[Starlingx-discuss] [starlingx-discuss][pci-passthrough] GPU passthrough failed
Hi all, There are some ERRORs when launching VM with NVIDIA GPU pci-passthrough in Stx1.0. Anyone have got this problem?
2019-08-02 17:17:09.916 52231 ERROR nova.scheduler.utils [req-aeb6ab2f-5c3e-4ca1-b4dd-45e47b3fc06c b9b0f2dcd0fc4bdab8239c5aaeb24c39 2f6c58b2e2e942b58acbedb73a5cb474 - default default] [instance: a40ef34a-0c47-4a6b-aa4b-e54c02dc61e4] Error from last host: controller-0 (node controller-0): [u'Traceback (most recent call last):\n', u' File "/usr/lib/python2.7/site-packages/nova/compute/manager.py", line 1997, in _do_build_and_run_instance\n filter_properties)\n', u' File "/usr/lib/python2.7/site-packages/nova/compute/manager.py", line 2244, in _build_and_run_instance\n instance_uuid=instance.uuid, reason=six.text_type(e))\n', u"RescheduledException: Build of instance a40ef34a-0c47-4a6b-aa4b-e54c02dc61e4 was re-scheduled: internal error: process exited while connecting to monitor: 2019-08-02T17:17:01.845173Z qemu-kvm: -chardev socket,id=charnet0,path=/var/run/openvswitch/vhu43f09376-ca,server: info: QEMU waiting for connection on: disconnected:unix:/var/run/openvswitch/vhu43f09376-ca,server\nwarning: host doesn't support requested feature: CPUID.80000001H:EDX.fxsr-opt [bit 25]\nwarning: host doesn't support requested feature: CPUID.80000001H:EDX.fxsr-opt [bit 25]\n2019-08-02T17:17:03.344966Z qemu-kvm: -device vfio-pci,host=04:00.0,id=hostdev0,bus=pci.0,addr=0x5: vfio error: 0000:04:00.0: failed to setup container for group 23: failed to set iommu for container: Operation not permitted\n"]
Thanks Kunpeng
participants (1)
-
张鲲鹏