Live Optics and Azure Stack HCI

The IT industry has coped with many challenges during the last decades. One of the most impactful ones, probably due to its financial implications, has been the “IT budget reduction”—the need for IT departments to increase efficiency, reduce the cost of their processes and operations, and optimize asset utilization.

This do-more-with-less mantra has a wide range of implications, from cost of acquisition to operational expenses and infrastructure payback period.

Cost of acquisition is not only related to our ability to get the best IT infrastructure price from technology vendors but also to the less obvious fact of optimal workload characterization that leads to the minimum infrastructure assets to service business demand.

Without the proper tools, assessing the specific needs that each infrastructure acquisition process requires is not simple. Obtaining precise workload requirements often involves input from several functional groups, requiring their time and dedication. This is often not possible, so the only choice is to do a high-level estimation of requirements and select a hardware offering that can cover by ample margin the performance requirements.

Those ample margins do not align very well with concepts such as optimal asset utilization and, thus, do not lead to the best choice under a budget reduction paradigm.

But there is free online software, Live Optics, that can be used to collect, visualize, and share data about your IT infrastructure and the workloads they host. Live Optics helps you understand your workloads’ performance by providing in-depth data analysis. It makes the project requirements much clearer, so the sizing decision—based on real data—is more accurate and less estimated.

Azure Stack HCI, as a hyperconverged system, greatly benefits from such sizing considerations. It is often used to host a mix of workloads with different performance profiles. Being able to characterize the CPU, memory, storage, network, or protection requirements is key when infrastructure needs to be defined. This way, the final node configuration for the Azure Stack HCI platform will be able to cope with the workload requirements without oversizing the hardware and software offerings, and we are able to select the type of Azure Stack HCI node that best fits the workload requirements.

Microsoft recommends using an official sizing tool such as Dell’s tool, and Live Optics incorporates all Azure Stack HCI design constraints and best practices, so the tool outcome is optimized to the workload requirements.

Imagine that we had to host in the Azure Stack HCI infrastructure a number of business applications with sets of users. With the performance data gathered by Live Optics, and using the Azure Stack HCI sizing tool, we can select the type of node we need, the amount of memory each node will have, what CPU we will equip, how many drives are needed to cover the I/O demand, and the network architecture.

We can see a sample of the sizing tool input in the following figure:

Figure 1.  Example from Dell's sizing tool for Azure Stack HCI

In this case, we have chosen to base our Azure Stack HCI infrastructure on four AX-750 nodes, with Intel Gold 6342 CPUs and 1 GB of RAM per node.

Because we have used Live Optics to gather and analyze performance data, we have sized our hardware assets based on real customer usage data such as that shown in the next figure:

Figure 2.  Live Optics performance dashboard

This Live Optics dashboard shows the general requirements of the analyzed environment. Data of aggregated network throughput, IOPS, and memory usage or CPU utilization are displayed and, thus, can be used to size the required hardware.

There are more specific dashboards that show more details on each performance core statistic. For precise storage sizing, we can display read and write I/O behavior in great detail, as we can see in the following figure:

Figure 3.  IOPS graphics through a Live Optics read/write I/O dashboard

With a tool such as Live Optics, we can size our Azure Stack HCI infrastructure based on real workload requirements, not assumptions made because information is lacking. This leads to an accurate configuration, usually resulting in a lower price, and warranties that the proposed infrastructure can handle even the peak business workload requirements.

Check the resources shown below to find links to the Live Optics site and collector application, as well as some Dell technical information and sizing tools for Azure Stack HCI.

Source: infohub.delltechnologies.com