* [PATCH v4 01/31] super: fix calculation of shrinkable objects for small numbers
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
@ 2013-04-26 23:18 ` Glauber Costa
2013-04-30 13:03 ` Mel Gorman
2013-04-26 23:18 ` [PATCH v4 02/31] vmscan: take at least one pass with shrinkers Glauber Costa
` (30 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:18 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Dave Chinner,
Theodore Ts'o, Al Viro
The sysctl knob sysctl_vfs_cache_pressure is used to determine which
percentage of the shrinkable objects in our cache we should actively try
to shrink.
It works great in situations in which we have many objects (at least
more than 100), because the aproximation errors will be negligible. But
if this is not the case, specially when total_objects < 100, we may end
up concluding that we have no objects at all (total / 100 = 0, if total
< 100).
This is certainly not the biggest killer in the world, but may matter in
very low kernel memory situations.
[ v2: fix it for all occurrences of sysctl_vfs_cache_pressure ]
Signed-off-by: Glauber Costa <glommer@openvz.org>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
CC: Dave Chinner <david@fromorbit.com>
CC: "Theodore Ts'o" <tytso@mit.edu>
CC: Al Viro <viro@zeniv.linux.org.uk>
---
fs/gfs2/glock.c | 2 +-
fs/gfs2/quota.c | 2 +-
fs/mbcache.c | 2 +-
fs/nfs/dir.c | 2 +-
fs/quota/dquot.c | 5 ++---
fs/super.c | 14 +++++++-------
fs/xfs/xfs_qm.c | 2 +-
include/linux/dcache.h | 4 ++++
8 files changed, 18 insertions(+), 15 deletions(-)
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 3b9e178..2119516 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1463,7 +1463,7 @@ static int gfs2_shrink_glock_memory(struct shrinker *shrink,
gfs2_scan_glock_lru(sc->nr_to_scan);
}
- return (atomic_read(&lru_count) / 100) * sysctl_vfs_cache_pressure;
+ return vfs_pressure_ratio(atomic_read(&lru_count));
}
static struct shrinker glock_shrinker = {
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index c7c840e..5c14206 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -114,7 +114,7 @@ int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc)
spin_unlock(&qd_lru_lock);
out:
- return (atomic_read(&qd_lru_count) * sysctl_vfs_cache_pressure) / 100;
+ return vfs_pressure_ratio(atomic_read(&qd_lru_count));
}
static u64 qd2index(struct gfs2_quota_data *qd)
diff --git a/fs/mbcache.c b/fs/mbcache.c
index 8c32ef3..5eb0476 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -189,7 +189,7 @@ mb_cache_shrink_fn(struct shrinker *shrink, struct shrink_control *sc)
list_for_each_entry_safe(entry, tmp, &free_list, e_lru_list) {
__mb_cache_entry_forget(entry, gfp_mask);
}
- return (count / 100) * sysctl_vfs_cache_pressure;
+ return vfs_pressure_ratio(count);
}
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index e093e73..54d7c47 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1998,7 +1998,7 @@ remove_lru_entry:
}
spin_unlock(&nfs_access_lru_lock);
nfs_access_free_list(&head);
- return (atomic_long_read(&nfs_access_nr_entries) / 100) * sysctl_vfs_cache_pressure;
+ return vfs_pressure_ratio(atomic_long_read(&nfs_access_nr_entries));
}
static void __nfs_access_zap_cache(struct nfs_inode *nfsi, struct list_head *head)
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 3e64169..762b09c 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -719,9 +719,8 @@ static int shrink_dqcache_memory(struct shrinker *shrink,
prune_dqcache(nr);
spin_unlock(&dq_list_lock);
}
- return ((unsigned)
- percpu_counter_read_positive(&dqstats.counter[DQST_FREE_DQUOTS])
- /100) * sysctl_vfs_cache_pressure;
+ return vfs_pressure_ratio(
+ percpu_counter_read_positive(&dqstats.counter[DQST_FREE_DQUOTS]));
}
static struct shrinker dqcache_shrinker = {
diff --git a/fs/super.c b/fs/super.c
index 7465d43..2a37fd6 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -82,13 +82,13 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
int inodes;
/* proportion the scan between the caches */
- dentries = (sc->nr_to_scan * sb->s_nr_dentry_unused) /
- total_objects;
- inodes = (sc->nr_to_scan * sb->s_nr_inodes_unused) /
- total_objects;
+ dentries = mult_frac(sc->nr_to_scan, sb->s_nr_dentry_unused,
+ total_objects);
+ inodes = mult_frac(sc->nr_to_scan, sb->s_nr_inodes_unused,
+ total_objects);
if (fs_objects)
- fs_objects = (sc->nr_to_scan * fs_objects) /
- total_objects;
+ fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
+ total_objects);
/*
* prune the dcache first as the icache is pinned by it, then
* prune the icache, followed by the filesystem specific caches
@@ -104,7 +104,7 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
sb->s_nr_inodes_unused + fs_objects;
}
- total_objects = (total_objects / 100) * sysctl_vfs_cache_pressure;
+ total_objects = vfs_pressure_ratio(total_objects);
drop_super(sb);
return total_objects;
}
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index d0acb4e..82604c3 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1568,7 +1568,7 @@ xfs_qm_shake(
}
out:
- return (qi->qi_lru_count / 100) * sysctl_vfs_cache_pressure;
+ return vfs_pressure_ratio(qi->qi_lru_count);
}
/*
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 1a6bb81..4d24a12 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -411,4 +411,8 @@ static inline bool d_mountpoint(struct dentry *dentry)
extern int sysctl_vfs_cache_pressure;
+static inline unsigned long vfs_pressure_ratio(unsigned long val)
+{
+ return mult_frac(val, sysctl_vfs_cache_pressure, 100);
+}
#endif /* __LINUX_DCACHE_H */
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 01/31] super: fix calculation of shrinkable objects for small numbers
2013-04-26 23:18 ` [PATCH v4 01/31] super: fix calculation of shrinkable objects for small numbers Glauber Costa
@ 2013-04-30 13:03 ` Mel Gorman
0 siblings, 0 replies; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 13:03 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner, Theodore Ts'o,
Al Viro
On Sat, Apr 27, 2013 at 03:18:57AM +0400, Glauber Costa wrote:
> The sysctl knob sysctl_vfs_cache_pressure is used to determine which
> percentage of the shrinkable objects in our cache we should actively try
> to shrink.
>
> It works great in situations in which we have many objects (at least
> more than 100), because the aproximation errors will be negligible. But
> if this is not the case, specially when total_objects < 100, we may end
> up concluding that we have no objects at all (total / 100 = 0, if total
> < 100).
>
> This is certainly not the biggest killer in the world, but may matter in
> very low kernel memory situations.
>
> [ v2: fix it for all occurrences of sysctl_vfs_cache_pressure ]
>
> Signed-off-by: Glauber Costa <glommer@openvz.org>
> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
> CC: Dave Chinner <david@fromorbit.com>
> CC: "Theodore Ts'o" <tytso@mit.edu>
> CC: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Mel Gorman <mgorman@suse.de>
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 02/31] vmscan: take at least one pass with shrinkers
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
2013-04-26 23:18 ` [PATCH v4 01/31] super: fix calculation of shrinkable objects for small numbers Glauber Costa
@ 2013-04-26 23:18 ` Glauber Costa
2013-04-30 13:22 ` Mel Gorman
2013-04-26 23:18 ` [PATCH v4 03/31] dcache: convert dentry_stat.nr_unused to per-cpu counters Glauber Costa
` (29 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:18 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Theodore Ts'o,
Al Viro
In very low free kernel memory situations, it may be the case that we
have less objects to free than our initial batch size. If this is the
case, it is better to shrink those, and open space for the new workload
then to keep them and fail the new allocations.
More specifically, this happens because we encode this in a loop with
the condition: "while (total_scan >= batch_size)". So if we are in such
a case, we'll not even enter the loop.
This patch modifies turns it into a do () while {} loop, that will
guarantee that we scan it at least once, while keeping the behaviour
exactly the same for the cases in which total_scan > batch_size.
Signed-off-by: Glauber Costa <glommer@openvz.org>
Reviewed-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
CC: "Theodore Ts'o" <tytso@mit.edu>
CC: Al Viro <viro@zeniv.linux.org.uk>
---
mm/vmscan.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index fa6a853..f9d2fba 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -281,7 +281,7 @@ unsigned long shrink_slab(struct shrink_control *shrink,
nr_pages_scanned, lru_pages,
max_pass, delta, total_scan);
- while (total_scan >= batch_size) {
+ do {
int nr_before;
nr_before = do_shrinker_shrink(shrinker, shrink, 0);
@@ -295,7 +295,7 @@ unsigned long shrink_slab(struct shrink_control *shrink,
total_scan -= batch_size;
cond_resched();
- }
+ } while (total_scan >= batch_size);
/*
* move the unused scan count back into the shrinker in a
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 02/31] vmscan: take at least one pass with shrinkers
2013-04-26 23:18 ` [PATCH v4 02/31] vmscan: take at least one pass with shrinkers Glauber Costa
@ 2013-04-30 13:22 ` Mel Gorman
2013-04-30 13:31 ` Glauber Costa
0 siblings, 1 reply; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 13:22 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Theodore Ts'o, Al Viro
On Sat, Apr 27, 2013 at 03:18:58AM +0400, Glauber Costa wrote:
> In very low free kernel memory situations, it may be the case that we
> have less objects to free than our initial batch size. If this is the
> case, it is better to shrink those, and open space for the new workload
> then to keep them and fail the new allocations.
>
> More specifically, this happens because we encode this in a loop with
> the condition: "while (total_scan >= batch_size)". So if we are in such
> a case, we'll not even enter the loop.
>
> This patch modifies turns it into a do () while {} loop, that will
> guarantee that we scan it at least once, while keeping the behaviour
> exactly the same for the cases in which total_scan > batch_size.
>
> Signed-off-by: Glauber Costa <glommer@openvz.org>
> Reviewed-by: Dave Chinner <david@fromorbit.com>
> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
> CC: "Theodore Ts'o" <tytso@mit.edu>
> CC: Al Viro <viro@zeniv.linux.org.uk>
There are two cases where this *might* cause a problem and worth keeping
an eye out for.
The first is that it's possible for caches to shrink to zero where before
the last SHRINK_SLAB objects would often be protected for any slab. If
this is an inode or dentry cache and there are very few objects then it's
possible that objects will be reclaimed before they can be used by the
process allocating them.
The second is if any of the shrinker users have generally a small number
of large objects then any shrink of them may chunk out even the live
objects. This will depend on the quality of the shrinker implementation
but it might expose problems that were hidden before.
Neither potential issue are the fault of your patch so I'm not going
to nack. However, bear in mind that we should watch out for bugs where
processes stall making forward progress because they are constantly
reallocating inodes or bugs like graphics stalls because their objects
keep getting fully reclaimed as only a small number exist.
I suspect that you need this patch because it's very reasonable for a memcg
to have slabs with tiny numbers of objects you want to reclaim. However,
if my imagined scenarios are a problem in reality then you'll need to
revert this patch and special case for memcg. Alternatively you could
shrink in two passes. The first which never shrinks a slab below
shrinker->batch *but* if all slabs are below that threshold then shrink
the slab to 0.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 02/31] vmscan: take at least one pass with shrinkers
2013-04-30 13:22 ` Mel Gorman
@ 2013-04-30 13:31 ` Glauber Costa
2013-04-30 15:37 ` Mel Gorman
0 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-30 13:31 UTC (permalink / raw)
To: Mel Gorman
Cc: Glauber Costa, linux-mm, cgroups, Andrew Morton, Greg Thelen,
kamezawa.hiroyu, Michal Hocko, Johannes Weiner, Theodore Ts'o,
Al Viro
On 04/30/2013 05:22 PM, Mel Gorman wrote:
> On Sat, Apr 27, 2013 at 03:18:58AM +0400, Glauber Costa wrote:
>> In very low free kernel memory situations, it may be the case that we
>> have less objects to free than our initial batch size. If this is the
>> case, it is better to shrink those, and open space for the new workload
>> then to keep them and fail the new allocations.
>>
>> More specifically, this happens because we encode this in a loop with
>> the condition: "while (total_scan >= batch_size)". So if we are in such
>> a case, we'll not even enter the loop.
>>
>> This patch modifies turns it into a do () while {} loop, that will
>> guarantee that we scan it at least once, while keeping the behaviour
>> exactly the same for the cases in which total_scan > batch_size.
>>
>> Signed-off-by: Glauber Costa <glommer@openvz.org>
>> Reviewed-by: Dave Chinner <david@fromorbit.com>
>> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
>> CC: "Theodore Ts'o" <tytso@mit.edu>
>> CC: Al Viro <viro@zeniv.linux.org.uk>
>
> There are two cases where this *might* cause a problem and worth keeping
> an eye out for.
>
Any test case that you envision that could help bringing those issues
forward should they exist ? (aside from getting it into upstream trees
early?)
>
> Neither potential issue are the fault of your patch so I'm not going
> to nack. However, bear in mind that we should watch out for bugs where
> processes stall making forward progress because they are constantly
> reallocating inodes or bugs like graphics stalls because their objects
> keep getting fully reclaimed as only a small number exist.
>
> I suspect that you need this patch because it's very reasonable for a memcg
> to have slabs with tiny numbers of objects you want to reclaim.
Precisely.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 02/31] vmscan: take at least one pass with shrinkers
2013-04-30 13:31 ` Glauber Costa
@ 2013-04-30 15:37 ` Mel Gorman
2013-05-07 13:35 ` Glauber Costa
0 siblings, 1 reply; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 15:37 UTC (permalink / raw)
To: Glauber Costa
Cc: Glauber Costa, linux-mm, cgroups, Andrew Morton, Greg Thelen,
kamezawa.hiroyu, Michal Hocko, Johannes Weiner, Theodore Ts'o,
Al Viro
On Tue, Apr 30, 2013 at 05:31:32PM +0400, Glauber Costa wrote:
> On 04/30/2013 05:22 PM, Mel Gorman wrote:
> > On Sat, Apr 27, 2013 at 03:18:58AM +0400, Glauber Costa wrote:
> >> In very low free kernel memory situations, it may be the case that we
> >> have less objects to free than our initial batch size. If this is the
> >> case, it is better to shrink those, and open space for the new workload
> >> then to keep them and fail the new allocations.
> >>
> >> More specifically, this happens because we encode this in a loop with
> >> the condition: "while (total_scan >= batch_size)". So if we are in such
> >> a case, we'll not even enter the loop.
> >>
> >> This patch modifies turns it into a do () while {} loop, that will
> >> guarantee that we scan it at least once, while keeping the behaviour
> >> exactly the same for the cases in which total_scan > batch_size.
> >>
> >> Signed-off-by: Glauber Costa <glommer@openvz.org>
> >> Reviewed-by: Dave Chinner <david@fromorbit.com>
> >> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
> >> CC: "Theodore Ts'o" <tytso@mit.edu>
> >> CC: Al Viro <viro@zeniv.linux.org.uk>
> >
> > There are two cases where this *might* cause a problem and worth keeping
> > an eye out for.
> >
>
> Any test case that you envision that could help bringing those issues
> forward should they exist ? (aside from getting it into upstream trees
> early?)
>
hmm.
fsmark multi-threaded in a small-memory machine with a small number of
very large files greater than the size of physical memory might trigger
it. There should be a small number of inodes active so less than the 128
that would have been ignored before the patch. As the files are larger
than memory, kswapd will be awake and calling shrinkers so if the
shrinker is really discarding active inodes then the performance will
degrade.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 02/31] vmscan: take at least one pass with shrinkers
2013-04-30 15:37 ` Mel Gorman
@ 2013-05-07 13:35 ` Glauber Costa
0 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-05-07 13:35 UTC (permalink / raw)
To: Mel Gorman
Cc: Glauber Costa, linux-mm, cgroups, Andrew Morton, Greg Thelen,
kamezawa.hiroyu, Michal Hocko, Johannes Weiner, Theodore Ts'o,
Al Viro
On 04/30/2013 07:37 PM, Mel Gorman wrote:
> On Tue, Apr 30, 2013 at 05:31:32PM +0400, Glauber Costa wrote:
>> On 04/30/2013 05:22 PM, Mel Gorman wrote:
>>> On Sat, Apr 27, 2013 at 03:18:58AM +0400, Glauber Costa wrote:
>>>> In very low free kernel memory situations, it may be the case that we
>>>> have less objects to free than our initial batch size. If this is the
>>>> case, it is better to shrink those, and open space for the new workload
>>>> then to keep them and fail the new allocations.
>>>>
>>>> More specifically, this happens because we encode this in a loop with
>>>> the condition: "while (total_scan >= batch_size)". So if we are in such
>>>> a case, we'll not even enter the loop.
>>>>
>>>> This patch modifies turns it into a do () while {} loop, that will
>>>> guarantee that we scan it at least once, while keeping the behaviour
>>>> exactly the same for the cases in which total_scan > batch_size.
>>>>
>>>> Signed-off-by: Glauber Costa <glommer@openvz.org>
>>>> Reviewed-by: Dave Chinner <david@fromorbit.com>
>>>> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
>>>> CC: "Theodore Ts'o" <tytso@mit.edu>
>>>> CC: Al Viro <viro@zeniv.linux.org.uk>
>>>
>>> There are two cases where this *might* cause a problem and worth keeping
>>> an eye out for.
>>>
>>
>> Any test case that you envision that could help bringing those issues
>> forward should they exist ? (aside from getting it into upstream trees
>> early?)
>>
>
> hmm.
>
> fsmark multi-threaded in a small-memory machine with a small number of
> very large files greater than the size of physical memory might trigger
> it. There should be a small number of inodes active so less than the 128
> that would have been ignored before the patch. As the files are larger
> than memory, kswapd will be awake and calling shrinkers so if the
> shrinker is really discarding active inodes then the performance will
> degrade.
>
FYI: The weird behavior you found on benchmarks is due to this patch.
The problem is twofold:
first, by always scanning we fail to differentiate from the 0 condition,
which means skip it. We should have at least 1 object in the counter to
scan.
second, nr_to_scan continues being a batch. So when count returns, say,
3 objects, the shrinker will still try to free, say, 128 objects. And in
some situations, it might very well succeed.
I have already fixed this, and as soon as I finish merging all your
suggestions I will send an updated version.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 03/31] dcache: convert dentry_stat.nr_unused to per-cpu counters
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
2013-04-26 23:18 ` [PATCH v4 01/31] super: fix calculation of shrinkable objects for small numbers Glauber Costa
2013-04-26 23:18 ` [PATCH v4 02/31] vmscan: take at least one pass with shrinkers Glauber Costa
@ 2013-04-26 23:18 ` Glauber Costa
2013-04-30 13:37 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 04/31] dentry: move to per-sb LRU locks Glauber Costa
` (28 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:18 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
From: Dave Chinner <dchinner@redhat.com>
Before we split up the dcache_lru_lock, the unused dentry counter
needs to be made independent of the global dcache_lru_lock. Convert
it to per-cpu counters to do this.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/dcache.c | 17 ++++++++++++++---
1 file changed, 14 insertions(+), 3 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index e689268..8df1cd9 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -118,6 +118,7 @@ struct dentry_stat_t dentry_stat = {
};
static DEFINE_PER_CPU(unsigned int, nr_dentry);
+static DEFINE_PER_CPU(unsigned int, nr_dentry_unused);
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
static int get_nr_dentry(void)
@@ -129,10 +130,20 @@ static int get_nr_dentry(void)
return sum < 0 ? 0 : sum;
}
+static int get_nr_dentry_unused(void)
+{
+ int i;
+ int sum = 0;
+ for_each_possible_cpu(i)
+ sum += per_cpu(nr_dentry_unused, i);
+ return sum < 0 ? 0 : sum;
+}
+
int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
size_t *lenp, loff_t *ppos)
{
dentry_stat.nr_dentry = get_nr_dentry();
+ dentry_stat.nr_unused = get_nr_dentry_unused();
return proc_dointvec(table, write, buffer, lenp, ppos);
}
#endif
@@ -312,7 +323,7 @@ static void dentry_lru_add(struct dentry *dentry)
spin_lock(&dcache_lru_lock);
list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
dentry->d_sb->s_nr_dentry_unused++;
- dentry_stat.nr_unused++;
+ this_cpu_inc(nr_dentry_unused);
spin_unlock(&dcache_lru_lock);
}
}
@@ -322,7 +333,7 @@ static void __dentry_lru_del(struct dentry *dentry)
list_del_init(&dentry->d_lru);
dentry->d_flags &= ~DCACHE_SHRINK_LIST;
dentry->d_sb->s_nr_dentry_unused--;
- dentry_stat.nr_unused--;
+ this_cpu_dec(nr_dentry_unused);
}
/*
@@ -360,7 +371,7 @@ static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list)
if (list_empty(&dentry->d_lru)) {
list_add_tail(&dentry->d_lru, list);
dentry->d_sb->s_nr_dentry_unused++;
- dentry_stat.nr_unused++;
+ this_cpu_inc(nr_dentry_unused);
} else {
list_move_tail(&dentry->d_lru, list);
}
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 03/31] dcache: convert dentry_stat.nr_unused to per-cpu counters
2013-04-26 23:18 ` [PATCH v4 03/31] dcache: convert dentry_stat.nr_unused to per-cpu counters Glauber Costa
@ 2013-04-30 13:37 ` Mel Gorman
0 siblings, 0 replies; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 13:37 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
On Sat, Apr 27, 2013 at 03:18:59AM +0400, Glauber Costa wrote:
> From: Dave Chinner <dchinner@redhat.com>
>
> Before we split up the dcache_lru_lock, the unused dentry counter
> needs to be made independent of the global dcache_lru_lock. Convert
> it to per-cpu counters to do this.
>
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> ---
> fs/dcache.c | 17 ++++++++++++++---
> 1 file changed, 14 insertions(+), 3 deletions(-)
>
> diff --git a/fs/dcache.c b/fs/dcache.c
> index e689268..8df1cd9 100644
> --- a/fs/dcache.c
> +++ b/fs/dcache.c
> @@ -118,6 +118,7 @@ struct dentry_stat_t dentry_stat = {
> };
>
> static DEFINE_PER_CPU(unsigned int, nr_dentry);
> +static DEFINE_PER_CPU(unsigned int, nr_dentry_unused);
>
> #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
> static int get_nr_dentry(void)
> @@ -129,10 +130,20 @@ static int get_nr_dentry(void)
> return sum < 0 ? 0 : sum;
> }
>
> +static int get_nr_dentry_unused(void)
> +{
> + int i;
> + int sum = 0;
> + for_each_possible_cpu(i)
> + sum += per_cpu(nr_dentry_unused, i);
> + return sum < 0 ? 0 : sum;
> +}
> +
I was going to raise questions on the use of for_each_possible_cpu() and
ask why it was not for_each_online_cpu() but I see now that it has been
discussed already -- it's to avoid lost counters from offlined CPUs
without having to cope with CPU hotplug just to keep a proc handler
happy.
A comment either here or in the changelog saying that
for_each_possible_cpu() is deliberate would not hurt in case someone
tries to "fix" this but it's no big deal so
Acked-by: Mel Gorman <mgorman@suse.de>
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 04/31] dentry: move to per-sb LRU locks
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (2 preceding siblings ...)
2013-04-26 23:18 ` [PATCH v4 03/31] dcache: convert dentry_stat.nr_unused to per-cpu counters Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-30 14:01 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 05/31] dcache: remove dentries from LRU before putting on dispose list Glauber Costa
` (27 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
From: Dave Chinner <dchinner@redhat.com>
With the dentry LRUs being per-sb structures, there is no real need
for a global dentry_lru_lock. The locking can be made more
fine-grained by moving to a per-sb LRU lock, isolating the LRU
operations of different filesytsems completely from each other.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/dcache.c | 37 ++++++++++++++++++-------------------
fs/super.c | 1 +
include/linux/fs.h | 4 +++-
3 files changed, 22 insertions(+), 20 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index 8df1cd9..434468d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -48,7 +48,7 @@
* - the dcache hash table
* s_anon bl list spinlock protects:
* - the s_anon list (see __d_drop)
- * dcache_lru_lock protects:
+ * dentry->d_sb->s_dentry_lru_lock protects:
* - the dcache lru lists and counters
* d_lock protects:
* - d_flags
@@ -63,7 +63,7 @@
* Ordering:
* dentry->d_inode->i_lock
* dentry->d_lock
- * dcache_lru_lock
+ * dentry->d_sb->s_dentry_lru_lock
* dcache_hash_bucket lock
* s_anon lock
*
@@ -81,7 +81,6 @@
int sysctl_vfs_cache_pressure __read_mostly = 100;
EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
-static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lru_lock);
__cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
EXPORT_SYMBOL(rename_lock);
@@ -320,11 +319,11 @@ static void dentry_unlink_inode(struct dentry * dentry)
static void dentry_lru_add(struct dentry *dentry)
{
if (list_empty(&dentry->d_lru)) {
- spin_lock(&dcache_lru_lock);
+ spin_lock(&dentry->d_sb->s_dentry_lru_lock);
list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
dentry->d_sb->s_nr_dentry_unused++;
this_cpu_inc(nr_dentry_unused);
- spin_unlock(&dcache_lru_lock);
+ spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
}
}
@@ -342,9 +341,9 @@ static void __dentry_lru_del(struct dentry *dentry)
static void dentry_lru_del(struct dentry *dentry)
{
if (!list_empty(&dentry->d_lru)) {
- spin_lock(&dcache_lru_lock);
+ spin_lock(&dentry->d_sb->s_dentry_lru_lock);
__dentry_lru_del(dentry);
- spin_unlock(&dcache_lru_lock);
+ spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
}
}
@@ -359,15 +358,15 @@ static void dentry_lru_prune(struct dentry *dentry)
if (dentry->d_flags & DCACHE_OP_PRUNE)
dentry->d_op->d_prune(dentry);
- spin_lock(&dcache_lru_lock);
+ spin_lock(&dentry->d_sb->s_dentry_lru_lock);
__dentry_lru_del(dentry);
- spin_unlock(&dcache_lru_lock);
+ spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
}
}
static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list)
{
- spin_lock(&dcache_lru_lock);
+ spin_lock(&dentry->d_sb->s_dentry_lru_lock);
if (list_empty(&dentry->d_lru)) {
list_add_tail(&dentry->d_lru, list);
dentry->d_sb->s_nr_dentry_unused++;
@@ -375,7 +374,7 @@ static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list)
} else {
list_move_tail(&dentry->d_lru, list);
}
- spin_unlock(&dcache_lru_lock);
+ spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
}
/**
@@ -853,14 +852,14 @@ void prune_dcache_sb(struct super_block *sb, int count)
LIST_HEAD(tmp);
relock:
- spin_lock(&dcache_lru_lock);
+ spin_lock(&sb->s_dentry_lru_lock);
while (!list_empty(&sb->s_dentry_lru)) {
dentry = list_entry(sb->s_dentry_lru.prev,
struct dentry, d_lru);
BUG_ON(dentry->d_sb != sb);
if (!spin_trylock(&dentry->d_lock)) {
- spin_unlock(&dcache_lru_lock);
+ spin_unlock(&sb->s_dentry_lru_lock);
cpu_relax();
goto relock;
}
@@ -876,11 +875,11 @@ relock:
if (!--count)
break;
}
- cond_resched_lock(&dcache_lru_lock);
+ cond_resched_lock(&sb->s_dentry_lru_lock);
}
if (!list_empty(&referenced))
list_splice(&referenced, &sb->s_dentry_lru);
- spin_unlock(&dcache_lru_lock);
+ spin_unlock(&sb->s_dentry_lru_lock);
shrink_dentry_list(&tmp);
}
@@ -896,14 +895,14 @@ void shrink_dcache_sb(struct super_block *sb)
{
LIST_HEAD(tmp);
- spin_lock(&dcache_lru_lock);
+ spin_lock(&sb->s_dentry_lru_lock);
while (!list_empty(&sb->s_dentry_lru)) {
list_splice_init(&sb->s_dentry_lru, &tmp);
- spin_unlock(&dcache_lru_lock);
+ spin_unlock(&sb->s_dentry_lru_lock);
shrink_dentry_list(&tmp);
- spin_lock(&dcache_lru_lock);
+ spin_lock(&sb->s_dentry_lru_lock);
}
- spin_unlock(&dcache_lru_lock);
+ spin_unlock(&sb->s_dentry_lru_lock);
}
EXPORT_SYMBOL(shrink_dcache_sb);
diff --git a/fs/super.c b/fs/super.c
index 2a37fd6..0be75fb 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -182,6 +182,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
INIT_HLIST_BL_HEAD(&s->s_anon);
INIT_LIST_HEAD(&s->s_inodes);
INIT_LIST_HEAD(&s->s_dentry_lru);
+ spin_lock_init(&s->s_dentry_lru_lock);
INIT_LIST_HEAD(&s->s_inode_lru);
spin_lock_init(&s->s_inode_lru_lock);
INIT_LIST_HEAD(&s->s_mounts);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8d47c9a..df3174d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1263,7 +1263,9 @@ struct super_block {
struct list_head s_files;
#endif
struct list_head s_mounts; /* list of mounts; _not_ for fs use */
- /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */
+
+ /* s_dentry_lru_lock protects s_dentry_lru and s_nr_dentry_unused */
+ spinlock_t s_dentry_lru_lock ____cacheline_aligned_in_smp;
struct list_head s_dentry_lru; /* unused dentry lru */
int s_nr_dentry_unused; /* # of dentry on lru */
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 04/31] dentry: move to per-sb LRU locks
2013-04-26 23:19 ` [PATCH v4 04/31] dentry: move to per-sb LRU locks Glauber Costa
@ 2013-04-30 14:01 ` Mel Gorman
0 siblings, 0 replies; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 14:01 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
On Sat, Apr 27, 2013 at 03:19:00AM +0400, Glauber Costa wrote:
> From: Dave Chinner <dchinner@redhat.com>
>
> With the dentry LRUs being per-sb structures, there is no real need
> for a global dentry_lru_lock. The locking can be made more
> fine-grained by moving to a per-sb LRU lock, isolating the LRU
> operations of different filesytsems completely from each other.
>
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Mel Gorman <mgorman@suse.de>
But one comment below
> @@ -81,7 +81,6 @@
> int sysctl_vfs_cache_pressure __read_mostly = 100;
> EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
>
> -static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lru_lock);
> __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
>
> EXPORT_SYMBOL(rename_lock);
It made sense to cache-align these locks because you don't want two
unrelated global locks causing each other to bounce but ....
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 8d47c9a..df3174d 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -1263,7 +1263,9 @@ struct super_block {
> struct list_head s_files;
> #endif
> struct list_head s_mounts; /* list of mounts; _not_ for fs use */
> - /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */
> +
> + /* s_dentry_lru_lock protects s_dentry_lru and s_nr_dentry_unused */
> + spinlock_t s_dentry_lru_lock ____cacheline_aligned_in_smp;
> struct list_head s_dentry_lru; /* unused dentry lru */
> int s_nr_dentry_unused; /* # of dentry on lru */
>
It's less compelling to align within a structure like this. If move the
lock and the fields it protects to a read-mostly section then there
should be no need to cache-align the lock, create a large hole in the
struct and grow the size of struct super_block unnecessarily.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 05/31] dcache: remove dentries from LRU before putting on dispose list
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (3 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 04/31] dentry: move to per-sb LRU locks Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-30 14:14 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 06/31] mm: new shrinker API Glauber Costa
` (26 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner, Glauber Costa
From: Dave Chinner <dchinner@redhat.com>
One of the big problems with modifying the way the dcache shrinker
and LRU implementation works is that the LRU is abused in several
ways. One of these is shrink_dentry_list().
Basically, we can move a dentry off the LRU onto a different list
without doing any accounting changes, and then use dentry_lru_prune()
to remove it from what-ever list it is now on to do the LRU
accounting at that point.
This makes it -really hard- to change the LRU implementation. The
use of the per-sb LRU lock serialises movement of the dentries
between the different lists and the removal of them, and this is the
only reason that it works. If we want to break up the dentry LRU
lock and lists into, say, per-node lists, we remove the only
serialisation that allows this lru list/dispose list abuse to work.
To make this work effectively, the dispose list has to be isolated
from the LRU list - dentries have to be removed from the LRU
*before* being placed on the dispose list. This means that the LRU
accounting and isolation is completed before disposal is started,
and that means we can change the LRU implementation freely in
future.
This means that dentries *must* be marked with DCACHE_SHRINK_LIST
when they are placed on the dispose list so that we don't think that
parent dentries found in try_prune_one_dentry() are on the LRU when
the are actually on the dispose list. This would result in
accounting the dentry to the LRU a second time. Hence
dentry_lru_prune() has to handle the DCACHE_SHRINK_LIST case
differently because the dentry isn't on the LRU list.
[ v2: don't decrement nr unused twice, spotted by Sha Zhengju ]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
---
fs/dcache.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++++++++---------
1 file changed, 62 insertions(+), 10 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index 434468d..2c99c1d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -330,7 +330,6 @@ static void dentry_lru_add(struct dentry *dentry)
static void __dentry_lru_del(struct dentry *dentry)
{
list_del_init(&dentry->d_lru);
- dentry->d_flags &= ~DCACHE_SHRINK_LIST;
dentry->d_sb->s_nr_dentry_unused--;
this_cpu_dec(nr_dentry_unused);
}
@@ -340,6 +339,8 @@ static void __dentry_lru_del(struct dentry *dentry)
*/
static void dentry_lru_del(struct dentry *dentry)
{
+ BUG_ON(dentry->d_flags & DCACHE_SHRINK_LIST);
+
if (!list_empty(&dentry->d_lru)) {
spin_lock(&dentry->d_sb->s_dentry_lru_lock);
__dentry_lru_del(dentry);
@@ -351,28 +352,42 @@ static void dentry_lru_del(struct dentry *dentry)
* Remove a dentry that is unreferenced and about to be pruned
* (unhashed and destroyed) from the LRU, and inform the file system.
* This wrapper should be called _prior_ to unhashing a victim dentry.
+ *
+ * Check that the dentry really is on the LRU as it may be on a private dispose
+ * list and in that case we do not want to call the generic LRU removal
+ * functions. This typically happens when shrink_dcache_sb() clears the LRU in
+ * one go and then try_prune_one_dentry() walks back up the parent chain finding
+ * dentries that are also on the dispose list.
*/
static void dentry_lru_prune(struct dentry *dentry)
{
if (!list_empty(&dentry->d_lru)) {
+
if (dentry->d_flags & DCACHE_OP_PRUNE)
dentry->d_op->d_prune(dentry);
- spin_lock(&dentry->d_sb->s_dentry_lru_lock);
- __dentry_lru_del(dentry);
- spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
+ if ((dentry->d_flags & DCACHE_SHRINK_LIST))
+ list_del_init(&dentry->d_lru);
+ else {
+ spin_lock(&dentry->d_sb->s_dentry_lru_lock);
+ __dentry_lru_del(dentry);
+ spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
+ }
+ dentry->d_flags &= ~DCACHE_SHRINK_LIST;
}
}
static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list)
{
+ BUG_ON(dentry->d_flags & DCACHE_SHRINK_LIST);
+
spin_lock(&dentry->d_sb->s_dentry_lru_lock);
if (list_empty(&dentry->d_lru)) {
list_add_tail(&dentry->d_lru, list);
- dentry->d_sb->s_nr_dentry_unused++;
- this_cpu_inc(nr_dentry_unused);
} else {
list_move_tail(&dentry->d_lru, list);
+ dentry->d_sb->s_nr_dentry_unused--;
+ this_cpu_dec(nr_dentry_unused);
}
spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
}
@@ -814,12 +829,18 @@ static void shrink_dentry_list(struct list_head *list)
}
/*
+ * The dispose list is isolated and dentries are not accounted
+ * to the LRU here, so we can simply remove it from the list
+ * here regardless of whether it is referenced or not.
+ */
+ list_del_init(&dentry->d_lru);
+
+ /*
* We found an inuse dentry which was not removed from
- * the LRU because of laziness during lookup. Do not free
- * it - just keep it off the LRU list.
+ * the LRU because of laziness during lookup. Do not free it.
*/
if (dentry->d_count) {
- dentry_lru_del(dentry);
+ dentry->d_flags &= ~DCACHE_SHRINK_LIST;
spin_unlock(&dentry->d_lock);
continue;
}
@@ -871,6 +892,8 @@ relock:
} else {
list_move_tail(&dentry->d_lru, &tmp);
dentry->d_flags |= DCACHE_SHRINK_LIST;
+ this_cpu_dec(nr_dentry_unused);
+ sb->s_nr_dentry_unused--;
spin_unlock(&dentry->d_lock);
if (!--count)
break;
@@ -884,6 +907,27 @@ relock:
shrink_dentry_list(&tmp);
}
+/*
+ * Mark all the dentries as on being the dispose list so we don't think they are
+ * still on the LRU if we try to kill them from ascending the parent chain in
+ * try_prune_one_dentry() rather than directly from the dispose list.
+ */
+static void
+shrink_dcache_list(
+ struct list_head *dispose)
+{
+ struct dentry *dentry;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(dentry, dispose, d_lru) {
+ spin_lock(&dentry->d_lock);
+ dentry->d_flags |= DCACHE_SHRINK_LIST;
+ spin_unlock(&dentry->d_lock);
+ }
+ rcu_read_unlock();
+ shrink_dentry_list(dispose);
+}
+
/**
* shrink_dcache_sb - shrink dcache for a superblock
* @sb: superblock
@@ -898,8 +942,16 @@ void shrink_dcache_sb(struct super_block *sb)
spin_lock(&sb->s_dentry_lru_lock);
while (!list_empty(&sb->s_dentry_lru)) {
list_splice_init(&sb->s_dentry_lru, &tmp);
+
+ /*
+ * account for removal here so we don't need to handle it later
+ * even though the dentry is no longer on the lru list.
+ */
+ this_cpu_sub(nr_dentry_unused, sb->s_nr_dentry_unused);
+ sb->s_nr_dentry_unused = 0;
+
spin_unlock(&sb->s_dentry_lru_lock);
- shrink_dentry_list(&tmp);
+ shrink_dcache_list(&tmp);
spin_lock(&sb->s_dentry_lru_lock);
}
spin_unlock(&sb->s_dentry_lru_lock);
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 05/31] dcache: remove dentries from LRU before putting on dispose list
2013-04-26 23:19 ` [PATCH v4 05/31] dcache: remove dentries from LRU before putting on dispose list Glauber Costa
@ 2013-04-30 14:14 ` Mel Gorman
0 siblings, 0 replies; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 14:14 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
On Sat, Apr 27, 2013 at 03:19:01AM +0400, Glauber Costa wrote:
> From: Dave Chinner <dchinner@redhat.com>
>
> One of the big problems with modifying the way the dcache shrinker
> and LRU implementation works is that the LRU is abused in several
> ways. One of these is shrink_dentry_list().
>
> Basically, we can move a dentry off the LRU onto a different list
> without doing any accounting changes, and then use dentry_lru_prune()
> to remove it from what-ever list it is now on to do the LRU
> accounting at that point.
>
> This makes it -really hard- to change the LRU implementation. The
> use of the per-sb LRU lock serialises movement of the dentries
> between the different lists and the removal of them, and this is the
> only reason that it works. If we want to break up the dentry LRU
> lock and lists into, say, per-node lists, we remove the only
> serialisation that allows this lru list/dispose list abuse to work.
>
> To make this work effectively, the dispose list has to be isolated
> from the LRU list - dentries have to be removed from the LRU
> *before* being placed on the dispose list. This means that the LRU
> accounting and isolation is completed before disposal is started,
> and that means we can change the LRU implementation freely in
> future.
>
> This means that dentries *must* be marked with DCACHE_SHRINK_LIST
> when they are placed on the dispose list so that we don't think that
> parent dentries found in try_prune_one_dentry() are on the LRU when
> the are actually on the dispose list. This would result in
> accounting the dentry to the LRU a second time. Hence
> dentry_lru_prune() has to handle the DCACHE_SHRINK_LIST case
> differently because the dentry isn't on the LRU list.
