Introduction

Small offices and remote branch office (ROBO) use cases present special challenges for IT organizations. The issues tend to revolve around how to implement a scalable, resilient, secure, and highly performant platform at an affordable TCO. The infrastructure must be capable enough to efficiently run a highly diversified portfolio of applications and services and yet be simple to deploy, update, and support by a local IT generalist. Dell Technologies and Microsoft help you accelerate business outcomes in these unique ROBO environments with our Dell EMC Solutions for Microsoft Azure Stack HCI.

In this blog post, we share VMFleet results observed in the Dell Technologies labs for our newest AX-6515 two-node configuration – ideal for ROBO environments. Optimized for value, the small but powerful AX-6515 node packs a dense, single-socket 2^nd Gen AMD EPYC processor in a 1RU chassis delivering peak performance and excellent TCO. We also included the Dell EMC PowerSwitch S5212F-ON in our testing to provide 25GbE network connectivity for the storage, management, and VM traffic in a small form factor. The Dell EMC Solutions for Azure Stack HCI Deployment Guide was followed to construct the test lab and applies only to infrastructure that is built with validated and certified AX nodes running Microsoft Windows Server 2019 Datacenter from Dell Technologies.

We were quite impressed with the VMFleet results. First, we stressed the cluster’s storage subsystem to its limits using scenarios aimed at identifying maximum IOPS, latency, and throughput. Then, we adjusted the test parameters to be more representative of real-world workloads. The following summary of findings indicated to us that this two-node, AMD-based, all-flash cluster could meet or exceed the performance requirements of workload profiles often found in ROBO environments:

• Achieved over 1 million IOPS at microsecond latency using a 4k block size and 100% random-read IO pattern.
• Achieved over 400,000 IOPS at 4 millisecond latency using a 4k block size and 100% random-write IO pattern.
• Using 512k block sizes, drove 6 GB/s and 12 GB/s throughput for 100% sequential-write and 100% sequential-read IO patterns, respectively.
• Using a range of real-world scenarios, the cluster achieved hundreds of thousands of IOPS at under 7 milliseconds latency and drove between 5 – 12 GB/s of sustained throughput.

Lab Setup

The following diagram illustrates the environment created in the Dell Technologies labs for the VMFleet testing. Ancillary services required for cluster operations such as DNS, Active Directory, and a file server for cluster quorum are not depicted.

Figure 1 Network topology

Table 1 Cluster configuration

Table 2 Cluster node resources

The architectures of Azure Stack HCI solutions are highly opinionated and prescriptive. Each design is extensively tested and validated by Dell Technologies Engineering. Here is a summary of the key quality attributes that define these architectures followed by a section devoted to our performance findings.

• Efficiency – Many customers are interested in improving performance and gaining efficiencies by modernizing their aging virtualization platforms with HCI. Using Azure Stack HCI helps avoid a DIY approach to IT infrastructure, which is prone to human error and is more labor intensive.
• Maintainability – Our solution makes it simple to incorporate hybrid capabilities to reduce operational burden using Microsoft Windows Admin Center (WAC). Services in Azure can also be leveraged to avoid additional on-premises investments for management, monitoring, BCDR, security, and more. We have also developed the Dell EMC OpenManage Integration with Microsoft Windows Admin Center to assist with hardware monitoring and to simplify updates with Cluster Aware Updates (CAU).
• Availability – Using a two-way mirror, we always have two copies of our data.  This configuration can survive a single drive failure in one node or survive an entire node failure. However, the cluster cannot survive two failures simultaneously on both nodes. In case greater resiliency is desired, volumes can be created using nested resiliency. Nested resiliency is discussed in more detail in the "Optional modifications to the architecture" section later in this blog post.
• Supportability – Support is provided by dedicated Dell Technologies ProSupport Plus and ProSupport for Software technicians who have expertise specifically tailored to Azure Stack HCI solutions.

Testing Results

We leveraged VMFleet to benchmark the storage subsystem of our 2-node cluster. Many Microsoft customers and partners rely on this tool to help them stress test their Azure Stack HCI clusters. VMFleet consists of a set of PowerShell scripts that deploy virtual machines to a Hyper-V cluster and execute Microsoft’s DiskSpd within those VMs to generate IO. The following table presents the range of VMFleet and DiskSpd parameters used during our testing in the Dell Technologies labs.

Table 3 Test parameters

We first selected DiskSpd scenarios aimed at identifying the maximum IOPS, latency, and throughput thresholds of the cluster. By pushing the limits of the storage subsystem, we confirmed that the networking, compute, operating systems, and virtualization layer were configured correctly according to our Deployment Guide and Network Integration and Host Network Configuration Options guide. This also ensured that that no misconfiguration occurred during initial deployment that could skew the real-world storage performance results. Our results are depicted in Table 4.

