Skip to content

RFC re-shrink 'struct page' when SLUB is on.

Dave Hansen linux-mm lkml 1 version In review

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 RFC Latest7 patches 12 repliesIn review

Patches in v1 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/7mm: print more details for bad_page()include/linux/mm.h mm/balloon_compaction.c mm/memory.c +2 more+62 -232 replies
2/7mm: page->pfmemalloc only used by slab/skbinclude/linux/mm.h include/linux/mm_types.h include/linux/skbuff.h +3 more+26 -180 replies
3/7mm: slabs: reset page at freeinclude/linux/mm.h mm/slab.c mm/slab.h +2 more+15 -40 replies
4/7mm: rearrange struct pageinclude/linux/mm_types.h mm/slab.c mm/slab_common.c +2 more+121 -1030 replies
5/7mm: slub: rearrange 'struct page' fieldsinclude/linux/mm_types.h mm/slab_common.c mm/slub.c+195 -1550 replies
6/7mm: slub: remove 'struct page' alignment restrictionsinclude/linux/mm_types.h mm/slab_common.c mm/slub.c+26 -451 reply
7/7mm: slub: cleanups after code churnmm/slub.c+78 -690 replies

Reviews trailers per patch

1 of 7 patches has a Reviewed-by or Acked-by.

PatchChristoph Lameter
1/7R-b
2/7
3/7
4/7
5/7
6/7
7/7

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

Read the v1 thread

Cover letter [RFC][PATCH 0/7] re-shrink 'struct page' when SLUB is on.

SLUB depends on a 16-byte cmpxchg for an optimization. For the purposes of this series, I'm assuming that it is a very important optimization that we desperately need to keep around.

In order to get guaranteed 16-byte alignment (required by the hardware on x86), 'struct page' is padded out from 56 to 64 bytes.

Those 8-bytes matter. We've gone to great lengths to keep 'struct page' small in the past. It's a shame that we bloat it now just for alignment reasons when we have extra space. Plus, bloating such a commonly-touched structure *HAS* to have cache footprint implications.

These patches attempt _internal_ alignment instead of external alignment for slub.

I also got a bug report from some folks running a large database benchmark. Their old kernel uses slab and their new one uses slub. They were swapping and couldn't figure out why. It turned out to be the 2GB of RAM that the slub padding wastes on their system.

On my box, that 2GB cost about $200 to populate back when we bought it. I want my $200 back.

This set takes me from 16909584K of reserved memory at boot down to 14814472K, so almost *exactly* 2GB of savings! It also helps performance, presumably because it touches 14% fewer struct page cachelines. A 30GB dd to a ramfs file:

        dd if=/dev/zero of=bigfile bs=$((1<<30)) count=30

is sped up by about 4.4% in my testing.

This is compile tested and lightly runtime tested. I'm curious what people think of it before we push it futher. I believe this gets rid of the concerns Christoph had about adding additional branches in the fast path, although I still disagree that this has any benefit in practice.

I also wrote up a document describing 'struct page's layout:

http://tinyurl.com/n6kmedz