Monitoring Desktops with Nvidia Grid/vGPU

[HPU-ADM]

Is there any vGPU "monitoring" with VirtualCenter?  Or do you have to get vRealize to monitor performance and to troubleshoot virtual desktops with nvidia's grid vGPU?

[nburton935]

https://docs.vmware.com/en/VMware-vSphere/6.7/com.vmware.vsphere.resmgmt.doc/GUID-1EEF05FA-BD39-4594...

It appears in 6.7, however, that the "GPU" selection in the drop-down is only available in the Flash client - I am unable to see it in the HTML client. This will at least give you overall utilization of the cards in the hosts. It may be available in 7.0 for HTML but I cannot confirm at the moment. 

If you're looking at a per-VM frame buffer and GPU utilization, NVIDIA provides perfmon counters that you can utilize and remotely connect to the Windows guest machine to check them out: 

[RTVNoord]

We also have NVIDIA Grid cards (M10) and I was wondering if I could monitor them 24/7 
For monitoring we are using PRTG and after lots of testing I figured out an option to monitor the vGPU utilisation.

Monitoring all the NVIDIA GPU's usage can only be done within the nvidia-smi CLI command. So I have made a script, that reads out this GPU usage and generates an output that PRTG could read. Finally in PRTG I used the SSH Script that runs this script and reads out the output.

I posted this solution into the PRTG knowledgebase, and can be found here: https://kb.paessler.com/en/topic/82377-monitor-gpu-usage-with-prtg

I'm aware that not everybody is using PRTG. But they have a free version that can monitor 100 sensors. That are enough sensors for monitoring your NVIDIA vGPU 😎