Re: [PATCH v5 4/4] mm: Defer ZONE_DEVICE page initialization to the point where we init pgmap

[Dan Williams]

On Mon, Oct 29, 2018 at 11:29 PM Michal Hocko <mhocko@xxxxxxxxxx> wrote:
>
> On Mon 29-10-18 12:59:11, Alexander Duyck wrote:
> > On Mon, 2018-10-29 at 19:18 +0100, Michal Hocko wrote:
[..]
> > The patches Andrew pushed addressed the immediate issue so that now
> > systems with nvdimm/DAX memory can at least initialize quick enough
> > that systemd doesn't refuse to mount the root file system due to a
> > timeout.
>
> This is about the first time you actually mention that. I have re-read
> the cover letter and all changelogs of patches in this serious. Unless I
> have missed something there is nothing about real users hitting issues
> out there. nvdimm is still considered a toy because there is no real HW
> users can play with.

Yes, you have missed something, because that's incorrect. There's been
public articles about these parts sampling since May.

    https://www.anandtech.com/show/12828/intel-launches-optane-dimms-up-to-512gb-apache-pass-is-here

That testing identified this initialization performance problem and
thankfully got it addressed in time for the current merge window.