mm/page-writeback.c: do not count anon pages as dirtyable memory

commit a1c3bfb2f67ef766de03f1f56bdfff9c8595ab14 upstream.

The VM is currently heavily tuned to avoid swapping.  Whether that is
good or bad is a separate discussion, but as long as the VM won't swap
to make room for dirty cache, we can not consider anonymous pages when
calculating the amount of dirtyable memory, the baseline to which
dirty_background_ratio and dirty_ratio are applied.

A simple workload that occupies a significant size (40+%, depending on
memory layout, storage speeds etc.) of memory with anon/tmpfs pages and
uses the remainder for a streaming writer demonstrates this problem.  In
that case, the actual cache pages are a small fraction of what is
considered dirtyable overall, which results in an relatively large
portion of the cache pages to be dirtied.  As kswapd starts rotating
these, random tasks enter direct reclaim and stall on IO.

Only consider free pages and file pages dirtyable.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Tejun Heo <tj@kernel.org>
Tested-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
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@linuxfoundation.org>

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index c586679b6fefd4f8f15fe68d123295fc4d7af39f..9044769f2296df6fd52ad2ea0d653d88e3807ce2 100644 (file)
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -142,9 +142,6 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
        return x;
 }
 
-extern unsigned long global_reclaimable_pages(void);
-extern unsigned long zone_reclaimable_pages(struct zone *zone);
-
 #ifdef CONFIG_NUMA
 /*
  * Determine the per node value of a stat item. This function

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index bcd929093e64c36b849bc5495e206ad5b659e420..5a06d4cb9a3de669c4f60c6708325288559ce91b 100644 (file)
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -202,7 +202,8 @@ static unsigned long zone_dirtyable_memory(struct zone *zone)
        nr_pages = zone_page_state(zone, NR_FREE_PAGES);
        nr_pages -= min(nr_pages, zone->dirty_balance_reserve);
 
-       nr_pages += zone_reclaimable_pages(zone);
+       nr_pages += zone_page_state(zone, NR_INACTIVE_FILE);
+       nr_pages += zone_page_state(zone, NR_ACTIVE_FILE);
 
        return nr_pages;
 }
@@ -255,7 +256,8 @@ static unsigned long global_dirtyable_memory(void)
        x = global_page_state(NR_FREE_PAGES);
        x -= min(x, dirty_balance_reserve);
 
-       x += global_reclaimable_pages();
+       x += global_page_state(NR_INACTIVE_FILE);
+       x += global_page_state(NR_ACTIVE_FILE);
 
        if (!vm_highmem_is_dirtyable)
                x -= highmem_dirtyable_memory(x);

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7dbdb6afd101f12d1a766be1b13e801ed2c25fe1..43ddef3cf44fedd96ec16fb288c6ff940b47a93c 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2117,6 +2117,20 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
        return aborted_reclaim;
 }
 
+static unsigned long zone_reclaimable_pages(struct zone *zone)
+{
+       int nr;
+
+       nr = zone_page_state(zone, NR_ACTIVE_FILE) +
+            zone_page_state(zone, NR_INACTIVE_FILE);
+
+       if (get_nr_swap_pages() > 0)
+               nr += zone_page_state(zone, NR_ACTIVE_ANON) +
+                     zone_page_state(zone, NR_INACTIVE_ANON);
+
+       return nr;
+}
+
 static bool zone_reclaimable(struct zone *zone)
 {
        return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
@@ -3075,41 +3089,6 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
        wake_up_interruptible(&pgdat->kswapd_wait);
 }
 
-/*
- * The reclaimable count would be mostly accurate.
- * The less reclaimable pages may be
- * - mlocked pages, which will be moved to unevictable list when encountered
- * - mapped pages, which may require several travels to be reclaimed
- * - dirty pages, which is not "instantly" reclaimable
- */
-unsigned long global_reclaimable_pages(void)
-{
-       int nr;
-
-       nr = global_page_state(NR_ACTIVE_FILE) +
-            global_page_state(NR_INACTIVE_FILE);
-
-       if (get_nr_swap_pages() > 0)
-               nr += global_page_state(NR_ACTIVE_ANON) +
-                     global_page_state(NR_INACTIVE_ANON);
-
-       return nr;
-}
-
-unsigned long zone_reclaimable_pages(struct zone *zone)
-{
-       int nr;
-
-       nr = zone_page_state(zone, NR_ACTIVE_FILE) +
-            zone_page_state(zone, NR_INACTIVE_FILE);
-
-       if (get_nr_swap_pages() > 0)
-               nr += zone_page_state(zone, NR_ACTIVE_ANON) +
-                     zone_page_state(zone, NR_INACTIVE_ANON);
-
-       return nr;
-}
-
 #ifdef CONFIG_HIBERNATION
 /*
  * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of