Hi there,
I’m trying to help setup a remote visualization protocol on my University’s HPC using VirtualGL and EGL, and the issues seem to be related to a missing file /dev/dri/renderd{number} which as far as I understand should be created by the Direct Rendering Manager when the drivers are installed, but it appears that didn’t happen.
The nvidia drivers were successfully installed, so that programs can use the P100 available on the machine, and nvidia-smi shows
±----------------------------------------------------------------------------+
| NVIDIA-SMI 440.64.00 Driver Version: 440.64.00 CUDA Version: 10.2 |
|-------------------------------±---------------------±---------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 Tesla P100-PCIE… On | 00000000:0B:00.0 Off | 0 |
| N/A 21C P0 25W / 250W | 0MiB / 16280MiB | 0% Default |
±------------------------------±---------------------±---------------------+
±----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| No running processes found |
±----------------------------------------------------------------------------+
I also see that /dev/dri/card0 exists.
Can anyone explain what step needs to be taken to ensure /dev/dri/renderd{number} exists for this card? Thanks!