineering Technologist at Dell Technologies
Related Blog Posts
The Dell EMC vSAN Ready Nodes Differentiator
Thu, 14 Oct 2021 20:45:18 -0000|
Read Time: 0 minutes
It’s been over a decade since hyper converged infrastructure (HCI) disrupted technology. An ideal architecture for HCI would be a simple, modular architecture, in which all datacenter components (compute, storage, and networking) are consumed in a virtualized way to simplify allocating and managing resources. With this architecture, all physical components reside in the same box. When we combine these boxes, we can scale our datacenter power in all resource domains to accommodate almost any type of workload. This is due to extremely fast processors, large and efficient storage devices, and advanced network connections.
If we abstract the hardware layer in this architecture and imagine a solution that fills all the roles previously described, (virtualization of the three infrastructure domains, compute, network and storage) VMware can easily come to mind. VMware has a strong portfolio of software defined compute (vSphere), storage (vSAN), and networking (NSX family) to create a best of breed hyper-converged infrastructure product.
It will come as no surprise that VMware leads the HCI market due to its vSAN based systems, as reported by IDC1:
In this VMware led market, Dell PowerEdge servers stand out as a logical choice in terms of providing the modular box (server), for this hyperconvergence paradigm. Dell Technologies, as a global server market leader (Worldwide Server Market, IDC), has a long tradition of Ready Systems that allow a simpler customer deployment experience.
Dell EMC vSAN Ready Nodes (vSAN Ready Nodes) are a great example of an HCI implementation, providing a robust and mature datacenter platform — pre-configured, tested, and certified to run VMware vSAN.
This HCI market is especially relevant as its current growth rate far surpasses that of the server market. According to Gartner2 while the server market is growing at 5.6%, the HCI market is increasing by 23 percent (IDC3). That represents a growth rate more than four times that of the server market:
Server market growth:
HCI market growth:
In this prosperous landscape, Dell Technologies holds an outstanding leading place, with a wide portfolio of HCI offerings, led by Dell EMC VxRail in tandem with vSAN Ready Nodes. More than 20 years of collaboration endorses the relationship between Dell Technologies and VMware, specifically in the server space, where we have worked to simplify our joint customers’ technology experience.4
Dell EMC Ready Nodes simplify and accelerate infrastructure modernization providing IT a strategic advantage with their flexibility, simplified operations, and breadth of choice.
This leadership is founded on four pillars:
- Form factors: Dell Technologies offers an unmatched portfolio of vSAN Ready Nodes options, ranging from 1 to 2U rackmount servers, tower models, and MX series blade options. There are more than 250 different configurations available for Dell EMC vSAN Ready Nodes. As part of this rich offering, Dell provides unique solutions that scale up to four processors per node.
- Identity Module: This module declares the system a vSAN Ready Node, distinguishing it from a standard off-the-shelf server. All vSAN Ready Node capabilities derive from this Identity Module, facilitating the Day 0 operations provided by vLCM in unison with OMIVV.
- OMIVV (OME): The Dell EMC Open Manage Integration for VMware vCenter (OMIVV) is designed to streamline the management processes in your data center environment by allowing you to use VMware vCenter Server to manage your full server infrastructure, both physical and virtual.
- vSphere Lifecycle Management (vLCM): Consistency across ESXi hosts is essential for creating reliable and high performing platforms, but it is difficult to obtain, especially at scale. vLCM solves the complexity by enforcing consistency across ESXi hosts in a cluster using a declarative model. vLCM not only accomplishes this by using an ESXi base image but extends it with the desired state for firmware and driver versions as well.
Watch for my next blog where I’ll provide more info about the rich variety of vSAN Ready Nodes form factors available from Dell Technologies and how that represents a significant business advantage. For the latest technical content on vSAN Ready Nodes, check out our Info Hub site!
Inigo Olcoz, Technical Marketing Engineer at Dell Technologies
- IDC’s Q32020 Worldwide Quarterly Converged Systems Tracker, December 15th, 2020
- Worldwide End-User Spending on IT by Technology Segment and Subsegment, 2019-2025 (Millions of U.S Dollars).
- IDC Converged Systems Tracker Forecast, Q4020, March 2021
- IDC Quarterly Converged Systems tracker, 2021-Q1.
MLPerf™ Inference v2.0 Edge Workloads Powered by Dell PowerEdge Servers
Fri, 06 May 2022 19:23:11 -0000|
Read Time: 0 minutes
Dell Technologies recently submitted results to the MLPerf Inference v2.0 benchmark suite. This blog examines the results of two specialty edge servers: the Dell PowerEdge XE2420 server with the NVIDIA T4 Tensor Core GPU and the Dell PowerEdge XR12 server with the NVIDIA A2 Tensor Core GPU.
It is 6:00 am on a Saturday morning. You drag yourself out of bed, splash water on your face, brush your hair, and head to your dimly lit kitchen for a bite to eat before your morning run. Today, you have decided to explore a new part of the neighborhood because your dog’s nose needs new bushes to sniff. As you wait for your bagel to toast, you ask your voice assistant “what’s the weather like?” Within a couple of seconds, you know that you need to grab an extra layer because there is a slight chance of rain. Edge computing has saved your morning run.
Although this use case is covered in the MLPerf Mobile benchmarks, the data discussed in this blog is from the MLPerf Inference benchmark that has been run on Dell servers.
Edge computing is computing that takes place at the “edge of networks.” Edge of networks refers to where devices such as phones, tablets, laptops, smart speakers, and even industrial robots can access the rest of the network. In this case, smart speakers can perform speech-to-text recognition to offload processing that ordinarily must be accomplished in the cloud. This offloading not only improves response time but also decreases the amount of sensitive data that is sent and stored in the cloud. The scope for edge computing expands far beyond voice assistants with use cases including autonomous vehicles, 5G mobile computing, smart cities, security, and more.
The Dell PowerEdge XE2420 and PowerEdge XR 12 servers are designed for edge computing workloads. The design criteria is based on real life scenarios such as extreme heat, dust, and vibration from factory floors, for example. However, despite these servers not being physically located in a data center, server reliability and performance are not compromised.
PowerEdge XE2420 server
The PowerEdge XE2420 server is a specialty edge server that delivers high performance in harsh environments. This server is designed for demanding edge applications such as streaming analytics, manufacturing logistics, 5G cell processing, and other AI applications. It is a short-depth, dense, dual-socket, 2U server that can handle great environmental stress on its electrical and physical components. Also, this server is ideal for low-latency and large-storage edge applications because it supports 16x DDR4 RDIMM/LR-DIMM (12 DIMMs are balanced) up to 2993 MT/s. Importantly, this server can support the following GPU/Flash PCI card configurations:
- Up to 2 x PCIe x16, up to 300 W passive FHFL cards (for example, NVIDIA V100/s or NVIDIA RTX6000)
- Up to 4 x PCIe x8; 75 W passive (for example, NVIDIA T4 GPU)
- Up to 2 x FE1 storage expansion cards (up to 20 x M.2 drives on each)
The following figures show the PowerEdge XE2420 server (source):
Figure 1: Front view of the PowerEdge XE2420 server
Figure 2: Rear view of the PowerEdge XE2420 server
PowerEdge XR12 server
The PowerEdge XR12 server is part of a line of rugged servers that deliver high performance and reliability in extreme conditions. This server is a marine-compliant, single-socket 2U server that offers boosted services for the edge. It includes one CPU that has up to 36 x86 cores, support for accelerators, DDR4, PCIe 4.0, persistent memory and up to six drives. Also, the PowerEdge XR12 server offers 3rd Generation Intel Xeon Scalable Processors.
The following figures show the PowerEdge XR12 server (source):
Figure 3: Front view of the PowerEdge XR12 server
Figure 4: Rear view of the PowerEdge XR12 server
The following figure shows the comparison of the ResNet 50 Offline performance of various server and GPU configurations, including:
- PowerEdge XE8545 server with the 80 GB A100 Multi-Instance GPU (MIG) with seven instances of the one compute instance of the 10gb memory profile
- PowerEdge XR12 server with the A2 GPU
- PowerEdge XE2420 server with the T4 and A30 GPU
Figure 5: MLPerf Inference ResNet 50 Offline performance
ResNet 50 falls under the computer vision category of applications because it includes image classification, object detection, and object classification detection workloads.
The MIG numbers are per card and have been divided by 28 because of the four physical GPU cards in the systems multiplied by second instances of the MIG profile. The non-MIG numbers are also per card.
For the ResNet 50 benchmark, the PowerEdge XE2420 server with the T4 GPU showed more than double the performance of the PowerEdge XR12 server with the A2 GPU. The PowerEdge XE8545 server with the A100 MIG showed competitive performance when compared to the PowerEdge XE2420 server with the T4 GPU. The performance delta of 12.8 percent favors the PowerEdge XE2420 system. However, the PowerEdge XE2420 server with A30 GPU card takes the top spot in this comparison as it shows almost triple the performance over the PowerEdge XE2420 server with the T4 GPU.
The following figure shows a comparison of the SSD-ResNet 34 Offline performance of the PowerEdge XE8545 server with the A100 MIG and the PowerEdge XE2420 server with the A30 GPU.
Figure 6: MLPerf Inference SSD-ResNet 34 Offline performance
The SSD-ResNet 34 model falls under the computer vision category because it performs object detection. The PowerEdge XE2420 server with the A30 GPU card performed more than three times better than the PowerEdge XE8545 server with the A100 MIG.
