tree 7a6969fd7aae85fdaa8e63a90494950d8e4a0792
parent c5fdae469a6a26cd882d7fe0aa3fbfffb6b72fc5
author Rik van Riel <riel@redhat.com> 1224386796 -0700
committer Linus Torvalds <torvalds@linux-foundation.org> 1224517826 -0700

more aggressively use lumpy reclaim

During an AIM7 run on a 16GB system, fork started failing around 32000
threads, despite the system having plenty of free swap and 15GB of
pageable memory.  This was on x86-64, so 8k stacks.

If a higher order allocation fails, we can either:
- keep evicting pages off the end of the LRUs and hope that
  we eventually create a contiguous region; this is somewhat
  unlikely if the system is under enough stress by new
  allocations
- after trying normal eviction for a bit, use lumpy reclaim

This patch switches the system to lumpy reclaim if the VM is having
trouble freeing enough pages, using the same threshold for detection as
used by pageout congestion wait.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>