ack. Yeah, I had seen that and thought I corrected it. Thank you very much, the instances start.

Now I just have to figure out why I seem to be using 2x the number of hugepages I think I should be. Numstat seems to think that now that I've started up the two VMs, I am using twice as many hugepages as the amount I had allocated via sysctl [1].


On Sat, Jan 31, 2015 at 9:55 AM, Martin Kletzander <> wrote:
On Fri, Jan 30, 2015 at 03:33:43PM -0800, G. Richard Bellamy wrote:
Hello All,

I'm trying to enable hugepages, I've turned off THP (Transparent Huge
Pages), and enabled hugepages in memoryBacking, and set my 2MB
hugepages count via sysctl.

I'm getting "libvirtd[5788]: Failed to autostart VM 'atlas': internal
error: Unable to find any usable hugetlbfs mount for 16777216 KiB"
where atlas is one of my guests and 16777216 KiB is the amount of
memory I'm trying to give to the guest.

Looking at the XML:

     <page size='16777216' unit='KiB' nodeset='0'/>

This means you want the guest's memory to be allocated from 16GiB
hugepages.  You probably wanted to put this there:

 <page size='2' unit='MiB' ...

Yes, i can see the hugepages via numastat -m and hugetlbfs is mounted
via /dev/hugepages and there is a dir structure
/dev/hugepages/libvirt/qemu (it's empty).

HugePages is big enough to accommodate the 16G i'm allocating... and
changing the perms on that directory structure to 777 doesn't work

Any help is much appreciated.



libvirt-users mailing list