All of lore.kernel.org
 help / color / mirror / Atom feed
* + zram-use-__gfp_movable-for-memory-allocation.patch added to -mm tree
@ 2016-06-01 21:41 akpm
  0 siblings, 0 replies; 2+ messages in thread
From: akpm @ 2016-06-01 21:41 UTC (permalink / raw)
  To: minchan, sergey.senozhatsky, vbabka, mm-commits


The patch titled
     Subject: zram: use __GFP_MOVABLE for memory allocation
has been added to the -mm tree.  Its filename is
     zram-use-__gfp_movable-for-memory-allocation.patch

This patch should soon appear at
    http://ozlabs.org/~akpm/mmots/broken-out/zram-use-__gfp_movable-for-memory-allocation.patch
and later at
    http://ozlabs.org/~akpm/mmotm/broken-out/zram-use-__gfp_movable-for-memory-allocation.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 ***

The -mm tree is included into linux-next and is updated
there every 3-4 working days

------------------------------------------------------
From: Minchan Kim <minchan@kernel.org>
Subject: zram: use __GFP_MOVABLE for memory allocation

Zsmalloc is ready for page migration so zram can use __GFP_MOVABLE
from now on.

I did test to see how it helps to make higher order pages.
Test scenario is as follows.

KVM guest, 1G memory, ext4 formated zram block device,

for i in `seq 1 8`;
do
        dd if=/dev/vda1 of=mnt/test$i.txt bs=128M count=1 &
done

wait `pidof dd`

for i in `seq 1 2 8`;
do
        rm -rf mnt/test$i.txt
done
fstrim -v mnt

echo "init"
cat /proc/buddyinfo

echo "compaction"
echo 1 > /proc/sys/vm/compact_memory
cat /proc/buddyinfo

old:

init
Node 0, zone      DMA    208    120     51     41     11      0      0      0      0      0      0
Node 0, zone    DMA32  16380  13777   9184   3805    789     54      3      0      0      0      0
compaction
Node 0, zone      DMA    132     82     40     39     16      2      1      0      0      0      0
Node 0, zone    DMA32   5219   5526   4969   3455   1831    677    139     15      0      0      0

new:

init
Node 0, zone      DMA    379    115     97     19      2      0      0      0      0      0      0
Node 0, zone    DMA32  18891  16774  10862   3947    637     21      0      0      0      0      0
compaction  1
Node 0, zone      DMA    214     66     87     29     10      3      0      0      0      0      0
Node 0, zone    DMA32   1612   3139   3154   2469   1745    990    384     94      7      0      0

As you can see, compaction made so many high-order pages. Yay!

Link: http://lkml.kernel.org/r/1464736881-24886-13-git-send-email-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 drivers/block/zram/zram_drv.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff -puN drivers/block/zram/zram_drv.c~zram-use-__gfp_movable-for-memory-allocation drivers/block/zram/zram_drv.c
--- a/drivers/block/zram/zram_drv.c~zram-use-__gfp_movable-for-memory-allocation
+++ a/drivers/block/zram/zram_drv.c
@@ -738,7 +738,8 @@ compress_again:
 		handle = zs_malloc(meta->mem_pool, clen,
 				__GFP_KSWAPD_RECLAIM |
 				__GFP_NOWARN |
-				__GFP_HIGHMEM);
+				__GFP_HIGHMEM |
+				__GFP_MOVABLE);
 	if (!handle) {
 		zcomp_stream_put(zram->comp);
 		zstrm = NULL;
@@ -746,7 +747,8 @@ compress_again:
 		atomic64_inc(&zram->stats.writestall);
 
 		handle = zs_malloc(meta->mem_pool, clen,
-				GFP_NOIO | __GFP_HIGHMEM);
+				GFP_NOIO | __GFP_HIGHMEM |
+				__GFP_MOVABLE);
 		if (handle)
 			goto compress_again;
 
_

Patches currently in -mm which might be from minchan@kernel.org are

mm-use-put_page-to-free-page-instead-of-putback_lru_page.patch
mm-migrate-support-non-lru-movable-page-migration.patch
mm-balloon-use-general-non-lru-movable-page-feature.patch
zsmalloc-keep-max_object-in-size_class.patch
zsmalloc-use-bit_spin_lock.patch
zsmalloc-use-accessor.patch
zsmalloc-factor-page-chain-functionality-out.patch
zsmalloc-introduce-zspage-structure.patch
zsmalloc-separate-free_zspage-from-putback_zspage.patch
zsmalloc-use-freeobj-for-index.patch
zsmalloc-page-migration-support.patch
zram-use-__gfp_movable-for-memory-allocation.patch


^ permalink raw reply	[flat|nested] 2+ messages in thread

* + zram-use-__gfp_movable-for-memory-allocation.patch added to -mm tree
@ 2016-03-30 23:11 akpm
  0 siblings, 0 replies; 2+ messages in thread
From: akpm @ 2016-03-30 23:11 UTC (permalink / raw)
  To: minchan, aquini, chan.jeong, gi-oh.kim, hughd, iamjoonsoo.kim,
	koct9i, mgorman, n-horiguchi, riel, rknize, sangseok.lee,
	sergey.senozhatsky, vbabka, viro, xuyiping, mm-commits


The patch titled
     Subject: zram: use __GFP_MOVABLE for memory allocation
has been added to the -mm tree.  Its filename is
     zram-use-__gfp_movable-for-memory-allocation.patch

This patch should soon appear at
    http://ozlabs.org/~akpm/mmots/broken-out/zram-use-__gfp_movable-for-memory-allocation.patch
and later at
    http://ozlabs.org/~akpm/mmotm/broken-out/zram-use-__gfp_movable-for-memory-allocation.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 ***

The -mm tree is included into linux-next and is updated
there every 3-4 working days

------------------------------------------------------
From: Minchan Kim <minchan@kernel.org>
Subject: zram: use __GFP_MOVABLE for memory allocation

Zsmalloc is ready for page migration so zram can use __GFP_MOVABLE
from now on.

