yahoo-eng-team team mailing list archive

[Sylvain Bauza <sbauza@xxxxxxx>]

While I understand your problem, it's not related to a Nova bug.
See https://gridforums.nvidia.com/default/topic/9541/general-discussion/trouble-assigning-vgpu/ 
In general, it's due to the nvidia driver that doesn't support ECC (yet) so you need to call the same : "nvidia-smi -e 0"

Closing the bug here since like I said it's not related to Nova.

** Changed in: nova
       Status: New => Invalid

-- 
You received this bug notification because you are a member of Yahoo!
Engineering Team, which is subscribed to OpenStack Compute (nova).
https://bugs.launchpad.net/bugs/1837681

Title:
  Failed to create vgpu cause of IOError

Status in OpenStack Compute (nova):
  Invalid

Bug description:
  Description
  ===========
  I used 'Tesla V100' to create vm with vgpu.
  Got error.

  Steps to reproduce
  ==================
  * Create flavor with resources:VGPU='1'
  * Create vm with CLI `openstack server create --image 27dc8e63-6d28-4f80-a6f4-e5a855a02e46 --flavor 224e1385-7de4-4c0b-931d-a7431d329f78 --network net-1 ins-vgpu-t`

  Expected result
  ===============
  Create successfully

  Actual result
  =============
  Got ERROR

  Environment
  ===========
  1. Exact version of OpenStack you are running. See the following
    # apt list --installed | grep nova

  WARNING: apt does not have a stable CLI interface. Use with caution in
  scripts.

  nova-common/xenial,xenial,now 2:17.0.7-6~u16.01 all [installed]
  nova-compute/xenial,xenial,now 2:17.0.7-6~u16.01 all [installed,automatic]
  nova-compute-kvm/xenial,xenial,now 2:17.0.7-6~u16.01 all [installed]
  python-nova/xenial,xenial,now 2:17.0.7-6~u16.01 all [installed,automatic]
  python-novaclient/xenial,xenial,now 2:9.1.1-1~u16.04 all [installed]

  2. Which hypervisor did you use?
      Libvirt + KVM

  
  Logs & Configs
  ==============
  2019-07-22 08:12:18,500.500 21346 ERROR nova.virt.libvirt.driver [req-4053b3df-ae7d-4378-b3c4-1c26e8482e24 4c31323efa7e4abf824399b63a687ff8 187e1165ec2a40e9a72efab673e940d9 - default default] [instance: c9737cde-af6c-40b5-b719-2190428a0a03] Failed to start libvirt guest: libvirtError: internal error: qemu unexpectedly closed the monitor: 2019-07-22T00:12:18.186786Z qemu-system-x86_64: -device vfio-pci,id=hostdev0,sysfsdev=/sys/bus/mdev/devices/78c27f7b-e2ed-4fe8-afcf-84c6107620b9,bus=pci.0,addr=0x7: vfio error: 78c27f7b-e2ed-4fe8-afcf-84c6107620b9: error getting device from group 0: Input/output error

To manage notifications about this bug go to:
https://bugs.launchpad.net/nova/+bug/1837681/+subscriptions