[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

[rdo-list] Nova scheduler tries to assign an already-in-use SRIOV QAT VF to a new instance (openstack-mitaka)



Hi,


Upon trying to create VM instance (Say A) with one QAT VF, it fails with the following error i.e., “Requested operation is not valid: PCI device 0000:88:04.7 is in use by driver QEMU, domain instance-00000081”. Please note that, PCI device 0000:88:04.7 is already being assigned to another VM (Say B) .  We have installed openstack-mitaka release on CentO7 system. It has two Intel QAT devices. There are 32 VF devices available per QAT Device/DH895xCC device Out of 64 VFs, only 8 VFs are allocated (to VM instances) and rest should be available.

But the nova scheduler tries to assign an already-in-use SRIOV VF to a new instance and instance fails. It appears that the nova database is not tracking which VF's have already been taken. But if I shut down VM B instance, then other instance VM A boots up and vice-versa. Note that, both the VM instances cannot run simultaneously because of the aforesaid issue.     


We should always be able to create as many instances with the requested PCI devices as there are available VFs.


Please feel free to let me know if additional information is needed. Can anyone please suggest why it tries to assign same PCI device which has been assigned already? Is there any way to resolve this issue? Thank you in advance for your support and help.


[root localhost ~(keystone_admin)]# lspci -d:435

83:00.0 Co-processor: Intel Corporation DH895XCC Series QAT

88:00.0 Co-processor: Intel Corporation DH895XCC Series QAT

[root localhost ~(keystone_admin)]#



[root localhost ~(keystone_admin)]# lspci -d:443 | grep "QAT Virtual Function" | wc -l

64

[root localhost ~(keystone_admin)]#

 

 

[root localhost ~(keystone_admin)]# mysql -u root nova -e "SELECT hypervisor_hostname, address, instance_uuid, status FROM pci_devices JOIN compute_nodes oncompute_nodes.id=compute_node_id" | grep 0000:88:04.7

localhost  0000:88:04.7    e10a76f3-e58e-4071-a4dd-7a545e8000de    allocated

localhost  0000:88:04.7    c3dbac90-198d-4150-ba0f-a80b912d8021    allocated

localhost  0000:88:04.7    c7f6adad-83f0-4881-b68f-6d154d565ce3    allocated

localhost.nfv.benunets.com 0000:88:04.7    0c3c11a5-f9a4-4f0d-b120-40e4dde843d4    allocated

[root localhost ~(keystone_admin)]#

 

[root localhost ~(keystone_admin)]# grep -r e10a76f3-e58e-4071-a4dd-7a545e8000de /etc/libvirt/qemu

/etc/libvirt/qemu/instance-00000081.xml:  <uuid>e10a76f3-e58e-4071-a4dd-7a545e8000de</uuid>

/etc/libvirt/qemu/instance-00000081.xml:      <entry name='uuid'>e10a76f3-e58e-4071-a4dd-7a545e8000de</entry>

/etc/libvirt/qemu/instance-00000081.xml:      <source file='/var/lib/nova/instances/e10a76f3-e58e-4071-a4dd-7a545e8000de/disk'/>

/etc/libvirt/qemu/instance-00000081.xml:      <source path='/var/lib/nova/instances/e10a76f3-e58e-4071-a4dd-7a545e8000de/console.log'/>

/etc/libvirt/qemu/instance-00000081.xml:      <source path='/var/lib/nova/instances/e10a76f3-e58e-4071-a4dd-7a545e8000de/console.log'/>

[root localhost ~(keystone_admin)]#

[root localhost ~(keystone_admin)]# grep -r 0c3c11a5-f9a4-4f0d-b120-40e4dde843d4 /etc/libvirt/qemu

/etc/libvirt/qemu/instance-000000ab.xml:  <uuid>0c3c11a5-f9a4-4f0d-b120-40e4dde843d4</uuid>

/etc/libvirt/qemu/instance-000000ab.xml:      <entry name='uuid'>0c3c11a5-f9a4-4f0d-b120-40e4dde843d4</entry>

/etc/libvirt/qemu/instance-000000ab.xml:      <source file='/var/lib/nova/instances/0c3c11a5-f9a4-4f0d-b120-40e4dde843d4/disk'/>

/etc/libvirt/qemu/instance-000000ab.xml:      <source path='/var/lib/nova/instances/0c3c11a5-f9a4-4f0d-b120-40e4dde843d4/console.log'/>

