On Mon, Oct 23, 2017 at 07:27:31AM -0400, Marc-André Lureau wrote: > Hi > > ----- Original Message ----- > > On Mon, Oct 23, 2017 at 10:59:08AM +0100, Marc-André Lureau wrote: > > > Linux commit 749df87bd7bee5a79cef073f5d032ddb2b211de8 (v4.14-rc1) > > > added a new flag MFD_HUGETLB to memfd_create() that specify the file > > > to be created resides in the hugetlbfs filesystem. This is the > > > generic hugetlbfs filesystem not associated with any specific mount > > > point. > > > > How do you know and/or control what size huge pages are used, > > when the platform supports many sizes ? > > From linux commit message: > "As with other system calls that request hugetlbfs backed pages, there is > the ability to encode huge page size in the flag arguments." > > I didn't add this option to memfd backend, as I don't know how generally > useful that is, and if there is already a similar option in qemu (probably > not?). It could be easily added later.
For the existing memory-backend-file, libvirt controls hugepage size based on what's requested in guest XML. So if we were to support the new memory-backend-memfd as an alternative, I think we need to be able to choose huge page size for that too. Regards, Daniel -- |: https://berrange.com -o- https://www.flickr.com/photos/dberrange :| |: https://libvirt.org -o- https://fstop138.berrange.com :| |: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
