Building a Monster VM

Microsoft Azure is all about the opportunity to push back on known boundaries. In the last couple of months, I dealt with some scenarios where on-premises Data Centers ran out of capacity. Consequently, we were not able to push our tests as far as we would have liked. Taking the work loads to Microsoft Azure gave us the opportunity to stretch workloads to their limits.

In one of these scenarios, the workload was limited to 16 aging physical machines, and the time required to process the data was not acceptable. We needed to find ways to reduce the compute time, and had means to accomplish this on-premises. Pushing this workload to its limits, we deployed it on Microsoft Azure and provisioned it with well over 256 cores. We ended up processing workloads so fast that we now had the opportunity to run them multiple times a day. This newly discovered agility gave us the ability to refine the workload processes without disturbing ongoing business activities.

The first scenario was all about the lack of compute resources necessary to push a workload to its full potential. In a second scenario, we needed an impressive amount of resources within a single Virtual Machine. This blog post is all about how we created this Monster VM.

The Requirement

16 Cores
112 GB of RAM
800 GB of local SSD for temp disk
32 TB for the data disk
50,000 IOPS for the data disk
512 MB per second for the data disk

Let’s think about that spec for a second. That’s monstrous! And we’re going to build it!