Failed to attach multiple vGPU to a VM

Currently, I am trying to add multiple "vGPU " in Ubuntu VM. But fails with the following error.

2022-01-11T11:04:40.574848Z qemu-system-x86_64: -device vfio-pci,id=hostdev0,sysfsdev=/sys/bus/mdev/devices/7c66720f-0dbd-4ccd-8ad0-f7ca98f5602b,display=off,bus=pci.8,addr=0x0: warning: vfio 7c66720f-0dbd-4ccd-8ad0-f7ca98f5602b: Could not enable error recovery for the device
2022-01-11T11:04:40.607929Z qemu-system-x86_64: -device vfio-pci,id=hostdev1,sysfsdev=/sys/bus/mdev/devices/8d794f51-2d8b-4c6c-8c91-323d54c383fd,display=off,bus=pci.7,addr=0x0: vfio 8d794f51-2d8b-4c6c-8c91-323d54c383fd: error getting device from group 296: Input/output error
Verify all devices in group 296 are bound to vfio-<bus> or pci-stub and not already in use

Added following content in virsh edit <vm-name>

    <hostdev mode='subsystem' type='mdev' managed='no' model='vfio-pci' display='off'>
        <address uuid='7c66720f-0dbd-4ccd-8ad0-f7ca98f5602b'/>
      <address type='pci' domain='0x0000' bus='0x08' slot='0x00' function='0x0'/>
    <hostdev mode='subsystem' type='mdev' managed='no' model='vfio-pci' display='off'>
        <address uuid='8d794f51-2d8b-4c6c-8c91-323d54c383fd'/>
      <address type='pci' domain='0x0000' bus='0x07' slot='0x00' function='0x0'/>

Following is the environment configuration
GPU model: “NVIDIA RTX A6000”
OS: “Ubuntu 20.04.3 LTS (Focal Fossa)”
Kernel: “5.11.0-41-generic”
Server: SYS-740GP-TNRT

While adding 1 vGPU to VM it’s a success, but fails during multiple vGPU.
Whether multiple vGPU supported in Ubuntu host hypervisor or something wrong in config?

Hi shan_8992,

I am facing the same issue, do you have any luck so far?


According to NVIDIA RTX A6000, its A6000-48Q/A6000-48C. For our use case, it’s not our target.

Is there any progress?


what kind of progress do you mean? If we work on enabling smaller vGPU profiles for multi-vGPU?