page-allocator: always change pageblock ownership when anti-fragmentation is disabled
authorMel Gorman <mel@csn.ul.ie>
Sat, 5 Sep 2009 18:17:11 +0000 (11:17 -0700)
committerLinus Torvalds <torvalds@linux-foundation.org>
Sat, 5 Sep 2009 18:30:42 +0000 (11:30 -0700)
commitdd5d241ea955006122d76af88af87de73fec25b4
tree2ca12406f407d476b1ba473dc376d1e621a383f6
parenta190887b58c32d19c2eee007c5eb8faa970a69ba
page-allocator: always change pageblock ownership when anti-fragmentation is disabled

On low-memory systems, anti-fragmentation gets disabled as fragmentation
cannot be avoided on a sufficiently large boundary to be worthwhile.  Once
disabled, there is a period of time when all the pageblocks are marked
MOVABLE and the expectation is that they get marked UNMOVABLE at each call
to __rmqueue_fallback().

However, when MAX_ORDER is large the pageblocks do not change ownership
because the normal criteria are not met.  This has the effect of
prematurely breaking up too many large contiguous blocks.  This is most
serious on NOMMU systems which depend on high-order allocations to boot.
This patch causes pageblocks to change ownership on every fallback when
anti-fragmentation is disabled.  This prevents the large blocks being
prematurely broken up.

This is a fix to commit 49255c619fbd482d704289b5eb2795f8e3b7ff2e [page
allocator: move check for disabled anti-fragmentation out of fastpath] and
the problem affects 2.6.31-rc8.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Tested-by: Paul Mundt <lethal@linux-sh.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Acked-by: Greg Ungerer <gerg@snapgear.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm/page_alloc.c