The following figure shows a comparison of the Recurrent Neural Network Transducers (RNNT) Offline performance of the PowerEdge XR12 server with the A2 GPU and the PowerEdge XE2420 server with the T4 GPU:
Figure 7: MLPerf Inference RNNT Offline performance
The RNNT model falls under the speech recognition category, which can be used for applications such as automatic closed captioning in YouTube videos and voice commands on smartphones. However, for speech recognition workloads, the PowerEdge XE2420 server with the T4 GPU and the PowerEdge XR12 server with the A2 GPU are closer in terms of performance. There is only a 32 percent performance delta.
The following figure shows a comparison of the BERT Offline performance of default and high accuracy runs of the PowerEdge XR12 server with the A2 GPU and the PowerEdge XE2420 server with the A30 GPU:
Figure 8: MLPerf Inference BERT Offline performance
BERT is a state-of-the-art, language-representational model for Natural Language Processing applications such as sentiment analysis. Although the PowerEdge XE2420 server with the A30 GPU shows significant performance gains, the PowerEdge XR12 server with the A2 GPU exceeds when considering achieved performance based on the money spent.
The following figure shows a comparison of the Deep Learning Recommendation Model (DLRM) Offline performance for the PowerEdge XE2420 server with the T4 GPU and the PowerEdge XR12 server with the A2 GPU:
Figure 9: MLPerf Inference DLRM Offline performance
DLRM uses collaborative filtering and predicative analysis-based approaches to make recommendations, based on the dataset provided. Recommender systems are extremely important in search, online shopping, and online social networks. The performance of the PowerEdge XE2420 T4 in the offline mode was 40 percent better than the PowerEdge XR12 server with the A2 GPU.
Despite the higher performance from the PowerEdge XE2420 server with the T4 GPU, the PowerEdge XR12 server with the A2 GPU is an excellent option for edge-related workloads. The A2 GPU is designed for high performance at the edge and consumes less power than the T4 GPU for similar workloads. Also, the A2 GPU is the more cost-effective option.
It is important to budget power consumption for the critical load in a data center. The critical load includes components such as servers, routers, storage devices, and security devices. For the MLPerf Inference v2.0 submission, Dell Technologies submitted power numbers for the PowerEdge XR12 server with the A2 GPU. Figures 8 through 11 showcase the performance and power results achieved on the PowerEdge XR12 system. The blue bars are the performance results, and the green bars are the system power results. For all power submissions with the A2 GPU, Dell Technologies took the Number One claim for performance per watt for the ResNet 50, RNNT, BERT, and DLRM benchmarks.
Figure 10: MLPerf Inference v2.0 ResNet 50 power results on the Dell PowerEdge XR12 server
Figure 11: MLPerf Inference v2.0 RNNT power results on the Dell PowerEdge XR12 server
Figure 12: MLPerf Inference v2.0 BERT power results on the Dell PowerEdge XR12 server
Figure 13: MLPerf Inference v2.0 DLRM power results on the Dell PowerEdge XR12 server
Note: During our submission to MLPerf Inference v2.0 including power numbers, the PowerEdge XR12 server was not tuned for optimal performance per watt score. These results reflect the performance-optimized power consumption numbers of the server.
This blog takes a closer look at Dell Technologies’ MLPerf Inference v2.0 edge-related submissions. Readers can compare performance results between the Dell PowerEdge XE2420 server with the T4 GPU and the Dell PowerEdge XR12 server with the A2 GPU with other systems with different accelerators. This comparison helps readers make informed decisions about ML workloads on the edge. Performance, power consumption, and cost are the important factors to consider when planning any ML workload. Both the PowerEdge XR12 and XE2420 servers are excellent choices for Deep Learning workloads on the edge.
The following table describes the System Under Test (SUT) configurations from MLPerf Inference v2.0 submissions:
Table 1: MLPerf Inference v2.0 system configuration of the PowerEdge XE2420 and XR12 servers
PowerEdge XE2420 1x T4, TensorRT
PowerEdge XR12 1x A2, TensorRT
PowerEdge XR12 1x A2, MaxQ, TensorRT
PowerEdge XE2420 2x A30, TensorRT
MLPerf system ID
Intel Xeon Gold 6238 CPU @ 2.10 GHz
Intel Xeon Gold 6312U CPU @ 2.40 GHz
Intel Xeon Gold 6252N CPU @ 2.30 GHz
GPU form factor
Table 2: MLPerf Inference v1.1 system configuration of the PowerEdge XE8545 server
PowerEdge XE8545 4x A100-SXM-80GB-7x1g.10gb, TensorRT, Triton
MLPerf system ID
AMD EPYC 7763
NVIDIA A100-SXM-80GB (7x1g.10gb MIG)
GPU form factor