mm, compaction: simplify deferred compaction

Since commit 53853e2d2bfb ("mm, compaction: defer each zone individually
instead of preferred zone"), compaction is deferred for each zone where
sync direct compaction fails, and reset where it succeeds.  However, it
was observed that for DMA zone compaction often appeared to succeed
while subsequent allocation attempt would not, due to different outcome
of watermark check.

In order to properly defer compaction in this zone, the candidate zone
has to be passed back to __alloc_pages_direct_compact() and compaction
deferred in the zone after the allocation attempt fails.

The large source of mismatch between watermark check in compaction and
allocation was the lack of alloc_flags and classzone_idx values in
compaction, which has been fixed in the previous patch.  So with this
problem fixed, we can simplify the code by removing the candidate_zone
parameter and deferring in __alloc_pages_direct_compact().

After this patch, the compaction activity during stress-highalloc
benchmark is still somewhat increased, but it's negligible compared to the
increase that occurred without the better watermark checking.  This
suggests that it is still possible to apparently succeed in compaction but
fail to allocate, possibly due to parallel allocation activity.

[akpm@linux-foundation.org: fix build]
Suggested-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index d896765..3238ffa 100644 (file)
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -33,8 +33,7 @@ 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,
                        enum migrate_mode mode, int *contended,
-                       int alloc_flags, int classzone_idx,
-                       struct zone **candidate_zone);
+                       int alloc_flags, int classzone_idx);
 extern void 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,
@@ -105,8 +104,7 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
                        int order, gfp_t gfp_mask, nodemask_t *nodemask,
                        enum migrate_mode mode, int *contended,
-                       int alloc_flags, int classzone_idx,
-                       struct zone **candidate_zone)
+                       int alloc_flags, int classzone_idx)
 {
        return COMPACT_CONTINUE;
 }

diff --git a/mm/compaction.c b/mm/compaction.c
index 1fc6736..75f4c12 100644 (file)
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1298,15 +1298,13 @@ int sysctl_extfrag_threshold = 500;
  * @mode: The migration mode for async, sync light, or sync migration
  * @contended: Return value that determines if compaction was aborted due to
  *            need_resched() or lock contention
- * @candidate_zone: Return the zone where we think allocation should succeed
  *
  * This is the main entry point for direct page compaction.
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
                        int order, gfp_t gfp_mask, nodemask_t *nodemask,
                        enum migrate_mode mode, int *contended,
-                       int alloc_flags, int classzone_idx,
-                       struct zone **candidate_zone)
+                       int alloc_flags, int classzone_idx)
 {
        enum zone_type high_zoneidx = gfp_zone(gfp_mask);
        int may_enter_fs = gfp_mask & __GFP_FS;
@@ -1343,7 +1341,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
                /* If a normal allocation would succeed, stop compacting */
                if (zone_watermark_ok(zone, order, low_wmark_pages(zone),
                                        classzone_idx, alloc_flags)) {
-                       *candidate_zone = zone;
                        /*
                         * We think the allocation will succeed in this zone,
                         * but it is not certain, hence the false. The caller

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e32121f..edb0ce1 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2330,7 +2330,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
        int classzone_idx, int migratetype, enum migrate_mode mode,
        int *contended_compaction, bool *deferred_compaction)
 {
-       struct zone *last_compact_zone = NULL;
        unsigned long compact_result;
        struct page *page;
 
@@ -2341,8 +2340,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
        compact_result = try_to_compact_pages(zonelist, order, gfp_mask,
                                                nodemask, mode,
                                                contended_compaction,
-                                               alloc_flags, classzone_idx,
-                                               &last_compact_zone);
+                                               alloc_flags, classzone_idx);
        current->flags &= ~PF_MEMALLOC;
 
        switch (compact_result) {
@@ -2379,14 +2377,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
                return page;
        }
 
-       /*
-        * last_compact_zone is where try_to_compact_pages thought allocation
-        * should succeed, so it did not defer compaction. But here we know
-        * that it didn't succeed, so we do the defer.
-        */
-       if (last_compact_zone && mode != MIGRATE_ASYNC)
-               defer_compaction(last_compact_zone, order);
-
        /*
         * It's bad if compaction run occurs and fails. The most likely reason
         * is that pages exist, but not enough to satisfy watermarks.