>
> [ v2: don't decrement nr unused twice, spotted by Sha Zhengju ]
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Signed-off-by: Glauber Costa <glommer@openvz.org>
Acked-by: Mel Gorman <mgorman@suse.de>
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 06/31] mm: new shrinker API
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (4 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 05/31] dcache: remove dentries from LRU before putting on dispose list Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-30 14:40 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 07/31] shrinker: convert superblock shrinkers to new API Glauber Costa
` (25 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
From: Dave Chinner <dchinner@redhat.com>
The current shrinker callout API uses an a single shrinker call for
multiple functions. To determine the function, a special magical
value is passed in a parameter to change the behaviour. This
complicates the implementation and return value specification for
the different behaviours.
Separate the two different behaviours into separate operations, one
to return a count of freeable objects in the cache, and another to
scan a certain number of objects in the cache for freeing. In
defining these new operations, ensure the return values and
resultant behaviours are clearly defined and documented.
Modify shrink_slab() to use the new API and implement the callouts
for all the existing shrinkers.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
include/linux/shrinker.h | 37 +++++++++++++++++++++++++----------
mm/vmscan.c | 51 +++++++++++++++++++++++++++++++-----------------
2 files changed, 60 insertions(+), 28 deletions(-)
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index ac6b8ee..4f59615 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -4,31 +4,47 @@
/*
* This struct is used to pass information from page reclaim to the shrinkers.
* We consolidate the values for easier extention later.
+ *
+ * The 'gfpmask' refers to the allocation we are currently trying to
+ * fulfil.
+ *
+ * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is
+ * querying the cache size, so a fastpath for that case is appropriate.
*/
struct shrink_control {
gfp_t gfp_mask;
/* How many slab objects shrinker() should scan and try to reclaim */
- unsigned long nr_to_scan;
+ long nr_to_scan;
};
/*
* A callback you can register to apply pressure to ageable caches.
*
- * 'sc' is passed shrink_control which includes a count 'nr_to_scan'
- * and a 'gfpmask'. It should look through the least-recently-used
- * 'nr_to_scan' entries and attempt to free them up. It should return
- * the number of objects which remain in the cache. If it returns -1, it means
- * it cannot do any scanning at this time (eg. there is a risk of deadlock).
+ * @shrink() should look through the least-recently-used 'nr_to_scan' entries
+ * and attempt to free them up. It should return the number of objects which
+ * remain in the cache. If it returns -1, it means it cannot do any scanning at
+ * this time (eg. there is a risk of deadlock).
*
- * The 'gfpmask' refers to the allocation we are currently trying to
- * fulfil.
+ * @count_objects should return the number of freeable items in the cache. If
+ * there are no objects to free or the number of freeable items cannot be
+ * determined, it should return 0. No deadlock checks should be done during the
+ * count callback - the shrinker relies on aggregating scan counts that couldn't
+ * be executed due to potential deadlocks to be run at a later call when the
+ * deadlock condition is no longer pending.
*
- * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is
- * querying the cache size, so a fastpath for that case is appropriate.
+ * @scan_objects will only be called if @count_objects returned a positive
+ * value for the number of freeable objects. The callout should scan the cache
+ * and attemp to free items from the cache. It should then return the number of
+ * objects freed during the scan, or -1 if progress cannot be made due to
+ * potential deadlocks. If -1 is returned, then no further attempts to call the
+ * @scan_objects will be made from the current reclaim context.
*/
struct shrinker {
int (*shrink)(struct shrinker *, struct shrink_control *sc);
+ long (*count_objects)(struct shrinker *, struct shrink_control *sc);
+ long (*scan_objects)(struct shrinker *, struct shrink_control *sc);
+
int seeks; /* seeks to recreate an obj */
long batch; /* reclaim batch size, 0 = default */
@@ -36,6 +52,7 @@ struct shrinker {
struct list_head list;
atomic_long_t nr_in_batch; /* objs pending delete */
};
+
#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
extern void register_shrinker(struct shrinker *);
extern void unregister_shrinker(struct shrinker *);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f9d2fba..ca3f690 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -205,19 +205,19 @@ static inline int do_shrinker_shrink(struct shrinker *shrinker,
*
* Returns the number of slab objects which we shrunk.
*/
-unsigned long shrink_slab(struct shrink_control *shrink,
+unsigned long shrink_slab(struct shrink_control *sc,
unsigned long nr_pages_scanned,
unsigned long lru_pages)
{
struct shrinker *shrinker;
- unsigned long ret = 0;
+ unsigned long freed = 0;
if (nr_pages_scanned == 0)
nr_pages_scanned = SWAP_CLUSTER_MAX;
if (!down_read_trylock(&shrinker_rwsem)) {
/* Assume we'll be able to shrink next time */
- ret = 1;
+ freed = 1;
goto out;
}
@@ -225,13 +225,16 @@ unsigned long shrink_slab(struct shrink_control *shrink,
unsigned long long delta;
long total_scan;
long max_pass;
- int shrink_ret = 0;
long nr;
long new_nr;
long batch_size = shrinker->batch ? shrinker->batch
: SHRINK_BATCH;
- max_pass = do_shrinker_shrink(shrinker, shrink, 0);
+ if (shrinker->scan_objects) {
+ max_pass = shrinker->count_objects(shrinker, sc);
+ WARN_ON(max_pass < 0);
+ } else
+ max_pass = do_shrinker_shrink(shrinker, sc, 0);
if (max_pass <= 0)
continue;
@@ -248,8 +251,8 @@ unsigned long shrink_slab(struct shrink_control *shrink,
do_div(delta, lru_pages + 1);
total_scan += delta;
if (total_scan < 0) {
- printk(KERN_ERR "shrink_slab: %pF negative objects to "
- "delete nr=%ld\n",
+ printk(KERN_ERR
+ "shrink_slab: %pF negative objects to delete nr=%ld\n",
shrinker->shrink, total_scan);
total_scan = max_pass;
}
@@ -277,20 +280,32 @@ unsigned long shrink_slab(struct shrink_control *shrink,
if (total_scan > max_pass * 2)
total_scan = max_pass * 2;
- trace_mm_shrink_slab_start(shrinker, shrink, nr,
+ trace_mm_shrink_slab_start(shrinker, sc, nr,
nr_pages_scanned, lru_pages,
max_pass, delta, total_scan);
do {
- int nr_before;
+ long ret;
+
+ if (shrinker->scan_objects) {
+ sc->nr_to_scan = batch_size;
+ ret = shrinker->scan_objects(shrinker, sc);
+
+ if (ret == -1)
+ break;
+ freed += ret;
+ } else {
+ int nr_before;
+
+ nr_before = do_shrinker_shrink(shrinker, sc, 0);
+ ret = do_shrinker_shrink(shrinker, sc,
+ batch_size);
+ if (ret == -1)
+ break;
+ if (ret < nr_before)
+ freed += nr_before - ret;
+ }
- nr_before = do_shrinker_shrink(shrinker, shrink, 0);
- shrink_ret = do_shrinker_shrink(shrinker, shrink,
- batch_size);
- if (shrink_ret == -1)
- break;
- if (shrink_ret < nr_before)
- ret += nr_before - shrink_ret;
count_vm_events(SLABS_SCANNED, batch_size);
total_scan -= batch_size;
@@ -308,12 +323,12 @@ unsigned long shrink_slab(struct shrink_control *shrink,
else
new_nr = atomic_long_read(&shrinker->nr_in_batch);
- trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
+ trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr);
}
up_read(&shrinker_rwsem);
out:
cond_resched();
- return ret;
+ return freed;
}
static inline int is_page_cache_freeable(struct page *page)
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 06/31] mm: new shrinker API
2013-04-26 23:19 ` [PATCH v4 06/31] mm: new shrinker API Glauber Costa
@ 2013-04-30 14:40 ` Mel Gorman
2013-04-30 15:03 ` Glauber Costa
0 siblings, 1 reply; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 14:40 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
On Sat, Apr 27, 2013 at 03:19:02AM +0400, Glauber Costa wrote:
> From: Dave Chinner <dchinner@redhat.com>
>
> The current shrinker callout API uses an a single shrinker call for
> multiple functions. To determine the function, a special magical
> value is passed in a parameter to change the behaviour. This
> complicates the implementation and return value specification for
> the different behaviours.
>
> Separate the two different behaviours into separate operations, one
> to return a count of freeable objects in the cache, and another to
> scan a certain number of objects in the cache for freeing. In
> defining these new operations, ensure the return values and
> resultant behaviours are clearly defined and documented.
>
> Modify shrink_slab() to use the new API and implement the callouts
> for all the existing shrinkers.
>
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
Glauber's signed-off appears to be missing.
> ---
> include/linux/shrinker.h | 37 +++++++++++++++++++++++++----------
> mm/vmscan.c | 51 +++++++++++++++++++++++++++++++-----------------
> 2 files changed, 60 insertions(+), 28 deletions(-)
>
> diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
> index ac6b8ee..4f59615 100644
> --- a/include/linux/shrinker.h
> +++ b/include/linux/shrinker.h
> @@ -4,31 +4,47 @@
> /*
> * This struct is used to pass information from page reclaim to the shrinkers.
> * We consolidate the values for easier extention later.
> + *
> + * The 'gfpmask' refers to the allocation we are currently trying to
> + * fulfil.
> + *
> + * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is
> + * querying the cache size, so a fastpath for that case is appropriate.
> */
> struct shrink_control {
> gfp_t gfp_mask;
>
> /* How many slab objects shrinker() should scan and try to reclaim */
> - unsigned long nr_to_scan;
> + long nr_to_scan;
> };
>
As unreasonable as it is, it means that this API can no longer can handle
more than "long" objects. While we'd never hit the limit in practice
unless shrinkers are insane or the objects represent something that is
not stored in memory, it still looks odd to allow an API to potentially
say it has a negative number of objects and as as far as I can gather,
it's just so the shrinkers can return -1.
Why not leave this as unsigned long and return SHRINK_UNCOUNTABLE
count_objects if the number of freeable items cannot be determined and
SHRINK_UNFREEABLE if scan_objects cannot free without risk of deadlock.
Underneath, SHRINK_* would be defined as ULONG_MAX.
> /*
> * A callback you can register to apply pressure to ageable caches.
> *
> - * 'sc' is passed shrink_control which includes a count 'nr_to_scan'
> - * and a 'gfpmask'. It should look through the least-recently-used
> - * 'nr_to_scan' entries and attempt to free them up. It should return
> - * the number of objects which remain in the cache. If it returns -1, it means
> - * it cannot do any scanning at this time (eg. there is a risk of deadlock).
> + * @shrink() should look through the least-recently-used 'nr_to_scan' entries
> + * and attempt to free them up. It should return the number of objects which
> + * remain in the cache. If it returns -1, it means it cannot do any scanning at
> + * this time (eg. there is a risk of deadlock).
> *
> - * The 'gfpmask' refers to the allocation we are currently trying to
> - * fulfil.
> + * @count_objects should return the number of freeable items in the cache. If
> + * there are no objects to free or the number of freeable items cannot be
> + * determined, it should return 0. No deadlock checks should be done during the
> + * count callback - the shrinker relies on aggregating scan counts that couldn't
> + * be executed due to potential deadlocks to be run at a later call when the
> + * deadlock condition is no longer pending.
> *
> - * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is
> - * querying the cache size, so a fastpath for that case is appropriate.
> + * @scan_objects will only be called if @count_objects returned a positive
> + * value for the number of freeable objects. The callout should scan the cache
> + * and attemp to free items from the cache. It should then return the number of
s/attemp/attempt/
> + * objects freed during the scan, or -1 if progress cannot be made due to
> + * potential deadlocks. If -1 is returned, then no further attempts to call the
> + * @scan_objects will be made from the current reclaim context.
> */
> struct shrinker {
> int (*shrink)(struct shrinker *, struct shrink_control *sc);
> + long (*count_objects)(struct shrinker *, struct shrink_control *sc);
> + long (*scan_objects)(struct shrinker *, struct shrink_control *sc);
> +
Similarly these would return unsigned long
> int seeks; /* seeks to recreate an obj */
> long batch; /* reclaim batch size, 0 = default */
>
> @@ -36,6 +52,7 @@ struct shrinker {
> struct list_head list;
> atomic_long_t nr_in_batch; /* objs pending delete */
> };
> +
> #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
> extern void register_shrinker(struct shrinker *);
> extern void unregister_shrinker(struct shrinker *);
Just random whitespace change there.
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index f9d2fba..ca3f690 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -205,19 +205,19 @@ static inline int do_shrinker_shrink(struct shrinker *shrinker,
> *
> * Returns the number of slab objects which we shrunk.
> */
> -unsigned long shrink_slab(struct shrink_control *shrink,
> +unsigned long shrink_slab(struct shrink_control *sc,
> unsigned long nr_pages_scanned,
> unsigned long lru_pages)
> {
In every other part of vmscan.c, sc is a scan_control but here it is a
shrink_control. That's an unfortunate reuse of a name that cause me to
scratch my head later when I looked at the tracepoint modification.
shrinkc? It's a crappy suggestion but if you think of a better name than
sc then a rename would be nice.
> struct shrinker *shrinker;
> - unsigned long ret = 0;
> + unsigned long freed = 0;
>
> if (nr_pages_scanned == 0)
> nr_pages_scanned = SWAP_CLUSTER_MAX;
>
> if (!down_read_trylock(&shrinker_rwsem)) {
> /* Assume we'll be able to shrink next time */
> - ret = 1;
> + freed = 1;
> goto out;
> }
>
> @@ -225,13 +225,16 @@ unsigned long shrink_slab(struct shrink_control *shrink,
> unsigned long long delta;
> long total_scan;
> long max_pass;
> - int shrink_ret = 0;
> long nr;
> long new_nr;
> long batch_size = shrinker->batch ? shrinker->batch
> : SHRINK_BATCH;
>
> - max_pass = do_shrinker_shrink(shrinker, shrink, 0);
> + if (shrinker->scan_objects) {
> + max_pass = shrinker->count_objects(shrinker, sc);
> + WARN_ON(max_pass < 0);
> + } else
> + max_pass = do_shrinker_shrink(shrinker, sc, 0);
> if (max_pass <= 0)
> continue;
>
This had me scratching my head but looking ahead you introduce the new API,
convert everything over and then kick this away. Presumably this is for
bisect safely and so the patch is not a megapatch of hurt.
Generally I saw no problems, this was mostly on the nit-picking end of
the spectrum and a count/scan pair of APIs is a lot nicer to look at
than the current interface.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 06/31] mm: new shrinker API
2013-04-30 14:40 ` Mel Gorman
@ 2013-04-30 15:03 ` Glauber Costa
2013-04-30 15:32 ` Mel Gorman
0 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-30 15:03 UTC (permalink / raw)
To: Mel Gorman
Cc: Glauber Costa, linux-mm, cgroups, Andrew Morton, Greg Thelen,
kamezawa.hiroyu, Michal Hocko, Johannes Weiner, Dave Chinner
On 04/30/2013 06:40 PM, Mel Gorman wrote:
> On Sat, Apr 27, 2013 at 03:19:02AM +0400, Glauber Costa wrote:
>> From: Dave Chinner <dchinner@redhat.com>
>>
>> The current shrinker callout API uses an a single shrinker call for
>> multiple functions. To determine the function, a special magical
>> value is passed in a parameter to change the behaviour. This
>> complicates the implementation and return value specification for
>> the different behaviours.
>>
>> Separate the two different behaviours into separate operations, one
>> to return a count of freeable objects in the cache, and another to
>> scan a certain number of objects in the cache for freeing. In
>> defining these new operations, ensure the return values and
>> resultant behaviours are clearly defined and documented.
>>
>> Modify shrink_slab() to use the new API and implement the callouts
>> for all the existing shrinkers.
>>
>> Signed-off-by: Dave Chinner <dchinner@redhat.com>
>
> Glauber's signed-off appears to be missing.
>
I didn't sign all patches, just the ones I have changed.
Should I sign them all ?
>
> As unreasonable as it is, it means that this API can no longer can handle
> more than "long" objects. While we'd never hit the limit in practice
> unless shrinkers are insane or the objects represent something that is
> not stored in memory, it still looks odd to allow an API to potentially
> say it has a negative number of objects and as as far as I can gather,
> it's just so the shrinkers can return -1.
>
> Why not leave this as unsigned long and return SHRINK_UNCOUNTABLE
> count_objects if the number of freeable items cannot be determined and
> SHRINK_UNFREEABLE if scan_objects cannot free without risk of deadlock.
> Underneath, SHRINK_* would be defined as ULONG_MAX.
>
I believe you have already saw the reason for that in the following patch.
Do you still have a problem with this ?
>
>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>> index f9d2fba..ca3f690 100644
>> --- a/mm/vmscan.c
>> +++ b/mm/vmscan.c
>> @@ -205,19 +205,19 @@ static inline int do_shrinker_shrink(struct shrinker *shrinker,
>> *
>> * Returns the number of slab objects which we shrunk.
>> */
>> -unsigned long shrink_slab(struct shrink_control *shrink,
>> +unsigned long shrink_slab(struct shrink_control *sc,
>> unsigned long nr_pages_scanned,
>> unsigned long lru_pages)
>> {
>
> In every other part of vmscan.c, sc is a scan_control but here it is a
> shrink_control. That's an unfortunate reuse of a name that cause me to
> scratch my head later when I looked at the tracepoint modification.
> shrinkc? It's a crappy suggestion but if you think of a better name than
> sc then a rename would be nice.
>
I am all in favor of being explicit. How about we rename sc to...
shrink_control ?
>>
>> - max_pass = do_shrinker_shrink(shrinker, shrink, 0);
>> + if (shrinker->scan_objects) {
>> + max_pass = shrinker->count_objects(shrinker, sc);
>> + WARN_ON(max_pass < 0);
>> + } else
>> + max_pass = do_shrinker_shrink(shrinker, sc, 0);
>> if (max_pass <= 0)
>> continue;
>>
>
> This had me scratching my head but looking ahead you introduce the new API,
> convert everything over and then kick this away. Presumably this is for
> bisect safely and so the patch is not a megapatch of hurt.
>
Yes, it is.
> Generally I saw no problems, this was mostly on the nit-picking end of
> the spectrum and a count/scan pair of APIs is a lot nicer to look at
> than the current interface.
>
Great!
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 06/31] mm: new shrinker API
2013-04-30 15:03 ` Glauber Costa
@ 2013-04-30 15:32 ` Mel Gorman
0 siblings, 0 replies; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 15:32 UTC (permalink / raw)
To: Glauber Costa
Cc: Glauber Costa, linux-mm, cgroups, Andrew Morton, Greg Thelen,
kamezawa.hiroyu, Michal Hocko, Johannes Weiner, Dave Chinner
On Tue, Apr 30, 2013 at 07:03:05PM +0400, Glauber Costa wrote:
> On 04/30/2013 06:40 PM, Mel Gorman wrote:
> > On Sat, Apr 27, 2013 at 03:19:02AM +0400, Glauber Costa wrote:
> >> From: Dave Chinner <dchinner@redhat.com>
> >>
> >> The current shrinker callout API uses an a single shrinker call for
> >> multiple functions. To determine the function, a special magical
> >> value is passed in a parameter to change the behaviour. This
> >> complicates the implementation and return value specification for
> >> the different behaviours.
> >>
> >> Separate the two different behaviours into separate operations, one
> >> to return a count of freeable objects in the cache, and another to
> >> scan a certain number of objects in the cache for freeing. In
> >> defining these new operations, ensure the return values and
> >> resultant behaviours are clearly defined and documented.
> >>
> >> Modify shrink_slab() to use the new API and implement the callouts
> >> for all the existing shrinkers.
> >>
> >> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> >
> > Glauber's signed-off appears to be missing.
> >
> I didn't sign all patches, just the ones I have changed.
> Should I sign them all ?
>
Yes because you are on the submission path and form part of the chain of
trust. Andrew does not change every patch he signs off, neither does Greg
(-stable) or Linus (mainline).
> >
> > As unreasonable as it is, it means that this API can no longer can handle
> > more than "long" objects. While we'd never hit the limit in practice
> > unless shrinkers are insane or the objects represent something that is
> > not stored in memory, it still looks odd to allow an API to potentially
> > say it has a negative number of objects and as as far as I can gather,
> > it's just so the shrinkers can return -1.
> >
> > Why not leave this as unsigned long and return SHRINK_UNCOUNTABLE
> > count_objects if the number of freeable items cannot be determined and
> > SHRINK_UNFREEABLE if scan_objects cannot free without risk of deadlock.
> > Underneath, SHRINK_* would be defined as ULONG_MAX.
> >
>
> I believe you have already saw the reason for that in the following patch.
>
Yes, although it was to match existing behaviour, not because it was
necessarily a good idea.
> Do you still have a problem with this ?
>
Not enough to NAK it but it would be desirable because it does feel strange
to have the API deal with negative numbers of objects just to have -1.
> >
> >> diff --git a/mm/vmscan.c b/mm/vmscan.c
> >> index f9d2fba..ca3f690 100644
> >> --- a/mm/vmscan.c
> >> +++ b/mm/vmscan.c
> >> @@ -205,19 +205,19 @@ static inline int do_shrinker_shrink(struct shrinker *shrinker,
> >> *
> >> * Returns the number of slab objects which we shrunk.
> >> */
> >> -unsigned long shrink_slab(struct shrink_control *shrink,
> >> +unsigned long shrink_slab(struct shrink_control *sc,
> >> unsigned long nr_pages_scanned,
> >> unsigned long lru_pages)
> >> {
> >
> > In every other part of vmscan.c, sc is a scan_control but here it is a
> > shrink_control. That's an unfortunate reuse of a name that cause me to
> > scratch my head later when I looked at the tracepoint modification.
> > shrinkc? It's a crappy suggestion but if you think of a better name than
> > sc then a rename would be nice.
> >
>
>
> I am all in favor of being explicit. How about we rename sc to...
> shrink_control ?
>
It has the advantage of being impossible to confuse :)
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 07/31] shrinker: convert superblock shrinkers to new API
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (5 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 06/31] mm: new shrinker API Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-30 14:49 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 08/31] list: add a new LRU list type Glauber Costa
` (24 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner, Glauber Costa
From: Dave Chinner <dchinner@redhat.com>
Convert superblock shrinker to use the new count/scan API, and
propagate the API changes through to the filesystem callouts. The
filesystem callouts already use a count/scan API, so it's just
changing counters to longs to match the VM API.
This requires the dentry and inode shrinker callouts to be converted
to the count/scan API. This is mainly a mechanical change.
[ glommer: use mult_frac for fractional proportions, build fixes ]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
---
fs/dcache.c | 10 +++++---
fs/inode.c | 7 +++--
fs/internal.h | 2 ++
fs/super.c | 74 ++++++++++++++++++++++++++++++++---------------------
fs/xfs/xfs_icache.c | 4 +--
fs/xfs/xfs_icache.h | 2 +-
fs/xfs/xfs_super.c | 8 +++---
include/linux/fs.h | 8 ++----
8 files changed, 67 insertions(+), 48 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index 2c99c1d..b413d77 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -866,11 +866,12 @@ static void shrink_dentry_list(struct list_head *list)
* This function may fail to free any resources if all the dentries are in
* use.
*/
-void prune_dcache_sb(struct super_block *sb, int count)
+long prune_dcache_sb(struct super_block *sb, long nr_to_scan)
{
struct dentry *dentry;
LIST_HEAD(referenced);
LIST_HEAD(tmp);
+ long freed = 0;
relock:
spin_lock(&sb->s_dentry_lru_lock);
@@ -895,7 +896,8 @@ relock:
this_cpu_dec(nr_dentry_unused);
sb->s_nr_dentry_unused--;
spin_unlock(&dentry->d_lock);
- if (!--count)
+ freed++;
+ if (!--nr_to_scan)
break;
}
cond_resched_lock(&sb->s_dentry_lru_lock);
@@ -905,6 +907,7 @@ relock:
spin_unlock(&sb->s_dentry_lru_lock);
shrink_dentry_list(&tmp);
+ return freed;
}
/*
@@ -1290,9 +1293,8 @@ rename_retry:
void shrink_dcache_parent(struct dentry * parent)
{
LIST_HEAD(dispose);
- int found;
- while ((found = select_parent(parent, &dispose)) != 0) {
+ while (select_parent(parent, &dispose)) {
shrink_dentry_list(&dispose);
cond_resched();
}
diff --git a/fs/inode.c b/fs/inode.c
index 00d5fc3..82c8c81 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -704,10 +704,11 @@ static int can_unuse(struct inode *inode)
* LRU does not have strict ordering. Hence we don't want to reclaim inodes
* with this flag set because they are the inodes that are out of order.
*/
-void prune_icache_sb(struct super_block *sb, int nr_to_scan)
+long prune_icache_sb(struct super_block *sb, long nr_to_scan)
{
LIST_HEAD(freeable);
- int nr_scanned;
+ long nr_scanned;
+ long freed = 0;
unsigned long reap = 0;
spin_lock(&sb->s_inode_lru_lock);
@@ -777,6 +778,7 @@ void prune_icache_sb(struct super_block *sb, int nr_to_scan)
list_move(&inode->i_lru, &freeable);
sb->s_nr_inodes_unused--;
this_cpu_dec(nr_unused);
+ freed++;
}
if (current_is_kswapd())
__count_vm_events(KSWAPD_INODESTEAL, reap);
@@ -787,6 +789,7 @@ void prune_icache_sb(struct super_block *sb, int nr_to_scan)
current->reclaim_state->reclaimed_slab += reap;
dispose_list(&freeable);
+ return freed;
}
static void __wait_on_freeing_inode(struct inode *inode);
diff --git a/fs/internal.h b/fs/internal.h
index eaa75f7..f2da2b5 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -110,6 +110,7 @@ extern int open_check_o_direct(struct file *f);
* inode.c
*/
extern spinlock_t inode_sb_list_lock;
+extern long prune_icache_sb(struct super_block *sb, long nr_to_scan);
extern void inode_add_lru(struct inode *inode);
/*
@@ -125,6 +126,7 @@ extern int invalidate_inodes(struct super_block *, bool);
* dcache.c
*/
extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
+extern long prune_dcache_sb(struct super_block *sb, long nr_to_scan);
/*
* read_write.c
diff --git a/fs/super.c b/fs/super.c
index 0be75fb..9d2f2e9 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -53,11 +53,14 @@ static char *sb_writers_name[SB_FREEZE_LEVELS] = {
* shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we
* take a passive reference to the superblock to avoid this from occurring.
*/
-static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
+static long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
{
struct super_block *sb;
- int fs_objects = 0;
- int total_objects;
+ long fs_objects = 0;
+ long total_objects;
+ long freed = 0;
+ long dentries;
+ long inodes;
sb = container_of(shrink, struct super_block, s_shrink);
@@ -65,7 +68,7 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
* Deadlock avoidance. We may hold various FS locks, and we don't want
* to recurse into the FS that called us in clear_inode() and friends..
*/
- if (sc->nr_to_scan && !(sc->gfp_mask & __GFP_FS))
+ if (!(sc->gfp_mask & __GFP_FS))
return -1;
if (!grab_super_passive(sb))
@@ -77,33 +80,45 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
total_objects = sb->s_nr_dentry_unused +
sb->s_nr_inodes_unused + fs_objects + 1;
- if (sc->nr_to_scan) {
- int dentries;
- int inodes;
-
- /* proportion the scan between the caches */
- dentries = mult_frac(sc->nr_to_scan, sb->s_nr_dentry_unused,
- total_objects);
- inodes = mult_frac(sc->nr_to_scan, sb->s_nr_inodes_unused,
- total_objects);
- if (fs_objects)
- fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
- total_objects);
- /*
- * prune the dcache first as the icache is pinned by it, then
- * prune the icache, followed by the filesystem specific caches
- */
- prune_dcache_sb(sb, dentries);
- prune_icache_sb(sb, inodes);
+ /* proportion the scan between the caches */
+ dentries = mult_frac(sc->nr_to_scan, sb->s_nr_dentry_unused,
+ total_objects);
+ inodes = mult_frac(sc->nr_to_scan, sb->s_nr_inodes_unused,
+ total_objects);
- if (fs_objects && sb->s_op->free_cached_objects) {
- sb->s_op->free_cached_objects(sb, fs_objects);
- fs_objects = sb->s_op->nr_cached_objects(sb);
- }
- total_objects = sb->s_nr_dentry_unused +
- sb->s_nr_inodes_unused + fs_objects;
+ /*
+ * prune the dcache first as the icache is pinned by it, then
+ * prune the icache, followed by the filesystem specific caches
+ */
+ freed = prune_dcache_sb(sb, dentries);
+ freed += prune_icache_sb(sb, inodes);
+
+ if (fs_objects) {
+ fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
+ total_objects);
+ freed += sb->s_op->free_cached_objects(sb, fs_objects);
}
+ drop_super(sb);
+ return freed;
+}
+
+static long super_cache_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ struct super_block *sb;
+ long total_objects = 0;
+
+ sb = container_of(shrink, struct super_block, s_shrink);
+
+ if (!grab_super_passive(sb))
+ return -1;
+
+ if (sb->s_op && sb->s_op->nr_cached_objects)
+ total_objects = sb->s_op->nr_cached_objects(sb);
+
+ total_objects += sb->s_nr_dentry_unused;
+ total_objects += sb->s_nr_inodes_unused;
+
total_objects = vfs_pressure_ratio(total_objects);
drop_super(sb);
return total_objects;
@@ -217,7 +232,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
s->cleancache_poolid = -1;
s->s_shrink.seeks = DEFAULT_SEEKS;
- s->s_shrink.shrink = prune_super;
+ s->s_shrink.scan_objects = super_cache_scan;
+ s->s_shrink.count_objects = super_cache_count;
s->s_shrink.batch = 1024;
}
out:
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 96e344e..b35c311 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1164,7 +1164,7 @@ xfs_reclaim_inodes(
* them to be cleaned, which we hope will not be very long due to the
* background walker having already kicked the IO off on those dirty inodes.
*/
-void
+long
xfs_reclaim_inodes_nr(
struct xfs_mount *mp,
int nr_to_scan)
@@ -1173,7 +1173,7 @@ xfs_reclaim_inodes_nr(
xfs_reclaim_work_queue(mp);
xfs_ail_push_all(mp->m_ail);
- xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan);
+ return xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan);
}
/*
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index e0f138c..2d6d2d3 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -31,7 +31,7 @@ void xfs_reclaim_worker(struct work_struct *work);
int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
int xfs_reclaim_inodes_count(struct xfs_mount *mp);
-void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
+long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index ea341ce..1ff991b 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1523,19 +1523,19 @@ xfs_fs_mount(
return mount_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super);
}
-static int
+static long
xfs_fs_nr_cached_objects(
struct super_block *sb)
{
return xfs_reclaim_inodes_count(XFS_M(sb));
}
-static void
+static long
xfs_fs_free_cached_objects(
struct super_block *sb,
- int nr_to_scan)
+ long nr_to_scan)
{
- xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan);
+ return xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan);
}
static const struct super_operations xfs_super_operations = {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index df3174d..6589288 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1326,10 +1326,6 @@ struct super_block {
int s_readonly_remount;
};
-/* superblock cache pruning functions */
-extern void prune_icache_sb(struct super_block *sb, int nr_to_scan);
-extern void prune_dcache_sb(struct super_block *sb, int nr_to_scan);
-
extern struct timespec current_fs_time(struct super_block *sb);
/*
@@ -1616,8 +1612,8 @@ struct super_operations {
ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
#endif
int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
- int (*nr_cached_objects)(struct super_block *);
- void (*free_cached_objects)(struct super_block *, int);
+ long (*nr_cached_objects)(struct super_block *);
+ long (*free_cached_objects)(struct super_block *, long);
};
/*
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 07/31] shrinker: convert superblock shrinkers to new API
2013-04-26 23:19 ` [PATCH v4 07/31] shrinker: convert superblock shrinkers to new API Glauber Costa
@ 2013-04-30 14:49 ` Mel Gorman
0 siblings, 0 replies; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 14:49 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
On Sat, Apr 27, 2013 at 03:19:03AM +0400, Glauber Costa wrote:
> From: Dave Chinner <dchinner@redhat.com>
>
> Convert superblock shrinker to use the new count/scan API, and
> propagate the API changes through to the filesystem callouts. The
> filesystem callouts already use a count/scan API, so it's just
> changing counters to longs to match the VM API.
>
> This requires the dentry and inode shrinker callouts to be converted
> to the count/scan API. This is mainly a mechanical change.
>
> [ glommer: use mult_frac for fractional proportions, build fixes ]
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Signed-off-by: Glauber Costa <glommer@openvz.org>
It's slightly clearer on seeing this patch why you went with long instead
of unsigned long in the previous patch. It matched closer to what the
shrinkers were already doing with their counters and of course they
already understood -1 but as the API is being churned anyway, it would
not hurt to use unsigned long for counters and ULONG_MAX for errors.
I spotted no specific problem with this patch itself and there is some
nice tidy-ups in there.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 08/31] list: add a new LRU list type
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (6 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 07/31] shrinker: convert superblock shrinkers to new API Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-30 15:18 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 09/31] inode: convert inode lru list to generic lru list code Glauber Costa
` (23 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner, Glauber Costa
From: Dave Chinner <dchinner@redhat.com>
Several subsystems use the same construct for LRU lists - a list
head, a spin lock and and item count. They also use exactly the same
code for adding and removing items from the LRU. Create a generic
type for these LRU lists.
This is the beginning of generic, node aware LRUs for shrinkers to
work with.
[ glommer: enum defined constants for lru. Suggested by gthelen,
don't relock over retry ]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
Reviewed-by: Greg Thelen <gthelen@google.com>
---
include/linux/list_lru.h | 45 ++++++++++++++++++
lib/Makefile | 2 +-
lib/list_lru.c | 118 +++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 164 insertions(+), 1 deletion(-)
create mode 100644 include/linux/list_lru.h
create mode 100644 lib/list_lru.c
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
new file mode 100644
index 0000000..c0b796d
--- /dev/null
+++ b/include/linux/list_lru.h
@@ -0,0 +1,45 @@
+/*
+ * Copyright (c) 2010-2012 Red Hat, Inc. All rights reserved.
+ * Author: David Chinner
+ *
+ * Generic LRU infrastructure
+ */
+#ifndef _LRU_LIST_H
+#define _LRU_LIST_H
+
+#include <linux/list.h>
+
+enum lru_status {
+ LRU_REMOVED, /* item removed from list */
+ LRU_ROTATE, /* item referenced, give another pass */
+ LRU_SKIP, /* item cannot be locked, skip */
+ LRU_RETRY, /* item not freeable. May drop the lock
+ internally, but has to return locked. */
+};
+
+struct list_lru {
+ spinlock_t lock;
+ struct list_head list;
+ long nr_items;
+};
+
+int list_lru_init(struct list_lru *lru);
+int list_lru_add(struct list_lru *lru, struct list_head *item);
+int list_lru_del(struct list_lru *lru, struct list_head *item);
+
+static inline long list_lru_count(struct list_lru *lru)
+{
+ return lru->nr_items;
+}
+
+typedef enum lru_status
+(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
+
+typedef void (*list_lru_dispose_cb)(struct list_head *dispose_list);
+
+long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
+ void *cb_arg, long nr_to_walk);
+
+long list_lru_dispose_all(struct list_lru *lru, list_lru_dispose_cb dispose);
+
+#endif /* _LRU_LIST_H */
diff --git a/lib/Makefile b/lib/Makefile
index af79e8c..40a6d4a 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -13,7 +13,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
- earlycpio.o percpu-refcount.o
+ earlycpio.o percpu-refcount.o list_lru.o
obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
lib-$(CONFIG_MMU) += ioremap.o
diff --git a/lib/list_lru.c b/lib/list_lru.c
new file mode 100644
index 0000000..937ee87
--- /dev/null
+++ b/lib/list_lru.c
@@ -0,0 +1,118 @@
+/*
+ * Copyright (c) 2010-2012 Red Hat, Inc. All rights reserved.
+ * Author: David Chinner
+ *
+ * Generic LRU infrastructure
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/list_lru.h>
+
+int
+list_lru_add(
+ struct list_lru *lru,
+ struct list_head *item)
+{
+ spin_lock(&lru->lock);
+ if (list_empty(item)) {
+ list_add_tail(item, &lru->list);
+ lru->nr_items++;
+ spin_unlock(&lru->lock);
+ return 1;
+ }
+ spin_unlock(&lru->lock);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(list_lru_add);
+
+int
+list_lru_del(
+ struct list_lru *lru,
+ struct list_head *item)
+{
+ spin_lock(&lru->lock);
+ if (!list_empty(item)) {
+ list_del_init(item);
+ lru->nr_items--;
+ spin_unlock(&lru->lock);
+ return 1;
+ }
+ spin_unlock(&lru->lock);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(list_lru_del);
+
+long
+list_lru_walk(
+ struct list_lru *lru,
+ list_lru_walk_cb isolate,
+ void *cb_arg,
+ long nr_to_walk)
+{
+ struct list_head *item, *n;
+ long removed = 0;
+
+ spin_lock(&lru->lock);
+restart:
+ list_for_each_safe(item, n, &lru->list) {
+ enum lru_status ret;
+
+ if (nr_to_walk-- < 0)
+ break;
+
+ ret = isolate(item, &lru->lock, cb_arg);
+ switch (ret) {
+ case LRU_REMOVED:
+ lru->nr_items--;
+ removed++;
+ break;
+ case LRU_ROTATE:
+ list_move_tail(item, &lru->list);
+ break;
+ case LRU_SKIP:
+ break;
+ case LRU_RETRY:
+ goto restart;
+ default:
+ BUG();
+ }
+ }
+ spin_unlock(&lru->lock);
+ return removed;
+}
+EXPORT_SYMBOL_GPL(list_lru_walk);
+
+long
+list_lru_dispose_all(
+ struct list_lru *lru,
+ list_lru_dispose_cb dispose)
+{
+ long disposed = 0;
+ LIST_HEAD(dispose_list);
+
+ spin_lock(&lru->lock);
+ while (!list_empty(&lru->list)) {
+ list_splice_init(&lru->list, &dispose_list);
+ disposed += lru->nr_items;
+ lru->nr_items = 0;
+ spin_unlock(&lru->lock);
+
+ dispose(&dispose_list);
+
+ spin_lock(&lru->lock);
+ }
+ spin_unlock(&lru->lock);
+ return disposed;
+}
+
+int
+list_lru_init(
+ struct list_lru *lru)
+{
+ spin_lock_init(&lru->lock);
+ INIT_LIST_HEAD(&lru->list);
+ lru->nr_items = 0;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(list_lru_init);
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 08/31] list: add a new LRU list type
2013-04-26 23:19 ` [PATCH v4 08/31] list: add a new LRU list type Glauber Costa
@ 2013-04-30 15:18 ` Mel Gorman
2013-04-30 16:01 ` Glauber Costa
0 siblings, 1 reply; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 15:18 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
On Sat, Apr 27, 2013 at 03:19:04AM +0400, Glauber Costa wrote:
> From: Dave Chinner <dchinner@redhat.com>
>
> Several subsystems use the same construct for LRU lists - a list
> head, a spin lock and and item count. They also use exactly the same
> code for adding and removing items from the LRU. Create a generic
> type for these LRU lists.
>
> This is the beginning of generic, node aware LRUs for shrinkers to
> work with.
>
> [ glommer: enum defined constants for lru. Suggested by gthelen,
> don't relock over retry ]
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Signed-off-by: Glauber Costa <glommer@openvz.org>
> Reviewed-by: Greg Thelen <gthelen@google.com>
> ---
> include/linux/list_lru.h | 45 ++++++++++++++++++
> lib/Makefile | 2 +-
> lib/list_lru.c | 118 +++++++++++++++++++++++++++++++++++++++++++++++
> 3 files changed, 164 insertions(+), 1 deletion(-)
> create mode 100644 include/linux/list_lru.h
> create mode 100644 lib/list_lru.c
>
> diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
> new file mode 100644
> index 0000000..c0b796d
> --- /dev/null
> +++ b/include/linux/list_lru.h
> @@ -0,0 +1,45 @@
> +/*
> + * Copyright (c) 2010-2012 Red Hat, Inc. All rights reserved.
