-
Bug
-
Resolution: Won't Do
-
Undefined
-
None
-
rhel-9.6
-
No
-
None
-
rhel-virt-core
-
ssg_virtualization
-
None
-
False
-
False
-
-
None
-
None
-
None
-
None
-
-
aarch64
-
None
What were you trying to do that didn't work?
The actual total downtime is much more than the maxdowntime we set after vfio migration with multiple VFs.
Please provide the package NVR for which the bug is seen:
5.14.0-539.el9.aarch64
libvirt-10.10.0-1.el9.aarch64
qemu-kvm-9.1.0-6.el9.aarch64
How reproducible is this bug?:
100%
Steps to reproduce
- Start a vm with 4 VFs
# virsh dumpxml avocado-vt-vm1 --xpath //hostdev <hostdev mode="subsystem" type="pci" managed="yes"> <driver name="vfio"/> <source> <address domain="0x0000" bus="0x01" slot="0x00" function="0x5"/> </source> <address type="pci" domain="0x0000" bus="0x01" slot="0x00" function="0x0"/> </hostdev> <hostdev mode="subsystem" type="pci" managed="yes"> <driver name="vfio"/> <source> <address domain="0x0000" bus="0x01" slot="0x00" function="0x2"/> </source> <address type="pci" domain="0x0000" bus="0x08" slot="0x00" function="0x0"/> </hostdev> <hostdev mode="subsystem" type="pci" managed="yes"> <driver name="vfio"/> <source> <address domain="0x0000" bus="0x01" slot="0x00" function="0x3"/> </source> <address type="pci" domain="0x0000" bus="0x09" slot="0x00" function="0x0"/> </hostdev> <hostdev mode="subsystem" type="pci" managed="yes"> <driver name="vfio"/> <source> <address domain="0x0000" bus="0x01" slot="0x00" function="0x4"/> </source> <address type="pci" domain="0x0000" bus="0x0a" slot="0x00" function="0x0"/> </hostdev> - virsh migrate-setmaxdowntime avocado-vt-vm1 280
- virsh migrate --live --verbose --domain avocado-vt-vm1 --desturi qemu+tcp://10.26.1.119/system
- Check downtime after migration on destination using 'virsh domjobinfo avocado-vt-vm1 --completed'
Expected results
The value of 'Total downtime' should be less or around the value we set.
Actual results
The actual downtime is 1230 ms, much more bigger than 280ms.
# virsh domjobinfo avocado-vt-vm1 --completed Job type: Completed Operation: Incoming migration Time elapsed: 356540 ms Time elapsed w/o network: 356539 ms Data processed: 6.156 GiB Data remaining: 0.000 B Data total: 8.125 GiB Memory processed: 6.156 GiB Memory remaining: 0.000 B Memory total: 8.125 GiB Memory bandwidth: 17.967 MiB/s Dirty rate: 0 pages/s Page size: 4096 bytes Iteration: 223466 Postcopy requests: 0 Constant pages: 1960235 Normal pages: 1145319 Normal data: 4.369 GiB Total downtime: 1230 ms Downtime w/o network: 1229 ms Setup time: 147 ms
Others
If vm has 1 VF, total dowmtime will be ~403 ms:
# virsh domjobinfo avocado-vt-vm1 --completed Job type: Completed Operation: Incoming migration Time elapsed: 12348 ms Time elapsed w/o network: 12347 ms Data processed: 887.443 MiB Data remaining: 0.000 B Data total: 8.125 GiB Memory processed: 887.443 MiB Memory remaining: 0.000 B Memory total: 8.125 GiB Memory bandwidth: 109.076 MiB/s Dirty rate: 0 pages/s Page size: 4096 bytes Iteration: 3 Postcopy requests: 0 Constant pages: 1913326 Normal pages: 220155 Normal data: 859.980 MiB Total downtime: 403 ms Downtime w/o network: 402 ms Setup time: 39 ms
If there're 2 VFs, it'll be 617 ms.
# virsh domjobinfo avocado-vt-vm1 --completed Job type: Completed Operation: Incoming migration Time elapsed: 12820 ms Time elapsed w/o network: 12819 ms Data processed: 878.694 MiB Data remaining: 0.000 B Data total: 8.125 GiB Memory processed: 878.694 MiB Memory remaining: 0.000 B Memory total: 8.125 GiB Memory bandwidth: 107.275 MiB/s Dirty rate: 0 pages/s Page size: 4096 bytes Iteration: 3 Postcopy requests: 0 Constant pages: 1914681 Normal pages: 216754 Normal data: 846.695 MiB Total downtime: 617 ms Downtime w/o network: 616 ms Setup time: 76 ms