I did test to see how it helps to make higher order pages.
Test scenario is as follows.

KVM guest, 1G memory, ext4 formated zram block device,

for i in `seq 1 8`;
do
        dd if=/dev/vda1 of=mnt/test$i.txt bs=128M count=1 &
done

wait `pidof dd`

for i in `seq 1 2 8`;
do
        rm -rf mnt/test$i.txt
done
fstrim -v mnt

echo "init"
cat /proc/buddyinfo

echo "compaction"
echo 1 > /proc/sys/vm/compact_memory
cat /proc/buddyinfo

old:

init
Node 0, zone      DMA    208    120     51     41     11      0      0      0      0      0      0
Node 0, zone    DMA32  16380  13777   9184   3805    789     54      3      0      0      0      0
compaction
Node 0, zone      DMA    132     82     40     39     16      2      1      0      0      0      0
Node 0, zone    DMA32   5219   5526   4969   3455   1831    677    139     15      0      0      0

new:

init
Node 0, zone      DMA    379    115     97     19      2      0      0      0      0      0      0
Node 0, zone    DMA32  18891  16774  10862   3947    637     21      0      0      0      0      0
compaction  1
Node 0, zone      DMA    214     66     87     29     10      3      0      0      0      0      0
Node 0, zone    DMA32   1612   3139   3154   2469   1745    990    384     94      7      0      0

As you can see, compaction made so many high-order pages. Yay!

Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Rafael Aquini <aquini@redhat.com>
Cc: Russ Knize <rknize@motorola.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Gioh Kim <gi-oh.kim@profitbricks.com>
Cc: Sangseok Lee <sangseok.lee@lge.com>
Cc: Chan Gyun Jeong <chan.jeong@lge.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: YiPing Xu <xuyiping@hisilicon.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 drivers/block/zram/zram_drv.c |    3 ++-
 mm/zsmalloc.c                 |    2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff -puN drivers/block/zram/zram_drv.c~zram-use-__gfp_movable-for-memory-allocation drivers/block/zram/zram_drv.c
--- a/drivers/block/zram/zram_drv.c~zram-use-__gfp_movable-for-memory-allocation
+++ a/drivers/block/zram/zram_drv.c
@@ -514,7 +514,8 @@ static struct zram_meta *zram_meta_alloc
 		goto out_error;
 	}
 
-	meta->mem_pool = zs_create_pool(pool_name, GFP_NOIO | __GFP_HIGHMEM);
+	meta->mem_pool = zs_create_pool(pool_name, GFP_NOIO|__GFP_HIGHMEM
+						|__GFP_MOVABLE);
 	if (!meta->mem_pool) {
 		pr_err("Error creating memory pool\n");
 		goto out_error;
diff -puN mm/zsmalloc.c~zram-use-__gfp_movable-for-memory-allocation mm/zsmalloc.c
--- a/mm/zsmalloc.c~zram-use-__gfp_movable-for-memory-allocation
+++ a/mm/zsmalloc.c
@@ -308,7 +308,7 @@ static void destroy_handle_cache(struct
 static unsigned long alloc_handle(struct zs_pool *pool)
 {
 	return (unsigned long)kmem_cache_alloc(pool->handle_cachep,
-		pool->flags & ~__GFP_HIGHMEM);
+		pool->flags & ~(__GFP_HIGHMEM|__GFP_MOVABLE));
 }
 
 static void free_handle(struct zs_pool *pool, unsigned long handle)
_

Patches currently in -mm which might be from minchan@kernel.org are

zsmalloc-use-first_page-rather-than-page.patch
zsmalloc-clean-up-many-bug_on.patch
zsmalloc-reordering-function-parameter.patch
zsmalloc-remove-unused-pool-param-in-obj_free.patch
mm-use-put_page-to-free-page-instead-of-putback_lru_page.patch
mm-compaction-support-non-lru-movable-page-migration.patch
mm-add-non-lru-movable-page-support-document.patch
mm-balloon-use-general-movable-page-feature-into-balloon.patch
zsmalloc-keep-max_object-in-size_class.patch
zsmalloc-squeeze-inuse-into-page-mapping.patch
zsmalloc-remove-page_mapcount_reset.patch
zsmalloc-squeeze-freelist-into-page-mapping.patch
zsmalloc-move-struct-zs_meta-from-mapping-to-freelist.patch
zsmalloc-factor-page-chain-functionality-out.patch
zsmalloc-separate-free_zspage-from-putback_zspage.patch
zsmalloc-zs_compact-refactoring.patch
zsmalloc-migrate-head-page-of-zspage.patch
zsmalloc-use-single-linked-list-for-page-chain.patch
zsmalloc-migrate-tail-pages-in-zspage.patch
zram-use-__gfp_movable-for-memory-allocation.patch


^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2016-06-01 21:41 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-06-01 21:41 + zram-use-__gfp_movable-for-memory-allocation.patch added to -mm tree akpm
  -- strict thread matches above, loose matches on Subject: below --
2016-03-30 23:11 akpm

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.