> + * Author: David Chinner
> + *
> + * Generic LRU infrastructure
> + */
> +#ifndef _LRU_LIST_H
> +#define _LRU_LIST_H
> +
> +#include <linux/list.h>
> +
> +enum lru_status {
> + LRU_REMOVED, /* item removed from list */
> + LRU_ROTATE, /* item referenced, give another pass */
> + LRU_SKIP, /* item cannot be locked, skip */
> + LRU_RETRY, /* item not freeable. May drop the lock
> + internally, but has to return locked. */
> +};
> +
> +struct list_lru {
> + spinlock_t lock;
> + struct list_head list;
> + long nr_items;
> +};
Is there ever a circumstance where nr_items is negative? If so, what
does that mean?
> +
> +int list_lru_init(struct list_lru *lru);
I was going to complain that this always returns 0 and should be void
but that changes later.
> +int list_lru_add(struct list_lru *lru, struct list_head *item);
> +int list_lru_del(struct list_lru *lru, struct list_head *item);
> +
However, these are bool and the return value determines if the item was
really added to the list or not. It fails if the item is already part of
a list and it would be very nice to have a comment explaining why it's
not a bug if this happens because it feels like it would be a lookup and
insertion race. Maybe it's clear later in the series why this is ok but
it's not very obvious at this point.
> +static inline long list_lru_count(struct list_lru *lru)
> +{
> + return lru->nr_items;
> +}
> +
> +typedef enum lru_status
> +(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
> +
> +typedef void (*list_lru_dispose_cb)(struct list_head *dispose_list);
> +
> +long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
> + void *cb_arg, long nr_to_walk);
> +
Is nr_to_walk ever negative?
> +long list_lru_dispose_all(struct list_lru *lru, list_lru_dispose_cb dispose);
> +
> +#endif /* _LRU_LIST_H */
> diff --git a/lib/Makefile b/lib/Makefile
> index af79e8c..40a6d4a 100644
> --- a/lib/Makefile
> +++ b/lib/Makefile
> @@ -13,7 +13,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
> sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
> proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
> is_single_threaded.o plist.o decompress.o kobject_uevent.o \
> - earlycpio.o percpu-refcount.o
> + earlycpio.o percpu-refcount.o list_lru.o
>
> obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
> lib-$(CONFIG_MMU) += ioremap.o
> diff --git a/lib/list_lru.c b/lib/list_lru.c
> new file mode 100644
> index 0000000..937ee87
> --- /dev/null
> +++ b/lib/list_lru.c
> @@ -0,0 +1,118 @@
> +/*
> + * Copyright (c) 2010-2012 Red Hat, Inc. All rights reserved.
> + * Author: David Chinner
> + *
> + * Generic LRU infrastructure
> + */
> +#include <linux/kernel.h>
> +#include <linux/module.h>
> +#include <linux/list_lru.h>
> +
> +int
> +list_lru_add(
> + struct list_lru *lru,
> + struct list_head *item)
> +{
> + spin_lock(&lru->lock);
> + if (list_empty(item)) {
> + list_add_tail(item, &lru->list);
> + lru->nr_items++;
> + spin_unlock(&lru->lock);
> + return 1;
> + }
> + spin_unlock(&lru->lock);
> + return 0;
> +}
> +EXPORT_SYMBOL_GPL(list_lru_add);
> +
> +int
> +list_lru_del(
> + struct list_lru *lru,
> + struct list_head *item)
> +{
> + spin_lock(&lru->lock);
> + if (!list_empty(item)) {
> + list_del_init(item);
> + lru->nr_items--;
> + spin_unlock(&lru->lock);
> + return 1;
> + }
> + spin_unlock(&lru->lock);
> + return 0;
> +}
> +EXPORT_SYMBOL_GPL(list_lru_del);
> +
> +long
> +list_lru_walk(
It returns long but never actually returns a negative number.
> + struct list_lru *lru,
> + list_lru_walk_cb isolate,
> + void *cb_arg,
> + long nr_to_walk)
> +{
> + struct list_head *item, *n;
> + long removed = 0;
> +
> + spin_lock(&lru->lock);
> +restart:
> + list_for_each_safe(item, n, &lru->list) {
> + enum lru_status ret;
> +
> + if (nr_to_walk-- < 0)
> + break;
> +
> + ret = isolate(item, &lru->lock, cb_arg);
> + switch (ret) {
> + case LRU_REMOVED:
> + lru->nr_items--;
> + removed++;
> + break;
> + case LRU_ROTATE:
> + list_move_tail(item, &lru->list);
> + break;
> + case LRU_SKIP:
> + break;
> + case LRU_RETRY:
> + goto restart;
Are the two users of LRU_RETRY guaranteed to eventually make progress
or can this infinite loop? It feels like the behaviour of LRU_RETRY is
not very desirable. Once an object that returns LRU_RETRY is isolated on
the list then it looks like XFS can stall for 100 ticks (bit arbitrary)
each time it tries and maybe do this forever.
The inode.c user looks like it could race where some other process is
reallocating the buffers between each time this isolate callback tries to
isolate it. Granted, it may accidentally break out because the spinlock
is contended and it returns LRU_SKIP so maybe no one will hit the problem
but if it's ok with LRU_SKIP then maybe a LRU_RETRY_ONCE would also be
suitable and use that in fs/inode.c?
Either hypothetical situation would require that the list you are trying
to walk is very small but maybe memcg will hit that problem. If there is
a guarantee of forward progress then a comment would be nice.
> + default:
> + BUG();
> + }
> + }
> + spin_unlock(&lru->lock);
> + return removed;
> +}
> +EXPORT_SYMBOL_GPL(list_lru_walk);
> +
> +long
> +list_lru_dispose_all(
> + struct list_lru *lru,
> + list_lru_dispose_cb dispose)
> +{
> + long disposed = 0;
> + LIST_HEAD(dispose_list);
> +
> + spin_lock(&lru->lock);
> + while (!list_empty(&lru->list)) {
> + list_splice_init(&lru->list, &dispose_list);
> + disposed += lru->nr_items;
> + lru->nr_items = 0;
> + spin_unlock(&lru->lock);
> +
> + dispose(&dispose_list);
> +
> + spin_lock(&lru->lock);
> + }
> + spin_unlock(&lru->lock);
> + return disposed;
> +}
> +
> +int
> +list_lru_init(
> + struct list_lru *lru)
> +{
> + spin_lock_init(&lru->lock);
> + INIT_LIST_HEAD(&lru->list);
> + lru->nr_items = 0;
> +
> + return 0;
> +}
> +EXPORT_SYMBOL_GPL(list_lru_init);
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 08/31] list: add a new LRU list type
2013-04-30 15:18 ` Mel Gorman
@ 2013-04-30 16:01 ` Glauber Costa
0 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-30 16:01 UTC (permalink / raw)
To: Mel Gorman
Cc: Glauber Costa, linux-mm, cgroups, Andrew Morton, Greg Thelen,
kamezawa.hiroyu, Michal Hocko, Johannes Weiner, Dave Chinner
>> +
>> +struct list_lru {
>> + spinlock_t lock;
>> + struct list_head list;
>> + long nr_items;
>> +};
>
> Is there ever a circumstance where nr_items is negative? If so, what
> does that mean?
>
No, but we would like to be able to detect it and BUG (which we actually do)
>
>> +int list_lru_add(struct list_lru *lru, struct list_head *item);
>> +int list_lru_del(struct list_lru *lru, struct list_head *item);
>> +
>
> However, these are bool and the return value determines if the item was
> really added to the list or not. It fails if the item is already part of
> a list and it would be very nice to have a comment explaining why it's
> not a bug if this happens because it feels like it would be a lookup and
> insertion race. Maybe it's clear later in the series why this is ok but
> it's not very obvious at this point.
>
I actually don't know.
I would appreciate Dave's comments on this one. Dave?
>> +static inline long list_lru_count(struct list_lru *lru)
>> +{
>> + return lru->nr_items;
>> +}
>> +
>> +typedef enum lru_status
>> +(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
>> +
>> +typedef void (*list_lru_dispose_cb)(struct list_head *dispose_list);
>> +
>> +long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
>> + void *cb_arg, long nr_to_walk);
>> +
>
> Is nr_to_walk ever negative?
>
Shouldn't be, and this one, we don't BUG.
>> +long list_lru_dispose_all(struct list_lru *lru, list_lru_dispose_cb dispose);
>> +
>> +#endif /* _LRU_LIST_H */
>> diff --git a/lib/Makefile b/lib/Makefile
>> index af79e8c..40a6d4a 100644
>> --- a/lib/Makefile
>> +++ b/lib/Makefile
>> @@ -13,7 +13,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
>> sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
>> proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
>> is_single_threaded.o plist.o decompress.o kobject_uevent.o \
>> - earlycpio.o percpu-refcount.o
>> + earlycpio.o percpu-refcount.o list_lru.o
>>
>> obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
>> lib-$(CONFIG_MMU) += ioremap.o
>> diff --git a/lib/list_lru.c b/lib/list_lru.c
>> new file mode 100644
>> index 0000000..937ee87
>> --- /dev/null
>> +++ b/lib/list_lru.c
>> @@ -0,0 +1,118 @@
>> +/*
>> + * Copyright (c) 2010-2012 Red Hat, Inc. All rights reserved.
>> + * Author: David Chinner
>> + *
>> + * Generic LRU infrastructure
>> + */
>> +#include <linux/kernel.h>
>> +#include <linux/module.h>
>> +#include <linux/list_lru.h>
>> +
>> +int
>> +list_lru_add(
>> + struct list_lru *lru,
>> + struct list_head *item)
>> +{
>> + spin_lock(&lru->lock);
>> + if (list_empty(item)) {
>> + list_add_tail(item, &lru->list);
>> + lru->nr_items++;
>> + spin_unlock(&lru->lock);
>> + return 1;
>> + }
>> + spin_unlock(&lru->lock);
>> + return 0;
>> +}
>> +EXPORT_SYMBOL_GPL(list_lru_add);
>> +
>> +int
>> +list_lru_del(
>> + struct list_lru *lru,
>> + struct list_head *item)
>> +{
>> + spin_lock(&lru->lock);
>> + if (!list_empty(item)) {
>> + list_del_init(item);
>> + lru->nr_items--;
>> + spin_unlock(&lru->lock);
>> + return 1;
>> + }
>> + spin_unlock(&lru->lock);
>> + return 0;
>> +}
>> +EXPORT_SYMBOL_GPL(list_lru_del);
>> +
>> +long
>> +list_lru_walk(
>
> It returns long but never actually returns a negative number.
>
>> + struct list_lru *lru,
>> + list_lru_walk_cb isolate,
>> + void *cb_arg,
>> + long nr_to_walk)
>> +{
>> + struct list_head *item, *n;
>> + long removed = 0;
>> +
>> + spin_lock(&lru->lock);
>> +restart:
>> + list_for_each_safe(item, n, &lru->list) {
>> + enum lru_status ret;
>> +
>> + if (nr_to_walk-- < 0)
>> + break;
>> +
>> + ret = isolate(item, &lru->lock, cb_arg);
>> + switch (ret) {
>> + case LRU_REMOVED:
>> + lru->nr_items--;
>> + removed++;
>> + break;
>> + case LRU_ROTATE:
>> + list_move_tail(item, &lru->list);
>> + break;
>> + case LRU_SKIP:
>> + break;
>> + case LRU_RETRY:
>> + goto restart;
>
> Are the two users of LRU_RETRY guaranteed to eventually make progress
> or can this infinite loop? It feels like the behaviour of LRU_RETRY is
> not very desirable. Once an object that returns LRU_RETRY is isolated on
> the list then it looks like XFS can stall for 100 ticks (bit arbitrary)
> each time it tries and maybe do this forever.
>
> The inode.c user looks like it could race where some other process is
> reallocating the buffers between each time this isolate callback tries to
> isolate it. Granted, it may accidentally break out because the spinlock
> is contended and it returns LRU_SKIP so maybe no one will hit the problem
> but if it's ok with LRU_SKIP then maybe a LRU_RETRY_ONCE would also be
> suitable and use that in fs/inode.c?
>
> Either hypothetical situation would require that the list you are trying
> to walk is very small but maybe memcg will hit that problem. If there is
> a guarantee of forward progress then a comment would be nice.
>
I have to look into this issue further, which I plan to do soon, but
can't today. Meanwhile, This is really a lot more under Dave's umbrella,
so Dave, if you would give us the honor =)
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 09/31] inode: convert inode lru list to generic lru list code.
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (7 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 08/31] list: add a new LRU list type Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-30 15:46 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 10/31] dcache: convert to use new lru list infrastructure Glauber Costa
` (22 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner, Glauber Costa
From: Dave Chinner <dchinner@redhat.com>
[ glommer: adapted for new LRU return codes ]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
---
fs/inode.c | 175 +++++++++++++++++++++--------------------------------
fs/super.c | 12 ++--
include/linux/fs.h | 6 +-
3 files changed, 77 insertions(+), 116 deletions(-)
diff --git a/fs/inode.c b/fs/inode.c
index 82c8c81..c6c62a8 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -17,6 +17,7 @@
#include <linux/prefetch.h>
#include <linux/buffer_head.h> /* for inode_has_buffers */
#include <linux/ratelimit.h>
+#include <linux/list_lru.h>
#include "internal.h"
/*
@@ -24,7 +25,7 @@
*
* inode->i_lock protects:
* inode->i_state, inode->i_hash, __iget()
- * inode->i_sb->s_inode_lru_lock protects:
+ * Inode LRU list locks protect:
* inode->i_sb->s_inode_lru, inode->i_lru
* inode_sb_list_lock protects:
* sb->s_inodes, inode->i_sb_list
@@ -37,7 +38,7 @@
*
* inode_sb_list_lock
* inode->i_lock
- * inode->i_sb->s_inode_lru_lock
+ * Inode LRU list locks
*
* bdi->wb.list_lock
* inode->i_lock
@@ -399,13 +400,8 @@ EXPORT_SYMBOL(ihold);
static void inode_lru_list_add(struct inode *inode)
{
- spin_lock(&inode->i_sb->s_inode_lru_lock);
- if (list_empty(&inode->i_lru)) {
- list_add(&inode->i_lru, &inode->i_sb->s_inode_lru);
- inode->i_sb->s_nr_inodes_unused++;
+ if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru))
this_cpu_inc(nr_unused);
- }
- spin_unlock(&inode->i_sb->s_inode_lru_lock);
}
/*
@@ -423,13 +419,9 @@ void inode_add_lru(struct inode *inode)
static void inode_lru_list_del(struct inode *inode)
{
- spin_lock(&inode->i_sb->s_inode_lru_lock);
- if (!list_empty(&inode->i_lru)) {
- list_del_init(&inode->i_lru);
- inode->i_sb->s_nr_inodes_unused--;
+
+ if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru))
this_cpu_dec(nr_unused);
- }
- spin_unlock(&inode->i_sb->s_inode_lru_lock);
}
/**
@@ -673,24 +665,8 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
return busy;
}
-static int can_unuse(struct inode *inode)
-{
- if (inode->i_state & ~I_REFERENCED)
- return 0;
- if (inode_has_buffers(inode))
- return 0;
- if (atomic_read(&inode->i_count))
- return 0;
- if (inode->i_data.nrpages)
- return 0;
- return 1;
-}
-
/*
- * Walk the superblock inode LRU for freeable inodes and attempt to free them.
- * This is called from the superblock shrinker function with a number of inodes
- * to trim from the LRU. Inodes to be freed are moved to a temporary list and
- * then are freed outside inode_lock by dispose_list().
+ * Isolate the inode from the LRU in preparation for freeing it.
*
* Any inodes which are pinned purely because of attached pagecache have their
* pagecache removed. If the inode has metadata buffers attached to
@@ -704,90 +680,79 @@ static int can_unuse(struct inode *inode)
* LRU does not have strict ordering. Hence we don't want to reclaim inodes
* with this flag set because they are the inodes that are out of order.
*/
-long prune_icache_sb(struct super_block *sb, long nr_to_scan)
+static enum lru_status
+inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
{
- LIST_HEAD(freeable);
- long nr_scanned;
- long freed = 0;
- unsigned long reap = 0;
+ struct list_head *freeable = arg;
+ struct inode *inode = container_of(item, struct inode, i_lru);
- spin_lock(&sb->s_inode_lru_lock);
- for (nr_scanned = nr_to_scan; nr_scanned >= 0; nr_scanned--) {
- struct inode *inode;
+ /*
+ * we are inverting the lru lock/inode->i_lock here, so use a trylock.
+ * If we fail to get the lock, just skip it.
+ */
+ if (!spin_trylock(&inode->i_lock))
+ return LRU_SKIP;
- if (list_empty(&sb->s_inode_lru))
- break;
+ /*
+ * Referenced or dirty inodes are still in use. Give them another pass
+ * through the LRU as we canot reclaim them now.
+ */
+ if (atomic_read(&inode->i_count) ||
+ (inode->i_state & ~I_REFERENCED)) {
+ list_del_init(&inode->i_lru);
+ spin_unlock(&inode->i_lock);
+ this_cpu_dec(nr_unused);
+ return LRU_REMOVED;
+ }
- inode = list_entry(sb->s_inode_lru.prev, struct inode, i_lru);
+ /* recently referenced inodes get one more pass */
+ if (inode->i_state & I_REFERENCED) {
+ inode->i_state &= ~I_REFERENCED;
+ spin_unlock(&inode->i_lock);
+ return LRU_ROTATE;
+ }
- /*
- * we are inverting the sb->s_inode_lru_lock/inode->i_lock here,
- * so use a trylock. If we fail to get the lock, just move the
- * inode to the back of the list so we don't spin on it.
- */
- if (!spin_trylock(&inode->i_lock)) {
- list_move(&inode->i_lru, &sb->s_inode_lru);
- continue;
+ if (inode_has_buffers(inode) || inode->i_data.nrpages) {
+ __iget(inode);
+ spin_unlock(&inode->i_lock);
+ spin_unlock(lru_lock);
+ if (remove_inode_buffers(inode)) {
+ unsigned long reap;
+ reap = invalidate_mapping_pages(&inode->i_data, 0, -1);
+ if (current_is_kswapd())
+ __count_vm_events(KSWAPD_INODESTEAL, reap);
+ else
+ __count_vm_events(PGINODESTEAL, reap);
+ if (current->reclaim_state)
+ current->reclaim_state->reclaimed_slab += reap;
}
+ iput(inode);
+ spin_lock(lru_lock);
+ return LRU_RETRY;
+ }
- /*
- * Referenced or dirty inodes are still in use. Give them
- * another pass through the LRU as we canot reclaim them now.
- */
- if (atomic_read(&inode->i_count) ||
- (inode->i_state & ~I_REFERENCED)) {
- list_del_init(&inode->i_lru);
- spin_unlock(&inode->i_lock);
- sb->s_nr_inodes_unused--;
- this_cpu_dec(nr_unused);
- continue;
- }
+ WARN_ON(inode->i_state & I_NEW);
+ inode->i_state |= I_FREEING;
+ spin_unlock(&inode->i_lock);
- /* recently referenced inodes get one more pass */
- if (inode->i_state & I_REFERENCED) {
- inode->i_state &= ~I_REFERENCED;
- list_move(&inode->i_lru, &sb->s_inode_lru);
- spin_unlock(&inode->i_lock);
- continue;
- }
- if (inode_has_buffers(inode) || inode->i_data.nrpages) {
- __iget(inode);
- spin_unlock(&inode->i_lock);
- spin_unlock(&sb->s_inode_lru_lock);
- if (remove_inode_buffers(inode))
- reap += invalidate_mapping_pages(&inode->i_data,
- 0, -1);
- iput(inode);
- spin_lock(&sb->s_inode_lru_lock);
-
- if (inode != list_entry(sb->s_inode_lru.next,
- struct inode, i_lru))
- continue; /* wrong inode or list_empty */
- /* avoid lock inversions with trylock */
- if (!spin_trylock(&inode->i_lock))
- continue;
- if (!can_unuse(inode)) {
- spin_unlock(&inode->i_lock);
- continue;
- }
- }
- WARN_ON(inode->i_state & I_NEW);
- inode->i_state |= I_FREEING;
- spin_unlock(&inode->i_lock);
+ list_move(&inode->i_lru, freeable);
+ this_cpu_dec(nr_unused);
+ return LRU_REMOVED;
+}
- list_move(&inode->i_lru, &freeable);
- sb->s_nr_inodes_unused--;
- this_cpu_dec(nr_unused);
- freed++;
- }
- if (current_is_kswapd())
- __count_vm_events(KSWAPD_INODESTEAL, reap);
- else
- __count_vm_events(PGINODESTEAL, reap);
- spin_unlock(&sb->s_inode_lru_lock);
- if (current->reclaim_state)
- current->reclaim_state->reclaimed_slab += reap;
+/*
+ * Walk the superblock inode LRU for freeable inodes and attempt to free them.
+ * This is called from the superblock shrinker function with a number of inodes
+ * to trim from the LRU. Inodes to be freed are moved to a temporary list and
+ * then are freed outside inode_lock by dispose_list().
+ */
+long prune_icache_sb(struct super_block *sb, long nr_to_scan)
+{
+ LIST_HEAD(freeable);
+ long freed;
+ freed = list_lru_walk(&sb->s_inode_lru, inode_lru_isolate,
+ &freeable, nr_to_scan);
dispose_list(&freeable);
return freed;
}
diff --git a/fs/super.c b/fs/super.c
index 9d2f2e9..9049110 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -77,14 +77,13 @@ static long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
if (sb->s_op && sb->s_op->nr_cached_objects)
fs_objects = sb->s_op->nr_cached_objects(sb);
- total_objects = sb->s_nr_dentry_unused +
- sb->s_nr_inodes_unused + fs_objects + 1;
+ inodes = list_lru_count(&sb->s_inode_lru);
+ total_objects = sb->s_nr_dentry_unused + inodes + fs_objects + 1;
/* proportion the scan between the caches */
dentries = mult_frac(sc->nr_to_scan, sb->s_nr_dentry_unused,
total_objects);
- inodes = mult_frac(sc->nr_to_scan, sb->s_nr_inodes_unused,
- total_objects);
+ inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
/*
* prune the dcache first as the icache is pinned by it, then
@@ -117,7 +116,7 @@ static long super_cache_count(struct shrinker *shrink, struct shrink_control *sc
total_objects = sb->s_op->nr_cached_objects(sb);
total_objects += sb->s_nr_dentry_unused;
- total_objects += sb->s_nr_inodes_unused;
+ total_objects += list_lru_count(&sb->s_inode_lru);
total_objects = vfs_pressure_ratio(total_objects);
drop_super(sb);
@@ -198,8 +197,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
INIT_LIST_HEAD(&s->s_inodes);
INIT_LIST_HEAD(&s->s_dentry_lru);
spin_lock_init(&s->s_dentry_lru_lock);
- INIT_LIST_HEAD(&s->s_inode_lru);
- spin_lock_init(&s->s_inode_lru_lock);
+ list_lru_init(&s->s_inode_lru);
INIT_LIST_HEAD(&s->s_mounts);
init_rwsem(&s->s_umount);
lockdep_set_class(&s->s_umount, &type->s_umount_key);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6589288..89cda65 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -10,6 +10,7 @@
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/list.h>
+#include <linux/list_lru.h>
#include <linux/radix-tree.h>
#include <linux/rbtree.h>
#include <linux/init.h>
@@ -1269,10 +1270,7 @@ struct super_block {
struct list_head s_dentry_lru; /* unused dentry lru */
int s_nr_dentry_unused; /* # of dentry on lru */
- /* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */
- spinlock_t s_inode_lru_lock ____cacheline_aligned_in_smp;
- struct list_head s_inode_lru; /* unused inode lru */
- int s_nr_inodes_unused; /* # of inodes on lru */
+ struct list_lru s_inode_lru ____cacheline_aligned_in_smp;
struct block_device *s_bdev;
struct backing_dev_info *s_bdi;
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 09/31] inode: convert inode lru list to generic lru list code.
2013-04-26 23:19 ` [PATCH v4 09/31] inode: convert inode lru list to generic lru list code Glauber Costa
@ 2013-04-30 15:46 ` Mel Gorman
2013-05-07 13:47 ` Glauber Costa
0 siblings, 1 reply; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 15:46 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
On Sat, Apr 27, 2013 at 03:19:05AM +0400, Glauber Costa wrote:
> From: Dave Chinner <dchinner@redhat.com>
>
> [ glommer: adapted for new LRU return codes ]
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Signed-off-by: Glauber Costa <glommer@openvz.org>
Looks mostly mechanical with the main mess in the conversion of the
isolate function.
> + if (inode_has_buffers(inode) || inode->i_data.nrpages) {
> + __iget(inode);
> + spin_unlock(&inode->i_lock);
> + spin_unlock(lru_lock);
> + if (remove_inode_buffers(inode)) {
> + unsigned long reap;
> + reap = invalidate_mapping_pages(&inode->i_data, 0, -1);
> + if (current_is_kswapd())
> + __count_vm_events(KSWAPD_INODESTEAL, reap);
> + else
> + __count_vm_events(PGINODESTEAL, reap);
> + if (current->reclaim_state)
> + current->reclaim_state->reclaimed_slab += reap;
> }
> + iput(inode);
> + spin_lock(lru_lock);
> + return LRU_RETRY;
> + }
Only concern is this and whether it can cause the lru_list_walk to
infinite loop if the inode is being continually used and the LRU list is
too small to win the race.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 09/31] inode: convert inode lru list to generic lru list code.
2013-04-30 15:46 ` Mel Gorman
@ 2013-05-07 13:47 ` Glauber Costa
0 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-05-07 13:47 UTC (permalink / raw)
To: Mel Gorman
Cc: Glauber Costa, linux-mm, cgroups, Andrew Morton, Greg Thelen,
kamezawa.hiroyu, Michal Hocko, Johannes Weiner, Dave Chinner
On 04/30/2013 07:46 PM, Mel Gorman wrote:
> On Sat, Apr 27, 2013 at 03:19:05AM +0400, Glauber Costa wrote:
>> From: Dave Chinner <dchinner@redhat.com>
>>
>> [ glommer: adapted for new LRU return codes ]
>> Signed-off-by: Dave Chinner <dchinner@redhat.com>
>> Signed-off-by: Glauber Costa <glommer@openvz.org>
>
> Looks mostly mechanical with the main mess in the conversion of the
> isolate function.
>
>> + if (inode_has_buffers(inode) || inode->i_data.nrpages) {
>> + __iget(inode);
>> + spin_unlock(&inode->i_lock);
>> + spin_unlock(lru_lock);
>> + if (remove_inode_buffers(inode)) {
>> + unsigned long reap;
>> + reap = invalidate_mapping_pages(&inode->i_data, 0, -1);
>> + if (current_is_kswapd())
>> + __count_vm_events(KSWAPD_INODESTEAL, reap);
>> + else
>> + __count_vm_events(PGINODESTEAL, reap);
>> + if (current->reclaim_state)
>> + current->reclaim_state->reclaimed_slab += reap;
>> }
>> + iput(inode);
>> + spin_lock(lru_lock);
>> + return LRU_RETRY;
>> + }
>
> Only concern is this and whether it can cause the lru_list_walk to
> infinite loop if the inode is being continually used and the LRU list is
> too small to win the race.
>
The way I read, this situation only happens when we have pending
buffers, and before returning LRU_RETRY, we do our best to release it.
That means that eventually, it will be released.
Now, of course it is hard to determine how long it will going to take,
and that can take a while in small LRUs. One way to avoid this, would be
to use a new flag in the inode. Set it before we return LRU_RETRY, and
don't retry twice.
I actually think this is sensible, but I am talking from the top of my
head. I haven't really measured how many retries does it usually take
for us to be able to free it.
Another option would be to just return LRU_SKIP and leave it to the next
shrinking cycle to free it.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 10/31] dcache: convert to use new lru list infrastructure
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (8 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 09/31] inode: convert inode lru list to generic lru list code Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-30 16:04 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 11/31] list_lru: per-node " Glauber Costa
` (21 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner, Glauber Costa
From: Dave Chinner <dchinner@redhat.com>
[ glommer: don't reintroduce double decrement of nr_unused_dentries,
adapted for new LRU return codes ]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
---
fs/dcache.c | 189 ++++++++++++++++++++++++-----------------------------
fs/super.c | 11 ++--
include/linux/fs.h | 15 ++---
3 files changed, 97 insertions(+), 118 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index b413d77..9c5406f 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -37,6 +37,7 @@
#include <linux/rculist_bl.h>
#include <linux/prefetch.h>
#include <linux/ratelimit.h>
+#include <linux/list_lru.h>
#include "internal.h"
#include "mount.h"
@@ -318,20 +319,8 @@ static void dentry_unlink_inode(struct dentry * dentry)
*/
static void dentry_lru_add(struct dentry *dentry)
{
- if (list_empty(&dentry->d_lru)) {
- spin_lock(&dentry->d_sb->s_dentry_lru_lock);
- list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
- dentry->d_sb->s_nr_dentry_unused++;
+ if (list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru))
this_cpu_inc(nr_dentry_unused);
- spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
- }
-}
-
-static void __dentry_lru_del(struct dentry *dentry)
-{
- list_del_init(&dentry->d_lru);
- dentry->d_sb->s_nr_dentry_unused--;
- this_cpu_dec(nr_dentry_unused);
}
/*
@@ -341,11 +330,8 @@ static void dentry_lru_del(struct dentry *dentry)
{
BUG_ON(dentry->d_flags & DCACHE_SHRINK_LIST);
- if (!list_empty(&dentry->d_lru)) {
- spin_lock(&dentry->d_sb->s_dentry_lru_lock);
- __dentry_lru_del(dentry);
- spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
- }
+ if (list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru))
+ this_cpu_dec(nr_dentry_unused);
}
/*
@@ -361,35 +347,19 @@ static void dentry_lru_del(struct dentry *dentry)
*/
static void dentry_lru_prune(struct dentry *dentry)
{
- if (!list_empty(&dentry->d_lru)) {
+ int prune = dentry->d_flags & DCACHE_OP_PRUNE;
- if (dentry->d_flags & DCACHE_OP_PRUNE)
- dentry->d_op->d_prune(dentry);
-
- if ((dentry->d_flags & DCACHE_SHRINK_LIST))
- list_del_init(&dentry->d_lru);
- else {
- spin_lock(&dentry->d_sb->s_dentry_lru_lock);
- __dentry_lru_del(dentry);
- spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
- }
- dentry->d_flags &= ~DCACHE_SHRINK_LIST;
- }
-}
-
-static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list)
-{
- BUG_ON(dentry->d_flags & DCACHE_SHRINK_LIST);
-
- spin_lock(&dentry->d_sb->s_dentry_lru_lock);
- if (list_empty(&dentry->d_lru)) {
- list_add_tail(&dentry->d_lru, list);
- } else {
- list_move_tail(&dentry->d_lru, list);
- dentry->d_sb->s_nr_dentry_unused--;
+ if (!list_empty(&dentry->d_lru) &&
+ (dentry->d_flags & DCACHE_SHRINK_LIST))
+ list_del_init(&dentry->d_lru);
+ else if (list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru))
this_cpu_dec(nr_dentry_unused);
- }
- spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
+ else
+ prune = 0;
+
+ dentry->d_flags &= ~DCACHE_SHRINK_LIST;
+ if (prune)
+ dentry->d_op->d_prune(dentry);
}
/**
@@ -854,12 +824,72 @@ static void shrink_dentry_list(struct list_head *list)
rcu_read_unlock();
}
+static enum lru_status
+dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
+{
+ struct list_head *freeable = arg;
+ struct dentry *dentry = container_of(item, struct dentry, d_lru);
+
+
+ /*
+ * we are inverting the lru lock/dentry->d_lock here,
+ * so use a trylock. If we fail to get the lock, just skip
+ * it
+ */
+ if (!spin_trylock(&dentry->d_lock))
+ return LRU_SKIP;
+
+ /*
+ * Referenced dentries are still in use. If they have active
+ * counts, just remove them from the LRU. Otherwise give them
+ * another pass through the LRU.
+ */
+ if (dentry->d_count) {
+ list_del_init(&dentry->d_lru);
+ spin_unlock(&dentry->d_lock);
+ return LRU_REMOVED;
+ }
+
+ if (dentry->d_flags & DCACHE_REFERENCED) {
+ dentry->d_flags &= ~DCACHE_REFERENCED;
+ spin_unlock(&dentry->d_lock);
+
+ /*
+ * The list move itself will be made by the common LRU code. At
+ * this point, we've dropped the dentry->d_lock but keep the
+ * lru lock. This is safe to do, since every list movement is
+ * protected by the lru lock even if both locks are held.
+ *
+ * This is guaranteed by the fact that all LRU management
+ * functions are intermediated by the LRU API calls like
+ * list_lru_add and list_lru_del. List movement in this file
+ * only ever occur through this functions or through callbacks
+ * like this one, that are called from the LRU API.
+ *
+ * The only exceptions to this are functions like
+ * shrink_dentry_list, and code that first checks for the
+ * DCACHE_SHRINK_LIST flag. Those are guaranteed to be
+ * operating only with stack provided lists after they are
+ * properly isolated from the main list. It is thus, always a
+ * local access.
+ */
+ return LRU_ROTATE;
+ }
+
+ dentry->d_flags |= DCACHE_SHRINK_LIST;
+ list_move_tail(&dentry->d_lru, freeable);
+ this_cpu_dec(nr_dentry_unused);
+ spin_unlock(&dentry->d_lock);
+
+ return LRU_REMOVED;
+}
+
/**
* prune_dcache_sb - shrink the dcache
* @sb: superblock
- * @count: number of entries to try to free
+ * @nr_to_scan : number of entries to try to free
*
- * Attempt to shrink the superblock dcache LRU by @count entries. This is
+ * Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is
* done when we need more memory an called from the superblock shrinker
* function.
*
@@ -868,45 +898,12 @@ static void shrink_dentry_list(struct list_head *list)
*/
long prune_dcache_sb(struct super_block *sb, long nr_to_scan)
{
- struct dentry *dentry;
- LIST_HEAD(referenced);
- LIST_HEAD(tmp);
- long freed = 0;
-
-relock:
- spin_lock(&sb->s_dentry_lru_lock);
- while (!list_empty(&sb->s_dentry_lru)) {
- dentry = list_entry(sb->s_dentry_lru.prev,
- struct dentry, d_lru);
- BUG_ON(dentry->d_sb != sb);
-
- if (!spin_trylock(&dentry->d_lock)) {
- spin_unlock(&sb->s_dentry_lru_lock);
- cpu_relax();
- goto relock;
- }
-
- if (dentry->d_flags & DCACHE_REFERENCED) {
- dentry->d_flags &= ~DCACHE_REFERENCED;
- list_move(&dentry->d_lru, &referenced);
- spin_unlock(&dentry->d_lock);
- } else {
- list_move_tail(&dentry->d_lru, &tmp);
- dentry->d_flags |= DCACHE_SHRINK_LIST;
- this_cpu_dec(nr_dentry_unused);
- sb->s_nr_dentry_unused--;
- spin_unlock(&dentry->d_lock);
- freed++;
- if (!--nr_to_scan)
- break;
- }
- cond_resched_lock(&sb->s_dentry_lru_lock);
- }
- if (!list_empty(&referenced))
- list_splice(&referenced, &sb->s_dentry_lru);
- spin_unlock(&sb->s_dentry_lru_lock);
+ LIST_HEAD(dispose);
+ long freed;
- shrink_dentry_list(&tmp);
+ freed = list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate,
+ &dispose, nr_to_scan);
+ shrink_dentry_list(&dispose);
return freed;
}
@@ -940,24 +937,7 @@ shrink_dcache_list(
*/
void shrink_dcache_sb(struct super_block *sb)
{
- LIST_HEAD(tmp);
-
- spin_lock(&sb->s_dentry_lru_lock);
- while (!list_empty(&sb->s_dentry_lru)) {
- list_splice_init(&sb->s_dentry_lru, &tmp);
-
- /*
- * account for removal here so we don't need to handle it later
- * even though the dentry is no longer on the lru list.
- */
- this_cpu_sub(nr_dentry_unused, sb->s_nr_dentry_unused);
- sb->s_nr_dentry_unused = 0;
-
- spin_unlock(&sb->s_dentry_lru_lock);
- shrink_dcache_list(&tmp);
- spin_lock(&sb->s_dentry_lru_lock);
- }
- spin_unlock(&sb->s_dentry_lru_lock);
+ list_lru_dispose_all(&sb->s_dentry_lru, shrink_dcache_list);
}
EXPORT_SYMBOL(shrink_dcache_sb);
@@ -1228,7 +1208,8 @@ resume:
if (dentry->d_count) {
dentry_lru_del(dentry);
} else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
- dentry_lru_move_list(dentry, dispose);
+ dentry_lru_del(dentry);
+ list_add_tail(&dentry->d_lru, dispose);
dentry->d_flags |= DCACHE_SHRINK_LIST;
found++;
}
diff --git a/fs/super.c b/fs/super.c
index 9049110..66f5cde 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -78,11 +78,11 @@ static long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
fs_objects = sb->s_op->nr_cached_objects(sb);
inodes = list_lru_count(&sb->s_inode_lru);
- total_objects = sb->s_nr_dentry_unused + inodes + fs_objects + 1;
+ dentries = list_lru_count(&sb->s_dentry_lru);
+ total_objects = dentries + inodes + fs_objects + 1;
/* proportion the scan between the caches */
- dentries = mult_frac(sc->nr_to_scan, sb->s_nr_dentry_unused,
- total_objects);
+ dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
/*
@@ -115,7 +115,7 @@ static long super_cache_count(struct shrinker *shrink, struct shrink_control *sc
if (sb->s_op && sb->s_op->nr_cached_objects)
total_objects = sb->s_op->nr_cached_objects(sb);
- total_objects += sb->s_nr_dentry_unused;
+ total_objects += list_lru_count(&sb->s_dentry_lru);
total_objects += list_lru_count(&sb->s_inode_lru);
total_objects = vfs_pressure_ratio(total_objects);
@@ -195,8 +195,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
INIT_HLIST_NODE(&s->s_instances);
INIT_HLIST_BL_HEAD(&s->s_anon);
INIT_LIST_HEAD(&s->s_inodes);
- INIT_LIST_HEAD(&s->s_dentry_lru);
- spin_lock_init(&s->s_dentry_lru_lock);
+ list_lru_init(&s->s_dentry_lru);
list_lru_init(&s->s_inode_lru);
INIT_LIST_HEAD(&s->s_mounts);
init_rwsem(&s->s_umount);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 89cda65..fc47371 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1264,14 +1264,6 @@ struct super_block {
struct list_head s_files;
#endif
struct list_head s_mounts; /* list of mounts; _not_ for fs use */
-
- /* s_dentry_lru_lock protects s_dentry_lru and s_nr_dentry_unused */
- spinlock_t s_dentry_lru_lock ____cacheline_aligned_in_smp;
- struct list_head s_dentry_lru; /* unused dentry lru */
- int s_nr_dentry_unused; /* # of dentry on lru */
-
- struct list_lru s_inode_lru ____cacheline_aligned_in_smp;
-
struct block_device *s_bdev;
struct backing_dev_info *s_bdi;
struct mtd_info *s_mtd;
@@ -1322,6 +1314,13 @@ struct super_block {
/* Being remounted read-only */
int s_readonly_remount;
+
+ /*
+ * Keep the lru lists last in the structure so they always sit on their
+ * own individual cachelines.
