Re: [PATCH 2/3] xfs: use folios in the buffer cache

[Dave Chinner <david@fromorbit.com>]

On Sun, Jan 21, 2024 at 10:39:12PM -0800, Christoph Hellwig wrote:
> On Thu, Jan 18, 2024 at 05:26:24PM -0800, Darrick J. Wong wrote:
> > Ugh, pointer casting.  I suppose here is where we might want an
> > alloc_folio_bulk_array that might give us successively smaller
> > large-folios until b_page_count is satisfied?  (Maybe that's in the next
> > patch?)
> > 
> > I guess you'd also need a large-folio capable vm_map_ram. 
> 
> We need to just stop using vm_map_ram, there is no reason to do that
> even right now.  It was needed when we used the page cache to back
> pagebuf, but these days just sing vmalloc is the right thing for
> !unmapped buffers that can't use large folios. 

I haven't looked at what using vmalloc means for packing the buffer
into a bio - we currently use bio_add_page(), so does that mean we
have to use some variant of virt_to_page() to break the vmalloc
region up into it's backing pages to feed them to the bio? Or is
there some helper that I'm unaware of that does it all for us
magically?

> And I'm seriously
> wondering if we should bother with unmapped buffers in the long run
> if we end up normally using larger folios or just consolidate down to:
> 
>  - kmalloc for buffers < PAGE_SIZE
>  - folio for buffers >= PAGE_SIZE
>  - vmalloc if allocation a larger folios is not possible

Yeah, that's kind of where I'm going with this. Large folios already
turn off unmapped buffers, and I'd really like to get rid of that
page straddling mess that unmapped buffers require in the buffer
item dirty region tracking. That means we have to get rid of
unmapped buffers....

-Dave.

-- 
Dave Chinner
david@fromorbit.com