Hi,
this e-mail is meant to caution people using hugepages and mixing those
VMs with non-hugepages VMs on the same hypervisors. I ran into major
trouble, the hypervisors ran out of memory because the VM scheduling
disregards the hugepages in it's calculations. So if you have hugepages
and non-hugepages VMs better check the memory commited on a hypervisor
manually :)
https://bugzilla.redhat.com/show_bug.cgi?id=1804037
https://bugzilla.redhat.com/show_bug.cgi?id=1804046
As for workarounds: so far it seems the only viable solution is
splitting hugepages/nonhugepages VMs with affinity groups but at least
for me that means wasting a lot of resources.
Greetings
Klaas
_______________________________________________
Users mailing list -- users@ovirt.org
To unsubscribe send an email to users-le...@ovirt.org
Privacy Statement: https://www.ovirt.org/site/privacy-policy/
oVirt Code of Conduct:
https://www.ovirt.org/community/about/community-guidelines/
List Archives:
https://lists.ovirt.org/archives/list/users@ovirt.org/message/PIYCVH33QR6SK5AS3QWF3DRBLJK3HQFK/