+ */
+ struct list_lru s_dentry_lru ____cacheline_aligned_in_smp;
+ struct list_lru s_inode_lru ____cacheline_aligned_in_smp;
};
extern struct timespec current_fs_time(struct super_block *sb);
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 10/31] dcache: convert to use new lru list infrastructure
2013-04-26 23:19 ` [PATCH v4 10/31] dcache: convert to use new lru list infrastructure Glauber Costa
@ 2013-04-30 16:04 ` Mel Gorman
2013-04-30 16:13 ` Glauber Costa
0 siblings, 1 reply; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 16:04 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
On Sat, Apr 27, 2013 at 03:19:06AM +0400, Glauber Costa wrote:
> From: Dave Chinner <dchinner@redhat.com>
>
> [ glommer: don't reintroduce double decrement of nr_unused_dentries,
> adapted for new LRU return codes ]
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Signed-off-by: Glauber Costa <glommer@openvz.org>
>
> <SNIP>
>
> @@ -361,35 +347,19 @@ static void dentry_lru_del(struct dentry *dentry)
> */
> static void dentry_lru_prune(struct dentry *dentry)
> {
> - if (!list_empty(&dentry->d_lru)) {
> + int prune = dentry->d_flags & DCACHE_OP_PRUNE;
>
> - if (dentry->d_flags & DCACHE_OP_PRUNE)
> - dentry->d_op->d_prune(dentry);
> -
> - if ((dentry->d_flags & DCACHE_SHRINK_LIST))
> - list_del_init(&dentry->d_lru);
> - else {
> - spin_lock(&dentry->d_sb->s_dentry_lru_lock);
> - __dentry_lru_del(dentry);
> - spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
> - }
> - dentry->d_flags &= ~DCACHE_SHRINK_LIST;
> - }
> -}
> -
> -static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list)
> -{
> - BUG_ON(dentry->d_flags & DCACHE_SHRINK_LIST);
> -
> - spin_lock(&dentry->d_sb->s_dentry_lru_lock);
> - if (list_empty(&dentry->d_lru)) {
> - list_add_tail(&dentry->d_lru, list);
> - } else {
> - list_move_tail(&dentry->d_lru, list);
> - dentry->d_sb->s_nr_dentry_unused--;
> + if (!list_empty(&dentry->d_lru) &&
> + (dentry->d_flags & DCACHE_SHRINK_LIST))
> + list_del_init(&dentry->d_lru);
> + else if (list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru))
> this_cpu_dec(nr_dentry_unused);
> - }
> - spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
> + else
> + prune = 0;
> +
> + dentry->d_flags &= ~DCACHE_SHRINK_LIST;
> + if (prune)
> + dentry->d_op->d_prune(dentry);
> }
>
It's a bit clearer now why list_lru_del deals with the object already
being deleted from the LRU. It's somewhat specific to the case where
an object on an LRU can also be looked up via an independent structure.
It's up to the user of list_lru to figure it out.
> <SNIP>
>
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 89cda65..fc47371 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -1264,14 +1264,6 @@ struct super_block {
> struct list_head s_files;
> #endif
> struct list_head s_mounts; /* list of mounts; _not_ for fs use */
> -
> - /* s_dentry_lru_lock protects s_dentry_lru and s_nr_dentry_unused */
> - spinlock_t s_dentry_lru_lock ____cacheline_aligned_in_smp;
> - struct list_head s_dentry_lru; /* unused dentry lru */
> - int s_nr_dentry_unused; /* # of dentry on lru */
> -
> - struct list_lru s_inode_lru ____cacheline_aligned_in_smp;
> -
> struct block_device *s_bdev;
> struct backing_dev_info *s_bdi;
> struct mtd_info *s_mtd;
> @@ -1322,6 +1314,13 @@ struct super_block {
>
> /* Being remounted read-only */
> int s_readonly_remount;
> +
> + /*
> + * Keep the lru lists last in the structure so they always sit on their
> + * own individual cachelines.
> + */
> + struct list_lru s_dentry_lru ____cacheline_aligned_in_smp;
> + struct list_lru s_inode_lru ____cacheline_aligned_in_smp;
> };
>
To save wasting space you could also put them each beside otherwise
read-mostly data, before s_mounts (per-cpu data before it should be
cache-aligned) and anywhere near the end of the structure without the
cache alignment directives.
Otherwise nothing jumped at me.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 10/31] dcache: convert to use new lru list infrastructure
2013-04-30 16:04 ` Mel Gorman
@ 2013-04-30 16:13 ` Glauber Costa
0 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-30 16:13 UTC (permalink / raw)
To: Mel Gorman
Cc: Glauber Costa, linux-mm, cgroups, Andrew Morton, Greg Thelen,
kamezawa.hiroyu, Michal Hocko, Johannes Weiner, Dave Chinner
>
> To save wasting space you could also put them each beside otherwise
> read-mostly data, before s_mounts (per-cpu data before it should be
> cache-aligned) and anywhere near the end of the structure without the
> cache alignment directives.
>
> Otherwise nothing jumped at me.
>
I will add:
Nothing-jumped-at: Mel Gorman <mgorman@suse.de>
=)
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 11/31] list_lru: per-node list infrastructure
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (9 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 10/31] dcache: convert to use new lru list infrastructure Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-30 16:33 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 12/31] shrinker: add node awareness Glauber Costa
` (20 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner, Glauber Costa
From: Dave Chinner <dchinner@redhat.com>
Now that we have an LRU list API, we can start to enhance the
implementation. This splits the single LRU list into per-node lists
and locks to enhance scalability. Items are placed on lists
according to the node the memory belongs to. To make scanning the
lists efficient, also track whether the per-node lists have entries
in them in a active nodemask.
[ glommer: fixed warnings ]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
Reviewed-by: Greg Thelen <gthelen@google.com>
---
include/linux/list_lru.h | 14 ++--
lib/list_lru.c | 162 +++++++++++++++++++++++++++++++++++------------
2 files changed, 130 insertions(+), 46 deletions(-)
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index c0b796d..c422782 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -8,6 +8,7 @@
#define _LRU_LIST_H
#include <linux/list.h>
+#include <linux/nodemask.h>
enum lru_status {
LRU_REMOVED, /* item removed from list */
@@ -17,20 +18,21 @@ enum lru_status {
internally, but has to return locked. */
};
-struct list_lru {
+struct list_lru_node {
spinlock_t lock;
struct list_head list;
long nr_items;
+} ____cacheline_aligned_in_smp;
+
+struct list_lru {
+ struct list_lru_node node[MAX_NUMNODES];
+ nodemask_t active_nodes;
};
int list_lru_init(struct list_lru *lru);
int list_lru_add(struct list_lru *lru, struct list_head *item);
int list_lru_del(struct list_lru *lru, struct list_head *item);
-
-static inline long list_lru_count(struct list_lru *lru)
-{
- return lru->nr_items;
-}
+long list_lru_count(struct list_lru *lru);
typedef enum lru_status
(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
diff --git a/lib/list_lru.c b/lib/list_lru.c
index 937ee87..248921d 100644
--- a/lib/list_lru.c
+++ b/lib/list_lru.c
@@ -6,6 +6,7 @@
*/
#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/mm.h>
#include <linux/list_lru.h>
int
@@ -13,14 +14,19 @@ list_lru_add(
struct list_lru *lru,
struct list_head *item)
{
- spin_lock(&lru->lock);
+ int nid = page_to_nid(virt_to_page(item));
+ struct list_lru_node *nlru = &lru->node[nid];
+
+ spin_lock(&nlru->lock);
+ BUG_ON(nlru->nr_items < 0);
if (list_empty(item)) {
- list_add_tail(item, &lru->list);
- lru->nr_items++;
- spin_unlock(&lru->lock);
+ list_add_tail(item, &nlru->list);
+ if (nlru->nr_items++ == 0)
+ node_set(nid, lru->active_nodes);
+ spin_unlock(&nlru->lock);
return 1;
}
- spin_unlock(&lru->lock);
+ spin_unlock(&nlru->lock);
return 0;
}
EXPORT_SYMBOL_GPL(list_lru_add);
@@ -30,44 +36,73 @@ list_lru_del(
struct list_lru *lru,
struct list_head *item)
{
- spin_lock(&lru->lock);
+ int nid = page_to_nid(virt_to_page(item));
+ struct list_lru_node *nlru = &lru->node[nid];
+
+ spin_lock(&nlru->lock);
if (!list_empty(item)) {
list_del_init(item);
- lru->nr_items--;
- spin_unlock(&lru->lock);
+ if (--nlru->nr_items == 0)
+ node_clear(nid, lru->active_nodes);
+ BUG_ON(nlru->nr_items < 0);
+ spin_unlock(&nlru->lock);
return 1;
}
- spin_unlock(&lru->lock);
+ spin_unlock(&nlru->lock);
return 0;
}
EXPORT_SYMBOL_GPL(list_lru_del);
long
-list_lru_walk(
- struct list_lru *lru,
- list_lru_walk_cb isolate,
- void *cb_arg,
- long nr_to_walk)
+list_lru_count(
+ struct list_lru *lru)
{
+ long count = 0;
+ int nid;
+
+ for_each_node_mask(nid, lru->active_nodes) {
+ struct list_lru_node *nlru = &lru->node[nid];
+
+ spin_lock(&nlru->lock);
+ BUG_ON(nlru->nr_items < 0);
+ count += nlru->nr_items;
+ spin_unlock(&nlru->lock);
+ }
+
+ return count;
+}
+EXPORT_SYMBOL_GPL(list_lru_count);
+
+static long
+list_lru_walk_node(
+ struct list_lru *lru,
+ int nid,
+ list_lru_walk_cb isolate,
+ void *cb_arg,
+ long *nr_to_walk)
+{
+ struct list_lru_node *nlru = &lru->node[nid];
struct list_head *item, *n;
- long removed = 0;
+ long isolated = 0;
- spin_lock(&lru->lock);
+ spin_lock(&nlru->lock);
restart:
- list_for_each_safe(item, n, &lru->list) {
+ list_for_each_safe(item, n, &nlru->list) {
enum lru_status ret;
- if (nr_to_walk-- < 0)
+ if ((*nr_to_walk)-- < 0)
break;
- ret = isolate(item, &lru->lock, cb_arg);
+ ret = isolate(item, &nlru->lock, cb_arg);
switch (ret) {
case LRU_REMOVED:
- lru->nr_items--;
- removed++;
+ if (--nlru->nr_items == 0)
+ node_clear(nid, lru->active_nodes);
+ BUG_ON(nlru->nr_items < 0);
+ isolated++;
break;
case LRU_ROTATE:
- list_move_tail(item, &lru->list);
+ list_move_tail(item, &nlru->list);
break;
case LRU_SKIP:
break;
@@ -77,42 +112,89 @@ restart:
BUG();
}
}
- spin_unlock(&lru->lock);
- return removed;
+ spin_unlock(&nlru->lock);
+ return isolated;
}
-EXPORT_SYMBOL_GPL(list_lru_walk);
long
-list_lru_dispose_all(
- struct list_lru *lru,
- list_lru_dispose_cb dispose)
+list_lru_walk(
+ struct list_lru *lru,
+ list_lru_walk_cb isolate,
+ void *cb_arg,
+ long nr_to_walk)
{
- long disposed = 0;
+ long isolated = 0;
+ int nid;
+
+ for_each_node_mask(nid, lru->active_nodes) {
+ isolated += list_lru_walk_node(lru, nid, isolate,
+ cb_arg, &nr_to_walk);
+ if (nr_to_walk <= 0)
+ break;
+ }
+ return isolated;
+}
+EXPORT_SYMBOL_GPL(list_lru_walk);
+
+static long
+list_lru_dispose_all_node(
+ struct list_lru *lru,
+ int nid,
+ list_lru_dispose_cb dispose)
+{
+ struct list_lru_node *nlru = &lru->node[nid];
LIST_HEAD(dispose_list);
+ long disposed = 0;
- spin_lock(&lru->lock);
- while (!list_empty(&lru->list)) {
- list_splice_init(&lru->list, &dispose_list);
- disposed += lru->nr_items;
- lru->nr_items = 0;
- spin_unlock(&lru->lock);
+ spin_lock(&nlru->lock);
+ while (!list_empty(&nlru->list)) {
+ list_splice_init(&nlru->list, &dispose_list);
+ disposed += nlru->nr_items;
+ nlru->nr_items = 0;
+ node_clear(nid, lru->active_nodes);
+ spin_unlock(&nlru->lock);
dispose(&dispose_list);
- spin_lock(&lru->lock);
+ spin_lock(&nlru->lock);
}
- spin_unlock(&lru->lock);
+ spin_unlock(&nlru->lock);
return disposed;
}
+long
+list_lru_dispose_all(
+ struct list_lru *lru,
+ list_lru_dispose_cb dispose)
+{
+ long disposed;
+ long total = 0;
+ int nid;
+
+ do {
+ disposed = 0;
+ for_each_node_mask(nid, lru->active_nodes) {
+ disposed += list_lru_dispose_all_node(lru, nid,
+ dispose);
+ }
+ total += disposed;
+ } while (disposed != 0);
+
+ return total;
+}
+
int
list_lru_init(
struct list_lru *lru)
{
- spin_lock_init(&lru->lock);
- INIT_LIST_HEAD(&lru->list);
- lru->nr_items = 0;
+ int i;
+ nodes_clear(lru->active_nodes);
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ spin_lock_init(&lru->node[i].lock);
+ INIT_LIST_HEAD(&lru->node[i].list);
+ lru->node[i].nr_items = 0;
+ }
return 0;
}
EXPORT_SYMBOL_GPL(list_lru_init);
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 11/31] list_lru: per-node list infrastructure
2013-04-26 23:19 ` [PATCH v4 11/31] list_lru: per-node " Glauber Costa
@ 2013-04-30 16:33 ` Mel Gorman
2013-04-30 21:44 ` Glauber Costa
0 siblings, 1 reply; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 16:33 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
On Sat, Apr 27, 2013 at 03:19:07AM +0400, Glauber Costa wrote:
> From: Dave Chinner <dchinner@redhat.com>
>
> Now that we have an LRU list API, we can start to enhance the
> implementation. This splits the single LRU list into per-node lists
> and locks to enhance scalability. Items are placed on lists
> according to the node the memory belongs to. To make scanning the
> lists efficient, also track whether the per-node lists have entries
> in them in a active nodemask.
>
> [ glommer: fixed warnings ]
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Signed-off-by: Glauber Costa <glommer@openvz.org>
> Reviewed-by: Greg Thelen <gthelen@google.com>
> ---
> include/linux/list_lru.h | 14 ++--
> lib/list_lru.c | 162 +++++++++++++++++++++++++++++++++++------------
> 2 files changed, 130 insertions(+), 46 deletions(-)
>
> diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
> index c0b796d..c422782 100644
> --- a/include/linux/list_lru.h
> +++ b/include/linux/list_lru.h
> @@ -8,6 +8,7 @@
> #define _LRU_LIST_H
>
> #include <linux/list.h>
> +#include <linux/nodemask.h>
>
> enum lru_status {
> LRU_REMOVED, /* item removed from list */
> @@ -17,20 +18,21 @@ enum lru_status {
> internally, but has to return locked. */
> };
>
> -struct list_lru {
> +struct list_lru_node {
> spinlock_t lock;
> struct list_head list;
> long nr_items;
> +} ____cacheline_aligned_in_smp;
> +
> +struct list_lru {
> + struct list_lru_node node[MAX_NUMNODES];
> + nodemask_t active_nodes;
> };
struct list_lru is going to be large. 64K just for the list_lru_nodes on a
distribution configuration that has NODES_SHIFT==10. On most machines it'll
be mostly unused space. How big is super_block now with two of these things?
xfs_buftarg? They are rarely allocated structures but it would be a little
embarassing if we failed to mount a usb stick because kmalloc() of some
large buffer failed on a laptop.
You may need to convert "list_lru_node node" to be an array of MAX_NUMNODES
pointers to list_lru_nodes. It'd need a lookup helper for list_lru_add
and list_lru_del that lazily allocates the list_lru_nodes on first usage
in case of node hot-add. You could allocate the online nodes at
list_lru_init.
It'd be awkward but avoid the need for a large kmalloc at runtime just
because someone plugged in a USB stick.
Otherwise I didn't spot a major problem. There are now per-node lists to
walk but the overall size of the LRU for walkers should be similar and
the additional overhead in list_lru_count is hardly going to be
noticable. I liked the use of active_mask.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 11/31] list_lru: per-node list infrastructure
2013-04-30 16:33 ` Mel Gorman
@ 2013-04-30 21:44 ` Glauber Costa
0 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-30 21:44 UTC (permalink / raw)
To: Mel Gorman
Cc: Glauber Costa, linux-mm, cgroups, Andrew Morton, Greg Thelen,
kamezawa.hiroyu, Michal Hocko, Johannes Weiner, Dave Chinner
On 04/30/2013 08:33 PM, Mel Gorman wrote:
> On Sat, Apr 27, 2013 at 03:19:07AM +0400, Glauber Costa wrote:
>> From: Dave Chinner <dchinner@redhat.com>
>>
>> Now that we have an LRU list API, we can start to enhance the
>> implementation. This splits the single LRU list into per-node lists
>> and locks to enhance scalability. Items are placed on lists
>> according to the node the memory belongs to. To make scanning the
>> lists efficient, also track whether the per-node lists have entries
>> in them in a active nodemask.
>>
>> [ glommer: fixed warnings ]
>> Signed-off-by: Dave Chinner <dchinner@redhat.com>
>> Signed-off-by: Glauber Costa <glommer@openvz.org>
>> Reviewed-by: Greg Thelen <gthelen@google.com>
>> ---
>> include/linux/list_lru.h | 14 ++--
>> lib/list_lru.c | 162 +++++++++++++++++++++++++++++++++++------------
>> 2 files changed, 130 insertions(+), 46 deletions(-)
>>
>> diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
>> index c0b796d..c422782 100644
>> --- a/include/linux/list_lru.h
>> +++ b/include/linux/list_lru.h
>> @@ -8,6 +8,7 @@
>> #define _LRU_LIST_H
>>
>> #include <linux/list.h>
>> +#include <linux/nodemask.h>
>>
>> enum lru_status {
>> LRU_REMOVED, /* item removed from list */
>> @@ -17,20 +18,21 @@ enum lru_status {
>> internally, but has to return locked. */
>> };
>>
>> -struct list_lru {
>> +struct list_lru_node {
>> spinlock_t lock;
>> struct list_head list;
>> long nr_items;
>> +} ____cacheline_aligned_in_smp;
>> +
>> +struct list_lru {
>> + struct list_lru_node node[MAX_NUMNODES];
>> + nodemask_t active_nodes;
>> };
>
> struct list_lru is going to be large. 64K just for the list_lru_nodes on a
> distribution configuration that has NODES_SHIFT==10. On most machines it'll
> be mostly unused space. How big is super_block now with two of these things?
> xfs_buftarg? They are rarely allocated structures but it would be a little
> embarassing if we failed to mount a usb stick because kmalloc() of some
> large buffer failed on a laptop.
If you take a look at the memcg patches, because they are dynamic by
nature, I am using nr_node_ids instead of MAX_NUMNODES. There is some
care to be taken, for instance, now we always have to filter a complete
nodemask against present nodes. But I do that for memcg, and could bring
the code earlier in the series.
The main disadvantage that I see for it, is that a lot of the LRUs are
statically defined. Since nr_node_ids is a runtime constant, we would
have to allocate them all and let them live outside the structure that
contains them. We can size the structure itself, but then we need to go
with the standard trickery of forcing it to be the last element, etc.
May not always work for such a generic construct.
So maybe it should wait to see if there is ever a problem? I tend to run
my VMs with 300Mb run, with even smaller memcgs, particularly to stress
low memory situation easily. I don't recall ever seeing a problem like
that, although of course we would always want to keep memory consumption
low if we can...
>
> You may need to convert "list_lru_node node" to be an array of MAX_NUMNODES
> pointers to list_lru_nodes. It'd need a lookup helper for list_lru_add
> and list_lru_del that lazily allocates the list_lru_nodes on first usage
> in case of node hot-add. You could allocate the online nodes at
> list_lru_init.
>
> It'd be awkward but avoid the need for a large kmalloc at runtime just
> because someone plugged in a USB stick.
>
> Otherwise I didn't spot a major problem. There are now per-node lists to
> walk but the overall size of the LRU for walkers should be similar and
> the additional overhead in list_lru_count is hardly going to be
> noticable. I liked the use of active_mask.
>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 12/31] shrinker: add node awareness
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (10 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 11/31] list_lru: per-node " Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-30 16:35 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 13/31] fs: convert inode and dentry shrinking to be node aware Glauber Costa
` (19 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner, Glauber Costa
From: Dave Chinner <dchinner@redhat.com>
Pass the node of the current zone being reclaimed to shrink_slab(),
allowing the shrinker control nodemask to be set appropriately for
node aware shrinkers.
[ v3: update ashmem ]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
---
drivers/staging/android/ashmem.c | 3 +++
fs/drop_caches.c | 1 +
include/linux/shrinker.h | 3 +++
mm/memory-failure.c | 2 ++
mm/vmscan.c | 12 +++++++++---
5 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index e681bdd..3240d34 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -692,6 +692,9 @@ static long ashmem_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
.gfp_mask = GFP_KERNEL,
.nr_to_scan = 0,
};
+
+ nodes_setall(sc.nodes_to_scan);
+
ret = ashmem_shrink(&ashmem_shrinker, &sc);
sc.nr_to_scan = ret;
ashmem_shrink(&ashmem_shrinker, &sc);
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index f23d2a7..c3f44e7 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -44,6 +44,7 @@ static void drop_slab(void)
.gfp_mask = GFP_KERNEL,
};
+ nodes_setall(shrink.nodes_to_scan);
do {
nr_objects = shrink_slab(&shrink, 1000, 1000);
} while (nr_objects > 10);
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 4f59615..e71286f 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -16,6 +16,9 @@ struct shrink_control {
/* How many slab objects shrinker() should scan and try to reclaim */
long nr_to_scan;
+
+ /* shrink from these nodes */
+ nodemask_t nodes_to_scan;
};
/*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index ceb0c7f..86788ff 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -248,10 +248,12 @@ void shake_page(struct page *p, int access)
*/
if (access) {
int nr;
+ int nid = page_to_nid(p);
do {
struct shrink_control shrink = {
.gfp_mask = GFP_KERNEL,
};
+ node_set(nid, shrink.nodes_to_scan);
nr = shrink_slab(&shrink, 1000, 1000);
if (page_count(p) == 1)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ca3f690..b11a9cc 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2199,15 +2199,20 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
*/
if (global_reclaim(sc)) {
unsigned long lru_pages = 0;
+
+ nodes_clear(shrink->nodes_to_scan);
for_each_zone_zonelist(zone, z, zonelist,
gfp_zone(sc->gfp_mask)) {
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
lru_pages += zone_reclaimable_pages(zone);
+ node_set(zone_to_nid(zone),
+ shrink->nodes_to_scan);
}
shrink_slab(shrink, sc->nr_scanned, lru_pages);
+
if (reclaim_state) {
sc->nr_reclaimed += reclaim_state->reclaimed_slab;
reclaim_state->reclaimed_slab = 0;
@@ -2783,6 +2788,8 @@ loop_again:
shrink_zone(zone, &sc);
reclaim_state->reclaimed_slab = 0;
+ nodes_clear(shrink.nodes_to_scan);
+ node_set(zone_to_nid(zone), shrink.nodes_to_scan);
nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages);
sc.nr_reclaimed += reclaim_state->reclaimed_slab;
@@ -3368,10 +3375,9 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
* number of slab pages and shake the slab until it is reduced
* by the same nr_pages that we used for reclaiming unmapped
* pages.
- *
- * Note that shrink_slab will free memory on all zones and may
- * take a long time.
*/
+ nodes_clear(shrink.nodes_to_scan);
+ node_set(zone_to_nid(zone), shrink.nodes_to_scan);
for (;;) {
unsigned long lru_pages = zone_reclaimable_pages(zone);
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 12/31] shrinker: add node awareness
2013-04-26 23:19 ` [PATCH v4 12/31] shrinker: add node awareness Glauber Costa
@ 2013-04-30 16:35 ` Mel Gorman
0 siblings, 0 replies; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 16:35 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
On Sat, Apr 27, 2013 at 03:19:08AM +0400, Glauber Costa wrote:
> From: Dave Chinner <dchinner@redhat.com>
>
> Pass the node of the current zone being reclaimed to shrink_slab(),
> allowing the shrinker control nodemask to be set appropriately for
> node aware shrinkers.
>
> [ v3: update ashmem ]
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Signed-off-by: Glauber Costa <glommer@openvz.org>
Acked-by: Mel Gorman <mgorman@suse.de>
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 13/31] fs: convert inode and dentry shrinking to be node aware
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (11 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 12/31] shrinker: add node awareness Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-30 17:39 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 14/31] xfs: convert buftarg LRU to generic code Glauber Costa
` (18 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
From: Dave Chinner <dchinner@redhat.com>
Now that the shrinker is passing a nodemask in the scan control
structure, we can pass this to the the generic LRU list code to
isolate reclaim to the lists on matching nodes.
This requires a small amount of refactoring of the LRU list API,
which might be best split out into a separate patch.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
fs/dcache.c | 8 +++++---
fs/inode.c | 7 ++++---
fs/internal.h | 6 ++++--
fs/super.c | 22 +++++++++++++---------
fs/xfs/xfs_super.c | 6 ++++--
include/linux/fs.h | 4 ++--
include/linux/list_lru.h | 19 ++++++++++++++++---
lib/list_lru.c | 18 ++++++++++--------
8 files changed, 58 insertions(+), 32 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index 9c5406f..60b34fc 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -888,6 +888,7 @@ dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
* prune_dcache_sb - shrink the dcache
* @sb: superblock
* @nr_to_scan : number of entries to try to free
+ * @nodes_to_walk: which nodes to scan for freeable entities
*
* Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is
* done when we need more memory an called from the superblock shrinker
@@ -896,13 +897,14 @@ dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
* This function may fail to free any resources if all the dentries are in
* use.
*/
-long prune_dcache_sb(struct super_block *sb, long nr_to_scan)
+long prune_dcache_sb(struct super_block *sb, long nr_to_scan,
+ nodemask_t *nodes_to_walk)
{
LIST_HEAD(dispose);
long freed;
- freed = list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate,
- &dispose, nr_to_scan);
+ freed = list_lru_walk_nodemask(&sb->s_dentry_lru, dentry_lru_isolate,
+ &dispose, nr_to_scan, nodes_to_walk);
shrink_dentry_list(&dispose);
return freed;
}
diff --git a/fs/inode.c b/fs/inode.c
index c6c62a8..dd1f6e9 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -746,13 +746,14 @@ inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
* to trim from the LRU. Inodes to be freed are moved to a temporary list and
* then are freed outside inode_lock by dispose_list().
*/
-long prune_icache_sb(struct super_block *sb, long nr_to_scan)
+long prune_icache_sb(struct super_block *sb, long nr_to_scan,
+ nodemask_t *nodes_to_walk)
{
LIST_HEAD(freeable);
long freed;
- freed = list_lru_walk(&sb->s_inode_lru, inode_lru_isolate,
- &freeable, nr_to_scan);
+ freed = list_lru_walk_nodemask(&sb->s_inode_lru, inode_lru_isolate,
+ &freeable, nr_to_scan, nodes_to_walk);
dispose_list(&freeable);
return freed;
}
diff --git a/fs/internal.h b/fs/internal.h
index f2da2b5..552cdd6 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -110,7 +110,8 @@ extern int open_check_o_direct(struct file *f);
* inode.c
*/
extern spinlock_t inode_sb_list_lock;
-extern long prune_icache_sb(struct super_block *sb, long nr_to_scan);
+extern long prune_icache_sb(struct super_block *sb, long nr_to_scan,
+ nodemask_t *nodes_to_scan);
extern void inode_add_lru(struct inode *inode);
/*
@@ -126,7 +127,8 @@ extern int invalidate_inodes(struct super_block *, bool);
* dcache.c
*/
extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
-extern long prune_dcache_sb(struct super_block *sb, long nr_to_scan);
+extern long prune_dcache_sb(struct super_block *sb, long nr_to_scan,
+ nodemask_t *nodes_to_scan);
/*
* read_write.c
diff --git a/fs/super.c b/fs/super.c
index 66f5cde..5c7b879 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -75,10 +75,10 @@ static long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
return -1;
if (sb->s_op && sb->s_op->nr_cached_objects)
- fs_objects = sb->s_op->nr_cached_objects(sb);
+ fs_objects = sb->s_op->nr_cached_objects(sb, &sc->nodes_to_scan);
- inodes = list_lru_count(&sb->s_inode_lru);
- dentries = list_lru_count(&sb->s_dentry_lru);
+ inodes = list_lru_count_nodemask(&sb->s_inode_lru, &sc->nodes_to_scan);
+ dentries = list_lru_count_nodemask(&sb->s_dentry_lru, &sc->nodes_to_scan);
total_objects = dentries + inodes + fs_objects + 1;
/* proportion the scan between the caches */
@@ -89,13 +89,14 @@ static long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
* prune the dcache first as the icache is pinned by it, then
* prune the icache, followed by the filesystem specific caches
*/
- freed = prune_dcache_sb(sb, dentries);
- freed += prune_icache_sb(sb, inodes);
+ freed = prune_dcache_sb(sb, dentries, &sc->nodes_to_scan);
+ freed += prune_icache_sb(sb, inodes, &sc->nodes_to_scan);
if (fs_objects) {
fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
total_objects);
- freed += sb->s_op->free_cached_objects(sb, fs_objects);
+ freed += sb->s_op->free_cached_objects(sb, fs_objects,
+ &sc->nodes_to_scan);
}
drop_super(sb);
@@ -113,10 +114,13 @@ static long super_cache_count(struct shrinker *shrink, struct shrink_control *sc
return -1;
if (sb->s_op && sb->s_op->nr_cached_objects)
- total_objects = sb->s_op->nr_cached_objects(sb);
+ total_objects = sb->s_op->nr_cached_objects(sb,
+ &sc->nodes_to_scan);
- total_objects += list_lru_count(&sb->s_dentry_lru);
- total_objects += list_lru_count(&sb->s_inode_lru);
+ total_objects += list_lru_count_nodemask(&sb->s_dentry_lru,
+ &sc->nodes_to_scan);
+ total_objects += list_lru_count_nodemask(&sb->s_inode_lru,
+ &sc->nodes_to_scan);
total_objects = vfs_pressure_ratio(total_objects);
drop_super(sb);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 1ff991b..7fa60214 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1525,7 +1525,8 @@ xfs_fs_mount(
static long
xfs_fs_nr_cached_objects(
- struct super_block *sb)
+ struct super_block *sb,
+ nodemask_t *nodes_to_count)
{
return xfs_reclaim_inodes_count(XFS_M(sb));
}
@@ -1533,7 +1534,8 @@ xfs_fs_nr_cached_objects(
static long
xfs_fs_free_cached_objects(
struct super_block *sb,
- long nr_to_scan)
+ long nr_to_scan,
+ nodemask_t *nodes_to_scan)
{
return xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan);
}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index fc47371..28eb053 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1609,8 +1609,8 @@ struct super_operations {
ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
#endif
int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
- long (*nr_cached_objects)(struct super_block *);
- long (*free_cached_objects)(struct super_block *, long);
+ long (*nr_cached_objects)(struct super_block *, nodemask_t *);
+ long (*free_cached_objects)(struct super_block *, long, nodemask_t *);
};
/*
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index c422782..5ed2b94 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -32,15 +32,28 @@ struct list_lru {
int list_lru_init(struct list_lru *lru);
int list_lru_add(struct list_lru *lru, struct list_head *item);
int list_lru_del(struct list_lru *lru, struct list_head *item);
-long list_lru_count(struct list_lru *lru);
+long list_lru_count_nodemask(struct list_lru *lru, nodemask_t *nodes_to_count);
+
+static inline long list_lru_count(struct list_lru *lru)
+{
+ return list_lru_count_nodemask(lru, &lru->active_nodes);
+}
+
typedef enum lru_status
(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
typedef void (*list_lru_dispose_cb)(struct list_head *dispose_list);
-long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
- void *cb_arg, long nr_to_walk);
+long list_lru_walk_nodemask(struct list_lru *lru, list_lru_walk_cb isolate,
+ void *cb_arg, long nr_to_walk, nodemask_t *nodes_to_walk);
+
+static inline long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
+ void *cb_arg, long nr_to_walk)
+{
+ return list_lru_walk_nodemask(lru, isolate, cb_arg, nr_to_walk,
+ &lru->active_nodes);
+}
long list_lru_dispose_all(struct list_lru *lru, list_lru_dispose_cb dispose);
diff --git a/lib/list_lru.c b/lib/list_lru.c
index 248921d..221e361 100644
--- a/lib/list_lru.c
+++ b/lib/list_lru.c
@@ -54,13 +54,14 @@ list_lru_del(
EXPORT_SYMBOL_GPL(list_lru_del);
long
-list_lru_count(
- struct list_lru *lru)
+list_lru_count_nodemask(
+ struct list_lru *lru,
+ nodemask_t *nodes_to_count)
{
long count = 0;
int nid;
- for_each_node_mask(nid, lru->active_nodes) {
+ for_each_node_mask(nid, *nodes_to_count) {
struct list_lru_node *nlru = &lru->node[nid];
spin_lock(&nlru->lock);
@@ -71,7 +72,7 @@ list_lru_count(
return count;
}
-EXPORT_SYMBOL_GPL(list_lru_count);
+EXPORT_SYMBOL_GPL(list_lru_count_nodemask);
static long
list_lru_walk_node(
@@ -117,16 +118,17 @@ restart:
}
long
-list_lru_walk(
+list_lru_walk_nodemask(
struct list_lru *lru,
list_lru_walk_cb isolate,
void *cb_arg,
- long nr_to_walk)
+ long nr_to_walk,
+ nodemask_t *nodes_to_walk)
{
long isolated = 0;
int nid;
- for_each_node_mask(nid, lru->active_nodes) {
+ for_each_node_mask(nid, *nodes_to_walk) {
isolated += list_lru_walk_node(lru, nid, isolate,
cb_arg, &nr_to_walk);
if (nr_to_walk <= 0)
@@ -134,7 +136,7 @@ list_lru_walk(
}
return isolated;
}
-EXPORT_SYMBOL_GPL(list_lru_walk);
+EXPORT_SYMBOL_GPL(list_lru_walk_nodemask);
static long
list_lru_dispose_all_node(
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 13/31] fs: convert inode and dentry shrinking to be node aware
2013-04-26 23:19 ` [PATCH v4 13/31] fs: convert inode and dentry shrinking to be node aware Glauber Costa
@ 2013-04-30 17:39 ` Mel Gorman
0 siblings, 0 replies; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 17:39 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
On Sat, Apr 27, 2013 at 03:19:09AM +0400, Glauber Costa wrote:
> From: Dave Chinner <dchinner@redhat.com>
>
> Now that the shrinker is passing a nodemask in the scan control
> structure, we can pass this to the the generic LRU list code to
> isolate reclaim to the lists on matching nodes.
>
> This requires a small amount of refactoring of the LRU list API,
> which might be best split out into a separate patch.
>
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off missing but otherwise
Acked-by: Mel Gorman <mgorman@suse.de>
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 14/31] xfs: convert buftarg LRU to generic code
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (12 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 13/31] fs: convert inode and dentry shrinking to be node aware Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 15/31] xfs: convert dquot cache lru to list_lru Glauber Costa
` (17 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Dave Chinner
From: Dave Chinner <dchinner@redhat.com>
Convert the buftarg LRU to use the new generic LRU list and take
advantage of the functionality it supplies to make the buffer cache
shrinker node aware.
Signed-off-by: Glauber Costa <glommer@openvz.org>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Conflicts with 3b19034d4f:
fs/xfs/xfs_buf.c
---
fs/xfs/xfs_buf.c | 169 ++++++++++++++++++++++++++-----------------------------
fs/xfs/xfs_buf.h | 5 +-
2 files changed, 81 insertions(+), 93 deletions(-)
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index cee0e42..802b65b 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -85,20 +85,14 @@ xfs_buf_vmap_len(
* The LRU takes a new reference to the buffer so that it will only be freed
* once the shrinker takes the buffer off the LRU.
*/
-STATIC void
+static void
xfs_buf_lru_add(
struct xfs_buf *bp)
{
- struct xfs_buftarg *btp = bp->b_target;
-
- spin_lock(&btp->bt_lru_lock);
- if (list_empty(&bp->b_lru)) {
- atomic_inc(&bp->b_hold);
- list_add_tail(&bp->b_lru, &btp->bt_lru);
- btp->bt_lru_nr++;
+ if (list_lru_add(&bp->b_target->bt_lru, &bp->b_lru)) {
bp->b_lru_flags &= ~_XBF_LRU_DISPOSE;
+ atomic_inc(&bp->b_hold);
}
- spin_unlock(&btp->bt_lru_lock);
}
/*
@@ -107,24 +101,13 @@ xfs_buf_lru_add(
* The unlocked check is safe here because it only occurs when there are not
* b_lru_ref counts left on the inode under the pag->pag_buf_lock. it is there
* to optimise the shrinker removing the buffer from the LRU and calling
- * xfs_buf_free(). i.e. it removes an unnecessary round trip on the
- * bt_lru_lock.
+ * xfs_buf_free().
*/
-STATIC void
+static void
xfs_buf_lru_del(
struct xfs_buf *bp)
{
- struct xfs_buftarg *btp = bp->b_target;
-
- if (list_empty(&bp->b_lru))
- return;
-
- spin_lock(&btp->bt_lru_lock);
- if (!list_empty(&bp->b_lru)) {
- list_del_init(&bp->b_lru);
- btp->bt_lru_nr--;
- }
- spin_unlock(&btp->bt_lru_lock);
+ list_lru_del(&bp->b_target->bt_lru, &bp->b_lru);
}
/*
@@ -151,18 +134,10 @@ xfs_buf_stale(
bp->b_flags &= ~_XBF_DELWRI_Q;
atomic_set(&(bp)->b_lru_ref, 0);
- if (!list_empty(&bp->b_lru)) {
- struct xfs_buftarg *btp = bp->b_target;
-
- spin_lock(&btp->bt_lru_lock);
- if (!list_empty(&bp->b_lru) &&
- !(bp->b_lru_flags & _XBF_LRU_DISPOSE)) {
- list_del_init(&bp->b_lru);
- btp->bt_lru_nr--;
- atomic_dec(&bp->b_hold);
- }
- spin_unlock(&btp->bt_lru_lock);
- }
+ if (!(bp->b_lru_flags & _XBF_LRU_DISPOSE) &&
+ (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru)))
+ atomic_dec(&bp->b_hold);
+
ASSERT(atomic_read(&bp->b_hold) >= 1);
}
@@ -1501,83 +1476,97 @@ xfs_buf_iomove(
* returned. These buffers will have an elevated hold count, so wait on those
* while freeing all the buffers only held by the LRU.
*/
-void
-xfs_wait_buftarg(
- struct xfs_buftarg *btp)
+static enum lru_status
+xfs_buftarg_wait_rele(
+ struct list_head *item,
+ spinlock_t *lru_lock,
+ void *arg)
+
{
- struct xfs_buf *bp;
+ struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru);
-restart:
- spin_lock(&btp->bt_lru_lock);
- while (!list_empty(&btp->bt_lru)) {
- bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru);
- if (atomic_read(&bp->b_hold) > 1) {
- trace_xfs_buf_wait_buftarg(bp, _RET_IP_);
- list_move_tail(&bp->b_lru, &btp->bt_lru);
- spin_unlock(&btp->bt_lru_lock);
- delay(100);
- goto restart;
- }
+ if (atomic_read(&bp->b_hold) > 1) {
+ /* need to wait */
+ trace_xfs_buf_wait_buftarg(bp, _RET_IP_);
+ spin_unlock(lru_lock);
+ delay(100);
+ } else {
/*
* clear the LRU reference count so the buffer doesn't get
* ignored in xfs_buf_rele().
*/
atomic_set(&bp->b_lru_ref, 0);
- spin_unlock(&btp->bt_lru_lock);
+ spin_unlock(lru_lock);
xfs_buf_rele(bp);
- spin_lock(&btp->bt_lru_lock);
}
- spin_unlock(&btp->bt_lru_lock);
+
+ spin_lock(lru_lock);
+ return LRU_RETRY;
}
-int
-xfs_buftarg_shrink(
+void
+xfs_wait_buftarg(
+ struct xfs_buftarg *btp)
+{
+ while (list_lru_count(&btp->bt_lru))
+ list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele,
+ NULL, LONG_MAX);
+}
+
+static enum lru_status
+xfs_buftarg_isolate(
+ struct list_head *item,
+ spinlock_t *lru_lock,
+ void *arg)
+{
+ struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru);
+ struct list_head *dispose = arg;
+
+ /*
+ * Decrement the b_lru_ref count unless the value is already
+ * zero. If the value is already zero, we need to reclaim the
+ * buffer, otherwise it gets another trip through the LRU.