/etc/libvirt/qemu/instance-000000ab.xml:      <source path='/var/lib/nova/instances/0c3c11a5-f9a4-4f0d-b120-40e4dde843d4/console.log'/>

[root localhost ~(keystone_admin)]#

 

On the controller, , it appears there are duplicate PCI device entries in the Database:

 

MariaDB [nova]> select hypervisor_hostname,address,count(*) from pci_devices JOIN compute_nodes on compute_nodes.id=compute_node_id group by hypervisor_hostname,address having count(*) > 1;

+---------------------+--------------+----------+

| hypervisor_hostname | address      | count(*) |

+---------------------+--------------+----------+

| localhost              | 0000:05:00.0 |        3 |

| localhost              | 0000:05:00.1 |        3 |

| localhost              | 0000:83:01.0 |        3 |

| localhost              | 0000:83:01.1 |        3 |

| localhost              | 0000:83:01.2 |        3 |

| localhost              | 0000:83:01.3 |        3 |

| localhost              | 0000:83:01.4 |        3 |

| localhost              | 0000:83:01.5 |        3 |

| localhost              | 0000:83:01.6 |        3 |

| localhost              | 0000:83:01.7 |        3 |

| localhost              | 0000:83:02.0 |        3 |

| localhost              | 0000:83:02.1 |        3 |

| localhost              | 0000:83:02.2 |        3 |

| localhost              | 0000:83:02.3 |        3 |

| localhost              | 0000:83:02.4 |        3 |

| localhost              | 0000:83:02.5 |        3 |

| localhost              | 0000:83:02.6 |        3 |

| localhost              | 0000:83:02.7 |        3 |

| localhost              | 0000:83:03.0 |        3 |

| localhost              | 0000:83:03.1 |        3 |

| localhost              | 0000:83:03.2 |        3 |

| localhost              | 0000:83:03.3 |        3 |

| localhost              | 0000:83:03.4 |        3 |

| localhost              | 0000:83:03.5 |        3 |

| localhost              | 0000:83:03.6 |        3 |

| localhost              | 0000:83:03.7 |        3 |

| localhost              | 0000:83:04.0 |        3 |

| localhost              | 0000:83:04.1 |        3 |

| localhost              | 0000:83:04.2 |        3 |

| localhost              | 0000:83:04.3 |        3 |

| localhost              | 0000:83:04.4 |        3 |

| localhost              | 0000:83:04.5 |        3 |

| localhost              | 0000:83:04.6 |        3 |

| localhost              | 0000:83:04.7 |        3 |

| localhost              | 0000:88:01.0 |        3 |

| localhost              | 0000:88:01.1 |        3 |

| localhost              | 0000:88:01.2 |        3 |

| localhost              | 0000:88:01.3 |        3 |

| localhost              | 0000:88:01.4 |        3 |

| localhost              | 0000:88:01.5 |        3 |

| localhost              | 0000:88:01.6 |        3 |

| localhost              | 0000:88:01.7 |        3 |

| localhost              | 0000:88:02.0 |        3 |

| localhost              | 0000:88:02.1 |        3 |

| localhost              | 0000:88:02.2 |        3 |

| localhost              | 0000:88:02.3 |        3 |

| localhost              | 0000:88:02.4 |        3 |

| localhost              | 0000:88:02.5 |        3 |

| localhost              | 0000:88:02.6 |        3 |

| localhost              | 0000:88:02.7 |        3 |

| localhost              | 0000:88:03.0 |        3 |

| localhost              | 0000:88:03.1 |        3 |

| localhost              | 0000:88:03.2 |        3 |

| localhost              | 0000:88:03.3 |        3 |

| localhost              | 0000:88:03.4 |        3 |

| localhost              | 0000:88:03.5 |        3 |

| localhost              | 0000:88:03.6 |        3 |

| localhost              | 0000:88:03.7 |        3 |

| localhost              | 0000:88:04.0 |        3 |

| localhost              | 0000:88:04.1 |        3 |

| localhost              | 0000:88:04.2 |        3 |

| localhost              | 0000:88:04.3 |        3 |

| localhost              | 0000:88:04.4 |        3 |

| localhost              | 0000:88:04.5 |        3 |

| localhost              | 0000:88:04.6 |        3 |

| localhost              | 0000:88:04.7 |        3 |

+---------------------+--------------+----------+

66 rows in set (0.00 sec)

 

MariaDB [nova]>

 

Regards,

Chinmaya


[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]