Home > Workload Solutions > Virtual Desktop Infrastructure > Design and Implementation Guides > Dell Validated Designs for VDI—Designs for Citrix Virtual Apps and Desktops on vSAN Ready Nodes > Validation
The Dell VDI Solutions team carries out performance analysis and characterization (PAAC) on Dell VDI solutions to ensure the optimal combination of end-user experience (EUE) and cost-per-user. The team uses a carefully designed, holistic methodology that monitors both hardware resource utilization parameters and EUE during load-testing.
Each user load was tested against four runs: a pilot run to validate that the infrastructure was performing properly (and that valid data could be captured), and three subsequent runs to enable data correlation.
The team monitored the following resources to ensure that the user experience was not compromised:
Parameter | Pass/fail threshold |
Physical host CPU utilization | 85% |
Physical host memory utilization | 85% |
Network throughput | 85% |
Disk latency | 20 milliseconds |
Failed sessions | 2% |
Note: The Dell VDI Solutions team recommends that the average CPU utilization does not exceed 85 percent in a production environment. A five percent margin of error was allocated for this validation effort. CPU utilization sometimes exceeds Dell’s recommended percentage, but because of the nature of Login PAAC testing, these exceptions are reasonable for determining Dell’s sizing guidance.
Login Enterprise installs a standard collection of desktop application software, including Microsoft Office and Adobe Acrobat Reader, on each VDI desktop testing instance. It then uses a configurable launcher system to connect a specified number of simulated users to available desktops within the environment. When the simulated user is connected, a login script configures the user environment and starts a defined workload. Each launcher system can launch connections to several VDI desktops (target machines). A centralized management console configures and manages the launchers and the Login Enterprise environment.
The team used the following login and boot conditions:
The following table describes the Login Enterprise workloads that the team used in testing:
Login Enterprise workload name | Workload description |
Task Worker | This is a light workload, which runs fewer applications and starts or stops them less frequently than the other workloads, resulting in lower CPU, RAM, and IO usage. This workload uses the following applications:
|
The following table summarizes the software versions that the team used to test the Login Enterprise workloads:
Hypervisor | Broker agent | Login Enterprise Version |
7.0.3, 20328353 | Citrix VAD 2203 CU2 LTSR | 5.0.5 |
The following table summarizes the desktop VM configurations that the team used to test the Login Enterprise workloads:
Login Enterprise workload | vCPUs | ESXi configured memory | ESXi reserved memory | Screen resolution | Operating system |
Task Worker | 2 | 4 GB | 2 GB | 1280 x 720 | 10 Enterprise 22H2 64-bit |
The following table summarizes the host utilization metrics that the team observed for the different Login Enterprise workloads, as well as the user density derived from Login Enterprise performance testing:
Login Enterprise workload | Operating system | User density | Average CPU | Average active memory | Average IOPS per user | Average network Mbps per user | |
Density Optimized | Task | 10 Enterprise 22H2 64-bit | 155 | 85% | 234 GB | 15 | 6.12 |
The host utilization metrics in the preceding table are defined as: