We conducted PAAC testing on this solution using the Login VSI load- generation tool. Login VSI is an industry-standard tool for benchmarking VDI workloads. It uses a carefully designed, holistic methodology that monitors both hardware resource utilization parameters and EUE during load testing.
We performed this test with the Login VSI Task Worker workload on a 3-node VxRail cluster (see Table 2). We created the RDSH VMs using Citrix Virtual and Apps and Desktops using MCS clone technology. We used default Citrix Thinwire+ display protocol. We populated each compute host with 12 RDSH VMs.
The following graphs show the CPU utilization across the three hosts during the testing. CPU usage with all VMs powered on was approximately 1.8 percent before the test started. The CPU usage steadily increased during the login phase, as shown in the following figure.
During the steady state phase, an average CPU utilization of 85 percent was recorded. This value is exactly at the pass/fail threshold that we set for average CPU utilization (see Table 4). To maintain good EUE, do not exceed this threshold. You can load more user sessions while exceeding this threshold for CPU, but you might experience a degradation in user experience.
As shown in the following figure, the CPU readiness was well below the 5 percent threshold that we set. The average steady state CPU core utilization across the four hosts was 69 percent, as shown in the second figure.
We observed no memory constraints during the testing on the compute hosts. Out of 1024 GB of available memory per node, the compute host reached a maximum consumed memory of 316 GB and a steady state average of 316 GB. Active memory usage reached a maximum active memory of 173 GB and recorded a steady state average memory of 96 GB. There was no memory ballooning or swapping on the hosts. The following figures shows consumed memory and active memory.
Network bandwidth was not an issue during the testing. The network usage recorded a steady state average of 814 Mbps. The busiest period for network traffic was immediately after all users had logged in when a peak value of 1,997 Mbps was recorded. The following figure shows network usage.
Cluster IOPS reached a maximum value of 145 for read IOPS and 1,901 for write IOPS during the steady state phase. The average steady average IOPS were 698, as shown in the following figure.
Cluster disk latency reached a maximum read latency of 0.552 milliseconds and a maximum write latency of 0.852 milliseconds during the steady state phase. The average steady state latency was 0.61 milliseconds, as shown in the following figure.
The baseline score for the Login VSI test was 588. This score falls in the 0 to 799 range rated as "Very Good" by Login VSI. For more information about Login VSI baseline ratings and baseline calculations, see VSImax baseline scores. As indicated by the blue line in the following figure, the system reached a VSImax average score of 992 when 1,110 sessions were loaded. This value is well below the VSI threshold score of 1,588 set by the Login VSI tool. During the testing, VSImax was never reached, which typically indicates a stable system and a better user experience.
The Login VSImax user experience score for this test was not reached. When manually interacting with the sessions during the steady state phase, the mouse and window movement were responsive, and video playback was good. No "stuck sessions" were reported during the testing, indicating that the system was not overloaded at any point. See Appendix A, which explains the Login VSI metrics.
We performed this test with the Login VSI Task Worker workload on a 3-node VxRail cluster (see Table 2). We created the desktop VMs using Citrix Virtual Apps and Desktops MCS clone technology. We used the default Citrix Thinwire+ display protocol. We populated each compute hosts with 240 desktop VMs.
The following graphs show the CPU utilization across the three hosts during the testing. CPU usage with all VMs powered on was approximately 10 percent before the test started. The CPU usage steadily increased during the login phase, as shown in the following figure.
During the steady state phase, an average CPU utilization of 85 percent was recorded. This value is close to the pass/fail threshold that we set for average CPU utilization (see Table 4). To maintain good EUE, do not exceed this threshold. You can load more user sessions while exceeding this threshold for CPU, but you might experience a degradation in user experience.
As shown in the following figure, the CPU readiness was well below the 5 percent threshold that we set during steady state. There was a spike in CPU readiness during the logoff phase due to the aggressive settings that were set in the Citrix Hosting Configuration for high concurrency of vSphere operations when re-creating the VMs using MCS.
The average steady state CPU core utilization across the four hosts was 74 percent, as shown in the following figure:
We observed no memory constraints during the testing on the compute hosts. Out of 1024 GB of available memory per node, the compute host reached a maximum consumed memory of 994 GB and a steady state average of 991 GB. Active memory usage reached a maximum active memory of 583 GB and recorded a steady state average memory of 281 GB. There was a small amount of memory ballooning during steady state (3.2 GB) and no swapping on the hosts. This indicates that memory was starting to become a constraint. The following figures show consumed and active memory.
Network bandwidth was not an issue during the testing. The network usage recorded a steady state average of 1420 Mbps. The busiest period for network traffic was during the re-create phase when a peak value of 11,351 Mbps was recorded. The following figure shows network usage.
Cluster IOPS, as shown in the following figure, reached a maximum value of 3,766 for read IOPS and 3,766 for write IOPS during the steady state phase. The average steady average IOPS were 2,254.
Cluster disk latency, as shown in the following figure, reached a maximum read latency of 0.427 milliseconds and a maximum write latency of 0.838 milliseconds during the steady state phase. The average steady state latency was 0.42 milliseconds.
The baseline score for the Login VSI test was 685. This score falls in the 0 to 799 range rated as "Very Good" by Login VSI. For more information about Login VSI baseline ratings and baseline calculations, see VSImax baseline scores. As indicated by the blue line in the following figure, the system reached a VSImax average score of 940 when 720 sessions were loaded. This value is well below the VSI threshold score of 1,685 set by the Login VSI tool. During the testing, VSImax was never reached, which typically indicates a stable system and a better user experience.
The Login VSImax user experience score for this test was not reached. When manually interacting with the sessions during the steady state phase, the mouse and window movement were responsive, and video playback was good. No "stuck sessions" were reported during the testing, indicating that the system was not overloaded at any point. See Appendix A, which explains the Login VSI metrics.
