aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux
diff options
context:
space:
mode:
authorMel Gorman <mgorman@suse.de>2013-01-11 14:32:16 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-01-11 14:54:56 -0800
commit8fb74b9fb2b182d54beee592350d9ea1f325917a (patch)
treeccdcf36cfedb0cf54268226ebde75330e4882539 /include/linux
parentc0a3a20b6c4b5229ef5d26fd9b1c4b1957632aa7 (diff)
mm: compaction: partially revert capture of suitable high-order page
Eric Wong reported on 3.7 and 3.8-rc2 that ppoll() got stuck when waiting for POLLIN on a local TCP socket. It was easier to trigger if there was disk IO and dirty pages at the same time and he bisected it to commit 1fb3f8ca0e92 ("mm: compaction: capture a suitable high-order page immediately when it is made available"). The intention of that patch was to improve high-order allocations under memory pressure after changes made to reclaim in 3.6 drastically hurt THP allocations but the approach was flawed. For Eric, the problem was that page->pfmemalloc was not being cleared for captured pages leading to a poor interaction with swap-over-NFS support causing the packets to be dropped. However, I identified a few more problems with the patch including the fact that it can increase contention on zone->lock in some cases which could result in async direct compaction being aborted early. In retrospect the capture patch took the wrong approach. What it should have done is mark the pageblock being migrated as MIGRATE_ISOLATE if it was allocating for THP and avoided races that way. While the patch was showing to improve allocation success rates at the time, the benefit is marginal given the relative complexity and it should be revisited from scratch in the context of the other reclaim-related changes that have taken place since the patch was first written and tested. This patch partially reverts commit 1fb3f8ca0e92 ("mm: compaction: capture a suitable high-order page immediately when it is made available"). Reported-and-tested-by: Eric Wong <normalperson@yhbt.net> Tested-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/linux')
-rw-r--r--include/linux/compaction.h4
-rw-r--r--include/linux/mm.h1
2 files changed, 2 insertions, 3 deletions
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 6ecb6dc2f30..cc7bddeaf55 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -22,7 +22,7 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
extern int fragmentation_index(struct zone *zone, unsigned int order);
extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
int order, gfp_t gfp_mask, nodemask_t *mask,
- bool sync, bool *contended, struct page **page);
+ bool sync, bool *contended);
extern int compact_pgdat(pg_data_t *pgdat, int order);
extern void reset_isolation_suitable(pg_data_t *pgdat);
extern unsigned long compaction_suitable(struct zone *zone, int order);
@@ -75,7 +75,7 @@ static inline bool compaction_restarting(struct zone *zone, int order)
#else
static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
int order, gfp_t gfp_mask, nodemask_t *nodemask,
- bool sync, bool *contended, struct page **page)
+ bool sync, bool *contended)
{
return COMPACT_CONTINUE;
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 63204078f72..66e2f7c61e5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -455,7 +455,6 @@ void put_pages_list(struct list_head *pages);
void split_page(struct page *page, unsigned int order);
int split_free_page(struct page *page);
-int capture_free_page(struct page *page, int alloc_order, int migratetype);
/*
* Compound pages have a destructor function. Provide a