Re: DAX can not work on virtual nvdimm device

[Ross Zwisler]

On Fri, Sep 09, 2016 at 10:03:27AM -0400, Theodore Ts'o wrote:
> On Fri, Sep 09, 2016 at 11:19:25AM +0200, Jan Kara wrote:
> > > > > > 1. make the guest kernel based on your tree, the top commit is
> > > > > >    10d7902fa0e82b (dax: unmap/truncate on device shutdown) and
> > > > > >    the config file can be found in this thread.
> 
> What git tree is 10d7902fa0e82b from?

It's from djbw's libnvdimm tree.

https://git.kernel.org/cgit/linux/kernel/git/djbw/nvdimm.git/

I don't think that commit is relevant, though.  I believe this should
reproduce with a vanilla v4.7 tree.  I can verify if you'd like.

> > Hum, nothing unusual in there. I've tried reproducing on a local SLE11 SP3
> > machine (which is from about the same time) but everything works as
> > expected there. Shrug...
> 
> I just tried reproducing it via "gce-xfstests --pmem-device shell"
> with a downgraded e2fsprogs to stock upstream 1.42.12, and I can't
> reproduce it with the ext4.git tree.  I'm not sure whether the git
> commit is critical, though.  Is this a regression that was working
> before?

I'm not sure if we've ever tested Centos6/RHEL6 with DAX.  It could be that it
has never worked.

> Or it's possible that Red Hat did something weird with the CentOS 6
> e2fsprogs....