Table 4 Maximums test results

We then stressed the storage subsystem using IO patterns more reflective of the types of workloads found in a ROBO use case. These applications are typically characterized by smaller block sizes, random I/O patterns, and a variety of read/write ratios. Examples include general enterprise and small office LOB applications and OLTP workloads. The testing results in Figure 2 below indicate that the cluster has the potential to accelerate OLTP workloads and make enterprise applications highly responsive to end users.

Figure 2 Performance results with smaller block sizes

Other services like backups, streaming video, and large dataset scans have larger block sizes and sequential IO patterns. With these workloads, throughput becomes the key performance indicator to analyze. The results shown in the following graph indicate an impressive sustained throughput that can greatly benefit this category of IT services and applications.

Figure 3 Performance results with larger block sizes

Optional modifications to the architecture

Customers could make modifications to the lab configuration to accommodate different requirements in the ROBO use case. For example, Dell Technologies completely supports a dual-link full mesh topology for Azure Stack HCI. This non-converged storage switchless topology eliminates the need for network switches for storage communications and enables you to use existing infrastructure for management and VM traffic. This approach will result in similar or improved performance metrics versus those mentioned in this blog due to the 2 x 25 GB direct connections between the nodes and the isolation of the storage traffic on these dedicated connections.  

Figure 4 Two-node back-to-back architecture option

There may be situations in ROBO scenarios where there are no IT generalists near the site to address hardware failures. When a drive or entire node fails, it may take days or weeks before someone can service the nodes and return the cluster to full functionality. Consider nested resiliency instead of two-way mirroring to handle multiple failures on a two-node cluster. Inspired by RAID 5 + 1 technology, workloads remain online and accessible even in the following circumstances:

Figure 5 Nested resiliency option

Be aware that there is a capacity efficiency cost when using nested resiliency. Two-way mirroring is 50% efficient, meaning 1 TB of data takes up 2 TB of physical storage capacity. Depending on the type of nested resiliency you choose to configure, capacity efficiency can range between 25% - 40%. Therefore, ensure you have an adequate amount of raw storage capacity if you intend to use this technology. Performance is also going to be affected when using nested resiliency – especially on workloads with a higher percentage of write IO since more copies of the data need to be maintained on the cluster.

If you need greater flexibility in cluster resources, Dell Technologies offers Azure Stack HCI configurations to meet any workload profile and business requirement. The table below shows the different resource options available for each AX node. To find more detailed specifications about these configurations, please review the detailed product specifications on our product page.

Table 5 Azure Stack HCI configuration options

Visit our website for more details on Dell EMC Solutions for Azure Stack HCI.

Just the facts:

• A Dell EMC Storage Spaces Direct four-node cluster was tested with VM Fleet in a 100 random-read workload and achieved 2,953,095 IOPS with an average read latency of 242 microseconds.
• A Dell EMC Storage Spaces Direct four-node cluster was tested with VM Fleet in a 100 percent random-write workload and achieved 818,982 IOPS at an average write latency of 4 milliseconds.
• A Dell EMC Storage Space Direct four-node cluster was tested with VM Fleet in a 100 percent sequential-read workload and achieved 63 GB/s and with a 100 percent sequential-write workload 9 GB/s

The details:

User experience is everything. In today’s world, fast and intuitive applications are a necessity, and anything less might be labeled slow and not very useful. Once an application is labeled slow, it’s hard to change that impression with end users. Thus, architecting a system for performance is a key consideration in ensuring a good application experience.

In this blog, we explore a Dell EMC Storage Spaces Direct solution that delivered amazing performance in our internal tests. Storage Spaces Direct is part of Azure Stack HCI and enables customers to use industry-standard servers with locally attached drives to create high-performance and high-availability storage. Azure Stack HCI enables the IT organization to run virtual machines with cloud services on-premises. Benefits include:

• The capability to consolidate data center applications with software-defined compute, storage, and networking.
• Using virtual machines to drive greater operational efficiencies while accelerating performance with Storage Spaces Direct. Support for Non-Volatile Memory Express (NVMe) drives enables software-defined storage to reach new levels of performance.
• Improved high availability with clustering and distributed software resiliency.

Database and other storage-intensive applications could benefit from the faster NVMe drives. NVMe is an open logical device specification that has been designed for low latency and internal parallelism of solid-state storage devices. The result is a significant boost in storage performance because data can be accessed faster and with less I/O overhead.