+ */
+ if (!atomic_add_unless(&bp->b_lru_ref, -1, 0))
+ return LRU_ROTATE;
+
+ bp->b_lru_flags |= _XBF_LRU_DISPOSE;
+ list_move(item, dispose);
+ return LRU_REMOVED;
+}
+
+static long
+xfs_buftarg_shrink_scan(
struct shrinker *shrink,
struct shrink_control *sc)
{
struct xfs_buftarg *btp = container_of(shrink,
struct xfs_buftarg, bt_shrinker);
- struct xfs_buf *bp;
- int nr_to_scan = sc->nr_to_scan;
LIST_HEAD(dispose);
+ long freed;
- if (!nr_to_scan)
- return btp->bt_lru_nr;
-
- spin_lock(&btp->bt_lru_lock);
- while (!list_empty(&btp->bt_lru)) {
- if (nr_to_scan-- <= 0)
- break;
-
- bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru);
-
- /*
- * Decrement the b_lru_ref count unless the value is already
- * zero. If the value is already zero, we need to reclaim the
- * buffer, otherwise it gets another trip through the LRU.
- */
- if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) {
- list_move_tail(&bp->b_lru, &btp->bt_lru);
- continue;
- }
-
- /*
- * remove the buffer from the LRU now to avoid needing another
- * lock round trip inside xfs_buf_rele().
- */
- list_move(&bp->b_lru, &dispose);
- btp->bt_lru_nr--;
- bp->b_lru_flags |= _XBF_LRU_DISPOSE;
- }
- spin_unlock(&btp->bt_lru_lock);
+ freed = list_lru_walk_nodemask(&btp->bt_lru, xfs_buftarg_isolate,
+ &dispose, sc->nr_to_scan,
+ &sc->nodes_to_scan);
while (!list_empty(&dispose)) {
+ struct xfs_buf *bp;
bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
list_del_init(&bp->b_lru);
xfs_buf_rele(bp);
}
- return btp->bt_lru_nr;
+ return freed;
+}
+
+static long
+xfs_buftarg_shrink_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct xfs_buftarg *btp = container_of(shrink,
+ struct xfs_buftarg, bt_shrinker);
+ return list_lru_count_nodemask(&btp->bt_lru, &sc->nodes_to_scan);
}
void
@@ -1659,11 +1648,11 @@ xfs_alloc_buftarg(
if (!btp->bt_bdi)
goto error;
- INIT_LIST_HEAD(&btp->bt_lru);
- spin_lock_init(&btp->bt_lru_lock);
+ list_lru_init(&btp->bt_lru);
if (xfs_setsize_buftarg_early(btp, bdev))
goto error;
- btp->bt_shrinker.shrink = xfs_buftarg_shrink;
+ btp->bt_shrinker.count_objects = xfs_buftarg_shrink_count;
+ btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan;
btp->bt_shrinker.seeks = DEFAULT_SEEKS;
register_shrinker(&btp->bt_shrinker);
return btp;
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 433a12e..5ec7d35 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -25,6 +25,7 @@
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/uio.h>
+#include <linux/list_lru.h>
/*
* Base types
@@ -92,9 +93,7 @@ typedef struct xfs_buftarg {
/* LRU control structures */
struct shrinker bt_shrinker;
- struct list_head bt_lru;
- spinlock_t bt_lru_lock;
- unsigned int bt_lru_nr;
+ struct list_lru bt_lru;
} xfs_buftarg_t;
struct xfs_buf;
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 15/31] xfs: convert dquot cache lru to list_lru
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (13 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 14/31] xfs: convert buftarg LRU to generic code Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 16/31] fs: convert fs shrinkers to new scan/count API Glauber Costa
` (16 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner, Glauber Costa
From: Dave Chinner <dchinner@redhat.com>
Convert the XFS dquot lru to use the list_lru construct and convert
the shrinker to being node aware.
[ glommer: edited for conflicts + warning fixes ]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
---
fs/xfs/xfs_dquot.c | 7 +-
fs/xfs/xfs_qm.c | 275 +++++++++++++++++++++++++++--------------------------
fs/xfs/xfs_qm.h | 4 +-
3 files changed, 142 insertions(+), 144 deletions(-)
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 45bb08f..f2ce99c 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -875,13 +875,8 @@ xfs_qm_dqput_final(
trace_xfs_dqput_free(dqp);
- mutex_lock(&qi->qi_lru_lock);
- if (list_empty(&dqp->q_lru)) {
- list_add_tail(&dqp->q_lru, &qi->qi_lru_list);
- qi->qi_lru_count++;
+ if (list_lru_add(&qi->qi_lru, &dqp->q_lru))
XFS_STATS_INC(xs_qm_dquot_unused);
- }
- mutex_unlock(&qi->qi_lru_lock);
/*
* If we just added a udquot to the freelist, then we want to release
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 82604c3..2991954 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -50,8 +50,9 @@
*/
STATIC int xfs_qm_init_quotainos(xfs_mount_t *);
STATIC int xfs_qm_init_quotainfo(xfs_mount_t *);
-STATIC int xfs_qm_shake(struct shrinker *, struct shrink_control *);
+
+STATIC void xfs_qm_dqfree_one(struct xfs_dquot *dqp);
/*
* We use the batch lookup interface to iterate over the dquots as it
* currently is the only interface into the radix tree code that allows
@@ -196,12 +197,9 @@ xfs_qm_dqpurge(
* We move dquots to the freelist as soon as their reference count
* hits zero, so it really should be on the freelist here.
*/
- mutex_lock(&qi->qi_lru_lock);
ASSERT(!list_empty(&dqp->q_lru));
- list_del_init(&dqp->q_lru);
- qi->qi_lru_count--;
+ list_lru_del(&qi->qi_lru, &dqp->q_lru);
XFS_STATS_DEC(xs_qm_dquot_unused);
- mutex_unlock(&qi->qi_lru_lock);
xfs_qm_dqdestroy(dqp);
@@ -617,6 +615,140 @@ xfs_qm_dqdetach(
}
}
+struct xfs_qm_isolate {
+ struct list_head buffers;
+ struct list_head dispose;
+};
+
+static enum lru_status
+xfs_qm_dquot_isolate(
+ struct list_head *item,
+ spinlock_t *lru_lock,
+ void *arg)
+{
+ struct xfs_dquot *dqp = container_of(item,
+ struct xfs_dquot, q_lru);
+ struct xfs_qm_isolate *isol = arg;
+
+ if (!xfs_dqlock_nowait(dqp))
+ goto out_miss_busy;
+
+ /*
+ * This dquot has acquired a reference in the meantime remove it from
+ * the freelist and try again.
+ */
+ if (dqp->q_nrefs) {
+ xfs_dqunlock(dqp);
+ XFS_STATS_INC(xs_qm_dqwants);
+
+ trace_xfs_dqreclaim_want(dqp);
+ list_del_init(&dqp->q_lru);
+ XFS_STATS_DEC(xs_qm_dquot_unused);
+ return 0;
+ }
+
+ /*
+ * If the dquot is dirty, flush it. If it's already being flushed, just
+ * skip it so there is time for the IO to complete before we try to
+ * reclaim it again on the next LRU pass.
+ */
+ if (!xfs_dqflock_nowait(dqp)) {
+ xfs_dqunlock(dqp);
+ goto out_miss_busy;
+ }
+
+ if (XFS_DQ_IS_DIRTY(dqp)) {
+ struct xfs_buf *bp = NULL;
+ int error;
+
+ trace_xfs_dqreclaim_dirty(dqp);
+
+ /* we have to drop the LRU lock to flush the dquot */
+ spin_unlock(lru_lock);
+
+ error = xfs_qm_dqflush(dqp, &bp);
+ if (error) {
+ xfs_warn(dqp->q_mount, "%s: dquot %p flush failed",
+ __func__, dqp);
+ goto out_unlock_dirty;
+ }
+
+ xfs_buf_delwri_queue(bp, &isol->buffers);
+ xfs_buf_relse(bp);
+ goto out_unlock_dirty;
+ }
+ xfs_dqfunlock(dqp);
+
+ /*
+ * Prevent lookups now that we are past the point of no return.
+ */
+ dqp->dq_flags |= XFS_DQ_FREEING;
+ xfs_dqunlock(dqp);
+
+ ASSERT(dqp->q_nrefs == 0);
+ list_move_tail(&dqp->q_lru, &isol->dispose);
+ XFS_STATS_DEC(xs_qm_dquot_unused);
+ trace_xfs_dqreclaim_done(dqp);
+ XFS_STATS_INC(xs_qm_dqreclaims);
+ return 0;
+
+out_miss_busy:
+ trace_xfs_dqreclaim_busy(dqp);
+ XFS_STATS_INC(xs_qm_dqreclaim_misses);
+ return 2;
+
+out_unlock_dirty:
+ trace_xfs_dqreclaim_busy(dqp);
+ XFS_STATS_INC(xs_qm_dqreclaim_misses);
+ return 3;
+}
+
+static long
+xfs_qm_shrink_scan(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct xfs_quotainfo *qi = container_of(shrink,
+ struct xfs_quotainfo, qi_shrinker);
+ struct xfs_qm_isolate isol;
+ long freed;
+ int error;
+
+ if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
+ return 0;
+
+ INIT_LIST_HEAD(&isol.buffers);
+ INIT_LIST_HEAD(&isol.dispose);
+
+ freed = list_lru_walk_nodemask(&qi->qi_lru, xfs_qm_dquot_isolate, &isol,
+ sc->nr_to_scan, &sc->nodes_to_scan);
+
+ error = xfs_buf_delwri_submit(&isol.buffers);
+ if (error)
+ xfs_warn(NULL, "%s: dquot reclaim failed", __func__);
+
+ while (!list_empty(&isol.dispose)) {
+ struct xfs_dquot *dqp;
+
+ dqp = list_first_entry(&isol.dispose, struct xfs_dquot, q_lru);
+ list_del_init(&dqp->q_lru);
+ xfs_qm_dqfree_one(dqp);
+ }
+
+ return freed;
+}
+
+static long
+xfs_qm_shrink_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct xfs_quotainfo *qi = container_of(shrink,
+ struct xfs_quotainfo, qi_shrinker);
+
+ return list_lru_count_nodemask(&qi->qi_lru, &sc->nodes_to_scan);
+}
+
/*
* This initializes all the quota information that's kept in the
* mount structure
@@ -647,9 +779,7 @@ xfs_qm_init_quotainfo(
INIT_RADIX_TREE(&qinf->qi_gquota_tree, GFP_NOFS);
mutex_init(&qinf->qi_tree_lock);
- INIT_LIST_HEAD(&qinf->qi_lru_list);
- qinf->qi_lru_count = 0;
- mutex_init(&qinf->qi_lru_lock);
+ list_lru_init(&qinf->qi_lru);
/* mutex used to serialize quotaoffs */
mutex_init(&qinf->qi_quotaofflock);
@@ -716,7 +846,8 @@ xfs_qm_init_quotainfo(
qinf->qi_rtbwarnlimit = XFS_QM_RTBWARNLIMIT;
}
- qinf->qi_shrinker.shrink = xfs_qm_shake;
+ qinf->qi_shrinker.count_objects = xfs_qm_shrink_count;
+ qinf->qi_shrinker.scan_objects = xfs_qm_shrink_scan;
qinf->qi_shrinker.seeks = DEFAULT_SEEKS;
register_shrinker(&qinf->qi_shrinker);
return 0;
@@ -1445,132 +1576,6 @@ xfs_qm_dqfree_one(
xfs_qm_dqdestroy(dqp);
}
-STATIC void
-xfs_qm_dqreclaim_one(
- struct xfs_dquot *dqp,
- struct list_head *buffer_list,
- struct list_head *dispose_list)
-{
- struct xfs_mount *mp = dqp->q_mount;
- struct xfs_quotainfo *qi = mp->m_quotainfo;
- int error;
-
- if (!xfs_dqlock_nowait(dqp))
- goto out_move_tail;
-
- /*
- * This dquot has acquired a reference in the meantime remove it from
- * the freelist and try again.
- */
- if (dqp->q_nrefs) {
- xfs_dqunlock(dqp);
-
- trace_xfs_dqreclaim_want(dqp);
- XFS_STATS_INC(xs_qm_dqwants);
-
- list_del_init(&dqp->q_lru);
- qi->qi_lru_count--;
- XFS_STATS_DEC(xs_qm_dquot_unused);
- return;
- }
-
- /*
- * Try to grab the flush lock. If this dquot is in the process of
- * getting flushed to disk, we don't want to reclaim it.
- */
- if (!xfs_dqflock_nowait(dqp))
- goto out_unlock_move_tail;
-
- if (XFS_DQ_IS_DIRTY(dqp)) {
- struct xfs_buf *bp = NULL;
-
- trace_xfs_dqreclaim_dirty(dqp);
-
- error = xfs_qm_dqflush(dqp, &bp);
- if (error) {
- xfs_warn(mp, "%s: dquot %p flush failed",
- __func__, dqp);
- goto out_unlock_move_tail;
- }
-
- xfs_buf_delwri_queue(bp, buffer_list);
- xfs_buf_relse(bp);
- /*
- * Give the dquot another try on the freelist, as the
- * flushing will take some time.
- */
- goto out_unlock_move_tail;
- }
- xfs_dqfunlock(dqp);
-
- /*
- * Prevent lookups now that we are past the point of no return.
- */
- dqp->dq_flags |= XFS_DQ_FREEING;
- xfs_dqunlock(dqp);
-
- ASSERT(dqp->q_nrefs == 0);
- list_move_tail(&dqp->q_lru, dispose_list);
- qi->qi_lru_count--;
- XFS_STATS_DEC(xs_qm_dquot_unused);
-
- trace_xfs_dqreclaim_done(dqp);
- XFS_STATS_INC(xs_qm_dqreclaims);
- return;
-
- /*
- * Move the dquot to the tail of the list so that we don't spin on it.
- */
-out_unlock_move_tail:
- xfs_dqunlock(dqp);
-out_move_tail:
- list_move_tail(&dqp->q_lru, &qi->qi_lru_list);
- trace_xfs_dqreclaim_busy(dqp);
- XFS_STATS_INC(xs_qm_dqreclaim_misses);
-}
-
-STATIC int
-xfs_qm_shake(
- struct shrinker *shrink,
- struct shrink_control *sc)
-{
- struct xfs_quotainfo *qi =
- container_of(shrink, struct xfs_quotainfo, qi_shrinker);
- int nr_to_scan = sc->nr_to_scan;
- LIST_HEAD (buffer_list);
- LIST_HEAD (dispose_list);
- struct xfs_dquot *dqp;
- int error;
-
- if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
- return 0;
- if (!nr_to_scan)
- goto out;
-
- mutex_lock(&qi->qi_lru_lock);
- while (!list_empty(&qi->qi_lru_list)) {
- if (nr_to_scan-- <= 0)
- break;
- dqp = list_first_entry(&qi->qi_lru_list, struct xfs_dquot,
- q_lru);
- xfs_qm_dqreclaim_one(dqp, &buffer_list, &dispose_list);
- }
- mutex_unlock(&qi->qi_lru_lock);
-
- error = xfs_buf_delwri_submit(&buffer_list);
- if (error)
- xfs_warn(NULL, "%s: dquot reclaim failed", __func__);
-
- while (!list_empty(&dispose_list)) {
- dqp = list_first_entry(&dispose_list, struct xfs_dquot, q_lru);
- list_del_init(&dqp->q_lru);
- xfs_qm_dqfree_one(dqp);
- }
-
-out:
- return vfs_pressure_ratio(qi->qi_lru_count);
-}
-
/*
* Start a transaction and write the incore superblock changes to
* disk. flags parameter indicates which fields have changed.
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index 82c2108..3e8c4b9 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -47,9 +47,7 @@ typedef struct xfs_quotainfo {
struct mutex qi_tree_lock;
xfs_inode_t *qi_uquotaip; /* user quota inode */
xfs_inode_t *qi_gquotaip; /* group quota inode */
- struct list_head qi_lru_list;
- struct mutex qi_lru_lock;
- int qi_lru_count;
+ struct list_lru qi_lru;
int qi_dquots;
time_t qi_btimelimit; /* limit for blks timer */
time_t qi_itimelimit; /* limit for inodes timer */
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 16/31] fs: convert fs shrinkers to new scan/count API
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (14 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 15/31] xfs: convert dquot cache lru to list_lru Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 17/31] drivers: convert shrinkers to new count/scan API Glauber Costa
` (15 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner, Glauber Costa
From: Dave Chinner <dchinner@redhat.com>
Convert the filesystem shrinkers to use the new API, and standardise
some of the behaviours of the shrinkers at the same time. For
example, nr_to_scan means the number of objects to scan, not the
number of objects to free.
I refactored the CIFS idmap shrinker a little - it really needs to
be broken up into a shrinker per tree and keep an item count with
the tree root so that we don't need to walk the tree every time the
shrinker needs to count the number of objects in the tree (i.e.
all the time under memory pressure).
[ glommer: fixes for ext4, ubifs, nfs, cifs and glock. Fixes are
needed mainly due to new code merged in the tree ]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
---
fs/ext4/extents_status.c | 30 ++++++++++++++++------------
fs/gfs2/glock.c | 28 +++++++++++++++-----------
fs/gfs2/main.c | 3 ++-
fs/gfs2/quota.c | 12 +++++++-----
fs/gfs2/quota.h | 4 +++-
fs/mbcache.c | 51 ++++++++++++++++++++++++++++--------------------
fs/nfs/dir.c | 18 ++++++++++++++---
fs/nfs/internal.h | 4 +++-
fs/nfs/super.c | 3 ++-
fs/nfsd/nfscache.c | 31 ++++++++++++++++++++---------
fs/quota/dquot.c | 34 +++++++++++++++-----------------
fs/ubifs/shrinker.c | 20 +++++++++++--------
fs/ubifs/super.c | 3 ++-
fs/ubifs/ubifs.h | 3 ++-
14 files changed, 151 insertions(+), 93 deletions(-)
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index fe3337a..7120f31 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -871,20 +871,26 @@ int ext4_es_zeroout(struct inode *inode, struct ext4_extent *ex)
EXTENT_STATUS_WRITTEN);
}
-static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
+
+static long ext4_es_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ long nr;
+ struct ext4_sb_info *sbi = container_of(shrink,
+ struct ext4_sb_info, s_es_shrinker);
+
+ nr = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
+ trace_ext4_es_shrink_enter(sbi->s_sb, sc->nr_to_scan, nr);
+ return nr;
+}
+
+static long ext4_es_scan(struct shrinker *shrink, struct shrink_control *sc)
{
struct ext4_sb_info *sbi = container_of(shrink,
struct ext4_sb_info, s_es_shrinker);
struct ext4_inode_info *ei;
struct list_head *cur, *tmp, scanned;
int nr_to_scan = sc->nr_to_scan;
- int ret, nr_shrunk = 0;
-
- ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
- trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret);
-
- if (!nr_to_scan)
- return ret;
+ int ret = 0, nr_shrunk = 0;
INIT_LIST_HEAD(&scanned);
@@ -913,9 +919,8 @@ static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
list_splice_tail(&scanned, &sbi->s_es_lru);
spin_unlock(&sbi->s_es_lru_lock);
- ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret);
- return ret;
+ return nr_shrunk;
}
void ext4_es_register_shrinker(struct super_block *sb)
@@ -925,7 +930,8 @@ void ext4_es_register_shrinker(struct super_block *sb)
sbi = EXT4_SB(sb);
INIT_LIST_HEAD(&sbi->s_es_lru);
spin_lock_init(&sbi->s_es_lru_lock);
- sbi->s_es_shrinker.shrink = ext4_es_shrink;
+ sbi->s_es_shrinker.scan_objects = ext4_es_scan;
+ sbi->s_es_shrinker.count_objects = ext4_es_count;
sbi->s_es_shrinker.seeks = DEFAULT_SEEKS;
register_shrinker(&sbi->s_es_shrinker);
}
@@ -966,7 +972,7 @@ static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
struct ext4_es_tree *tree = &ei->i_es_tree;
struct rb_node *node;
struct extent_status *es;
- int nr_shrunk = 0;
+ long nr_shrunk = 0;
if (ei->i_es_lru_nr == 0)
return 0;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 2119516..06c083a 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1428,21 +1428,22 @@ __acquires(&lru_lock)
* gfs2_dispose_glock_lru() above.
*/
-static void gfs2_scan_glock_lru(int nr)
+static long gfs2_scan_glock_lru(int nr)
{
struct gfs2_glock *gl;
LIST_HEAD(skipped);
LIST_HEAD(dispose);
+ long freed = 0;
spin_lock(&lru_lock);
- while(nr && !list_empty(&lru_list)) {
+ while ((nr-- >= 0) && !list_empty(&lru_list)) {
gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru);
/* Test for being demotable */
if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
list_move(&gl->gl_lru, &dispose);
atomic_dec(&lru_count);
- nr--;
+ freed++;
continue;
}
@@ -1452,23 +1453,28 @@ static void gfs2_scan_glock_lru(int nr)
if (!list_empty(&dispose))
gfs2_dispose_glock_lru(&dispose);
spin_unlock(&lru_lock);
+
+ return freed;
}
-static int gfs2_shrink_glock_memory(struct shrinker *shrink,
- struct shrink_control *sc)
+static long gfs2_glock_shrink_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
{
- if (sc->nr_to_scan) {
- if (!(sc->gfp_mask & __GFP_FS))
- return -1;
- gfs2_scan_glock_lru(sc->nr_to_scan);
- }
+ if (!(sc->gfp_mask & __GFP_FS))
+ return -1;
+ return gfs2_scan_glock_lru(sc->nr_to_scan);
+}
+static long gfs2_glock_shrink_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
return vfs_pressure_ratio(atomic_read(&lru_count));
}
static struct shrinker glock_shrinker = {
- .shrink = gfs2_shrink_glock_memory,
.seeks = DEFAULT_SEEKS,
+ .count_objects = gfs2_glock_shrink_count,
+ .scan_objects = gfs2_glock_shrink_scan,
};
/**
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index e04d0e0..a105d84 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -32,7 +32,8 @@
struct workqueue_struct *gfs2_control_wq;
static struct shrinker qd_shrinker = {
- .shrink = gfs2_shrink_qd_memory,
+ .count_objects = gfs2_qd_shrink_count,
+ .scan_objects = gfs2_qd_shrink_scan,
.seeks = DEFAULT_SEEKS,
};
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 5c14206..77b82f6 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -75,14 +75,12 @@ static LIST_HEAD(qd_lru_list);
static atomic_t qd_lru_count = ATOMIC_INIT(0);
static DEFINE_SPINLOCK(qd_lru_lock);
-int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc)
+long gfs2_qd_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
struct gfs2_quota_data *qd;
struct gfs2_sbd *sdp;
int nr_to_scan = sc->nr_to_scan;
-
- if (nr_to_scan == 0)
- goto out;
+ long freed = 0;
if (!(sc->gfp_mask & __GFP_FS))
return -1;
@@ -110,10 +108,14 @@ int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc)
kmem_cache_free(gfs2_quotad_cachep, qd);
spin_lock(&qd_lru_lock);
nr_to_scan--;
+ freed++;
}
spin_unlock(&qd_lru_lock);
+ return freed;
+}
-out:
+long gfs2_qd_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
return vfs_pressure_ratio(atomic_read(&qd_lru_count));
}
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index 4f5e6e4..4f61708 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -53,7 +53,9 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip)
return ret;
}
-extern int gfs2_shrink_qd_memory(struct shrinker *shrink,
+extern long gfs2_qd_shrink_count(struct shrinker *shrink,
+ struct shrink_control *sc);
+extern long gfs2_qd_shrink_scan(struct shrinker *shrink,
struct shrink_control *sc);
extern const struct quotactl_ops gfs2_quotactl_ops;
diff --git a/fs/mbcache.c b/fs/mbcache.c
index 5eb0476..009a463 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -86,18 +86,6 @@ static LIST_HEAD(mb_cache_list);
static LIST_HEAD(mb_cache_lru_list);
static DEFINE_SPINLOCK(mb_cache_spinlock);
-/*
- * What the mbcache registers as to get shrunk dynamically.
- */
-
-static int mb_cache_shrink_fn(struct shrinker *shrink,
- struct shrink_control *sc);
-
-static struct shrinker mb_cache_shrinker = {
- .shrink = mb_cache_shrink_fn,
- .seeks = DEFAULT_SEEKS,
-};
-
static inline int
__mb_cache_entry_is_hashed(struct mb_cache_entry *ce)
{
@@ -151,7 +139,7 @@ forget:
/*
- * mb_cache_shrink_fn() memory pressure callback
+ * mb_cache_shrink_scan() memory pressure callback
*
* This function is called by the kernel memory management when memory
* gets low.
@@ -159,17 +147,18 @@ forget:
* @shrink: (ignored)
* @sc: shrink_control passed from reclaim
*
- * Returns the number of objects which are present in the cache.
+ * Returns the number of objects freed.
*/
-static int
-mb_cache_shrink_fn(struct shrinker *shrink, struct shrink_control *sc)
+static long
+mb_cache_shrink_scan(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
{
LIST_HEAD(free_list);
- struct mb_cache *cache;
struct mb_cache_entry *entry, *tmp;
- int count = 0;
int nr_to_scan = sc->nr_to_scan;
gfp_t gfp_mask = sc->gfp_mask;
+ long freed = 0;
mb_debug("trying to free %d entries", nr_to_scan);
spin_lock(&mb_cache_spinlock);
@@ -179,19 +168,39 @@ mb_cache_shrink_fn(struct shrinker *shrink, struct shrink_control *sc)
struct mb_cache_entry, e_lru_list);
list_move_tail(&ce->e_lru_list, &free_list);
__mb_cache_entry_unhash(ce);
+ freed++;
+ }
+ spin_unlock(&mb_cache_spinlock);
+ list_for_each_entry_safe(entry, tmp, &free_list, e_lru_list) {
+ __mb_cache_entry_forget(entry, gfp_mask);
}
+ return freed;
+}
+
+static long
+mb_cache_shrink_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct mb_cache *cache;
+ long count = 0;
+
+ spin_lock(&mb_cache_spinlock);
list_for_each_entry(cache, &mb_cache_list, c_cache_list) {
mb_debug("cache %s (%d)", cache->c_name,
atomic_read(&cache->c_entry_count));
count += atomic_read(&cache->c_entry_count);
}
spin_unlock(&mb_cache_spinlock);
- list_for_each_entry_safe(entry, tmp, &free_list, e_lru_list) {
- __mb_cache_entry_forget(entry, gfp_mask);
- }
+
return vfs_pressure_ratio(count);
}
+static struct shrinker mb_cache_shrinker = {
+ .count_objects = mb_cache_shrink_count,
+ .scan_objects = mb_cache_shrink_scan,
+ .seeks = DEFAULT_SEEKS,
+};
/*
* mb_cache_create() create a new cache
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 54d7c47..b355905 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1958,17 +1958,20 @@ static void nfs_access_free_list(struct list_head *head)
}
}
-int nfs_access_cache_shrinker(struct shrinker *shrink,
- struct shrink_control *sc)
+long
+nfs_access_cache_scan(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
{
LIST_HEAD(head);
struct nfs_inode *nfsi, *next;
struct nfs_access_entry *cache;
int nr_to_scan = sc->nr_to_scan;
gfp_t gfp_mask = sc->gfp_mask;
+ long freed = 0;
if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL)
- return (nr_to_scan == 0) ? 0 : -1;
+ return -1;
spin_lock(&nfs_access_lru_lock);
list_for_each_entry_safe(nfsi, next, &nfs_access_lru_list, access_cache_inode_lru) {
@@ -1984,6 +1987,7 @@ int nfs_access_cache_shrinker(struct shrinker *shrink,
struct nfs_access_entry, lru);
list_move(&cache->lru, &head);
rb_erase(&cache->rb_node, &nfsi->access_cache);
+ freed++;
if (!list_empty(&nfsi->access_cache_entry_lru))
list_move_tail(&nfsi->access_cache_inode_lru,
&nfs_access_lru_list);
@@ -1998,6 +2002,14 @@ remove_lru_entry:
}
spin_unlock(&nfs_access_lru_lock);
nfs_access_free_list(&head);
+ return freed;
+}
+
+long
+nfs_access_cache_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
return vfs_pressure_ratio(atomic_long_read(&nfs_access_nr_entries));
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 91e59a3..9651e20 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -269,7 +269,9 @@ extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
const char *ip_addr, rpc_authflavor_t authflavour);
/* dir.c */
-extern int nfs_access_cache_shrinker(struct shrinker *shrink,
+extern long nfs_access_cache_count(struct shrinker *shrink,
+ struct shrink_control *sc);
+extern long nfs_access_cache_scan(struct shrinker *shrink,
struct shrink_control *sc);
struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int);
int nfs_create(struct inode *, struct dentry *, umode_t, bool);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 1bb071d..fdcc6bb 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -359,7 +359,8 @@ static void unregister_nfs4_fs(void)
#endif
static struct shrinker acl_shrinker = {
- .shrink = nfs_access_cache_shrinker,
+ .count_objects = nfs_access_cache_count,
+ .scan_objects = nfs_access_cache_scan,
.seeks = DEFAULT_SEEKS,
};
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index eb25877..3a3164a 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -59,11 +59,14 @@ static unsigned int longest_chain_cachesize;
static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);
static void cache_cleaner_func(struct work_struct *unused);
-static int nfsd_reply_cache_shrink(struct shrinker *shrink,
- struct shrink_control *sc);
+static long nfsd_reply_cache_count(struct shrinker *shrink,
+ struct shrink_control *sc);
+static long nfsd_reply_cache_scan(struct shrinker *shrink,
+ struct shrink_control *sc);
struct shrinker nfsd_reply_cache_shrinker = {
- .shrink = nfsd_reply_cache_shrink,
+ .scan_objects = nfsd_reply_cache_scan,
+ .count_objects = nfsd_reply_cache_count,
.seeks = 1,
};
@@ -232,16 +235,18 @@ nfsd_cache_entry_expired(struct svc_cacherep *rp)
* Walk the LRU list and prune off entries that are older than RC_EXPIRE.
* Also prune the oldest ones when the total exceeds the max number of entries.
*/
-static void
+static long
prune_cache_entries(void)
{
struct svc_cacherep *rp, *tmp;
+ long freed = 0;
list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) {
if (!nfsd_cache_entry_expired(rp) &&
num_drc_entries <= max_drc_entries)
break;
nfsd_reply_cache_free_locked(rp);
+ freed++;
}
/*
@@ -254,6 +259,7 @@ prune_cache_entries(void)
cancel_delayed_work(&cache_cleaner);
else
mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE);
+ return freed;
}
static void
@@ -264,20 +270,27 @@ cache_cleaner_func(struct work_struct *unused)
spin_unlock(&cache_lock);
}
-static int
-nfsd_reply_cache_shrink(struct shrinker *shrink, struct shrink_control *sc)
+static long
+nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc)
{
- unsigned int num;
+ long num;
spin_lock(&cache_lock);
- if (sc->nr_to_scan)
- prune_cache_entries();
num = num_drc_entries;
spin_unlock(&cache_lock);
return num;
}
+static long
+nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+ long freed;
+ spin_lock(&cache_lock);
+ freed = prune_cache_entries();
+ spin_unlock(&cache_lock);
+ return freed;
+}
/*
* Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes
*/
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 762b09c..fd6b762 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -687,44 +687,42 @@ int dquot_quota_sync(struct super_block *sb, int type)
}
EXPORT_SYMBOL(dquot_quota_sync);
-/* Free unused dquots from cache */
-static void prune_dqcache(int count)
+static long
+dqcache_shrink_scan(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
{
struct list_head *head;
struct dquot *dquot;
+ long freed = 0;
head = free_dquots.prev;
- while (head != &free_dquots && count) {
+ while (head != &free_dquots && sc->nr_to_scan) {
dquot = list_entry(head, struct dquot, dq_free);
remove_dquot_hash(dquot);
remove_free_dquot(dquot);
remove_inuse(dquot);
do_destroy_dquot(dquot);
- count--;
+ sc->nr_to_scan--;
+ freed++;
head = free_dquots.prev;
}
+ return freed;
}
-/*
- * This is called from kswapd when we think we need some
- * more memory
- */
-static int shrink_dqcache_memory(struct shrinker *shrink,
- struct shrink_control *sc)
-{
- int nr = sc->nr_to_scan;
+static long
+dqcache_shrink_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
- if (nr) {
- spin_lock(&dq_list_lock);
- prune_dqcache(nr);
- spin_unlock(&dq_list_lock);
- }
+{
return vfs_pressure_ratio(
percpu_counter_read_positive(&dqstats.counter[DQST_FREE_DQUOTS]));
}
static struct shrinker dqcache_shrinker = {
- .shrink = shrink_dqcache_memory,
+ .count_objects = dqcache_shrink_count,
+ .scan_objects = dqcache_shrink_scan,
.seeks = DEFAULT_SEEKS,
};
diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c
index 9e1d056..669d8c0 100644
--- a/fs/ubifs/shrinker.c
+++ b/fs/ubifs/shrinker.c
@@ -277,19 +277,23 @@ static int kick_a_thread(void)
return 0;
}
-int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc)
+long ubifs_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt);
+
+ /*
+ * Due to the way UBIFS updates the clean znode counter it may
+ * temporarily be negative.
+ */
+ return clean_zn_cnt >= 0 ? clean_zn_cnt : 1;
+}
+
+long ubifs_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
int nr = sc->nr_to_scan;
int freed, contention = 0;
long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt);
- if (nr == 0)
- /*
- * Due to the way UBIFS updates the clean znode counter it may
- * temporarily be negative.
- */
- return clean_zn_cnt >= 0 ? clean_zn_cnt : 1;
-
if (!clean_zn_cnt) {
/*
* No clean znodes, nothing to reap. All we can do in this case
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index f21acf0..ff357e0 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -49,7 +49,8 @@ struct kmem_cache *ubifs_inode_slab;
/* UBIFS TNC shrinker description */
static struct shrinker ubifs_shrinker_info = {
- .shrink = ubifs_shrinker,
+ .scan_objects = ubifs_shrink_scan,
+ .count_objects = ubifs_shrink_count,
.seeks = DEFAULT_SEEKS,
};
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index b2babce..bcdafcc 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -1624,7 +1624,8 @@ int ubifs_tnc_start_commit(struct ubifs_info *c, struct ubifs_zbranch *zroot);
int ubifs_tnc_end_commit(struct ubifs_info *c);
/* shrinker.c */
-int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc);
+long ubifs_shrink_scan(struct shrinker *shrink, struct shrink_control *sc);
+long ubifs_shrink_count(struct shrinker *shrink, struct shrink_control *sc);
/* commit.c */
int ubifs_bg_thread(void *info);
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 17/31] drivers: convert shrinkers to new count/scan API
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (15 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 16/31] fs: convert fs shrinkers to new scan/count API Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-30 21:53 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 18/31] shrinker: convert remaining shrinkers to " Glauber Costa
` (14 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner, Glauber Costa
From: Dave Chinner <dchinner@redhat.com>
Convert the driver shrinkers to the new API. Most changes are
compile tested only because I either don't have the hardware or it's
staging stuff.
FWIW, the md and android code is pretty good, but the rest of it
makes me want to claw my eyes out. The amount of broken code I just
encountered is mind boggling. I've added comments explaining what
is broken, but I fear that some of the code would be best dealt with
by being dragged behind the bike shed, burying in mud up to it's
neck and then run over repeatedly with a blunt lawn mower.
Special mention goes to the zcache/zcache2 drivers. They can't
co-exist in the build at the same time, they are under different
menu options in menuconfig, they only show up when you've got the
right set of mm subsystem options configured and so even compile
testing is an exercise in pulling teeth. And that doesn't even take
into account the horrible, broken code...
[ glommer: fixes for i915, android lowmem, zcache, bcache ]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
---
drivers/gpu/drm/i915/i915_dma.c | 4 +-
drivers/gpu/drm/i915/i915_drv.h | 2 +-
drivers/gpu/drm/i915/i915_gem.c | 69 ++++++++++++++++++++++--------
drivers/gpu/drm/i915/i915_gem_evict.c | 10 +++--
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
drivers/gpu/drm/ttm/ttm_page_alloc.c | 48 ++++++++++++++-------
drivers/gpu/drm/ttm/ttm_page_alloc_dma.c | 55 ++++++++++++++++--------
drivers/md/bcache/btree.c | 30 +++++++------
drivers/md/bcache/sysfs.c | 2 +-
drivers/md/dm-bufio.c | 65 ++++++++++++++++++----------
drivers/staging/android/ashmem.c | 45 ++++++++++++-------
drivers/staging/android/lowmemorykiller.c | 40 ++++++++++-------
drivers/staging/zcache/zcache-main.c | 29 ++++++++-----
13 files changed, 259 insertions(+), 142 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 3b315ba..cfe3373 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1669,7 +1669,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
return 0;
out_gem_unload:
- if (dev_priv->mm.inactive_shrinker.shrink)
+ if (dev_priv->mm.inactive_shrinker.scan_objects)
unregister_shrinker(&dev_priv->mm.inactive_shrinker);
if (dev->pdev->msi_enabled)
@@ -1705,7 +1705,7 @@ int i915_driver_unload(struct drm_device *dev)
i915_teardown_sysfs(dev);
- if (dev_priv->mm.inactive_shrinker.shrink)
+ if (dev_priv->mm.inactive_shrinker.scan_objects)
unregister_shrinker(&dev_priv->mm.inactive_shrinker);
mutex_lock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d80bced..a7ac740 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1749,7 +1749,7 @@ int __must_check i915_gem_evict_something(struct drm_device *dev, int min_size,
unsigned cache_level,
bool mappable,
bool nonblock);
-int i915_gem_evict_everything(struct drm_device *dev);
+long i915_gem_evict_everything(struct drm_device *dev);
/* i915_gem_stolen.c */
int i915_gem_init_stolen(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 6be940e..2e44733 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -53,10 +53,12 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
struct drm_i915_fence_reg *fence,
bool enable);
-static int i915_gem_inactive_shrink(struct shrinker *shrinker,
+static long i915_gem_inactive_count(struct shrinker *shrinker,
struct shrink_control *sc);
+static long i915_gem_inactive_scan(struct shrinker *shrinker,
+ struct shrink_control *sc);
static long i915_gem_purge(struct drm_i915_private *dev_priv, long target);
-static void i915_gem_shrink_all(struct drm_i915_private *dev_priv);
+static long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
static void i915_gem_object_truncate(struct drm_i915_gem_object *obj);
static inline void i915_gem_object_fence_lost(struct drm_i915_gem_object *obj)
@@ -1729,15 +1731,20 @@ i915_gem_purge(struct drm_i915_private *dev_priv, long target)
return __i915_gem_shrink(dev_priv, target, true);
}
-static void
+static long
i915_gem_shrink_all(struct drm_i915_private *dev_priv)
{
struct drm_i915_gem_object *obj, *next;
+ long freed = 0;
- i915_gem_evict_everything(dev_priv->dev);
+ freed += i915_gem_evict_everything(dev_priv->dev);
- list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list)
+ list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list) {
+ if (obj->pages_pin_count == 0)
+ freed += obj->base.size >> PAGE_SHIFT;
i915_gem_object_put_pages(obj);
+ }
+ return freed;
}
static int
@@ -4205,7 +4212,8 @@ i915_gem_load(struct drm_device *dev)
dev_priv->mm.interruptible = true;
- dev_priv->mm.inactive_shrinker.shrink = i915_gem_inactive_shrink;
+ dev_priv->mm.inactive_shrinker.scan_objects = i915_gem_inactive_scan;
+ dev_priv->mm.inactive_shrinker.count_objects = i915_gem_inactive_count;
dev_priv->mm.inactive_shrinker.seeks = DEFAULT_SEEKS;
register_shrinker(&dev_priv->mm.inactive_shrinker);
}
@@ -4428,8 +4436,8 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
#endif
}
-static int
-i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
+static long
+i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc)
{
struct drm_i915_private *dev_priv =
container_of(shrinker,
@@ -4437,9 +4445,8 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
mm.inactive_shrinker);
struct drm_device *dev = dev_priv->dev;
struct drm_i915_gem_object *obj;
- int nr_to_scan = sc->nr_to_scan;
bool unlock = true;
- int cnt;
+ long cnt;
if (!mutex_trylock(&dev->struct_mutex)) {
if (!mutex_is_locked_by(&dev->struct_mutex, current))
@@ -4451,15 +4458,6 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
unlock = false;
}
- if (nr_to_scan) {
- nr_to_scan -= i915_gem_purge(dev_priv, nr_to_scan);
- if (nr_to_scan > 0)
- nr_to_scan -= __i915_gem_shrink(dev_priv, nr_to_scan,
- false);
- if (nr_to_scan > 0)
- i915_gem_shrink_all(dev_priv);
- }
-
cnt = 0;
list_for_each_entry(obj, &dev_priv->mm.unbound_list, gtt_list)
if (obj->pages_pin_count == 0)
@@ -4472,3 +4470,36 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
mutex_unlock(&dev->struct_mutex);
return cnt;
}
+static long
+i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc)
+{
+ struct drm_i915_private *dev_priv =
+ container_of(shrinker,
+ struct drm_i915_private,
+ mm.inactive_shrinker);
+ struct drm_device *dev = dev_priv->dev;
+ int nr_to_scan = sc->nr_to_scan;
+ long freed;
+ bool unlock = true;
+
+ if (!mutex_trylock(&dev->struct_mutex)) {
+ if (!mutex_is_locked_by(&dev->struct_mutex, current))
+ return 0;
+
+ if (dev_priv->mm.shrinker_no_lock_stealing)
+ return 0;
+
+ unlock = false;
+ }
+
+ freed = i915_gem_purge(dev_priv, nr_to_scan);
+ if (freed < nr_to_scan)
+ freed += __i915_gem_shrink(dev_priv, nr_to_scan,
+ false);
+ if (freed < nr_to_scan)
+ freed += i915_gem_shrink_all(dev_priv);
+
+ if (unlock)
+ mutex_unlock(&dev->struct_mutex);
+ return freed;
+}
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index c86d5d9..e379340 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -150,13 +150,13 @@ found:
return ret;
}
-int
+long
i915_gem_evict_everything(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = dev->dev_private;
struct drm_i915_gem_object *obj, *next;
bool lists_empty;
- int ret;
+ long ret = 0;
lists_empty = (list_empty(&dev_priv->mm.inactive_list) &&
list_empty(&dev_priv->mm.active_list));
@@ -178,8 +178,10 @@ i915_gem_evict_everything(struct drm_device *dev)
/* Having flushed everything, unbind() should never raise an error */
list_for_each_entry_safe(obj, next,
&dev_priv->mm.inactive_list, mm_list)
- if (obj->pin_count == 0)
+ if (obj->pin_count == 0) {
+ ret += obj->base.size >> PAGE_SHIFT;
WARN_ON(i915_gem_object_unbind(obj));
+ }
- return 0;
+ return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 117ce38..da0017a 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -566,7 +566,7 @@ err: /* Decrement pin count for bound objects */
return ret;
ret = i915_gem_evict_everything(ring->dev);
- if (ret)
+ if (ret < 0)
return ret;
} while (1);
}
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index bd2a3b4..83058a2 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -377,28 +377,28 @@ out:
return nr_free;
}
-/* Get good estimation how many pages are free in pools */
-static int ttm_pool_get_num_unused_pages(void)
-{
- unsigned i;
- int total = 0;
- for (i = 0; i < NUM_POOLS; ++i)
- total += _manager->pools[i].npages;
-
- return total;
-}
-
/**
* Callback for mm to request pool to reduce number of page held.
