Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1380667

Re: [PATCH mmotm 5/5] huge tmpfs: add shmem_pmd_fault()

Show all headers | View raw

On Sat, Apr 16, 2016 at 04:41:33PM -0700, Hugh Dickins wrote:
> The pmd_fault() method gives the filesystem an opportunity to place
> a trans huge pmd entry at *pmd, before any pagetable is exposed (and
> an opportunity to split it on COW fault): now use it for huge tmpfs.
> 
> This patch is a little raw: with more time before LSF/MM, I would
> probably want to dress it up better - the shmem_mapping() calls look
> a bit ugly; it's odd to want FAULT_FLAG_MAY_HUGE and VM_FAULT_HUGE just
> for a private conversation between shmem_fault() and shmem_pmd_fault();
> and there might be a better distribution of work between those two, but
> prising apart that series of huge tests is not to be done in a hurry.
> 
> Good for now, presents the new way, but might be improved later.
> 
> This patch still leaves the huge tmpfs map_team_by_pmd() allocating a
> pagetable while holding page lock, but other filesystems are no longer
> doing so; and we've not yet settled whether huge tmpfs should (like anon
> THP) or should not (like DAX) participate in deposit/withdraw protocol.
> 
> Signed-off-by: Hugh Dickins <hughd@google.com>

Just for record: I don't like ->pmd_fault() approach because it results in
two requests to file system (two shmem_fault() in this case) if we don't
have a huge page to map: one for huge page (failed) and then one for small.
I think this case should be rather common: all mounts without huge pages
enabled. I expect performance regression from this too.

-- 
 Kirill A. Shutemov

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH mmotm 1/5] huge tmpfs: try to allocate huge pages split into  a team fix Hugh Dickins <hughd@google.com> - 2016-04-17 01:30 +0200
  [PATCH mmotm 2/5] huge tmpfs: fix mlocked meminfo track huge unhuge  mlocks fix Hugh Dickins <hughd@google.com> - 2016-04-17 01:40 +0200
    Re: [PATCH mmotm 2/5] huge tmpfs: fix mlocked meminfo track huge  unhuge mlocks fix Stephen Rothwell <sfr@canb.auug.org.au> - 2016-04-21 01:50 +0200
  [PATCH mmotm 4/5] huge tmpfs: avoid premature exposure of new  pagetable revert Hugh Dickins <hughd@google.com> - 2016-04-17 01:40 +0200
    Re: [PATCH mmotm 4/5] huge tmpfs: avoid premature exposure of new  pagetable revert Stephen Rothwell <sfr@canb.auug.org.au> - 2016-04-21 02:00 +0200
  [PATCH mmotm 3/5] huge tmpfs recovery: tweak shmem_getpage_gfp to  fill team fix Hugh Dickins <hughd@google.com> - 2016-04-17 01:40 +0200
    Re: [PATCH mmotm 3/5] huge tmpfs recovery: tweak shmem_getpage_gfp  to fill team fix Stephen Rothwell <sfr@canb.auug.org.au> - 2016-04-21 02:00 +0200
  [PATCH mmotm 5/5] huge tmpfs: add shmem_pmd_fault() Hugh Dickins <hughd@google.com> - 2016-04-17 01:50 +0200
    Re: [PATCH mmotm 5/5] huge tmpfs: add shmem_pmd_fault() "Kirill A. Shutemov" <kirill@shutemov.name> - 2016-04-17 02:50 +0200
      Re: [PATCH mmotm 5/5] huge tmpfs: add shmem_pmd_fault() Hugh Dickins <hughd@google.com> - 2016-04-17 03:30 +0200
    Re: [PATCH mmotm 5/5] huge tmpfs: add shmem_pmd_fault() Stephen Rothwell <sfr@canb.auug.org.au> - 2016-04-21 02:00 +0200
  Re: [PATCH mmotm 1/5] huge tmpfs: try to allocate huge pages split  into a team fix Stephen Rothwell <sfr@canb.auug.org.au> - 2016-04-21 01:50 +0200

csiph-web