[ovirt-users] Hugepages and running out of memory

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