+ *
+ * XXX: (dchinner) Deadlock warning!
+ *
+ * ttm_page_pool_free() does memory allocation using GFP_KERNEL. that means
+ * this can deadlock when called a sc->gfp_mask that is not equal to
+ * GFP_KERNEL.
+ *
+ * This code is crying out for a shrinker per pool....
*/
-static int ttm_pool_mm_shrink(struct shrinker *shrink,
- struct shrink_control *sc)
+static long
+ttm_pool_shrink_scan(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
{
static atomic_t start_pool = ATOMIC_INIT(0);
unsigned i;
unsigned pool_offset = atomic_add_return(1, &start_pool);
struct ttm_page_pool *pool;
int shrink_pages = sc->nr_to_scan;
+ long freed = 0;
pool_offset = pool_offset % NUM_POOLS;
/* select start pool in round robin fashion */
@@ -408,14 +408,30 @@ static int ttm_pool_mm_shrink(struct shrinker *shrink,
break;
pool = &_manager->pools[(i + pool_offset)%NUM_POOLS];
shrink_pages = ttm_page_pool_free(pool, nr_free);
+ freed += nr_free - shrink_pages;
}
- /* return estimated number of unused pages in pool */
- return ttm_pool_get_num_unused_pages();
+ return freed;
+}
+
+
+static long
+ttm_pool_shrink_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ unsigned i;
+ long count = 0;
+
+ for (i = 0; i < NUM_POOLS; ++i)
+ count += _manager->pools[i].npages;
+
+ return count;
}
static void ttm_pool_mm_shrink_init(struct ttm_pool_manager *manager)
{
- manager->mm_shrink.shrink = &ttm_pool_mm_shrink;
+ manager->mm_shrink.count_objects = &ttm_pool_shrink_count;
+ manager->mm_shrink.scan_objects = &ttm_pool_shrink_scan;
manager->mm_shrink.seeks = 1;
register_shrinker(&manager->mm_shrink);
}
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index b8b3943..b3b4f99 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -918,19 +918,6 @@ int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev)
}
EXPORT_SYMBOL_GPL(ttm_dma_populate);
-/* Get good estimation how many pages are free in pools */
-static int ttm_dma_pool_get_num_unused_pages(void)
-{
- struct device_pools *p;
- unsigned total = 0;
-
- mutex_lock(&_manager->lock);
- list_for_each_entry(p, &_manager->pools, pools)
- total += p->pool->npages_free;
- mutex_unlock(&_manager->lock);
- return total;
-}
-
/* Put all pages in pages list to correct pool to wait for reuse */
void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
{
@@ -1002,18 +989,31 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
/**
* Callback for mm to request pool to reduce number of page held.
+ *
+ * XXX: (dchinner) Deadlock warning!
+ *
+ * ttm_dma_page_pool_free() does GFP_KERNEL memory allocation, and so attention
+ * needs to be paid to sc->gfp_mask to determine if this can be done or not.
+ * GFP_KERNEL memory allocation in a GFP_ATOMIC reclaim context woul dbe really
+ * bad.
+ *
+ * I'm getting sadder as I hear more pathetical whimpers about needing per-pool
+ * shrinkers
*/
-static int ttm_dma_pool_mm_shrink(struct shrinker *shrink,
- struct shrink_control *sc)
+static long
+ttm_dma_pool_shrink_scan(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
{
static atomic_t start_pool = ATOMIC_INIT(0);
unsigned idx = 0;
unsigned pool_offset = atomic_add_return(1, &start_pool);
unsigned shrink_pages = sc->nr_to_scan;
struct device_pools *p;
+ long freed = 0;
if (list_empty(&_manager->pools))
- return 0;
+ return -1;
mutex_lock(&_manager->lock);
pool_offset = pool_offset % _manager->npools;
@@ -1029,18 +1029,35 @@ static int ttm_dma_pool_mm_shrink(struct shrinker *shrink,
continue;
nr_free = shrink_pages;
shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free);
+ freed += nr_free - shrink_pages;
+
pr_debug("%s: (%s:%d) Asked to shrink %d, have %d more to go\n",
p->pool->dev_name, p->pool->name, current->pid,
nr_free, shrink_pages);
}
mutex_unlock(&_manager->lock);
- /* return estimated number of unused pages in pool */
- return ttm_dma_pool_get_num_unused_pages();
+ return freed;
+}
+
+static long
+ttm_dma_pool_shrink_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct device_pools *p;
+ long count = 0;
+
+ mutex_lock(&_manager->lock);
+ list_for_each_entry(p, &_manager->pools, pools)
+ count += p->pool->npages_free;
+ mutex_unlock(&_manager->lock);
+ return count;
}
static void ttm_dma_pool_mm_shrink_init(struct ttm_pool_manager *manager)
{
- manager->mm_shrink.shrink = &ttm_dma_pool_mm_shrink;
+ manager->mm_shrink.count_objects = &ttm_dma_pool_shrink_count;
+ manager->mm_shrink.scan_objects = &ttm_dma_pool_shrink_scan;
manager->mm_shrink.seeks = 1;
register_shrinker(&manager->mm_shrink);
}
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 03e44c1..8b9c1a6 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -599,11 +599,12 @@ static int mca_reap(struct btree *b, struct closure *cl, unsigned min_order)
return 0;
}
-static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
+static long bch_mca_scan(struct shrinker *shrink, struct shrink_control *sc)
{
struct cache_set *c = container_of(shrink, struct cache_set, shrink);
struct btree *b, *t;
unsigned long i, nr = sc->nr_to_scan;
+ long freed = 0;
if (c->shrinker_disabled)
return 0;
@@ -611,12 +612,6 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
if (c->try_harder)
return 0;
- /*
- * If nr == 0, we're supposed to return the number of items we have
- * cached. Not allowed to return -1.
- */
- if (!nr)
- return mca_can_free(c) * c->btree_pages;
/* Return -1 if we can't do anything right now */
if (sc->gfp_mask & __GFP_WAIT)
@@ -629,14 +624,14 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
i = 0;
list_for_each_entry_safe(b, t, &c->btree_cache_freeable, list) {
- if (!nr)
+ if (freed >= nr)
break;
if (++i > 3 &&
!mca_reap(b, NULL, 0)) {
mca_data_free(b);
rw_unlock(true, b);
- --nr;
+ freed++;
}
}
@@ -647,7 +642,7 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
if (list_empty(&c->btree_cache))
goto out;
- for (i = 0; nr && i < c->bucket_cache_used; i++) {
+ for (i = 0; i < c->bucket_cache_used; i++) {
b = list_first_entry(&c->btree_cache, struct btree, list);
list_rotate_left(&c->btree_cache);
@@ -656,14 +651,20 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
mca_bucket_free(b);
mca_data_free(b);
rw_unlock(true, b);
- --nr;
+ freed++;
} else
b->accessed = 0;
}
out:
- nr = mca_can_free(c) * c->btree_pages;
mutex_unlock(&c->bucket_lock);
- return nr;
+ return freed;
+}
+
+static long bch_mca_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ struct cache_set *c = container_of(shrink, struct cache_set, shrink);
+
+ return mca_can_free(c) * c->btree_pages;
}
void bch_btree_cache_free(struct cache_set *c)
@@ -732,7 +733,8 @@ int bch_btree_cache_alloc(struct cache_set *c)
c->verify_data = NULL;
#endif
- c->shrink.shrink = bch_mca_shrink;
+ c->shrink.count_objects = bch_mca_count;
+ c->shrink.scan_objects = bch_mca_scan;
c->shrink.seeks = 4;
c->shrink.batch = c->btree_pages * 2;
register_shrinker(&c->shrink);
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 4d9cca4..fa8d048 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -535,7 +535,7 @@ STORE(__bch_cache_set)
struct shrink_control sc;
sc.gfp_mask = GFP_KERNEL;
sc.nr_to_scan = strtoul_or_return(buf);
- c->shrink.shrink(&c->shrink, &sc);
+ c->shrink.scan_objects(&c->shrink, &sc);
}
sysfs_strtoul(congested_read_threshold_us,
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 6f1b57a..59b6082 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1361,62 +1361,80 @@ static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp,
unsigned long max_jiffies)
{
if (jiffies - b->last_accessed < max_jiffies)
- return 1;
+ return 0;
if (!(gfp & __GFP_IO)) {
if (test_bit(B_READING, &b->state) ||
test_bit(B_WRITING, &b->state) ||
test_bit(B_DIRTY, &b->state))
- return 1;
+ return 0;
}
if (b->hold_count)
- return 1;
+ return 0;
__make_buffer_clean(b);
__unlink_buffer(b);
__free_buffer_wake(b);
- return 0;
+ return 1;
}
-static void __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
- struct shrink_control *sc)
+static long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
+ gfp_t gfp_mask)
{
int l;
struct dm_buffer *b, *tmp;
+ long freed = 0;
for (l = 0; l < LIST_SIZE; l++) {
- list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list)
- if (!__cleanup_old_buffer(b, sc->gfp_mask, 0) &&
- !--nr_to_scan)
- return;
+ list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) {
+ freed += __cleanup_old_buffer(b, gfp_mask, 0);
+ if (!--nr_to_scan)
+ break;
+ }
dm_bufio_cond_resched();
}
+ return freed;
}
-static int shrink(struct shrinker *shrinker, struct shrink_control *sc)
+static long
+dm_bufio_shrink_scan(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
{
struct dm_bufio_client *c =
- container_of(shrinker, struct dm_bufio_client, shrinker);
- unsigned long r;
- unsigned long nr_to_scan = sc->nr_to_scan;
+ container_of(shrink, struct dm_bufio_client, shrinker);
+ long freed;
if (sc->gfp_mask & __GFP_IO)
dm_bufio_lock(c);
else if (!dm_bufio_trylock(c))
- return !nr_to_scan ? 0 : -1;
+ return -1;
- if (nr_to_scan)
- __scan(c, nr_to_scan, sc);
+ freed = __scan(c, sc->nr_to_scan, sc->gfp_mask);
+ dm_bufio_unlock(c);
+ return freed;
+}
- r = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY];
- if (r > INT_MAX)
- r = INT_MAX;
+static 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);
+ long count;
+
+ if (sc->gfp_mask & __GFP_IO)
+ dm_bufio_lock(c);
+ else if (!dm_bufio_trylock(c))
+ return 0;
+ count = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY];
dm_bufio_unlock(c);
+ return count;
- return r;
}
/*
@@ -1518,7 +1536,8 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
__cache_size_refresh();
mutex_unlock(&dm_bufio_clients_lock);
- c->shrinker.shrink = shrink;
+ c->shrinker.count_objects = dm_bufio_shrink_count;
+ c->shrinker.scan_objects = dm_bufio_shrink_scan;
c->shrinker.seeks = 1;
c->shrinker.batch = 0;
register_shrinker(&c->shrinker);
@@ -1605,7 +1624,7 @@ static void cleanup_old_buffers(void)
struct dm_buffer *b;
b = list_entry(c->lru[LIST_CLEAN].prev,
struct dm_buffer, lru_list);
- if (__cleanup_old_buffer(b, 0, max_age * HZ))
+ if (!__cleanup_old_buffer(b, 0, max_age * HZ))
break;
dm_bufio_cond_resched();
}
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 3240d34..951d944 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -341,27 +341,28 @@ out:
/*
* ashmem_shrink - our cache shrinker, called from mm/vmscan.c :: shrink_slab
*
- * 'nr_to_scan' is the number of objects (pages) to prune, or 0 to query how
- * many objects (pages) we have in total.
+ * 'nr_to_scan' is the number of objects to scan for freeing.
*
* 'gfp_mask' is the mask of the allocation that got us into this mess.
*
- * Return value is the number of objects (pages) remaining, or -1 if we cannot
+ * Return value is the number of objects freed or -1 if we cannot
* proceed without risk of deadlock (due to gfp_mask).
*
* We approximate LRU via least-recently-unpinned, jettisoning unpinned partial
* chunks of ashmem regions LRU-wise one-at-a-time until we hit 'nr_to_scan'
* pages freed.
*/
-static int ashmem_shrink(struct shrinker *s, struct shrink_control *sc)
+static long
+ashmem_shrink_scan(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
{
struct ashmem_range *range, *next;
+ long freed = 0;
/* We might recurse into filesystem code, so bail out if necessary */
- if (sc->nr_to_scan && !(sc->gfp_mask & __GFP_FS))
+ if (!(sc->gfp_mask & __GFP_FS))
return -1;
- if (!sc->nr_to_scan)
- return lru_count;
mutex_lock(&ashmem_mutex);
list_for_each_entry_safe(range, next, &ashmem_lru_list, lru) {
@@ -374,17 +375,34 @@ static int ashmem_shrink(struct shrinker *s, struct shrink_control *sc)
range->purged = ASHMEM_WAS_PURGED;
lru_del(range);
- sc->nr_to_scan -= range_size(range);
- if (sc->nr_to_scan <= 0)
+ freed += range_size(range);
+ if (--sc->nr_to_scan <= 0)
break;
}
mutex_unlock(&ashmem_mutex);
+ return freed;
+}
+static long
+ashmem_shrink_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ /*
+ * note that lru_count is count of pages on the lru, not a count of
+ * objects on the list. This means the scan function needs to return the
+ * number of pages freed, not the number of objects scanned.
+ */
return lru_count;
}
static struct shrinker ashmem_shrinker = {
- .shrink = ashmem_shrink,
+ .count_objects = ashmem_shrink_count,
+ .scan_objects = ashmem_shrink_scan,
+ /*
+ * XXX (dchinner): I wish people would comment on why they need on
+ * significant changes to the default value here
+ */
.seeks = DEFAULT_SEEKS * 4,
};
@@ -690,14 +708,11 @@ static long ashmem_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
if (capable(CAP_SYS_ADMIN)) {
struct shrink_control sc = {
.gfp_mask = GFP_KERNEL,
- .nr_to_scan = 0,
+ .nr_to_scan = LONG_MAX,
};
nodes_setall(sc.nodes_to_scan);
-
- ret = ashmem_shrink(&ashmem_shrinker, &sc);
- sc.nr_to_scan = ret;
- ashmem_shrink(&ashmem_shrinker, &sc);
+ ashmem_shrink_scan(&ashmem_shrinker, &sc);
}
break;
}
diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
index fe74494..d23bfea 100644
--- a/drivers/staging/android/lowmemorykiller.c
+++ b/drivers/staging/android/lowmemorykiller.c
@@ -66,7 +66,15 @@ static unsigned long lowmem_deathpending_timeout;
pr_info(x); \
} while (0)
-static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
+static long lowmem_count(struct shrinker *s, struct shrink_control *sc)
+{
+ return global_page_state(NR_ACTIVE_ANON) +
+ global_page_state(NR_ACTIVE_FILE) +
+ global_page_state(NR_INACTIVE_ANON) +
+ global_page_state(NR_INACTIVE_FILE);
+}
+
+static long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
{
struct task_struct *tsk;
struct task_struct *selected = NULL;
@@ -92,19 +100,17 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
break;
}
}
- if (sc->nr_to_scan > 0)
- lowmem_print(3, "lowmem_shrink %lu, %x, ofree %d %d, ma %hd\n",
- sc->nr_to_scan, sc->gfp_mask, other_free,
- other_file, min_score_adj);
- rem = global_page_state(NR_ACTIVE_ANON) +
- global_page_state(NR_ACTIVE_FILE) +
- global_page_state(NR_INACTIVE_ANON) +
- global_page_state(NR_INACTIVE_FILE);
- if (sc->nr_to_scan <= 0 || min_score_adj == OOM_SCORE_ADJ_MAX + 1) {
- lowmem_print(5, "lowmem_shrink %lu, %x, return %d\n",
- sc->nr_to_scan, sc->gfp_mask, rem);
- return rem;
+
+ lowmem_print(3, "lowmem_scan %lu, %x, ofree %d %d, ma %hd\n",
+ sc->nr_to_scan, sc->gfp_mask, other_free,
+ other_file, min_score_adj);
+
+ if (min_score_adj == OOM_SCORE_ADJ_MAX + 1) {
+ lowmem_print(5, "lowmem_scan %lu, %x, return 0\n",
+ sc->nr_to_scan, sc->gfp_mask);
+ return 0;
}
+
selected_oom_score_adj = min_score_adj;
rcu_read_lock();
@@ -154,16 +160,18 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
lowmem_deathpending_timeout = jiffies + HZ;
send_sig(SIGKILL, selected, 0);
set_tsk_thread_flag(selected, TIF_MEMDIE);
- rem -= selected_tasksize;
+ rem += selected_tasksize;
}
- lowmem_print(4, "lowmem_shrink %lu, %x, return %d\n",
+
+ lowmem_print(4, "lowmem_scan %lu, %x, return %d\n",
sc->nr_to_scan, sc->gfp_mask, rem);
rcu_read_unlock();
return rem;
}
static struct shrinker lowmem_shrinker = {
- .shrink = lowmem_shrink,
+ .scan_objects = lowmem_scan,
+ .count_objects = lowmem_count,
.seeks = DEFAULT_SEEKS * 16
};
diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c
index 522cb8e..bbfcd4f 100644
--- a/drivers/staging/zcache/zcache-main.c
+++ b/drivers/staging/zcache/zcache-main.c
@@ -1140,23 +1140,19 @@ static bool zcache_freeze;
* pageframes in use. FIXME POLICY: Probably the writeback should only occur
* if the eviction doesn't free enough pages.
*/
-static int shrink_zcache_memory(struct shrinker *shrink,
- struct shrink_control *sc)
+static long scan_zcache_memory(struct shrinker *shrink,
+ struct shrink_control *sc)
{
static bool in_progress;
- int ret = -1;
- int nr = sc->nr_to_scan;
int nr_evict = 0;
int nr_writeback = 0;
struct page *page;
int file_pageframes_inuse, anon_pageframes_inuse;
-
- if (nr <= 0)
- goto skip_evict;
+ long freed = 0;
/* don't allow more than one eviction thread at a time */
if (in_progress)
- goto skip_evict;
+ return 0;
in_progress = true;
@@ -1176,6 +1172,7 @@ static int shrink_zcache_memory(struct shrinker *shrink,
if (page == NULL)
break;
zcache_free_page(page);
+ freed++;
}
zcache_last_active_anon_pageframes =
@@ -1192,13 +1189,22 @@ static int shrink_zcache_memory(struct shrinker *shrink,
#ifdef CONFIG_ZCACHE_WRITEBACK
int writeback_ret;
writeback_ret = zcache_frontswap_writeback();
- if (writeback_ret == -ENOMEM)
+ if (writeback_ret != -ENOMEM)
+ freed++;
+ else
#endif
break;
}
in_progress = false;
-skip_evict:
+ return freed;
+}
+
+static long count_zcache_memory(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ int ret = -1;
+
/* resample: has changed, but maybe not all the way yet */
zcache_last_active_file_pageframes =
global_page_state(NR_LRU_BASE + LRU_ACTIVE_FILE);
@@ -1212,7 +1218,8 @@ skip_evict:
}
static struct shrinker zcache_shrinker = {
- .shrink = shrink_zcache_memory,
+ .scan_objects = scan_zcache_memory,
+ .count_objects = count_zcache_memory,
.seeks = DEFAULT_SEEKS,
};
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 17/31] drivers: convert shrinkers to new count/scan API
2013-04-26 23:19 ` [PATCH v4 17/31] drivers: convert shrinkers to new count/scan API Glauber Costa
@ 2013-04-30 21:53 ` Mel Gorman
2013-04-30 22:00 ` Kent Overstreet
2013-05-01 15:26 ` Daniel Vetter
0 siblings, 2 replies; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 21:53 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner, intel-gfx, dri-devel,
Kent Overstreet, devel, Dan Magenheimer
On Sat, Apr 27, 2013 at 03:19:13AM +0400, Glauber Costa wrote:
> From: Dave Chinner <dchinner@redhat.com>
>
> Convert the driver shrinkers to the new API. Most changes are
> compile tested only because I either don't have the hardware or it's
> staging stuff.
>
> FWIW, the md and android code is pretty good, but the rest of it
> makes me want to claw my eyes out. The amount of broken code I just
> encountered is mind boggling. I've added comments explaining what
> is broken, but I fear that some of the code would be best dealt with
> by being dragged behind the bike shed, burying in mud up to it's
> neck and then run over repeatedly with a blunt lawn mower.
>
> Special mention goes to the zcache/zcache2 drivers. They can't
> co-exist in the build at the same time, they are under different
> menu options in menuconfig, they only show up when you've got the
> right set of mm subsystem options configured and so even compile
> testing is an exercise in pulling teeth. And that doesn't even take
> into account the horrible, broken code...
>
> [ glommer: fixes for i915, android lowmem, zcache, bcache ]
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Signed-off-by: Glauber Costa <glommer@openvz.org>
Mostly glancing through. For this patch, double check where I asked
about -1's because I think some of the scanners are returning 0 when it
should be -1. Other comments on the shrinkers are drive-by comments.
Affected maintainers are now on the cc which should probably be aware of
this patch.
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 6be940e..2e44733 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -1729,15 +1731,20 @@ i915_gem_purge(struct drm_i915_private *dev_priv, long target)
> return __i915_gem_shrink(dev_priv, target, true);
> }
>
> -static void
> +static long
> i915_gem_shrink_all(struct drm_i915_private *dev_priv)
> {
> struct drm_i915_gem_object *obj, *next;
> + long freed = 0;
>
> - i915_gem_evict_everything(dev_priv->dev);
> + freed += i915_gem_evict_everything(dev_priv->dev);
>
> - list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list)
> + list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list) {
> + if (obj->pages_pin_count == 0)
> + freed += obj->base.size >> PAGE_SHIFT;
> i915_gem_object_put_pages(obj);
> + }
> + return freed;
> }
>
i915_gem_shrink_all is a sledge hammer! That i915_gem_evict_everything
looks like it switches to every GPU context, waits for everything to
complete and then retire it all. I don't know the details of what it's
doing but it's sounds very heavy handed and is called from shrinker
context if it fails to shrink 128 objects. Those shrinker callsback can
be very frequently called even from kswapd.
> static int
> @@ -4205,7 +4212,8 @@ i915_gem_load(struct drm_device *dev)
>
> dev_priv->mm.interruptible = true;
>
> - dev_priv->mm.inactive_shrinker.shrink = i915_gem_inactive_shrink;
> + dev_priv->mm.inactive_shrinker.scan_objects = i915_gem_inactive_scan;
> + dev_priv->mm.inactive_shrinker.count_objects = i915_gem_inactive_count;
> dev_priv->mm.inactive_shrinker.seeks = DEFAULT_SEEKS;
> register_shrinker(&dev_priv->mm.inactive_shrinker);
> }
> @@ -4428,8 +4436,8 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
> #endif
> }
>
> -static int
> -i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
> +static long
> +i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc)
> {
> struct drm_i915_private *dev_priv =
> container_of(shrinker,
> @@ -4437,9 +4445,8 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
> mm.inactive_shrinker);
> struct drm_device *dev = dev_priv->dev;
> struct drm_i915_gem_object *obj;
> - int nr_to_scan = sc->nr_to_scan;
> bool unlock = true;
> - int cnt;
> + long cnt;
>
> if (!mutex_trylock(&dev->struct_mutex)) {
> if (!mutex_is_locked_by(&dev->struct_mutex, current))
> @@ -4451,15 +4458,6 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
> unlock = false;
> }
>
> - if (nr_to_scan) {
> - nr_to_scan -= i915_gem_purge(dev_priv, nr_to_scan);
> - if (nr_to_scan > 0)
> - nr_to_scan -= __i915_gem_shrink(dev_priv, nr_to_scan,
> - false);
> - if (nr_to_scan > 0)
> - i915_gem_shrink_all(dev_priv);
> - }
> -
> cnt = 0;
> list_for_each_entry(obj, &dev_priv->mm.unbound_list, gtt_list)
> if (obj->pages_pin_count == 0)
> @@ -4472,3 +4470,36 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
> mutex_unlock(&dev->struct_mutex);
> return cnt;
> }
> +static long
> +i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc)
> +{
> + struct drm_i915_private *dev_priv =
> + container_of(shrinker,
> + struct drm_i915_private,
> + mm.inactive_shrinker);
> + struct drm_device *dev = dev_priv->dev;
> + int nr_to_scan = sc->nr_to_scan;
> + long freed;
> + bool unlock = true;
> +
> + if (!mutex_trylock(&dev->struct_mutex)) {
> + if (!mutex_is_locked_by(&dev->struct_mutex, current))
> + return 0;
> +
return -1 if it's about preventing potential deadlocks?
> + if (dev_priv->mm.shrinker_no_lock_stealing)
> + return 0;
> +
same?
> + unlock = false;
> + }
> +
> + freed = i915_gem_purge(dev_priv, nr_to_scan);
> + if (freed < nr_to_scan)
> + freed += __i915_gem_shrink(dev_priv, nr_to_scan,
> + false);
> + if (freed < nr_to_scan)
> + freed += i915_gem_shrink_all(dev_priv);
> +
Do we *really* want to call i915_gem_shrink_all from the slab shrinker?
Are there any bug reports where i915 rendering jitters in low memory
situations while shrinkers might be active? Maybe it's really fast.
> + if (unlock)
> + mutex_unlock(&dev->struct_mutex);
> + return freed;
> +}
> diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
> index c86d5d9..e379340 100644
> --- a/drivers/gpu/drm/i915/i915_gem_evict.c
> +++ b/drivers/gpu/drm/i915/i915_gem_evict.c
> @@ -150,13 +150,13 @@ found:
> return ret;
> }
>
> -int
> +long
> i915_gem_evict_everything(struct drm_device *dev)
> {
> drm_i915_private_t *dev_priv = dev->dev_private;
> struct drm_i915_gem_object *obj, *next;
> bool lists_empty;
> - int ret;
> + long ret = 0;
>
> lists_empty = (list_empty(&dev_priv->mm.inactive_list) &&
> list_empty(&dev_priv->mm.active_list));
> @@ -178,8 +178,10 @@ i915_gem_evict_everything(struct drm_device *dev)
> /* Having flushed everything, unbind() should never raise an error */
> list_for_each_entry_safe(obj, next,
> &dev_priv->mm.inactive_list, mm_list)
> - if (obj->pin_count == 0)
> + if (obj->pin_count == 0) {
> + ret += obj->base.size >> PAGE_SHIFT;
> WARN_ON(i915_gem_object_unbind(obj));
> + }
>
> - return 0;
> + return ret;
> }
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 117ce38..da0017a 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -566,7 +566,7 @@ err: /* Decrement pin count for bound objects */
> return ret;
>
> ret = i915_gem_evict_everything(ring->dev);
> - if (ret)
> + if (ret < 0)
> return ret;
> } while (1);
> }
> diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
> index bd2a3b4..83058a2 100644
> --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
> +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
> @@ -377,28 +377,28 @@ out:
> return nr_free;
> }
>
> -/* Get good estimation how many pages are free in pools */
> -static int ttm_pool_get_num_unused_pages(void)
> -{
> - unsigned i;
> - int total = 0;
> - for (i = 0; i < NUM_POOLS; ++i)
> - total += _manager->pools[i].npages;
> -
> - return total;
> -}
> -
> /**
> * Callback for mm to request pool to reduce number of page held.
> + *
> + * XXX: (dchinner) Deadlock warning!
> + *
> + * ttm_page_pool_free() does memory allocation using GFP_KERNEL. that means
> + * this can deadlock when called a sc->gfp_mask that is not equal to
> + * GFP_KERNEL.
> + *
> + * This code is crying out for a shrinker per pool....
> */
Yep, direct reclaimers potentially hit this. Options include using
kmalloc atomic and falling back to a very small on-stack array or a lump
hammer like declaring a per-cpu buffer similar to what pagevecs do.
> -static int ttm_pool_mm_shrink(struct shrinker *shrink,
> - struct shrink_control *sc)
> +static long
> +ttm_pool_shrink_scan(
> + struct shrinker *shrink,
> + struct shrink_control *sc)
> {
> static atomic_t start_pool = ATOMIC_INIT(0);
> unsigned i;
> unsigned pool_offset = atomic_add_return(1, &start_pool);
> struct ttm_page_pool *pool;
> int shrink_pages = sc->nr_to_scan;
> + long freed = 0;
>
> pool_offset = pool_offset % NUM_POOLS;
> /* select start pool in round robin fashion */
> @@ -408,14 +408,30 @@ static int ttm_pool_mm_shrink(struct shrinker *shrink,
> break;
> pool = &_manager->pools[(i + pool_offset)%NUM_POOLS];
> shrink_pages = ttm_page_pool_free(pool, nr_free);
> + freed += nr_free - shrink_pages;
> }
> - /* return estimated number of unused pages in pool */
> - return ttm_pool_get_num_unused_pages();
> + return freed;
> +}
> +
> +
> +static long
> +ttm_pool_shrink_count(
> + struct shrinker *shrink,
> + struct shrink_control *sc)
> +{
> + unsigned i;
> + long count = 0;
> +
> + for (i = 0; i < NUM_POOLS; ++i)
> + count += _manager->pools[i].npages;
> +
> + return count;
> }
>
> static void ttm_pool_mm_shrink_init(struct ttm_pool_manager *manager)
> {
> - manager->mm_shrink.shrink = &ttm_pool_mm_shrink;
> + manager->mm_shrink.count_objects = &ttm_pool_shrink_count;
> + manager->mm_shrink.scan_objects = &ttm_pool_shrink_scan;
> manager->mm_shrink.seeks = 1;
> register_shrinker(&manager->mm_shrink);
> }
> diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
> index b8b3943..b3b4f99 100644
> --- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
> +++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
> @@ -918,19 +918,6 @@ int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev)
> }
> EXPORT_SYMBOL_GPL(ttm_dma_populate);
>
> -/* Get good estimation how many pages are free in pools */
> -static int ttm_dma_pool_get_num_unused_pages(void)
> -{
> - struct device_pools *p;
> - unsigned total = 0;
> -
> - mutex_lock(&_manager->lock);
> - list_for_each_entry(p, &_manager->pools, pools)
> - total += p->pool->npages_free;
> - mutex_unlock(&_manager->lock);
> - return total;
> -}
> -
> /* Put all pages in pages list to correct pool to wait for reuse */
> void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
> {
> @@ -1002,18 +989,31 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
>
> /**
> * Callback for mm to request pool to reduce number of page held.
> + *
> + * XXX: (dchinner) Deadlock warning!
> + *
> + * ttm_dma_page_pool_free() does GFP_KERNEL memory allocation, and so attention
> + * needs to be paid to sc->gfp_mask to determine if this can be done or not.
> + * GFP_KERNEL memory allocation in a GFP_ATOMIC reclaim context woul dbe really
> + * bad.
> + *
> + * I'm getting sadder as I hear more pathetical whimpers about needing per-pool
> + * shrinkers
> */
> -static int ttm_dma_pool_mm_shrink(struct shrinker *shrink,
> - struct shrink_control *sc)
> +static long
> +ttm_dma_pool_shrink_scan(
> + struct shrinker *shrink,
> + struct shrink_control *sc)
> {
> static atomic_t start_pool = ATOMIC_INIT(0);
> unsigned idx = 0;
> unsigned pool_offset = atomic_add_return(1, &start_pool);
> unsigned shrink_pages = sc->nr_to_scan;
> struct device_pools *p;
> + long freed = 0;
>
> if (list_empty(&_manager->pools))
> - return 0;
> + return -1;
>
> mutex_lock(&_manager->lock);
> pool_offset = pool_offset % _manager->npools;
> @@ -1029,18 +1029,35 @@ static int ttm_dma_pool_mm_shrink(struct shrinker *shrink,
> continue;
> nr_free = shrink_pages;
> shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free);
> + freed += nr_free - shrink_pages;
> +
> pr_debug("%s: (%s:%d) Asked to shrink %d, have %d more to go\n",
> p->pool->dev_name, p->pool->name, current->pid,
> nr_free, shrink_pages);
> }
> mutex_unlock(&_manager->lock);
> - /* return estimated number of unused pages in pool */
> - return ttm_dma_pool_get_num_unused_pages();
> + return freed;
> +}
> +
> +static long
> +ttm_dma_pool_shrink_count(
> + struct shrinker *shrink,
> + struct shrink_control *sc)
> +{
> + struct device_pools *p;
> + long count = 0;
> +
> + mutex_lock(&_manager->lock);
> + list_for_each_entry(p, &_manager->pools, pools)
> + count += p->pool->npages_free;
> + mutex_unlock(&_manager->lock);
> + return count;
> }
>
> static void ttm_dma_pool_mm_shrink_init(struct ttm_pool_manager *manager)
> {
> - manager->mm_shrink.shrink = &ttm_dma_pool_mm_shrink;
> + manager->mm_shrink.count_objects = &ttm_dma_pool_shrink_count;
> + manager->mm_shrink.scan_objects = &ttm_dma_pool_shrink_scan;
> manager->mm_shrink.seeks = 1;
> register_shrinker(&manager->mm_shrink);
> }
> diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
> index 03e44c1..8b9c1a6 100644
> --- a/drivers/md/bcache/btree.c
> +++ b/drivers/md/bcache/btree.c
> @@ -599,11 +599,12 @@ static int mca_reap(struct btree *b, struct closure *cl, unsigned min_order)
> return 0;
> }
>
> -static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
> +static long bch_mca_scan(struct shrinker *shrink, struct shrink_control *sc)
> {
> struct cache_set *c = container_of(shrink, struct cache_set, shrink);
> struct btree *b, *t;
> unsigned long i, nr = sc->nr_to_scan;
> + long freed = 0;
>
> if (c->shrinker_disabled)
> return 0;
-1 if shrinker disabled?
Otherwise if the shrinker is disabled we ultimately hit this loop in
shrink_slab_one()
do {
ret = shrinker->scan_objects(shrinker, sc);
if (ret == -1)
break
....
count_vm_events(SLABS_SCANNED, batch_size);
total_scan -= batch_size;
cond_resched();
} while (total_scan >= batch_size);
which won't break as such but we busy loop until total_scan drops and
account for SLABS_SCANNED incorrectly.
More using of mutex_lock in here which means that multiple direct reclaimers
will contend on each other. bch_mca_shrink() checks for __GFP_WAIT but an
atomic caller does not direct reclaim so it'll always try and contend.
> @@ -611,12 +612,6 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
> if (c->try_harder)
> return 0;
>
> - /*
> - * If nr == 0, we're supposed to return the number of items we have
> - * cached. Not allowed to return -1.
