Dear Kernel maintainers,
Could you please add commit id
fbc7c07ec23c040179384a1f16b62b6030eb6bdd from Linus's tree to stable
kernel trees?
Attached are the patches I prepared for stable 4.4, 4.9 and 4.14 branches.
For 4.4 and 4.19:
0001-BACKPORT-dm-bufio-fix-shrinker-scans-when-nr_to_scan-4.4-4.9.patch
For 4.14: 0001-BACKPORT-dm-bufio-fix-shrinker-scans-when-nr_to_scan-4.14.patch
Thanks,
Suren.
From 2ddf1cee10b5ccde89c5b01791e64e5a369a7694 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Date: Wed, 6 Dec 2017 09:27:30 -0800
Subject: [PATCH 1/1] BACKPORT: dm bufio: fix shrinker scans when (nr_to_scan <
retain_target)
When system is under memory pressure it is observed that dm bufio
shrinker often reclaims only one buffer per scan. This change fixes
the following two issues in dm bufio shrinker that cause this behavior:
1. ((nr_to_scan - freed) <= retain_target) condition is used to
terminate slab scan process. This assumes that nr_to_scan is equal
to the LRU size, which might not be correct because do_shrink_slab()
in vmscan.c calculates nr_to_scan using multiple inputs.
As a result when nr_to_scan is less than retain_target (64) the scan
will terminate after the first iteration, effectively reclaiming one
buffer per scan and making scans very inefficient. This hurts vmscan
performance especially because mutex is acquired/released every time
dm_bufio_shrink_scan() is called.
New implementation uses ((LRU size - freed) <= retain_target)
condition for scan termination. LRU size can be safely determined
inside __scan() because this function is called after dm_bufio_lock().
2. do_shrink_slab() uses value returned by dm_bufio_shrink_count() to
determine number of freeable objects in the slab. However dm_bufio
always retains retain_target buffers in its LRU and will terminate
a scan when this mark is reached. Therefore returning the entire LRU size
from dm_bufio_shrink_count() is misleading because that does not
represent the number of freeable objects that slab will reclaim during
a scan. Returning (LRU size - retain_target) better represents the
number of freeable objects in the slab. This way do_shrink_slab()
returns 0 when (LRU size < retain_target) and vmscan will not try to
scan this shrinker avoiding scans that will not reclaim any memory.
Test: tested using Android device running
<AOSP>/system/extras/alloc-stress that generates memory pressure
and causes intensive shrinker scans
Signed-off-by: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
(cherry picked from commit fbc7c07ec23c040179384a1f16b62b6030eb6bdd)
Change-Id: I61b9da5767644986a5815c391700a6b652e363f8
---
drivers/md/dm-bufio.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 7643f72adb1c..3ec647e8b9c6 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1554,7 +1554,8 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
int l;
struct dm_buffer *b, *tmp;
unsigned long freed = 0;
- unsigned long count = nr_to_scan;
+ unsigned long count = c->n_buffers[LIST_CLEAN] +
+ c->n_buffers[LIST_DIRTY];
unsigned long retain_target = get_retain_buffers(c);
for (l = 0; l < LIST_SIZE; l++) {
@@ -1591,6 +1592,7 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
struct dm_bufio_client *c;
unsigned long count;
+ unsigned long retain_target;
c = container_of(shrink, struct dm_bufio_client, shrinker);
if (sc->gfp_mask & __GFP_FS)
@@ -1599,8 +1601,9 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
return 0;
count = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY];
+ retain_target = get_retain_buffers(c);
dm_bufio_unlock(c);
- return count;
+ return (count < retain_target) ? 0 : (count - retain_target);
}
/*
--
2.15.1.620.gb9897f4670-goog
From 2e37e59a6f447e0b10e9e6ce604df6ee1ea5aa25 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Date: Wed, 6 Dec 2017 09:27:30 -0800
Subject: [PATCH 1/1] BACKPORT: dm bufio: fix shrinker scans when (nr_to_scan <
retain_target)
When system is under memory pressure it is observed that dm bufio
shrinker often reclaims only one buffer per scan. This change fixes
the following two issues in dm bufio shrinker that cause this behavior:
1. ((nr_to_scan - freed) <= retain_target) condition is used to
terminate slab scan process. This assumes that nr_to_scan is equal
to the LRU size, which might not be correct because do_shrink_slab()
in vmscan.c calculates nr_to_scan using multiple inputs.
As a result when nr_to_scan is less than retain_target (64) the scan
will terminate after the first iteration, effectively reclaiming one
buffer per scan and making scans very inefficient. This hurts vmscan
performance especially because mutex is acquired/released every time
dm_bufio_shrink_scan() is called.
New implementation uses ((LRU size - freed) <= retain_target)
condition for scan termination. LRU size can be safely determined
inside __scan() because this function is called after dm_bufio_lock().
2. do_shrink_slab() uses value returned by dm_bufio_shrink_count() to
determine number of freeable objects in the slab. However dm_bufio
always retains retain_target buffers in its LRU and will terminate
a scan when this mark is reached. Therefore returning the entire LRU size
from dm_bufio_shrink_count() is misleading because that does not
represent the number of freeable objects that slab will reclaim during
a scan. Returning (LRU size - retain_target) better represents the
number of freeable objects in the slab. This way do_shrink_slab()
returns 0 when (LRU size < retain_target) and vmscan will not try to
scan this shrinker avoiding scans that will not reclaim any memory.
Test: tested using Android device running
<AOSP>/system/extras/alloc-stress that generates memory pressure
and causes intensive shrinker scans
Signed-off-by: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
(cherry picked from commit fbc7c07ec23c040179384a1f16b62b6030eb6bdd)
Change-Id: I92cbd14fb2c543ff972c4cbcff4a0dfc8d975272
---
drivers/md/dm-bufio.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 8e3adcb46851..6d416fdc25cb 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1611,7 +1611,8 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
int l;
struct dm_buffer *b, *tmp;
unsigned long freed = 0;
- unsigned long count = nr_to_scan;
+ unsigned long count = c->n_buffers[LIST_CLEAN] +
+ c->n_buffers[LIST_DIRTY];
unsigned long retain_target = get_retain_buffers(c);
for (l = 0; l < LIST_SIZE; l++) {
@@ -1647,8 +1648,11 @@ static unsigned long
dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
struct dm_bufio_client *c = container_of(shrink, struct dm_bufio_client, shrinker);
+ unsigned long count = ACCESS_ONCE(c->n_buffers[LIST_CLEAN]) +
+ ACCESS_ONCE(c->n_buffers[LIST_DIRTY]);
+ unsigned long retain_target = get_retain_buffers(c);
- return ACCESS_ONCE(c->n_buffers[LIST_CLEAN]) + ACCESS_ONCE(c->n_buffers[LIST_DIRTY]);
+ return (count < retain_target) ? 0 : (count - retain_target);
}
/*
--
2.15.1.620.gb9897f4670-goog