vmscan: limit direct reclaim for higher order allocations

When suffering from memory fragmentation due to unfreeable pages, THP page
faults will repeatedly try to compact memory.  Due to the unfreeable
pages, compaction fails.

Needless to say, at that point page reclaim also fails to create free
contiguous 2MB areas.  However, that doesn't stop the current code from
trying, over and over again, and freeing a minimum of 4MB (2UL <<
sc->order pages) at every single invocation.

This resulted in my 12GB system having 2-3GB free memory, a corresponding
amount of used swap and very sluggish response times.

This can be avoided by having the direct reclaim code not reclaim from
zones that already have plenty of free memory available for compaction.

If compaction still fails due to unmovable memory, doing additional
reclaim will only hurt the system, not help.

[[email protected]: change comment to explain the order check]
Signed-off-by: Rik van Riel <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Acked-by: Mel Gorman <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Reviewed-by: Minchan Kim <[email protected]>
Signed-off-by: Johannes Weiner <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

mm/vmscan.c

@@ -2125,6 +2125,22 @@ static void shrink_zones(int priority, struct zonelist *zonelist,
 				continue;
 			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;	/* Let kswapd poll it */
+			if (COMPACTION_BUILD) {
+				/*
+				 * If we already have plenty of memory
+				 * free for compaction, don't free any
+				 * more.  Even though compaction is
+				 * invoked for any non-zero order,
+				 * only frequent costly order
+				 * reclamation is disruptive enough to
+				 * become a noticable problem, like
+				 * transparent huge page allocations.
+				 */
+				if (sc->order > PAGE_ALLOC_COSTLY_ORDER &&
+					(compaction_suitable(zone, sc->order) ||
+					 compaction_deferred(zone)))
+					continue;
+			}
 			/*
 			 * This steals pages from memory cgroups over softlimit
 			 * and returns the number of reclaimed pages and