Re: [PATCH 0/7] Patches to support subpagesize blocksize

[Chandra Seetharaman <sekharan@us.ibm.com>]

On Fri, 2013-12-13 at 02:17 +0100, David Sterba wrote:

Hi David,

> On Wed, Dec 11, 2013 at 05:38:35PM -0600, Chandra Seetharaman wrote:
> > In other words, one cannot create a filesystem in some other architecture
> > and use that filesystem in PPC64 or ARM64, and vice versa.,
> 
> For a full compatibility with any blocksize on arch with any pagesize
> you'd need to implement the case when sectorsize is larger than
> pagesize. Your patchset does the "4k sector/64k page", but I haven't
> noticed the "64k sector/4k page" counterpart.

My object was to make btrfs filesystems from other arches to be directly
usable in PPC64.

Nevertheless, IIUC, btrfs currently support such a case. Each extent
buffers currently can have up to INLINE_EXTENT_BUFFER_PAGES(16). 

-------
#define INLINE_EXTENT_BUFFER_PAGES 16

struct extent_buffer {
        :
        :
        struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
        :
};
--------

No ?

> 
> > Sometime last year, Wade Cline posted a patch(http://lwn.net/Articles/529682/).
> > I started testing it, and found many locking/race issues. So, I changed the
> > logic and created an extent_buffer_head that holds an array of extent buffers that
> > belong to a page.
> > 
> > There are few wrinkles in this patchset, like some xfstests are failing, which
> > could be due to me doing something incorrectly w.r.t how the blocksize and
> > PAGE_SIZE are used in these patched.
> 
> How does it handle compression? The current code relies on
> 
>   compression block == page size
> 
> but should rather use the sectorsize. That might be one of the reasons
> why xfstests fail.

Thanks for this information. I will look at the code more closely with
this in mind.

There are some issues with relocation too. Is there similar assumption
in that code path too ?

>