vmscan: do not unconditionally treat zones that fail zone_reclaim() as full

commit fa5e084e43eb14c14942027e1e2e894aeed96097 upstream.

vmscan: do not unconditionally treat zones that fail zone_reclaim() as full

On NUMA machines, the administrator can configure zone_reclaim_mode that
is a more targetted form of direct reclaim.  On machines with large NUMA
distances for example, a zone_reclaim_mode defaults to 1 meaning that
clean unmapped pages will be reclaimed if the zone watermarks are not
being met.  The problem is that zone_reclaim() failing at all means the
zone gets marked full.

This can cause situations where a zone is usable, but is being skipped
because it has been considered full.  Take a situation where a large tmpfs
mount is occuping a large percentage of memory overall.  The pages do not
get cleaned or reclaimed by zone_reclaim(), but the zone gets marked full
and the zonelist cache considers them not worth trying in the future.

This patch makes zone_reclaim() return more fine-grained information about
what occured when zone_reclaim() failued.  The zone only gets marked full
if it really is unreclaimable.  If it's a case that the scan did not occur
or if enough pages were not reclaimed with the limited reclaim_mode, then
the zone is simply skipped.

There is a side-effect to this patch.  Currently, if zone_reclaim()
successfully reclaimed SWAP_CLUSTER_MAX, an allocation attempt would go
ahead.  With this patch applied, zone watermarks are rechecked after
zone_reclaim() does some work.

This bug was introduced by commit 9276b1bc96a132f4068fdee00983c532f43d3a26
("memory page_alloc zonelist caching speedup") way back in 2.6.19 when the
zonelist_cache was introduced.  It was not intended that zone_reclaim()
aggressively consider the zone to be full when it failed as full direct
reclaim can still be an option.  Due to the age of the bug, it should be
considered a -stable candidate.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: Wu Fengguang <fengguang.wu@intel.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/mm/internal.h b/mm/internal.h
index 987bb03fbdd88f33f36986b6ecbb33f02a62c6e2..090c2671d0260e92fec2e6c5aa595ab1aef74aa3 100644 (file)
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -284,4 +284,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                     unsigned long start, int len, int flags,
                     struct page **pages, struct vm_area_struct **vmas);
 
+#define ZONE_RECLAIM_NOSCAN    -2
+#define ZONE_RECLAIM_FULL      -1
+#define ZONE_RECLAIM_SOME      0
+#define ZONE_RECLAIM_SUCCESS   1
 #endif

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f82038391ca71ee062e617eec808756390fb6e5b..480907cc28beb83494308544e777a30300b06da2 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1420,20 +1420,38 @@ zonelist_scan:
 
                if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
                        unsigned long mark;
+                       int ret;
                        if (alloc_flags & ALLOC_WMARK_MIN)
                                mark = zone->pages_min;
                        else if (alloc_flags & ALLOC_WMARK_LOW)
                                mark = zone->pages_low;
                        else
                                mark = zone->pages_high;
-                       if (!zone_watermark_ok(zone, order, mark,
-                                   classzone_idx, alloc_flags)) {
-                               if (!zone_reclaim_mode ||
-                                   !zone_reclaim(zone, gfp_mask, order))
+
+                       if (zone_watermark_ok(zone, order, mark,
+                                   classzone_idx, alloc_flags))
+                               goto try_this_zone;
+
+                       if (zone_reclaim_mode == 0)
+                               goto this_zone_full;
+
+                       ret = zone_reclaim(zone, gfp_mask, order);
+                       switch (ret) {
+                       case ZONE_RECLAIM_NOSCAN:
+                               /* did not scan */
+                               goto try_next_zone;
+                       case ZONE_RECLAIM_FULL:
+                               /* scanned but unreclaimable */
+                               goto this_zone_full;
+                       default:
+                               /* did we reclaim enough */
+                               if (!zone_watermark_ok(zone, order, mark,
+                                               classzone_idx, alloc_flags))
                                        goto this_zone_full;
                        }
                }
 
+try_this_zone:
                page = buffered_rmqueue(preferred_zone, zone, order, gfp_mask);
                if (page)
                        break;

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2500b01e7a781d6ebd93317fe9c002d4cd85fe7a..b3e39b58bbf51a7a119b042bbe7d2f5e1f20b4d0 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2426,16 +2426,16 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
         */
        if (zone_pagecache_reclaimable(zone) <= zone->min_unmapped_pages &&
            zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
-               return 0;
+               return ZONE_RECLAIM_FULL;
 
        if (zone_is_all_unreclaimable(zone))
-               return 0;
+               return ZONE_RECLAIM_FULL;
 
        /*
         * Do not scan if the allocation should not be delayed.
         */
        if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC))
-                       return 0;
+               return ZONE_RECLAIM_NOSCAN;
 
        /*
         * Only run zone reclaim on the local zone or on zones that do not
@@ -2445,10 +2445,11 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
         */
        node_id = zone_to_nid(zone);
        if (node_state(node_id, N_CPU) && node_id != numa_node_id())
-               return 0;
+               return ZONE_RECLAIM_NOSCAN;
 
        if (zone_test_and_set_flag(zone, ZONE_RECLAIM_LOCKED))
-               return 0;
+               return ZONE_RECLAIM_NOSCAN;
+
        ret = __zone_reclaim(zone, gfp_mask, order);
        zone_clear_flag(zone, ZONE_RECLAIM_LOCKED);