diff options
| author | Johannes Weiner <hannes@cmpxchg.org> | 2014-04-08 00:37:48 +0200 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-04-08 01:35:57 +0200 |
| commit | 3a025760fc158b3726eac89ee95d7f29599e9dfa (patch) | |
| tree | f4b0a8b3da5f361c2206c83c9ad9d5247aa4690e /mm/internal.h | |
| parent | memcg: rename high level charging functions (diff) | |
| download | linux-3a025760fc158b3726eac89ee95d7f29599e9dfa.tar.xz linux-3a025760fc158b3726eac89ee95d7f29599e9dfa.zip | |
mm: page_alloc: spill to remote nodes before waking kswapd
On NUMA systems, a node may start thrashing cache or even swap anonymous
pages while there are still free pages on remote nodes.
This is a result of commits 81c0a2bb515f ("mm: page_alloc: fair zone
allocator policy") and fff4068cba48 ("mm: page_alloc: revert NUMA aspect
of fair allocation policy").
Before those changes, the allocator would first try all allowed zones,
including those on remote nodes, before waking any kswapds. But now,
the allocator fastpath doubles as the fairness pass, which in turn can
only consider the local node to prevent remote spilling based on
exhausted fairness batches alone. Remote nodes are only considered in
the slowpath, after the kswapds are woken up. But if remote nodes still
have free memory, kswapd should not be woken to rebalance the local node
or it may thrash cash or swap prematurely.
Fix this by adding one more unfair pass over the zonelist that is
allowed to spill to remote nodes after the local fairness pass fails but
before entering the slowpath and waking the kswapds.
This also gets rid of the GFP_THISNODE exemption from the fairness
protocol because the unfair pass is no longer tied to kswapd, which
GFP_THISNODE is not allowed to wake up.
However, because remote spills can be more frequent now - we prefer them
over local kswapd reclaim - the allocation batches on remote nodes could
underflow more heavily. When resetting the batches, use
atomic_long_read() directly instead of zone_page_state() to calculate the
delta as the latter filters negative counter values.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: <stable@kernel.org> [3.12+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/internal.h')
| -rw-r--r-- | mm/internal.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/mm/internal.h b/mm/internal.h index 29e1e761f9eb..3e910000fda4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -370,5 +370,6 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ +#define ALLOC_FAIR 0x100 /* fair zone allocation */ #endif /* __MM_INTERNAL_H */ |