> - */
> - if (!nr)
> - return mca_can_free(c) * c->btree_pages;
>
> /* Return -1 if we can't do anything right now */
> if (sc->gfp_mask & __GFP_WAIT)
> @@ -629,14 +624,14 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
>
> i = 0;
> list_for_each_entry_safe(b, t, &c->btree_cache_freeable, list) {
> - if (!nr)
> + if (freed >= nr)
> break;
>
> if (++i > 3 &&
> !mca_reap(b, NULL, 0)) {
> mca_data_free(b);
> rw_unlock(true, b);
> - --nr;
> + freed++;
> }
> }
>
> @@ -647,7 +642,7 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
> if (list_empty(&c->btree_cache))
> goto out;
>
> - for (i = 0; nr && i < c->bucket_cache_used; i++) {
> + for (i = 0; i < c->bucket_cache_used; i++) {
> b = list_first_entry(&c->btree_cache, struct btree, list);
> list_rotate_left(&c->btree_cache);
>
> @@ -656,14 +651,20 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
> mca_bucket_free(b);
> mca_data_free(b);
> rw_unlock(true, b);
> - --nr;
> + freed++;
> } else
> b->accessed = 0;
> }
> out:
> - nr = mca_can_free(c) * c->btree_pages;
> mutex_unlock(&c->bucket_lock);
> - return nr;
> + return freed;
> +}
> +
> +static long bch_mca_count(struct shrinker *shrink, struct shrink_control *sc)
> +{
> + struct cache_set *c = container_of(shrink, struct cache_set, shrink);
> +
> + return mca_can_free(c) * c->btree_pages;
> }
>
> void bch_btree_cache_free(struct cache_set *c)
> @@ -732,7 +733,8 @@ int bch_btree_cache_alloc(struct cache_set *c)
> c->verify_data = NULL;
> #endif
>
> - c->shrink.shrink = bch_mca_shrink;
> + c->shrink.count_objects = bch_mca_count;
> + c->shrink.scan_objects = bch_mca_scan;
> c->shrink.seeks = 4;
> c->shrink.batch = c->btree_pages * 2;
> register_shrinker(&c->shrink);
> diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
> index 4d9cca4..fa8d048 100644
> --- a/drivers/md/bcache/sysfs.c
> +++ b/drivers/md/bcache/sysfs.c
> @@ -535,7 +535,7 @@ STORE(__bch_cache_set)
> struct shrink_control sc;
> sc.gfp_mask = GFP_KERNEL;
> sc.nr_to_scan = strtoul_or_return(buf);
> - c->shrink.shrink(&c->shrink, &sc);
> + c->shrink.scan_objects(&c->shrink, &sc);
> }
>
> sysfs_strtoul(congested_read_threshold_us,
> diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
> index 6f1b57a..59b6082 100644
> --- a/drivers/md/dm-bufio.c
> +++ b/drivers/md/dm-bufio.c
> @@ -1361,62 +1361,80 @@ static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp,
> unsigned long max_jiffies)
> {
> if (jiffies - b->last_accessed < max_jiffies)
> - return 1;
> + return 0;
>
> if (!(gfp & __GFP_IO)) {
> if (test_bit(B_READING, &b->state) ||
> test_bit(B_WRITING, &b->state) ||
> test_bit(B_DIRTY, &b->state))
> - return 1;
> + return 0;
> }
>
> if (b->hold_count)
> - return 1;
> + return 0;
>
> __make_buffer_clean(b);
> __unlink_buffer(b);
> __free_buffer_wake(b);
>
> - return 0;
> + return 1;
> }
>
> -static void __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
> - struct shrink_control *sc)
> +static long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
> + gfp_t gfp_mask)
> {
> int l;
> struct dm_buffer *b, *tmp;
> + long freed = 0;
>
> for (l = 0; l < LIST_SIZE; l++) {
> - list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list)
> - if (!__cleanup_old_buffer(b, sc->gfp_mask, 0) &&
> - !--nr_to_scan)
> - return;
> + list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) {
> + freed += __cleanup_old_buffer(b, gfp_mask, 0);
> + if (!--nr_to_scan)
> + break;
> + }
> dm_bufio_cond_resched();
> }
> + return freed;
> }
>
> -static int shrink(struct shrinker *shrinker, struct shrink_control *sc)
> +static long
> +dm_bufio_shrink_scan(
> + struct shrinker *shrink,
> + struct shrink_control *sc)
> {
> struct dm_bufio_client *c =
> - container_of(shrinker, struct dm_bufio_client, shrinker);
> - unsigned long r;
> - unsigned long nr_to_scan = sc->nr_to_scan;
> + container_of(shrink, struct dm_bufio_client, shrinker);
> + long freed;
>
> if (sc->gfp_mask & __GFP_IO)
> dm_bufio_lock(c);
> else if (!dm_bufio_trylock(c))
> - return !nr_to_scan ? 0 : -1;
> + return -1;
>
> - if (nr_to_scan)
> - __scan(c, nr_to_scan, sc);
> + freed = __scan(c, sc->nr_to_scan, sc->gfp_mask);
> + dm_bufio_unlock(c);
> + return freed;
> +}
>
> - r = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY];
> - if (r > INT_MAX)
> - r = INT_MAX;
> +static 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);
> + long count;
> +
> + if (sc->gfp_mask & __GFP_IO)
> + dm_bufio_lock(c);
> + else if (!dm_bufio_trylock(c))
> + return 0;
>
> + count = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY];
> dm_bufio_unlock(c);
> + return count;
>
> - return r;
> }
>
> /*
> @@ -1518,7 +1536,8 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
> __cache_size_refresh();
> mutex_unlock(&dm_bufio_clients_lock);
>
> - c->shrinker.shrink = shrink;
> + c->shrinker.count_objects = dm_bufio_shrink_count;
> + c->shrinker.scan_objects = dm_bufio_shrink_scan;
> c->shrinker.seeks = 1;
> c->shrinker.batch = 0;
> register_shrinker(&c->shrinker);
> @@ -1605,7 +1624,7 @@ static void cleanup_old_buffers(void)
> struct dm_buffer *b;
> b = list_entry(c->lru[LIST_CLEAN].prev,
> struct dm_buffer, lru_list);
> - if (__cleanup_old_buffer(b, 0, max_age * HZ))
> + if (!__cleanup_old_buffer(b, 0, max_age * HZ))
> break;
> dm_bufio_cond_resched();
> }
> diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
> index 3240d34..951d944 100644
> --- a/drivers/staging/android/ashmem.c
> +++ b/drivers/staging/android/ashmem.c
> @@ -341,27 +341,28 @@ out:
> /*
> * ashmem_shrink - our cache shrinker, called from mm/vmscan.c :: shrink_slab
> *
> - * 'nr_to_scan' is the number of objects (pages) to prune, or 0 to query how
> - * many objects (pages) we have in total.
> + * 'nr_to_scan' is the number of objects to scan for freeing.
> *
> * 'gfp_mask' is the mask of the allocation that got us into this mess.
> *
> - * Return value is the number of objects (pages) remaining, or -1 if we cannot
> + * Return value is the number of objects freed or -1 if we cannot
> * proceed without risk of deadlock (due to gfp_mask).
> *
> * We approximate LRU via least-recently-unpinned, jettisoning unpinned partial
> * chunks of ashmem regions LRU-wise one-at-a-time until we hit 'nr_to_scan'
> * pages freed.
> */
> -static int ashmem_shrink(struct shrinker *s, struct shrink_control *sc)
> +static long
> +ashmem_shrink_scan(
> + struct shrinker *shrink,
> + struct shrink_control *sc)
> {
> struct ashmem_range *range, *next;
> + long freed = 0;
>
> /* We might recurse into filesystem code, so bail out if necessary */
> - if (sc->nr_to_scan && !(sc->gfp_mask & __GFP_FS))
> + if (!(sc->gfp_mask & __GFP_FS))
> return -1;
> - if (!sc->nr_to_scan)
> - return lru_count;
>
> mutex_lock(&ashmem_mutex);
> list_for_each_entry_safe(range, next, &ashmem_lru_list, lru) {
> @@ -374,17 +375,34 @@ static int ashmem_shrink(struct shrinker *s, struct shrink_control *sc)
> range->purged = ASHMEM_WAS_PURGED;
> lru_del(range);
>
> - sc->nr_to_scan -= range_size(range);
> - if (sc->nr_to_scan <= 0)
> + freed += range_size(range);
> + if (--sc->nr_to_scan <= 0)
> break;
> }
> mutex_unlock(&ashmem_mutex);
> + return freed;
> +}
>
> +static long
> +ashmem_shrink_count(
> + struct shrinker *shrink,
> + struct shrink_control *sc)
> +{
> + /*
> + * note that lru_count is count of pages on the lru, not a count of
> + * objects on the list. This means the scan function needs to return the
> + * number of pages freed, not the number of objects scanned.
> + */
> return lru_count;
> }
>
> static struct shrinker ashmem_shrinker = {
> - .shrink = ashmem_shrink,
> + .count_objects = ashmem_shrink_count,
> + .scan_objects = ashmem_shrink_scan,
> + /*
> + * XXX (dchinner): I wish people would comment on why they need on
> + * significant changes to the default value here
> + */
> .seeks = DEFAULT_SEEKS * 4,
> };
>
> @@ -690,14 +708,11 @@ static long ashmem_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
> if (capable(CAP_SYS_ADMIN)) {
> struct shrink_control sc = {
> .gfp_mask = GFP_KERNEL,
> - .nr_to_scan = 0,
> + .nr_to_scan = LONG_MAX,
> };
>
> nodes_setall(sc.nodes_to_scan);
> -
> - ret = ashmem_shrink(&ashmem_shrinker, &sc);
> - sc.nr_to_scan = ret;
> - ashmem_shrink(&ashmem_shrinker, &sc);
> + ashmem_shrink_scan(&ashmem_shrinker, &sc);
> }
> break;
> }
> diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
> index fe74494..d23bfea 100644
> --- a/drivers/staging/android/lowmemorykiller.c
> +++ b/drivers/staging/android/lowmemorykiller.c
> @@ -66,7 +66,15 @@ static unsigned long lowmem_deathpending_timeout;
> pr_info(x); \
> } while (0)
>
> -static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
> +static long lowmem_count(struct shrinker *s, struct shrink_control *sc)
> +{
> + return global_page_state(NR_ACTIVE_ANON) +
> + global_page_state(NR_ACTIVE_FILE) +
> + global_page_state(NR_INACTIVE_ANON) +
> + global_page_state(NR_INACTIVE_FILE);
> +}
> +
> +static long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
> {
> struct task_struct *tsk;
> struct task_struct *selected = NULL;
> @@ -92,19 +100,17 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
> break;
> }
> }
> - if (sc->nr_to_scan > 0)
> - lowmem_print(3, "lowmem_shrink %lu, %x, ofree %d %d, ma %hd\n",
> - sc->nr_to_scan, sc->gfp_mask, other_free,
> - other_file, min_score_adj);
> - rem = global_page_state(NR_ACTIVE_ANON) +
> - global_page_state(NR_ACTIVE_FILE) +
> - global_page_state(NR_INACTIVE_ANON) +
> - global_page_state(NR_INACTIVE_FILE);
> - if (sc->nr_to_scan <= 0 || min_score_adj == OOM_SCORE_ADJ_MAX + 1) {
> - lowmem_print(5, "lowmem_shrink %lu, %x, return %d\n",
> - sc->nr_to_scan, sc->gfp_mask, rem);
> - return rem;
> +
> + lowmem_print(3, "lowmem_scan %lu, %x, ofree %d %d, ma %hd\n",
> + sc->nr_to_scan, sc->gfp_mask, other_free,
> + other_file, min_score_adj);
> +
> + if (min_score_adj == OOM_SCORE_ADJ_MAX + 1) {
> + lowmem_print(5, "lowmem_scan %lu, %x, return 0\n",
> + sc->nr_to_scan, sc->gfp_mask);
> + return 0;
> }
> +
-1 again?
Otherwise given the really high number that lowmem_count returns (which
is then basically ignored anyway), this thing will just loop for a while
being called by the slab shrinker. It's just a CPU sink if there is
nothing for the shrinker to do.
> selected_oom_score_adj = min_score_adj;
>
> rcu_read_lock();
> @@ -154,16 +160,18 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
> lowmem_deathpending_timeout = jiffies + HZ;
> send_sig(SIGKILL, selected, 0);
> set_tsk_thread_flag(selected, TIF_MEMDIE);
> - rem -= selected_tasksize;
> + rem += selected_tasksize;
> }
> - lowmem_print(4, "lowmem_shrink %lu, %x, return %d\n",
> +
> + lowmem_print(4, "lowmem_scan %lu, %x, return %d\n",
> sc->nr_to_scan, sc->gfp_mask, rem);
> rcu_read_unlock();
> return rem;
> }
>
> static struct shrinker lowmem_shrinker = {
> - .shrink = lowmem_shrink,
> + .scan_objects = lowmem_scan,
> + .count_objects = lowmem_count,
> .seeks = DEFAULT_SEEKS * 16
> };
>
> diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c
> index 522cb8e..bbfcd4f 100644
> --- a/drivers/staging/zcache/zcache-main.c
> +++ b/drivers/staging/zcache/zcache-main.c
> @@ -1140,23 +1140,19 @@ static bool zcache_freeze;
> * pageframes in use. FIXME POLICY: Probably the writeback should only occur
> * if the eviction doesn't free enough pages.
> */
> -static int shrink_zcache_memory(struct shrinker *shrink,
> - struct shrink_control *sc)
> +static long scan_zcache_memory(struct shrinker *shrink,
> + struct shrink_control *sc)
> {
> static bool in_progress;
> - int ret = -1;
> - int nr = sc->nr_to_scan;
> int nr_evict = 0;
> int nr_writeback = 0;
> struct page *page;
> int file_pageframes_inuse, anon_pageframes_inuse;
> -
> - if (nr <= 0)
> - goto skip_evict;
> + long freed = 0;
>
> /* don't allow more than one eviction thread at a time */
> if (in_progress)
> - goto skip_evict;
> + return 0;
>
-1?
Not clear why in_progress is not a static mutex and a trylock because
currently it's a race.
> in_progress = true;
>
> @@ -1176,6 +1172,7 @@ static int shrink_zcache_memory(struct shrinker *shrink,
> if (page == NULL)
> break;
> zcache_free_page(page);
> + freed++;
> }
>
> zcache_last_active_anon_pageframes =
> @@ -1192,13 +1189,22 @@ static int shrink_zcache_memory(struct shrinker *shrink,
> #ifdef CONFIG_ZCACHE_WRITEBACK
> int writeback_ret;
> writeback_ret = zcache_frontswap_writeback();
> - if (writeback_ret == -ENOMEM)
> + if (writeback_ret != -ENOMEM)
> + freed++;
> + else
> #endif
> break;
> }
> in_progress = false;
>
> -skip_evict:
> + return freed;
> +}
> +
> +static long count_zcache_memory(struct shrinker *shrink,
> + struct shrink_control *sc)
> +{
> + int ret = -1;
> +
> /* resample: has changed, but maybe not all the way yet */
> zcache_last_active_file_pageframes =
> global_page_state(NR_LRU_BASE + LRU_ACTIVE_FILE);
> @@ -1212,7 +1218,8 @@ skip_evict:
> }
>
> static struct shrinker zcache_shrinker = {
> - .shrink = shrink_zcache_memory,
> + .scan_objects = scan_zcache_memory,
> + .count_objects = count_zcache_memory,
> .seeks = DEFAULT_SEEKS,
> };
>
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 17/31] drivers: convert shrinkers to new count/scan API
2013-04-30 21:53 ` Mel Gorman
@ 2013-04-30 22:00 ` Kent Overstreet
2013-05-02 9:37 ` Mel Gorman
2013-05-01 15:26 ` Daniel Vetter
1 sibling, 1 reply; 63+ messages in thread
From: Kent Overstreet @ 2013-04-30 22:00 UTC (permalink / raw)
To: Mel Gorman
Cc: Glauber Costa, linux-mm, cgroups, Andrew Morton, Greg Thelen,
kamezawa.hiroyu, Michal Hocko, Johannes Weiner, Dave Chinner,
intel-gfx, dri-devel, devel, Dan Magenheimer
On Tue, Apr 30, 2013 at 10:53:55PM +0100, Mel Gorman wrote:
> On Sat, Apr 27, 2013 at 03:19:13AM +0400, Glauber Costa wrote:
> > diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
> > index 03e44c1..8b9c1a6 100644
> > --- a/drivers/md/bcache/btree.c
> > +++ b/drivers/md/bcache/btree.c
> > @@ -599,11 +599,12 @@ static int mca_reap(struct btree *b, struct closure *cl, unsigned min_order)
> > return 0;
> > }
> >
> > -static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
> > +static long bch_mca_scan(struct shrinker *shrink, struct shrink_control *sc)
> > {
> > struct cache_set *c = container_of(shrink, struct cache_set, shrink);
> > struct btree *b, *t;
> > unsigned long i, nr = sc->nr_to_scan;
> > + long freed = 0;
> >
> > if (c->shrinker_disabled)
> > return 0;
>
> -1 if shrinker disabled?
>
> Otherwise if the shrinker is disabled we ultimately hit this loop in
> shrink_slab_one()
My memory is very hazy on this stuff, but I recall there being another
loop that'd just spin if we always returned -1.
(It might've been /proc/sys/vm/drop_caches, or maybe that was another
bug..)
But 0 should certainly be safe - if we're always returning 0, then we're
claiming we don't have anything to shrink.
> do {
> ret = shrinker->scan_objects(shrinker, sc);
> if (ret == -1)
> break
> ....
> count_vm_events(SLABS_SCANNED, batch_size);
> total_scan -= batch_size;
>
> cond_resched();
> } while (total_scan >= batch_size);
>
> which won't break as such but we busy loop until total_scan drops and
> account for SLABS_SCANNED incorrectly.
>
> More using of mutex_lock in here which means that multiple direct reclaimers
> will contend on each other. bch_mca_shrink() checks for __GFP_WAIT but an
> atomic caller does not direct reclaim so it'll always try and contend.
>
> > @@ -611,12 +612,6 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
> > if (c->try_harder)
> > return 0;
> >
> > - /*
> > - * If nr == 0, we're supposed to return the number of items we have
> > - * cached. Not allowed to return -1.
> > - */
> > - if (!nr)
> > - return mca_can_free(c) * c->btree_pages;
> >
> > /* Return -1 if we can't do anything right now */
> > if (sc->gfp_mask & __GFP_WAIT)
> > @@ -629,14 +624,14 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
> >
> > i = 0;
> > list_for_each_entry_safe(b, t, &c->btree_cache_freeable, list) {
> > - if (!nr)
> > + if (freed >= nr)
> > break;
> >
> > if (++i > 3 &&
> > !mca_reap(b, NULL, 0)) {
> > mca_data_free(b);
> > rw_unlock(true, b);
> > - --nr;
> > + freed++;
> > }
> > }
> >
> > @@ -647,7 +642,7 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
> > if (list_empty(&c->btree_cache))
> > goto out;
> >
> > - for (i = 0; nr && i < c->bucket_cache_used; i++) {
> > + for (i = 0; i < c->bucket_cache_used; i++) {
> > b = list_first_entry(&c->btree_cache, struct btree, list);
> > list_rotate_left(&c->btree_cache);
> >
> > @@ -656,14 +651,20 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
> > mca_bucket_free(b);
> > mca_data_free(b);
> > rw_unlock(true, b);
> > - --nr;
> > + freed++;
> > } else
> > b->accessed = 0;
> > }
> > out:
> > - nr = mca_can_free(c) * c->btree_pages;
> > mutex_unlock(&c->bucket_lock);
> > - return nr;
> > + return freed;
> > +}
> > +
> > +static long bch_mca_count(struct shrinker *shrink, struct shrink_control *sc)
> > +{
> > + struct cache_set *c = container_of(shrink, struct cache_set, shrink);
> > +
> > + return mca_can_free(c) * c->btree_pages;
> > }
> >
> > void bch_btree_cache_free(struct cache_set *c)
> > @@ -732,7 +733,8 @@ int bch_btree_cache_alloc(struct cache_set *c)
> > c->verify_data = NULL;
> > #endif
> >
> > - c->shrink.shrink = bch_mca_shrink;
> > + c->shrink.count_objects = bch_mca_count;
> > + c->shrink.scan_objects = bch_mca_scan;
> > c->shrink.seeks = 4;
> > c->shrink.batch = c->btree_pages * 2;
> > register_shrinker(&c->shrink);
> > diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
> > index 4d9cca4..fa8d048 100644
> > --- a/drivers/md/bcache/sysfs.c
> > +++ b/drivers/md/bcache/sysfs.c
> > @@ -535,7 +535,7 @@ STORE(__bch_cache_set)
> > struct shrink_control sc;
> > sc.gfp_mask = GFP_KERNEL;
> > sc.nr_to_scan = strtoul_or_return(buf);
> > - c->shrink.shrink(&c->shrink, &sc);
> > + c->shrink.scan_objects(&c->shrink, &sc);
> > }
> >
> > sysfs_strtoul(congested_read_threshold_us,
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 17/31] drivers: convert shrinkers to new count/scan API
2013-04-30 22:00 ` Kent Overstreet
@ 2013-05-02 9:37 ` Mel Gorman
2013-05-02 13:37 ` Glauber Costa
0 siblings, 1 reply; 63+ messages in thread
From: Mel Gorman @ 2013-05-02 9:37 UTC (permalink / raw)
To: Kent Overstreet
Cc: Glauber Costa, linux-mm, cgroups, Andrew Morton, Greg Thelen,
kamezawa.hiroyu, Michal Hocko, Johannes Weiner, Dave Chinner,
intel-gfx, dri-devel, devel, Dan Magenheimer
On Tue, Apr 30, 2013 at 03:00:50PM -0700, Kent Overstreet wrote:
> On Tue, Apr 30, 2013 at 10:53:55PM +0100, Mel Gorman wrote:
> > On Sat, Apr 27, 2013 at 03:19:13AM +0400, Glauber Costa wrote:
> > > diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
> > > index 03e44c1..8b9c1a6 100644
> > > --- a/drivers/md/bcache/btree.c
> > > +++ b/drivers/md/bcache/btree.c
> > > @@ -599,11 +599,12 @@ static int mca_reap(struct btree *b, struct closure *cl, unsigned min_order)
> > > return 0;
> > > }
> > >
> > > -static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
> > > +static long bch_mca_scan(struct shrinker *shrink, struct shrink_control *sc)
> > > {
> > > struct cache_set *c = container_of(shrink, struct cache_set, shrink);
> > > struct btree *b, *t;
> > > unsigned long i, nr = sc->nr_to_scan;
> > > + long freed = 0;
> > >
> > > if (c->shrinker_disabled)
> > > return 0;
> >
> > -1 if shrinker disabled?
> >
> > Otherwise if the shrinker is disabled we ultimately hit this loop in
> > shrink_slab_one()
>
> My memory is very hazy on this stuff, but I recall there being another
> loop that'd just spin if we always returned -1.
>
> (It might've been /proc/sys/vm/drop_caches, or maybe that was another
> bug..)
>
It might be worth chasing down what that bug was and fixing it.
> But 0 should certainly be safe - if we're always returning 0, then we're
> claiming we don't have anything to shrink.
>
It won't crash, but in Glauber's current code, it'll call you a few more
times uselessly and the scanned statistics become misleading. I think
Glauber/Dave's series is a big improvement over what we currently have
and it would be nice to get it ironed out.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 17/31] drivers: convert shrinkers to new count/scan API
2013-05-02 9:37 ` Mel Gorman
@ 2013-05-02 13:37 ` Glauber Costa
0 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-05-02 13:37 UTC (permalink / raw)
To: mgorman@suse.de, koverstreet@google.com
Cc: glommer@openvz.org, linux-mm@kvack.org, cgroups@vger.kernel.org,
akpm@linux-foundation.org, gthelen@google.com,
kamezawa.hiroyu@jp.fujitsu.com, mhocko@suse.cz,
hannes@cmpxchg.org, dchinner@redhat.com,
intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org,
devel@driverdev.osuosl.org, dan.magenheimer@oracle.com
[-- Attachment #1: Type: text/plain, Size: 2864 bytes --]
Sorry for the following crappy message. I came travelling without my laptop.
Please note that one of my patches implement one shot shrinkers onto of vmpressure mechanism. It can still be called frequently, because right now it is called every time userspace would get an event. But at least it won't iterate.
You can try investigating if that interface suits your i915 needs better
Sent by Samsung Mobile
-------- Original message --------
From: Mel Gorman <mgorman@suse.de>
Date:
To: Kent Overstreet <koverstreet@google.com>
Cc: Glauber Costa <glommer@openvz.org>,linux-mm@kvack.org,cgroups@vger.kernel.org,Andrew Morton <akpm@linux-foundation.org>,Greg Thelen <gthelen@google.com>,kamezawa.hiroyu@jp.fujitsu.com,Michal Hocko <mhocko@suse.cz>,Johannes Weiner <hannes@cmpxchg.org>,Dave Chinner <dchinner@redhat.com>,intel-gfx@lists.freedesktop.org,dri-devel@lists.freedesktop.org,devel@driverdev.osuosl.org,Dan Magenheimer <dan.magenheimer@oracle.com>
Subject: Re: [PATCH v4 17/31] drivers: convert shrinkers to new count/scan API
On Tue, Apr 30, 2013 at 03:00:50PM -0700, Kent Overstreet wrote:
> On Tue, Apr 30, 2013 at 10:53:55PM +0100, Mel Gorman wrote:
> > On Sat, Apr 27, 2013 at 03:19:13AM +0400, Glauber Costa wrote:
> > > diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
> > > index 03e44c1..8b9c1a6 100644
> > > --- a/drivers/md/bcache/btree.c
> > > +++ b/drivers/md/bcache/btree.c
> > > @@ -599,11 +599,12 @@ static int mca_reap(struct btree *b, struct closure *cl, unsigned min_order)
> > > return 0;
> > > }
> > >
> > > -static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
> > > +static long bch_mca_scan(struct shrinker *shrink, struct shrink_control *sc)
> > > {
> > > struct cache_set *c = container_of(shrink, struct cache_set, shrink);
> > > struct btree *b, *t;
> > > unsigned long i, nr = sc->nr_to_scan;
> > > + long freed = 0;
> > >
> > > if (c->shrinker_disabled)
> > > return 0;
> >
> > -1 if shrinker disabled?
> >
> > Otherwise if the shrinker is disabled we ultimately hit this loop in
> > shrink_slab_one()
>
> My memory is very hazy on this stuff, but I recall there being another
> loop that'd just spin if we always returned -1.
>
> (It might've been /proc/sys/vm/drop_caches, or maybe that was another
> bug..)
>
It might be worth chasing down what that bug was and fixing it.
> But 0 should certainly be safe - if we're always returning 0, then we're
> claiming we don't have anything to shrink.
>
It won't crash, but in Glauber's current code, it'll call you a few more
times uselessly and the scanned statistics become misleading. I think
Glauber/Dave's series is a big improvement over what we currently have
and it would be nice to get it ironed out.
--
Mel Gorman
SUSE Labs
[-- Attachment #2: Type: text/html, Size: 4190 bytes --]
^ permalink raw reply [flat|nested] 63+ messages in thread
* Re: [PATCH v4 17/31] drivers: convert shrinkers to new count/scan API
2013-04-30 21:53 ` Mel Gorman
2013-04-30 22:00 ` Kent Overstreet
@ 2013-05-01 15:26 ` Daniel Vetter
2013-05-02 9:31 ` Mel Gorman
1 sibling, 1 reply; 63+ messages in thread
From: Daniel Vetter @ 2013-05-01 15:26 UTC (permalink / raw)
To: Mel Gorman
Cc: Glauber Costa, linux-mm, cgroups, Andrew Morton, Greg Thelen,
KAMEZAWA Hiroyuki, Michal Hocko, Johannes Weiner, Dave Chinner,
intel-gfx, dri-devel, Kent Overstreet, devel, Dan Magenheimer
On Tue, Apr 30, 2013 at 11:53 PM, Mel Gorman <mgorman@suse.de> wrote:
> On Sat, Apr 27, 2013 at 03:19:13AM +0400, Glauber Costa wrote:
>> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
>> index 6be940e..2e44733 100644
>> --- a/drivers/gpu/drm/i915/i915_gem.c
>> +++ b/drivers/gpu/drm/i915/i915_gem.c
>> @@ -1729,15 +1731,20 @@ i915_gem_purge(struct drm_i915_private *dev_priv, long target)
>> return __i915_gem_shrink(dev_priv, target, true);
>> }
>>
>> -static void
>> +static long
>> i915_gem_shrink_all(struct drm_i915_private *dev_priv)
>> {
>> struct drm_i915_gem_object *obj, *next;
>> + long freed = 0;
>>
>> - i915_gem_evict_everything(dev_priv->dev);
>> + freed += i915_gem_evict_everything(dev_priv->dev);
>>
>> - list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list)
>> + list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list) {
>> + if (obj->pages_pin_count == 0)
>> + freed += obj->base.size >> PAGE_SHIFT;
>> i915_gem_object_put_pages(obj);
>> + }
>> + return freed;
>> }
>>
>
> i915_gem_shrink_all is a sledge hammer! That i915_gem_evict_everything
> looks like it switches to every GPU context, waits for everything to
> complete and then retire it all. I don't know the details of what it's
> doing but it's sounds very heavy handed and is called from shrinker
> context if it fails to shrink 128 objects. Those shrinker callsback can
> be very frequently called even from kswapd.
i915_gem_shrink_all is our escape hatch, we only use it as a
last-ditch effort when all else fails. Imo there's no point in passing
the number of freed objects around from it since it really never
should get called (as long as we don't get called with more objects to
shrink than our counter counted beforehand at least). Also, the above
hunk is broken since i915_gem_evict_everything only unbinds object
from the gpu address space and puts them onto the unbound list, i.e.
those objects will be double-counted.
>> static int
>> @@ -4205,7 +4212,8 @@ i915_gem_load(struct drm_device *dev)
>>
>> dev_priv->mm.interruptible = true;
>>
>> - dev_priv->mm.inactive_shrinker.shrink = i915_gem_inactive_shrink;
>> + dev_priv->mm.inactive_shrinker.scan_objects = i915_gem_inactive_scan;
>> + dev_priv->mm.inactive_shrinker.count_objects = i915_gem_inactive_count;
>> dev_priv->mm.inactive_shrinker.seeks = DEFAULT_SEEKS;
>> register_shrinker(&dev_priv->mm.inactive_shrinker);
>> }
>> @@ -4428,8 +4436,8 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
>> #endif
>> }
>>
>> -static int
>> -i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
>> +static long
>> +i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc)
>> {
>> struct drm_i915_private *dev_priv =
>> container_of(shrinker,
>> @@ -4437,9 +4445,8 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
>> mm.inactive_shrinker);
>> struct drm_device *dev = dev_priv->dev;
>> struct drm_i915_gem_object *obj;
>> - int nr_to_scan = sc->nr_to_scan;
>> bool unlock = true;
>> - int cnt;
>> + long cnt;
>>
>> if (!mutex_trylock(&dev->struct_mutex)) {
>> if (!mutex_is_locked_by(&dev->struct_mutex, current))
>> @@ -4451,15 +4458,6 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
>> unlock = false;
>> }
>>
>> - if (nr_to_scan) {
>> - nr_to_scan -= i915_gem_purge(dev_priv, nr_to_scan);
>> - if (nr_to_scan > 0)
>> - nr_to_scan -= __i915_gem_shrink(dev_priv, nr_to_scan,
>> - false);
>> - if (nr_to_scan > 0)
>> - i915_gem_shrink_all(dev_priv);
>> - }
>> -
>> cnt = 0;
>> list_for_each_entry(obj, &dev_priv->mm.unbound_list, gtt_list)
>> if (obj->pages_pin_count == 0)
>> @@ -4472,3 +4470,36 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
>> mutex_unlock(&dev->struct_mutex);
>> return cnt;
>> }
>> +static long
>> +i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc)
>> +{
>> + struct drm_i915_private *dev_priv =
>> + container_of(shrinker,
>> + struct drm_i915_private,
>> + mm.inactive_shrinker);
>> + struct drm_device *dev = dev_priv->dev;
>> + int nr_to_scan = sc->nr_to_scan;
>> + long freed;
>> + bool unlock = true;
>> +
>> + if (!mutex_trylock(&dev->struct_mutex)) {
>> + if (!mutex_is_locked_by(&dev->struct_mutex, current))
>> + return 0;
>> +
>
> return -1 if it's about preventing potential deadlocks?
>
>> + if (dev_priv->mm.shrinker_no_lock_stealing)
>> + return 0;
>> +
>
> same?
No idea. Aside, the aggressive shrinking with shrink_all and the lock
stealing madness here are to paper our current "one lock for
everything" approach we have for i915 gem stuff. We've papered over
the worst offenders through lock-dropping tricks while waiting, the
lock stealing above plus aggressively calling shrink_all.
Still it's pretty trivial to (spuriously) OOM if you compete a gpu
workload with something else. Real fix is per-object locking plus some
watermark limits on how many pages are locked down this way, but
that's long term (and currently stalling for the wait/wound mutexes
from Maarten Lankhorst to get in).
>
>> + unlock = false;
>> + }
>> +
>> + freed = i915_gem_purge(dev_priv, nr_to_scan);
>> + if (freed < nr_to_scan)
>> + freed += __i915_gem_shrink(dev_priv, nr_to_scan,
>> + false);
>> + if (freed < nr_to_scan)
>> + freed += i915_gem_shrink_all(dev_priv);
>> +
>
> Do we *really* want to call i915_gem_shrink_all from the slab shrinker?
> Are there any bug reports where i915 rendering jitters in low memory
> situations while shrinkers might be active? Maybe it's really fast.
It's terrible for interactivity in X, but we need it :( See above for
how we plan to eventually fix this mess.
Cheers, Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 17/31] drivers: convert shrinkers to new count/scan API
2013-05-01 15:26 ` Daniel Vetter
@ 2013-05-02 9:31 ` Mel Gorman
0 siblings, 0 replies; 63+ messages in thread
From: Mel Gorman @ 2013-05-02 9:31 UTC (permalink / raw)
To: Daniel Vetter
Cc: Glauber Costa, linux-mm, cgroups, Andrew Morton, Greg Thelen,
KAMEZAWA Hiroyuki, Michal Hocko, Johannes Weiner, Dave Chinner,
intel-gfx, dri-devel, Kent Overstreet, devel, Dan Magenheimer
On Wed, May 01, 2013 at 05:26:38PM +0200, Daniel Vetter wrote:
> On Tue, Apr 30, 2013 at 11:53 PM, Mel Gorman <mgorman@suse.de> wrote:
> > On Sat, Apr 27, 2013 at 03:19:13AM +0400, Glauber Costa wrote:
> >> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> >> index 6be940e..2e44733 100644
> >> --- a/drivers/gpu/drm/i915/i915_gem.c
> >> +++ b/drivers/gpu/drm/i915/i915_gem.c
> >> @@ -1729,15 +1731,20 @@ i915_gem_purge(struct drm_i915_private *dev_priv, long target)
> >> return __i915_gem_shrink(dev_priv, target, true);
> >> }
> >>
> >> -static void
> >> +static long
> >> i915_gem_shrink_all(struct drm_i915_private *dev_priv)
> >> {
> >> struct drm_i915_gem_object *obj, *next;
> >> + long freed = 0;
> >>
> >> - i915_gem_evict_everything(dev_priv->dev);
> >> + freed += i915_gem_evict_everything(dev_priv->dev);
> >>
> >> - list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list)
> >> + list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list) {
> >> + if (obj->pages_pin_count == 0)
> >> + freed += obj->base.size >> PAGE_SHIFT;
> >> i915_gem_object_put_pages(obj);
> >> + }
> >> + return freed;
> >> }
> >>
> >
> > i915_gem_shrink_all is a sledge hammer! That i915_gem_evict_everything
> > looks like it switches to every GPU context, waits for everything to
> > complete and then retire it all. I don't know the details of what it's
> > doing but it's sounds very heavy handed and is called from shrinker
> > context if it fails to shrink 128 objects. Those shrinker callsback can
> > be very frequently called even from kswapd.
>
> i915_gem_shrink_all is our escape hatch, we only use it as a
> last-ditch effort when all else fails. Imo there's no point in passing
> the number of freed objects around from it since it really never
> should get called (as long as we don't get called with more objects to
> shrink than our counter counted beforehand at least).
The shrinkers can be called quite frequently so I'm concerned that you do
get called with "more objects to shrink than our counter counted beforehand"
if it's called from direct reclaim and kswapd at the same time. kswapd
can be a very frequent caller via
kswapd
balance_pgdat
shrink_slab
i915_gem_inactive_shrink
i915_gem_shrink_all
That can be active just because there is a streaming reader of a video
file that is larger than physical memory. If there is enough additional
pressure then direct reclaimers and kswapd can both call the shrinker.
The mutex on its own is not enough for them both to read "500 objects"
and then both trying to free 500 objects each with the second stalling
in i915_gem_shrink_all.
Unfortunately the laptop I'm using does not have an i915 card to check
how easy this is to trigger but I suspect filling memory with dd,
starting a video of some sort and writing to a USB stick may be enough
to trigger it.
> >> @@ -4472,3 +4470,36 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
> >> mutex_unlock(&dev->struct_mutex);
> >> return cnt;
> >> }
> >> +static long
> >> +i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc)
> >> +{
> >> + struct drm_i915_private *dev_priv =
> >> + container_of(shrinker,
> >> + struct drm_i915_private,
> >> + mm.inactive_shrinker);
> >> + struct drm_device *dev = dev_priv->dev;
> >> + int nr_to_scan = sc->nr_to_scan;
> >> + long freed;
> >> + bool unlock = true;
> >> +
> >> + if (!mutex_trylock(&dev->struct_mutex)) {
> >> + if (!mutex_is_locked_by(&dev->struct_mutex, current))
> >> + return 0;
> >> +
> >
> > return -1 if it's about preventing potential deadlocks?
> >
In Glauber's series, shrinkers are split into count and scan callbacks.
If a scan returns -1, it indicates to vmscan.c that the slab could not
be shrunk at this time be it due to a deadlock risk or because the necessary
locks could not be acquired at this time.
> >> + if (dev_priv->mm.shrinker_no_lock_stealing)
> >> + return 0;
> >> +
> >
> > same?
>
> No idea. Aside, the aggressive shrinking with shrink_all and the lock
> stealing madness here are to paper our current "one lock for
> everything" approach we have for i915 gem stuff. We've papered over
> the worst offenders through lock-dropping tricks while waiting, the
> lock stealing above plus aggressively calling shrink_all.
>
> Still it's pretty trivial to (spuriously) OOM if you compete a gpu
> workload with something else. Real fix is per-object locking plus some
> watermark limits on how many pages are locked down this way, but
> that's long term (and currently stalling for the wait/wound mutexes
> from Maarten Lankhorst to get in).
>
Hmm, that's unfortunate. Later in Glauber's series, he also hooks up
the vm_pressure for in-kernel notification which is a better indication
of pressure than a slab shrinker. Conceivably that could be used to call
shrink_all if the system is about to go OOM. This would only be necessary
if it can be shown that the shrinker currently calls i915_gem_shrink_all
and stalls the world too easily.
> >
> >> + unlock = false;
> >> + }
> >> +
> >> + freed = i915_gem_purge(dev_priv, nr_to_scan);
> >> + if (freed < nr_to_scan)
> >> + freed += __i915_gem_shrink(dev_priv, nr_to_scan,
> >> + false);
> >> + if (freed < nr_to_scan)
> >> + freed += i915_gem_shrink_all(dev_priv);
> >> +
> >
> > Do we *really* want to call i915_gem_shrink_all from the slab shrinker?
> > Are there any bug reports where i915 rendering jitters in low memory
> > situations while shrinkers might be active? Maybe it's really fast.
>
> It's terrible for interactivity in X, but we need it :( See above for
> how we plan to eventually fix this mess.
>
Ok, thanks.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 18/31] shrinker: convert remaining shrinkers to count/scan API
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (16 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 17/31] drivers: convert shrinkers to new count/scan API Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 19/31] hugepage: convert huge zero page shrinker to new shrinker API Glauber Costa
` (13 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
From: Dave Chinner <dchinner@redhat.com>
Convert the remaining couple of random shrinkers in the tree to the
new API.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
arch/x86/kvm/mmu.c | 28 +++++++++++++++++++++-------
net/sunrpc/auth.c | 45 +++++++++++++++++++++++++++++++--------------
2 files changed, 52 insertions(+), 21 deletions(-)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 004cc87..19b4edf 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4212,13 +4212,14 @@ restart:
spin_unlock(&kvm->mmu_lock);
}
-static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
+static long
+mmu_shrink_scan(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
{
struct kvm *kvm;
int nr_to_scan = sc->nr_to_scan;
-
- if (nr_to_scan == 0)
- goto out;
+ long freed = 0;
raw_spin_lock(&kvm_lock);
@@ -4246,24 +4247,37 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
idx = srcu_read_lock(&kvm->srcu);
spin_lock(&kvm->mmu_lock);
- prepare_zap_oldest_mmu_page(kvm, &invalid_list);
+ freed += prepare_zap_oldest_mmu_page(kvm, &invalid_list);
kvm_mmu_commit_zap_page(kvm, &invalid_list);
spin_unlock(&kvm->mmu_lock);
srcu_read_unlock(&kvm->srcu, idx);
+ /*
+ * unfair on small ones
+ * per-vm shrinkers cry out
+ * sadness comes quickly
+ */
list_move_tail(&kvm->vm_list, &vm_list);
break;
}
raw_spin_unlock(&kvm_lock);
+ return freed;
-out:
+}
+
+static long
+mmu_shrink_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
return percpu_counter_read_positive(&kvm_total_used_mmu_pages);
}
static struct shrinker mmu_shrinker = {
- .shrink = mmu_shrink,
+ .count_objects = mmu_shrink_count,
+ .scan_objects = mmu_shrink_scan,
.seeks = DEFAULT_SEEKS * 10,
};
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index ed2fdd2..9ce0976 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -413,12 +413,13 @@ EXPORT_SYMBOL_GPL(rpcauth_destroy_credcache);
/*
* Remove stale credentials. Avoid sleeping inside the loop.
