Skip to content

mm: hugetlbfs: fix hugetlbfs optimization v3

Andrea Arcangeli linux-mm lkml 1 version New

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 Latest8 patches 0 repliesNew

Changes since v2 from the cover letter

1) optimize away a few more locked ops in the get_page/put_page hugetlbfs and slab paths (see 3/8 and 4/8).

Patches in v1 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/8mm: hugetlbfs: fix hugetlbfs optimizationinclude/linux/hugetlb.h mm/hugetlb.c mm/swap.c+106 -600 replies
2/8mm: hugetlb: use get_page_foll in follow_hugetlb_pagemm/hugetlb.c+1 -10 replies
3/8mm: hugetlbfs: move the put/get_page slab and hugetlbfs optimization in a faster pathmm/swap.c+78 -620 replies
4/8mm: thp: optimize compound_trans_hugeinclude/linux/huge_mm.h+23 -00 replies
5/8mm: tail page refcounting optimization for slab and hugetlbfsinclude/linux/hugetlb.h include/linux/mm.h mm/internal.h +1 more+60 -140 replies
6/8mm/hugetlb.c: simplify PageHeadHuge() and PageHuge()mm/hugetlb.c+2 -100 replies
7/8mm/swap.c: reorganize put_compound_page()mm/swap.c+125 -1290 replies
8/8mm/hugetlb.c: defer PageHeadHuge() symbol exportmm/hugetlb.c+0 -10 replies

Reviews trailers per patch

2 of 8 patches have a Reviewed-by or Acked-by.

PatchKhalid Aziz
1/8
2/8R-b
3/8
4/8
5/8R-b
6/8
7/8
8/8

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.

Read the v1 thread

Cover letter [PATCH 0/8] mm: hugetlbfs: fix hugetlbfs optimization v3

Changes since v2:

1) optimize away a few more locked ops in the get_page/put_page hugetlbfs and slab paths (see 3/8 and 4/8).

3/8 is the least trivial addition to the series as we now are running PageSlab and PageHeadHuge on random page structure without holding any reference count on this. A smp_rmb() if any of the two checks succeeds is what is supposed to make it safe doing so and it's lighter weight than get_page_unless_zero (hence the supposed optimization out of it). 3/8 makes no difference whatsoever to the speed of the THP case. It's unclear if 3/8 is worth it but it seems every bit is affecting performance for directio over hugetlbfs with

Quoted 1 line

8GB/sec storage devices so I thought of trying it. 4/8 is quite

self explanatory and it removes some smp_rmb which is not needed with the current layout of the struct page.

2) two nice cleanups from Andrew

3) Removed the PageHeadHuge export as it's not needed right now

Andrea Arcangeli (6):
mm: hugetlbfs: fix hugetlbfs optimization
mm: hugetlb: use get_page_foll in follow_hugetlb_page
mm: hugetlbfs: move the put/get_page slab and hugetlbfs optimization
in a faster path
mm: thp: optimize compound_trans_huge
mm: tail page refcounting optimization for slab and hugetlbfs mm/hugetlb.c: defer PageHeadHuge() symbol export

Andrew Morton (2):
mm/hugetlb.c: simplify PageHeadHuge() and PageHuge() mm/swap.c: reorganize put_compound_page()

 include/linux/huge_mm.h |  23 ++++
 include/linux/mm.h      |  32 +++++-
 mm/hugetlb.c            |  20 +++-
 mm/internal.h           |   3 +-
 mm/swap.c               | 284 +++++++++++++++++++++++++++++-------------------
 5 files changed, 240 insertions(+), 122 deletions(-)

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>