In our labs, we created a Storage Spaces Direct performance cluster consisting of four Dell EMC PowerEdge R640 nodes. Each storage node had two Intel 6248 Cascade Lake processors, ten P4510 Intel NVMe drives, and one Mellanox CX5 dual-port 100 GbE adapter. Networking between the nodes consisted of a Dell EMC S5232 switch that supports up to thirty-two 100 GbE ports. Our goal was to drive simplicity in the configuration while showing performance value.

We used Storage Spaces Direct three-way mirroring because this configuration offers the greatest performance and protection. Protection does have a cost in terms of capacity. The capacity efficiency of a three-way mirror is 33 percent, meaning 3 TB equates to 1 TB of usable storage space. The data protection benefit with three-way mirroring is that the storage cluster can safely tolerate at least two hardware problems—for example, the loss of a drive and server at the same time. The following diagram is a simple representation of the four-node performance configuration of the Storage Spaces Direct cluster.

Figure 1: Storage Spaces Direct Cluster with four PowerEdge R640 nodes

We ran VM Fleet on the storage cluster to test performance, and the results were impressive! Here is the first test configuration:

• Block size: 4 KB
• Thread count: 2
• Outstanding I/O counts: 32
• Write ratio: 0
• Pattern: Random

Thus, this VM Fleet test used 4 KB block sizes, 100 percent reads, and a random-access pattern. This Storage Spaces Direct configuration achieved 2,953,095 IOPS with an average read latency of 242 microseconds. A microsecond is equal to one-millionth of a second. This is the kind of performance that can really accelerate online transaction processing (OLTP) workloads and make enterprise applications highly responsive to the end users.

We also tested a 100 percent random-write workload on the storage cluster. All the VM Fleet configuration settings remained the same, except the write ratio was 100. With 100 percent writes, the storage cluster achieved 818,982 IOPS at an average write latency of 4 milliseconds. We could have been less aggressive in our internal tests and delivered even lower write latency, but the goal was to push the storage cluster in terms of performance. Both these tests were done internally in our Dell EMC labs, and it’s important to note that results will vary.

Figure 2: Summary of internal test findings for 100 percent read and write workloads for IOPS and latency

Some applications, such as business intelligence and decision support systems, and some analytical workloads are more dependent on throughput. Throughput is defined by the amount of data that is delivered over a fixed period. The greater the throughput the more data that can be read and the faster the analysis or report. Our labs used the following VM Fleet configuration to test throughput:

• Block size: 512 KB
• Thread count: 2
• Outstanding I/O counts: 2
• Write ratio: 0
• Pattern: Sequential

The throughput test configuration uses larger blocks at 512 KB, 100 percent reads, and a sequential read pattern that is like scanning large datasets. The storage cluster sustained 63 gigabytes per second (GB/s). This throughput could enable faster analytics for the business and provide the capability to make timely decisions.

We also ran the same test with 100 percent writes, which simulates a data load activity such as streaming data from an IoT gateway to an internal database. In this test case, the storage cluster sustained a throughput of 9 GB/s for writes. Both the read and write throughput tests show the strength of this all-NVMe configuration from Dell EMC.

Figure 3: Summary of internal test findings for 100 percent read and write workloads for throughput

If performance is what you need, then Dell EMC can use NVMe technology to accelerate your applications. But flexibility is another factor that can be equally important. Not every application requires high IOPS and very low latencies. Dell EMC offers an expanded portfolio of Storage Spaces Direct nodes that can meet most any business requirements. A great resource for reviewing the Dell EMC Storage Spaces Direct options is the Azure Stack HCI certification pages. The following table summarizes all the Dell EMC options but doesn’t contain CPU, RAM, and other details that can be found on the certification pages.

Start with a minimal configuration using the R440 Ready Nodes, which can have up to 44 cores, 1 TB of RAM, and 19.2 TB of storage. Or go big with the R740xd2 hybrid with up to 44 cores, 384 GB of RAM, and 240 TB of storage capacity. The range of options provides you with the flexibility to configure a Storage Spaces Direct solution to meet your business needs.

The Dell EMC Ready Nodes have been configured to work with Windows 2019, so they are future-ready. For example, the Ready Nodes integrate with Windows Admin Center, so you can tier storage, implement resiliency, provision VMs and storage, configure networking, and monitor health and performance, all with just a few clicks. With your Windows Server 2019 Datacenter licenses, no separate hypervisor license is needed for VMs. You can create unlimited VMs, achieve high-availability clusters, and secure your tenants or applications with shielded VMs.

Dell EMC Storage Spaces Direct nodes have been designed to make storage in your Azure Stack HCI easy. If you are interested in learning more, see Dell EMC Cloud for Microsoft Azure Stack HCI and contact a Dell EMC expert.