The patch titled
     mm: vmscan: evaluate the watermarks against the correct classzone
has been added to the -mm tree.  Its filename is
     mm-vmscan-evaluate-the-watermarks-against-the-correct-classzone.patch

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/SubmitChecklist when testing your code ***

See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this

The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/

------------------------------------------------------
Subject: mm: vmscan: evaluate the watermarks against the correct classzone
From: Mel Gorman <[email protected]>

When deciding if kswapd is sleeping prematurely, the classzone is taken
into account but this is different to what balance_pgdat() and the
allocator are doing.  Specifically, the DMA zone will be checked based on
the classzone used when waking kswapd which could be for a GFP_KERNEL or
GFP_HIGHMEM request.  The lowmem reserve limit kicks in, the watermark is
not met and kswapd thinks it's sleeping prematurely keeping kswapd awake in
error.

Signed-off-by: Mel Gorman <[email protected]>
Reported-by: Pádraig Brady <[email protected]>
Tested-by: Pádraig Brady <[email protected]>
Tested-by: Andrew Lutomirski <[email protected]>
Acked-by: Rik van Riel <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: KOSAKI Motohiro <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
---

 mm/vmscan.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff -puN 
mm/vmscan.c~mm-vmscan-evaluate-the-watermarks-against-the-correct-classzone 
mm/vmscan.c
--- 
a/mm/vmscan.c~mm-vmscan-evaluate-the-watermarks-against-the-correct-classzone
+++ a/mm/vmscan.c
@@ -2344,7 +2344,7 @@ static bool sleeping_prematurely(pg_data
                }
 
                if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone),
-                                                       classzone_idx, 0))
+                                                       i, 0))
                        all_zones_ok = false;
                else
                        balanced += zone->present_pages;
_

Patches currently in -mm which might be from [email protected] are

mm-vmscan-correct-check-for-kswapd-sleeping-in-sleeping_prematurely.patch
mm-vmscan-do-not-apply-pressure-to-slab-if-we-are-not-applying-pressure-to-zone.patch
mm-vmscan-evaluate-the-watermarks-against-the-correct-classzone.patch
mm-vmscan-only-read-new_classzone_idx-from-pgdat-when-reclaiming-successfully.patch

_______________________________________________
stable mailing list
[email protected]
http://linux.kernel.org/mailman/listinfo/stable

Reply via email to