On Sun, 1 Oct 2017 16:15:06 -0700 Dan Williams <dan.j.williams(a)intel.com> wrote:
On Sun, Oct 1, 2017 at 2:59 PM, Dave Chinner
> The "capacity tax" had nothing to do with it - the major problem
> with self hosting struct pages was that page locks can be hot and
> contention on them will rapidly burn through write cycles on the
> pmem. That's still a problem, yes?
It was an early concern we had, but it has not born out in practice,
and stopped worrying about it 2 years ago when the ZONE_DEVICE
infrastructure was merged.
These are weighty matters and should have been covered in the
changelogs, please. Could you send along a few paragraphs which
summarise these thoughts and I'll add them in?