summaryrefslogtreecommitdiffstats
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
authorMel Gorman <mgorman@suse.de>2012-11-29 13:54:30 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2012-11-30 08:51:18 -0800
commit782fd30406ecb9d9b082816abe0c6008fc72a7b0 (patch)
tree50e6769cda69a088ecec4d477c740426329b6d2f /mm/page_alloc.c
parenta50915394f1fc02c2861d3b7ce7014788aa5066e (diff)
downloadop-kernel-dev-782fd30406ecb9d9b082816abe0c6008fc72a7b0.zip
op-kernel-dev-782fd30406ecb9d9b082816abe0c6008fc72a7b0.tar.gz
mm: avoid waking kswapd for THP allocations when compaction is deferred or contended
With "mm: vmscan: scale number of pages reclaimed by reclaim/compaction based on failures" reverted, Zdenek Kabelac reported the following Hmm, so it's just took longer to hit the problem and observe kswapd0 spinning on my CPU again - it's not as endless like before - but still it easily eats minutes - it helps to turn off Firefox or TB (memory hungry apps) so kswapd0 stops soon - and restart those apps again. (And I still have like >1GB of cached memory) kswapd0 R running task 0 30 2 0x00000000 Call Trace: preempt_schedule+0x42/0x60 _raw_spin_unlock+0x55/0x60 put_super+0x31/0x40 drop_super+0x22/0x30 prune_super+0x149/0x1b0 shrink_slab+0xba/0x510 The sysrq+m indicates the system has no swap so it'll never reclaim anonymous pages as part of reclaim/compaction. That is one part of the problem but not the root cause as file-backed pages could also be reclaimed. The likely underlying problem is that kswapd is woken up or kept awake for each THP allocation request in the page allocator slow path. If compaction fails for the requesting process then compaction will be deferred for a time and direct reclaim is avoided. However, if there are a storm of THP requests that are simply rejected, it will still be the the case that kswapd is awake for a prolonged period of time as pgdat->kswapd_max_order is updated each time. This is noticed by the main kswapd() loop and it will not call kswapd_try_to_sleep(). Instead it will loopp, shrinking a small number of pages and calling shrink_slab() on each iteration. This patch defers when kswapd gets woken up for THP allocations. For !THP allocations, kswapd is always woken up. For THP allocations, kswapd is woken up iff the process is willing to enter into direct reclaim/compaction. [akpm@linux-foundation.org: fix typo in comment] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Zdenek Kabelac <zkabelac@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: Jiri Slaby <jirislaby@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Robert Jennings <rcj@linux.vnet.ibm.com> Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Glauber Costa <glommer@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c37
1 files changed, 27 insertions, 10 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8193809..a8f2c87 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2378,6 +2378,15 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS);
}
+/* Returns true if the allocation is likely for THP */
+static bool is_thp_alloc(gfp_t gfp_mask, unsigned int order)
+{
+ if (order == pageblock_order &&
+ (gfp_mask & (__GFP_MOVABLE|__GFP_REPEAT)) == __GFP_MOVABLE)
+ return true;
+ return false;
+}
+
static inline struct page *
__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
@@ -2416,7 +2425,9 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
goto nopage;
restart:
- wake_all_kswapd(order, zonelist, high_zoneidx,
+ /* The decision whether to wake kswapd for THP is made later */
+ if (!is_thp_alloc(gfp_mask, order))
+ wake_all_kswapd(order, zonelist, high_zoneidx,
zone_idx(preferred_zone));
/*
@@ -2487,15 +2498,21 @@ rebalance:
goto got_pg;
sync_migration = true;
- /*
- * If compaction is deferred for high-order allocations, it is because
- * sync compaction recently failed. In this is the case and the caller
- * requested a movable allocation that does not heavily disrupt the
- * system then fail the allocation instead of entering direct reclaim.
- */
- if ((deferred_compaction || contended_compaction) &&
- (gfp_mask & (__GFP_MOVABLE|__GFP_REPEAT)) == __GFP_MOVABLE)
- goto nopage;
+ if (is_thp_alloc(gfp_mask, order)) {
+ /*
+ * If compaction is deferred for high-order allocations, it is
+ * because sync compaction recently failed. If this is the case
+ * and the caller requested a movable allocation that does not
+ * heavily disrupt the system then fail the allocation instead
+ * of entering direct reclaim.
+ */
+ if (deferred_compaction || contended_compaction)
+ goto nopage;
+
+ /* If process is willing to reclaim/compact then wake kswapd */
+ wake_all_kswapd(order, zonelist, high_zoneidx,
+ zone_idx(preferred_zone));
+ }
/* Try direct reclaim and then allocating */
page = __alloc_pages_direct_reclaim(gfp_mask, order,
OpenPOWER on IntegriCloud