Re: [PATCH] pmem: export the symbols __copy_user_flushcache and __copy_from_user_flushcache

[Dan Williams]

On Wed, Sep 16, 2020 at 10:24 AM Mikulas Patocka <mpatocka@xxxxxxxxxx> wrote:
>
>
>
> On Wed, 16 Sep 2020, Dan Williams wrote:
>
> > On Wed, Sep 16, 2020 at 3:57 AM Mikulas Patocka <mpatocka@xxxxxxxxxx> wrote:
> > >
> > >
> > >
> > > I'm submitting this patch that adds the required exports (so that we could
> > > use __copy_from_user_flushcache on x86, arm64 and powerpc). Please, queue
> > > it for the next merge window.
> >
> > Why? This should go with the first user, and it's not clear that it
> > needs to be relative to the current dax_operations export scheme.
>
> Before nvfs gets included in the kernel, I need to distribute it as a
> module. So, it would make my maintenance easier. But if you don't want to
> export it now, no problem, I can just copy __copy_user_flushcache from the
> kernel to the module.

That sounds a better plan than exporting symbols with no in-kernel consumer.

> > My first question about nvfs is how it compares to a daxfs with
> > executables and other binaries configured to use page cache with the
> > new per-file dax facility?
>
> nvfs is faster than dax-based filesystems on metadata-heavy operations
> because it doesn't have the overhead of the buffer cache and bios. See
> this: http://people.redhat.com/~mpatocka/nvfs/BENCHMARKS

...and that metadata problem is intractable upstream? Christoph poked
at bypassing the block layer for xfs metadata operations [1], I just
have not had time to carry that further.

[1]: "xfs: use dax_direct_access for log writes", although it seems
he's dropped that branch from his xfs.git