*/
-static int
+static long
rpcauth_prune_expired(struct list_head *free, int nr_to_scan)
{
spinlock_t *cache_lock;
struct rpc_cred *cred, *next;
unsigned long expired = jiffies - RPC_AUTH_EXPIRY_MORATORIUM;
+ long freed = 0;
list_for_each_entry_safe(cred, next, &cred_unused, cr_lru) {
@@ -430,10 +431,11 @@ rpcauth_prune_expired(struct list_head *free, int nr_to_scan)
*/
if (time_in_range(cred->cr_expire, expired, jiffies) &&
test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0)
- return 0;
+ break;
list_del_init(&cred->cr_lru);
number_cred_unused--;
+ freed++;
if (atomic_read(&cred->cr_count) != 0)
continue;
@@ -446,29 +448,43 @@ rpcauth_prune_expired(struct list_head *free, int nr_to_scan)
}
spin_unlock(cache_lock);
}
- return (number_cred_unused / 100) * sysctl_vfs_cache_pressure;
+ return freed;
}
/*
* Run memory cache shrinker.
*/
-static int
-rpcauth_cache_shrinker(struct shrinker *shrink, struct shrink_control *sc)
+static long
+rpcauth_cache_shrink_scan(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+
{
LIST_HEAD(free);
- int res;
- int nr_to_scan = sc->nr_to_scan;
- gfp_t gfp_mask = sc->gfp_mask;
+ long freed;
+
+ if ((sc->gfp_mask & GFP_KERNEL) != GFP_KERNEL)
+ return -1;
- if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL)
- return (nr_to_scan == 0) ? 0 : -1;
+ /* nothing left, don't come back */
if (list_empty(&cred_unused))
- return 0;
+ return -1;
+
spin_lock(&rpc_credcache_lock);
- res = rpcauth_prune_expired(&free, nr_to_scan);
+ freed = rpcauth_prune_expired(&free, sc->nr_to_scan);
spin_unlock(&rpc_credcache_lock);
rpcauth_destroy_credlist(&free);
- return res;
+
+ return freed;
+}
+
+static long
+rpcauth_cache_shrink_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+
+{
+ return (number_cred_unused / 100) * sysctl_vfs_cache_pressure;
}
/*
@@ -784,7 +800,8 @@ rpcauth_uptodatecred(struct rpc_task *task)
}
static struct shrinker rpc_cred_shrinker = {
- .shrink = rpcauth_cache_shrinker,
+ .count_objects = rpcauth_cache_shrink_count,
+ .scan_objects = rpcauth_cache_shrink_scan,
.seeks = DEFAULT_SEEKS,
};
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 19/31] hugepage: convert huge zero page shrinker to new shrinker API
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (17 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 18/31] shrinker: convert remaining shrinkers to " Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 20/31] shrinker: Kill old ->shrink API Glauber Costa
` (12 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Dave Chinner
It consists of:
* returning long instead of int
* separating count from scan
* returning the number of freed entities in scan
Signed-off-by: Glauber Costa <glommer@openvz.org>
Reviewed-by: Greg Thelen <gthelen@google.com>
CC: Dave Chinner <dchinner@redhat.com>
---
mm/huge_memory.c | 17 +++++++++++------
1 file changed, 11 insertions(+), 6 deletions(-)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4cb1684..ecfe285 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -211,24 +211,29 @@ static void put_huge_zero_page(void)
BUG_ON(atomic_dec_and_test(&huge_zero_refcount));
}
-static int shrink_huge_zero_page(struct shrinker *shrink,
- struct shrink_control *sc)
+static long shrink_huge_zero_page_count(struct shrinker *shrink,
+ struct shrink_control *sc)
{
- if (!sc->nr_to_scan)
- /* we can free zero page only if last reference remains */
- return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
+ /* we can free zero page only if last reference remains */
+ return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
+}
+static long shrink_huge_zero_page_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
struct page *zero_page = xchg(&huge_zero_page, NULL);
BUG_ON(zero_page == NULL);
__free_page(zero_page);
+ return HPAGE_PMD_NR;
}
return 0;
}
static struct shrinker huge_zero_page_shrinker = {
- .shrink = shrink_huge_zero_page,
+ .count_objects = shrink_huge_zero_page_count,
+ .scan_objects = shrink_huge_zero_page_scan,
.seeks = DEFAULT_SEEKS,
};
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 20/31] shrinker: Kill old ->shrink API.
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (18 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 19/31] hugepage: convert huge zero page shrinker to new shrinker API Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-30 21:57 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 21/31] vmscan: also shrink slab in memcg pressure Glauber Costa
` (11 subsequent siblings)
31 siblings, 1 reply; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner, Glauber Costa
From: Dave Chinner <dchinner@redhat.com>
There are no more users of this API, so kill it dead, dead, dead and
quietly bury the corpse in a shallow, unmarked grave in a dark
forest deep in the hills...
[ glommer: added flowers to the grave ]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
Reviewed-by: Greg Thelen <gthelen@google.com>
---
include/linux/shrinker.h | 15 +++++----------
include/trace/events/vmscan.h | 4 ++--
mm/vmscan.c | 40 ++++++++--------------------------------
3 files changed, 15 insertions(+), 44 deletions(-)
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index e71286f..d4636a0 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -7,14 +7,15 @@
*
* The 'gfpmask' refers to the allocation we are currently trying to
* fulfil.
- *
- * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is
- * querying the cache size, so a fastpath for that case is appropriate.
*/
struct shrink_control {
gfp_t gfp_mask;
- /* How many slab objects shrinker() should scan and try to reclaim */
+ /*
+ * How many objects scan_objects should scan and try to reclaim.
+ * This is reset before every call, so it is safe for callees
+ * to modify.
+ */
long nr_to_scan;
/* shrink from these nodes */
@@ -24,11 +25,6 @@ struct shrink_control {
/*
* A callback you can register to apply pressure to ageable caches.
*
- * @shrink() should look through the least-recently-used 'nr_to_scan' entries
- * and attempt to free them up. It should return the number of objects which
- * remain in the cache. If it returns -1, it means it cannot do any scanning at
- * this time (eg. there is a risk of deadlock).
- *
* @count_objects should return the number of freeable items in the cache. If
* there are no objects to free or the number of freeable items cannot be
* determined, it should return 0. No deadlock checks should be done during the
@@ -44,7 +40,6 @@ struct shrink_control {
* @scan_objects will be made from the current reclaim context.
*/
struct shrinker {
- int (*shrink)(struct shrinker *, struct shrink_control *sc);
long (*count_objects)(struct shrinker *, struct shrink_control *sc);
long (*scan_objects)(struct shrinker *, struct shrink_control *sc);
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 63cfccc..132a985 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -202,7 +202,7 @@ TRACE_EVENT(mm_shrink_slab_start,
TP_fast_assign(
__entry->shr = shr;
- __entry->shrink = shr->shrink;
+ __entry->shrink = shr->scan_objects;
__entry->nr_objects_to_shrink = nr_objects_to_shrink;
__entry->gfp_flags = sc->gfp_mask;
__entry->pgs_scanned = pgs_scanned;
@@ -241,7 +241,7 @@ TRACE_EVENT(mm_shrink_slab_end,
TP_fast_assign(
__entry->shr = shr;
- __entry->shrink = shr->shrink;
+ __entry->shrink = shr->scan_objects;
__entry->unused_scan = unused_scan_cnt;
__entry->new_scan = new_scan_cnt;
__entry->retval = shrinker_retval;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b11a9cc..5d0dfab 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -177,14 +177,6 @@ void unregister_shrinker(struct shrinker *shrinker)
}
EXPORT_SYMBOL(unregister_shrinker);
-static inline int do_shrinker_shrink(struct shrinker *shrinker,
- struct shrink_control *sc,
- unsigned long nr_to_scan)
-{
- sc->nr_to_scan = nr_to_scan;
- return (*shrinker->shrink)(shrinker, sc);
-}
-
#define SHRINK_BATCH 128
/*
* Call the shrink functions to age shrinkable caches
@@ -230,11 +222,8 @@ unsigned long shrink_slab(struct shrink_control *sc,
long batch_size = shrinker->batch ? shrinker->batch
: SHRINK_BATCH;
- if (shrinker->scan_objects) {
- max_pass = shrinker->count_objects(shrinker, sc);
- WARN_ON(max_pass < 0);
- } else
- max_pass = do_shrinker_shrink(shrinker, sc, 0);
+ max_pass = shrinker->count_objects(shrinker, sc);
+ WARN_ON(max_pass < 0);
if (max_pass <= 0)
continue;
@@ -253,7 +242,7 @@ unsigned long shrink_slab(struct shrink_control *sc,
if (total_scan < 0) {
printk(KERN_ERR
"shrink_slab: %pF negative objects to delete nr=%ld\n",
- shrinker->shrink, total_scan);
+ shrinker->scan_objects, total_scan);
total_scan = max_pass;
}
@@ -287,24 +276,11 @@ unsigned long shrink_slab(struct shrink_control *sc,
do {
long ret;
- if (shrinker->scan_objects) {
- sc->nr_to_scan = batch_size;
- ret = shrinker->scan_objects(shrinker, sc);
-
- if (ret == -1)
- break;
- freed += ret;
- } else {
- int nr_before;
-
- nr_before = do_shrinker_shrink(shrinker, sc, 0);
- ret = do_shrinker_shrink(shrinker, sc,
- batch_size);
- if (ret == -1)
- break;
- if (ret < nr_before)
- freed += nr_before - ret;
- }
+ sc->nr_to_scan = batch_size;
+ ret = shrinker->scan_objects(shrinker, sc);
+ if (ret == -1)
+ break;
+ freed += ret;
count_vm_events(SLABS_SCANNED, batch_size);
total_scan -= batch_size;
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 20/31] shrinker: Kill old ->shrink API.
2013-04-26 23:19 ` [PATCH v4 20/31] shrinker: Kill old ->shrink API Glauber Costa
@ 2013-04-30 21:57 ` Mel Gorman
0 siblings, 0 replies; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 21:57 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Dave Chinner
On Sat, Apr 27, 2013 at 03:19:16AM +0400, Glauber Costa wrote:
> From: Dave Chinner <dchinner@redhat.com>
>
> There are no more users of this API, so kill it dead, dead, dead and
> quietly bury the corpse in a shallow, unmarked grave in a dark
> forest deep in the hills...
>
> [ glommer: added flowers to the grave ]
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Signed-off-by: Glauber Costa <glommer@openvz.org>
> Reviewed-by: Greg Thelen <gthelen@google.com>
Acked-by: Mel Gorman <mgorman@suse.de>
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread
* [PATCH v4 21/31] vmscan: also shrink slab in memcg pressure
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (19 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 20/31] shrinker: Kill old ->shrink API Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 22/31] memcg,list_lru: duplicate LRUs upon kmemcg creation Glauber Costa
` (10 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Dave Chinner,
Mel Gorman, Rik van Riel, Hugh Dickins
Without the surrounding infrastructure, this patch is a bit of a hammer:
it will basically shrink objects from all memcgs under memcg pressure.
At least, however, we will keep the scan limited to the shrinkers marked
as per-memcg.
Future patches will implement the in-shrinker logic to filter objects
based on its memcg association.
Signed-off-by: Glauber Costa <glommer@openvz.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/memcontrol.h | 17 +++++++++++++++++
include/linux/shrinker.h | 4 ++++
mm/memcontrol.c | 16 +++++++++++++++-
mm/vmscan.c | 46 +++++++++++++++++++++++++++++++++++++++++++---
4 files changed, 79 insertions(+), 4 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d6183f0..4c24249 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -199,6 +199,9 @@ void mem_cgroup_split_huge_fixup(struct page *head);
bool mem_cgroup_bad_page_check(struct page *page);
void mem_cgroup_print_bad_page(struct page *page);
#endif
+
+unsigned long
+memcg_zone_reclaimable_pages(struct mem_cgroup *memcg, struct zone *zone);
#else /* CONFIG_MEMCG */
struct mem_cgroup;
@@ -377,6 +380,12 @@ static inline void mem_cgroup_replace_page_cache(struct page *oldpage,
struct page *newpage)
{
}
+
+static inline unsigned long
+memcg_zone_reclaimable_pages(struct mem_cgroup *memcg, struct zone *zone)
+{
+ return 0;
+}
#endif /* CONFIG_MEMCG */
#if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM)
@@ -429,6 +438,8 @@ static inline bool memcg_kmem_enabled(void)
return static_key_false(&memcg_kmem_enabled_key);
}
+bool memcg_kmem_is_active(struct mem_cgroup *memcg);
+
/*
* In general, we'll do everything in our power to not incur in any overhead
* for non-memcg users for the kmem functions. Not even a function call, if we
@@ -562,6 +573,12 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
return __memcg_kmem_get_cache(cachep, gfp);
}
#else
+
+static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+{
+ return false;
+}
+
#define for_each_memcg_cache_index(_idx) \
for (; NULL; )
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index d4636a0..4e9e53b 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -20,6 +20,9 @@ struct shrink_control {
/* shrink from these nodes */
nodemask_t nodes_to_scan;
+
+ /* reclaim from this memcg only (if not NULL) */
+ struct mem_cgroup *target_mem_cgroup;
};
/*
@@ -45,6 +48,7 @@ struct shrinker {
int seeks; /* seeks to recreate an obj */
long batch; /* reclaim batch size, 0 = default */
+ bool memcg_shrinker; /* memcg-aware shrinker */
/* These are for internal use */
struct list_head list;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a8a69b4..ef420e1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -397,7 +397,7 @@ static inline void memcg_kmem_set_active(struct mem_cgroup *memcg)
set_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
}
-static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+bool memcg_kmem_is_active(struct mem_cgroup *memcg)
{
return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
}
@@ -971,6 +971,20 @@ mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid,
return ret;
}
+unsigned long
+memcg_zone_reclaimable_pages(struct mem_cgroup *memcg, struct zone *zone)
+{
+ int nid = zone_to_nid(zone);
+ int zid = zone_idx(zone);
+ unsigned long val;
+
+ val = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid, LRU_ALL_FILE);
+ if (do_swap_account)
+ val += mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
+ LRU_ALL_ANON);
+ return val;
+}
+
static unsigned long
mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
int nid, unsigned int lru_mask)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5d0dfab..0319dd2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -139,11 +139,42 @@ static bool global_reclaim(struct scan_control *sc)
{
return !sc->target_mem_cgroup;
}
+
+/*
+ * kmem reclaim should usually not be triggered when we are doing targetted
+ * reclaim. It is only valid when global reclaim is triggered, or when the
+ * underlying memcg has kmem objects.
+ */
+static bool has_kmem_reclaim(struct scan_control *sc)
+{
+ return !sc->target_mem_cgroup ||
+ memcg_kmem_is_active(sc->target_mem_cgroup);
+}
+
+static unsigned long
+zone_nr_reclaimable_pages(struct scan_control *sc, struct zone *zone)
+{
+ if (global_reclaim(sc))
+ return zone_reclaimable_pages(zone);
+ return memcg_zone_reclaimable_pages(sc->target_mem_cgroup, zone);
+}
+
#else
static bool global_reclaim(struct scan_control *sc)
{
return true;
}
+
+static bool has_kmem_reclaim(struct scan_control *sc)
+{
+ return true;
+}
+
+static unsigned long
+zone_nr_reclaimable_pages(struct scan_control *sc, struct zone *zone)
+{
+ return zone_reclaimable_pages(zone);
+}
#endif
static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
@@ -222,6 +253,14 @@ unsigned long shrink_slab(struct shrink_control *sc,
long batch_size = shrinker->batch ? shrinker->batch
: SHRINK_BATCH;
+ /*
+ * If we don't have a target mem cgroup, we scan them all.
+ * Otherwise we will limit our scan to shrinkers marked as
+ * memcg aware
+ */
+ if (sc->target_mem_cgroup && !shrinker->memcg_shrinker)
+ continue;
+
max_pass = shrinker->count_objects(shrinker, sc);
WARN_ON(max_pass < 0);
if (max_pass <= 0)
@@ -2171,9 +2210,9 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
/*
* Don't shrink slabs when reclaiming memory from
- * over limit cgroups
+ * over limit cgroups, unless we know they have kmem objects
*/
- if (global_reclaim(sc)) {
+ if (has_kmem_reclaim(sc)) {
unsigned long lru_pages = 0;
nodes_clear(shrink->nodes_to_scan);
@@ -2182,7 +2221,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- lru_pages += zone_reclaimable_pages(zone);
+ lru_pages += zone_nr_reclaimable_pages(sc, zone);
node_set(zone_to_nid(zone),
shrink->nodes_to_scan);
}
@@ -2451,6 +2490,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
};
struct shrink_control shrink = {
.gfp_mask = sc.gfp_mask,
+ .target_mem_cgroup = memcg,
};
/*
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 22/31] memcg,list_lru: duplicate LRUs upon kmemcg creation
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (20 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 21/31] vmscan: also shrink slab in memcg pressure Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 23/31] lru: add an element to a memcg list Glauber Costa
` (9 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Dave Chinner,
Mel Gorman, Rik van Riel, Hugh Dickins
When a new memcg is created, we need to open up room for its descriptors
in all of the list_lrus that are marked per-memcg. The process is quite
similar to the one we are using for the kmem caches: we initialize the
new structures in an array indexed by kmemcg_id, and grow the array if
needed. Key data like the size of the array will be shared between the
kmem cache code and the list_lru code (they basically describe the same
thing)
Signed-off-by: Glauber Costa <glommer@openvz.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/list_lru.h | 48 +++++++++++++-
include/linux/memcontrol.h | 12 ++++
lib/list_lru.c | 102 +++++++++++++++++++++++++++---
mm/memcontrol.c | 151 +++++++++++++++++++++++++++++++++++++++++++--
mm/slab_common.c | 1 -
5 files changed, 297 insertions(+), 17 deletions(-)
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 5ed2b94..50dc00b 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -24,12 +24,58 @@ struct list_lru_node {
long nr_items;
} ____cacheline_aligned_in_smp;
+/*
+ * This is supposed to be M x N matrix, where M is kmem-limited memcg, and N is
+ * the number of nodes. Both dimensions are likely to be very small, but are
+ * potentially very big. Therefore we will allocate or grow them dynamically.
+ *
+ * The size of M will increase as new memcgs appear and can be 0 if no memcgs
+ * are being used. This is done in mm/memcontrol.c in a way quite similar than
+ * the way we use for the slab cache management.
+ *
+ * The size o N can't be determined at compile time, but won't increase once we
+ * determine it. It is nr_node_ids, the firmware-provided maximum number of
+ * nodes in a system.
+ */
+struct list_lru_array {
+ struct list_lru_node node[1];
+};
+
struct list_lru {
struct list_lru_node node[MAX_NUMNODES];
nodemask_t active_nodes;
+#ifdef CONFIG_MEMCG_KMEM
+ /* All memcg-aware LRUs will be chained in the lrus list */
+ struct list_head lrus;
+ /* M x N matrix as described above */
+ struct list_lru_array **memcg_lrus;
+#endif
};
-int list_lru_init(struct list_lru *lru);
+struct mem_cgroup;
+#ifdef CONFIG_MEMCG_KMEM
+struct list_lru_array *lru_alloc_array(void);
+int memcg_update_all_lrus(unsigned long num);
+void list_lru_destroy(struct list_lru *lru);
+void list_lru_destroy_memcg(struct mem_cgroup *memcg);
+int __memcg_init_lru(struct list_lru *lru);
+#else
+static inline void list_lru_destroy(struct list_lru *lru)
+{
+}
+#endif
+
+int __list_lru_init(struct list_lru *lru, bool memcg_enabled);
+static inline int list_lru_init(struct list_lru *lru)
+{
+ return __list_lru_init(lru, false);
+}
+
+static inline int list_lru_init_memcg(struct list_lru *lru)
+{
+ return __list_lru_init(lru, true);
+}
+
int list_lru_add(struct list_lru *lru, struct list_head *item);
int list_lru_del(struct list_lru *lru, struct list_head *item);
long list_lru_count_nodemask(struct list_lru *lru, nodemask_t *nodes_to_count);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 4c24249..ee3199d 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -23,6 +23,7 @@
#include <linux/vm_event_item.h>
#include <linux/hardirq.h>
#include <linux/jump_label.h>
+#include <linux/list_lru.h>
struct mem_cgroup;
struct page_cgroup;
@@ -469,6 +470,12 @@ void memcg_update_array_size(int num_groups);
struct kmem_cache *
__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
+int memcg_new_lru(struct list_lru *lru);
+int memcg_init_lru(struct list_lru *lru);
+
+int memcg_kmem_update_lru_size(struct list_lru *lru, int num_groups,
+ bool new_lru);
+
void mem_cgroup_destroy_cache(struct kmem_cache *cachep);
void kmem_cache_destroy_memcg_children(struct kmem_cache *s);
@@ -632,6 +639,11 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
static inline void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
{
}
+
+static inline int memcg_init_lru(struct list_lru *lru)
+{
+ return 0;
+}
#endif /* CONFIG_MEMCG_KMEM */
#endif /* _LINUX_MEMCONTROL_H */
diff --git a/lib/list_lru.c b/lib/list_lru.c
index 221e361..49b73ba 100644
--- a/lib/list_lru.c
+++ b/lib/list_lru.c
@@ -2,12 +2,17 @@
* Copyright (c) 2010-2012 Red Hat, Inc. All rights reserved.
* Author: David Chinner
*
+ * Memcg Awareness
+ * Copyright (C) 2013 Parallels Inc.
+ * Author: Glauber Costa
+ *
* Generic LRU infrastructure
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/list_lru.h>
+#include <linux/memcontrol.h>
int
list_lru_add(
@@ -185,18 +190,97 @@ list_lru_dispose_all(
return total;
}
-int
-list_lru_init(
- struct list_lru *lru)
+/*
+ * This protects the list of all LRU in the system. One only needs
+ * to take when registering an LRU, or when duplicating the list of lrus.
+ * Transversing an LRU can and should be done outside the lock
+ */
+static DEFINE_MUTEX(all_memcg_lrus_mutex);
+static LIST_HEAD(all_memcg_lrus);
+
+static void list_lru_init_one(struct list_lru_node *lru)
{
+ spin_lock_init(&lru->lock);
+ INIT_LIST_HEAD(&lru->list);
+ lru->nr_items = 0;
+}
+
+struct list_lru_array *lru_alloc_array(void)
+{
+ struct list_lru_array *lru_array;
int i;
- nodes_clear(lru->active_nodes);
- for (i = 0; i < MAX_NUMNODES; i++) {
- spin_lock_init(&lru->node[i].lock);
- INIT_LIST_HEAD(&lru->node[i].list);
- lru->node[i].nr_items = 0;
+ lru_array = kzalloc(nr_node_ids * sizeof(struct list_lru_node),
+ GFP_KERNEL);
+ if (!lru_array)
+ return NULL;
+
+ for (i = 0; i < nr_node_ids; i++)
+ list_lru_init_one(&lru_array->node[i]);
+
+ return lru_array;
+}
+
+#ifdef CONFIG_MEMCG_KMEM
+int __memcg_init_lru(struct list_lru *lru)
+{
+ int ret;
+
+ INIT_LIST_HEAD(&lru->lrus);
+ mutex_lock(&all_memcg_lrus_mutex);
+ list_add(&lru->lrus, &all_memcg_lrus);
+ ret = memcg_new_lru(lru);
+ mutex_unlock(&all_memcg_lrus_mutex);
+ return ret;
+}
+
+int memcg_update_all_lrus(unsigned long num)
+{
+ int ret = 0;
+ struct list_lru *lru;
+
+ mutex_lock(&all_memcg_lrus_mutex);
+ list_for_each_entry(lru, &all_memcg_lrus, lrus) {
+ ret = memcg_kmem_update_lru_size(lru, num, false);
+ if (ret)
+ goto out;
+ }
+out:
+ mutex_unlock(&all_memcg_lrus_mutex);
+ return ret;
+}
+
+void list_lru_destroy(struct list_lru *lru)
+{
+ mutex_lock(&all_memcg_lrus_mutex);
+ list_del(&lru->lrus);
+ mutex_unlock(&all_memcg_lrus_mutex);
+}
+
+void list_lru_destroy_memcg(struct mem_cgroup *memcg)
+{
+ struct list_lru *lru;
+ mutex_lock(&all_memcg_lrus_mutex);
+ list_for_each_entry(lru, &all_memcg_lrus, lrus) {
+ kfree(lru->memcg_lrus[memcg_cache_id(memcg)]);
+ lru->memcg_lrus[memcg_cache_id(memcg)] = NULL;
+ /* everybody must beaware that this memcg is no longer valid */
+ wmb();
}
+ mutex_unlock(&all_memcg_lrus_mutex);
+}
+#endif
+
+int __list_lru_init(struct list_lru *lru, bool memcg_enabled)
+{
+ int i;
+
+ nodes_clear(lru->active_nodes);
+ for (i = 0; i < MAX_NUMNODES; i++)
+ list_lru_init_one(&lru->node[i]);
+
+ if (memcg_enabled)
+ return memcg_init_lru(lru);
return 0;
}
-EXPORT_SYMBOL_GPL(list_lru_init);
+EXPORT_SYMBOL_GPL(__list_lru_init);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ef420e1..8a9a898 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3089,16 +3089,30 @@ int memcg_update_cache_sizes(struct mem_cgroup *memcg)
memcg_kmem_set_activated(memcg);
ret = memcg_update_all_caches(num+1);
- if (ret) {
- ida_simple_remove(&kmem_limited_groups, num);
- memcg_kmem_clear_activated(memcg);
- return ret;
- }
+ if (ret)
+ goto out;
+
+ /*
+ * We should make sure that the array size is not updated until we are
+ * done; otherwise we have no easy way to know whether or not we should
+ * grow the array.
+ */
+ ret = memcg_update_all_lrus(num + 1);
+ if (ret)
+ goto out;
memcg->kmemcg_id = num;
+
+ memcg_update_array_size(num + 1);
+
INIT_LIST_HEAD(&memcg->memcg_slab_caches);
mutex_init(&memcg->slab_caches_mutex);
+
return 0;
+out:
+ ida_simple_remove(&kmem_limited_groups, num);
+ memcg_kmem_clear_activated(memcg);
+ return ret;
}
static size_t memcg_caches_array_size(int num_groups)
@@ -3182,6 +3196,129 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
return 0;
}
+/*
+ * memcg_kmem_update_lru_size - fill in kmemcg info into a list_lru
+ *
+ * @lru: the lru we are operating with
+ * @num_groups: how many kmem-limited cgroups we have
+ * @new_lru: true if this is a new_lru being created, false if this
+ * was triggered from the memcg side
+ *
+ * Returns 0 on success, and an error code otherwise.
+ *
+ * This function can be called either when a new kmem-limited memcg appears,
+ * or when a new list_lru is created. The work is roughly the same in two cases,
+ * but in the later we never have to expand the array size.
+ *
+ * This is always protected by the all_lrus_mutex from the list_lru side. But
+ * a race can still exists if a new memcg becomes kmem limited at the same time
+ * that we are registering a new memcg. Creation is protected by the
+ * memcg_mutex, so the creation of a new lru have to be protected by that as
+ * well.
+ *
+ * The lock ordering is that the memcg_mutex needs to be acquired before the
+ * lru-side mutex.
+ */
+int memcg_kmem_update_lru_size(struct list_lru *lru, int num_groups,
+ bool new_lru)
+{
+ struct list_lru_array **new_lru_array;
+ struct list_lru_array *lru_array;
+
+ lru_array = lru_alloc_array();
+ if (!lru_array)
+ return -ENOMEM;
+
+ /*
+ * When a new LRU is created, we still need to update all data for that
+ * LRU. The procedure for late LRUs and new memcgs are quite similar, we
+ * only need to make sure we get into the loop even if num_groups <
+ * memcg_limited_groups_array_size.
+ */
+ if ((num_groups > memcg_limited_groups_array_size) || new_lru) {
+ int i;
+ struct list_lru_array **old_array;
+ size_t size = memcg_caches_array_size(num_groups);
+ int num_memcgs = memcg_limited_groups_array_size;
+
+ new_lru_array = kzalloc(size * sizeof(void *), GFP_KERNEL);
+ if (!new_lru_array) {
+ kfree(lru_array);
+ return -ENOMEM;
+ }
+
+ for (i = 0; lru->memcg_lrus && (i < num_memcgs); i++) {
+ if (lru->memcg_lrus && lru->memcg_lrus[i])
+ continue;
+ new_lru_array[i] = lru->memcg_lrus[i];
+ }
+
+ old_array = lru->memcg_lrus;
+ lru->memcg_lrus = new_lru_array;
+ /*
+ * We don't need a barrier here because we are just copying
+ * information over. Anybody operating in memcg_lrus will
+ * either follow the new array or the old one and they contain
+ * exactly the same information. The new space in the end is
+ * always empty anyway.
+ */
+ if (lru->memcg_lrus)
+ kfree(old_array);
+ }
+
+ if (lru->memcg_lrus) {
+ lru->memcg_lrus[num_groups - 1] = lru_array;
+ /*
+ * Here we do need the barrier, because of the state transition
+ * implied by the assignment of the array. All users should be
+ * able to see it
+ */
+ wmb();
+ }
+ return 0;
+}
+
+/*
+ * This is called with the LRU-mutex being held.
+ */
+int memcg_new_lru(struct list_lru *lru)
+{
+ struct mem_cgroup *iter;
+
+ if (!memcg_kmem_enabled())
+ return 0;
+
+ for_each_mem_cgroup(iter) {
+ int ret;
+ int memcg_id = memcg_cache_id(iter);
+ if (memcg_id < 0)
+ continue;
+
+ ret = memcg_kmem_update_lru_size(lru, memcg_id + 1, true);
+ if (ret) {
+ mem_cgroup_iter_break(root_mem_cgroup, iter);
+ return ret;
+ }
+ }
+ return 0;
+}
+
+/*
+ * We need to call back and forth from memcg to LRU because of the lock
+ * ordering. This complicates the flow a little bit, but since the memcg mutex
+ * is held through the whole duration of memcg creation, we need to hold it
+ * before we hold the LRU-side mutex in the case of a new list creation as
+ * well.
+ */
+int memcg_init_lru(struct list_lru *lru)
+{
+ int ret;
+ mutex_lock(&memcg_create_mutex);
+ ret = __memcg_init_lru(lru);
+ mutex_unlock(&memcg_create_mutex);
+ return ret;
+}
+
int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
struct kmem_cache *root_cache)
{
@@ -5868,8 +6005,10 @@ static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
* possible that the charges went down to 0 between mark_dead and the
* res_counter read, so in that case, we don't need the put
*/
- if (memcg_kmem_test_and_clear_dead(memcg))
+ if (memcg_kmem_test_and_clear_dead(memcg)) {
+ list_lru_destroy_memcg(memcg);
mem_cgroup_put(memcg);
+ }
}
#else
static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 2f0e7d5..ce81621 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -102,7 +102,6 @@ int memcg_update_all_caches(int num_memcgs)
goto out;
}
- memcg_update_array_size(num_memcgs);
out:
mutex_unlock(&slab_mutex);
return ret;
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 23/31] lru: add an element to a memcg list
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (21 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 22/31] memcg,list_lru: duplicate LRUs upon kmemcg creation Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 24/31] list_lru: per-memcg walks Glauber Costa
` (8 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Dave Chinner,
Mel Gorman, Rik van Riel, Hugh Dickins
With the infrastructure we now have, we can add an element to a memcg
LRU list instead of the global list. The memcg lists are still
per-node.
Technically, we will never trigger per-node shrinking in the memcg is
short of memory. Therefore an alternative to this would be to add the
element to *both* a single-node memcg array and a per-node global array.
There are two main reasons for this design choice:
1) adding an extra list_head to each of the objects would waste 16-bytes
per object, always remembering that we are talking about 1 dentry + 1
inode in the common case. This means a close to 10 % increase in the
dentry size, and a lower yet significant increase in the inode size. In
terms of total memory, this design pays 32-byte per-superblock-per-node
(size of struct list_lru_node), which means that in any scenario where
we have more than 10 dentries + inodes, we would already be paying more
memory in the two-list-heads approach than we will here with 1 node x 10
superblocks. The turning point of course depends on the workload, but I
hope the figures above would convince you that the memory footprint is
in my side in any workload that matters.
2) The main drawback of this, namely, that we loose global LRU order, is
not really seen by me as a disadvantage: if we are using memcg to
isolate the workloads, global pressure should try to balance the amount
reclaimed from all memcgs the same way the shrinkers will already
naturally balance the amount reclaimed from each superblock. (This
patchset needs some love in this regard, btw).
To help us easily tracking down which nodes have and which nodes doesn't
have elements in the list, we will count on an auxiliary node bitmap in
the global level.
[ v2: move memcg_kmem_lru_of_page to list_lru.c and then unpublish the
auxiliary functions it uses ]
Signed-off-by: Glauber Costa <glommer@openvz.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/list_lru.h | 11 +++++
include/linux/memcontrol.h | 8 ++++
lib/list_lru.c | 104 +++++++++++++++++++++++++++++++++++++++++----
mm/memcontrol.c | 24 ++++++++++-
4 files changed, 137 insertions(+), 10 deletions(-)
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 50dc00b..753f0bc 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -43,12 +43,23 @@ struct list_lru_array {
struct list_lru {
struct list_lru_node node[MAX_NUMNODES];
+ atomic_long_t node_totals[MAX_NUMNODES];
nodemask_t active_nodes;
#ifdef CONFIG_MEMCG_KMEM
/* All memcg-aware LRUs will be chained in the lrus list */
struct list_head lrus;
/* M x N matrix as described above */
struct list_lru_array **memcg_lrus;
+ /*
+ * The memcg_lrus is RCU protected, so we need to keep the previous
+ * array around when we update it. But we can only do that after
+ * synchronize_rcu(). A typical system has many LRUs, which means
+ * that if we call synchronize_rcu after each LRU update, this
+ * will become very expensive. We add this pointer here, and then
+ * after all LRUs are update, we call synchronize_rcu() once, and
+ * free all the old_arrays.
+ */
+ void *old_array;
#endif
};
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ee3199d..1e74610 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -24,6 +24,7 @@
#include <linux/hardirq.h>
#include <linux/jump_label.h>
#include <linux/list_lru.h>
+#include <linux/mm.h>
struct mem_cgroup;
struct page_cgroup;
@@ -473,6 +474,8 @@ __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
int memcg_new_lru(struct list_lru *lru);
int memcg_init_lru(struct list_lru *lru);
+struct mem_cgroup *mem_cgroup_from_kmem_page(struct page *page);
+
int memcg_kmem_update_lru_size(struct list_lru *lru, int num_groups,
bool new_lru);
@@ -644,6 +647,11 @@ static inline int memcg_init_lru(struct list_lru *lru)
{
return 0;
}
+
+static inline struct mem_cgroup *mem_cgroup_from_kmem_page(struct page *page)
+{
+ return NULL;
+}
#endif /* CONFIG_MEMCG_KMEM */
#endif /* _LINUX_MEMCONTROL_H */
diff --git a/lib/list_lru.c b/lib/list_lru.c
index 49b73ba..01f843f 100644
--- a/lib/list_lru.c
+++ b/lib/list_lru.c
@@ -14,19 +14,85 @@
#include <linux/list_lru.h>
#include <linux/memcontrol.h>
+/*
+ * lru_node_of_index - returns the node-lru of a specific lru
+ * @lru: the global lru we are operating at
+ * @index: if positive, the memcg id. If negative, means global lru.
+ * @nid: node id of the corresponding node we want to manipulate
+ */
+struct list_lru_node *
+lru_node_of_index(struct list_lru *lru, int index, int nid)
+{
+#ifdef CONFIG_MEMCG_KMEM
+ struct list_lru_node *nlru;
+
+ if (index < 0)
+ return &lru->node[nid];
+
+ if (!lru->memcg_lrus)
+ return NULL;
+
+ /*
+ * because we will only ever free the memcg_lrus after synchronize_rcu,
+ * we are safe with the rcu lock here: even if we are operating in the
+ * stale version of the array, the data is still valid and we are not
+ * risking anything.
+ *
+ * The read barrier is needed to make sure that we see the pointer
+ * assigment for the specific memcg
+ */
+ rcu_read_lock();
+ rmb();
+ /* The array exist, but the particular memcg does not */
+ if (!lru->memcg_lrus[index]) {
+ nlru = NULL;
+ goto out;
+ }
+ nlru = &lru->memcg_lrus[index]->node[nid];
+out:
+ rcu_read_unlock();
+ return nlru;
+#else
+ BUG_ON(index >= 0); /* nobody should be passing index < 0 with !KMEM */
+ return &lru->node[nid];
+#endif
+}
+
+struct list_lru_node *
+memcg_kmem_lru_of_page(struct list_lru *lru, struct page *page)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_kmem_page(page);
+ int nid = page_to_nid(page);
+ int memcg_id;
+
+ if (!memcg || !memcg_kmem_is_active(memcg))
+ return &lru->node[nid];
+
+ memcg_id = memcg_cache_id(memcg);
+ return lru_node_of_index(lru, memcg_id, nid);
+}
+
int
list_lru_add(
struct list_lru *lru,
struct list_head *item)
{
- int nid = page_to_nid(virt_to_page(item));
- struct list_lru_node *nlru = &lru->node[nid];
+ struct page *page = virt_to_page(item);
+ struct list_lru_node *nlru;
+ int nid = page_to_nid(page);
+
+ nlru = memcg_kmem_lru_of_page(lru, page);
spin_lock(&nlru->lock);
BUG_ON(nlru->nr_items < 0);
if (list_empty(item)) {
list_add_tail(item, &nlru->list);
- if (nlru->nr_items++ == 0)
+ nlru->nr_items++;
+ /*
+ * We only consider a node active or inactive based on the
+ * total figure for all involved children.
+ */
+ if (atomic_long_add_return(1, &lru->node_totals[nid]) == 1)
node_set(nid, lru->active_nodes);
spin_unlock(&nlru->lock);
return 1;
@@ -41,14 +107,20 @@ list_lru_del(
struct list_lru *lru,
struct list_head *item)
{
- int nid = page_to_nid(virt_to_page(item));
- struct list_lru_node *nlru = &lru->node[nid];
+ struct page *page = virt_to_page(item);
+ struct list_lru_node *nlru;
+ int nid = page_to_nid(page);
+
+ nlru = memcg_kmem_lru_of_page(lru, page);
spin_lock(&nlru->lock);
if (!list_empty(item)) {
list_del_init(item);
- if (--nlru->nr_items == 0)
+ nlru->nr_items--;
+
+ if (atomic_long_dec_and_test(&lru->node_totals[nid]))
node_clear(nid, lru->active_nodes);
+
BUG_ON(nlru->nr_items < 0);
spin_unlock(&nlru->lock);
return 1;
@@ -102,9 +174,10 @@ restart:
ret = isolate(item, &nlru->lock, cb_arg);
switch (ret) {
case LRU_REMOVED:
- if (--nlru->nr_items == 0)
- node_clear(nid, lru->active_nodes);
+ nlru->nr_items--;
BUG_ON(nlru->nr_items < 0);
+ if (atomic_long_dec_and_test(&lru->node_totals[nid]))
+ node_clear(nid, lru->active_nodes);
isolated++;
break;
case LRU_ROTATE:
@@ -246,6 +319,17 @@ int memcg_update_all_lrus(unsigned long num)
goto out;
}
out:
+ /*
+ * Even if we were to use call_rcu, we still have to keep the old array
+ * pointer somewhere. It is easier for us to just synchronize rcu here
+ * since we are in a fine context. Now we guarantee that there are no
+ * more users of old_array, and proceed freeing it for all LRUs
+ */
+ synchronize_rcu();
+ list_for_each_entry(lru, &all_memcg_lrus, lrus) {
+ kfree(lru->old_array);
+ lru->old_array = NULL;
+ }
mutex_unlock(&all_memcg_lrus_mutex);
return ret;
}
@@ -276,8 +360,10 @@ int __list_lru_init(struct list_lru *lru, bool memcg_enabled)
int i;
nodes_clear(lru->active_nodes);
- for (i = 0; i < MAX_NUMNODES; i++)
+ for (i = 0; i < MAX_NUMNODES; i++) {
list_lru_init_one(&lru->node[i]);
+ atomic_long_set(&lru->node_totals[i], 0);
+ }
if (memcg_enabled)
return memcg_init_lru(lru);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8a9a898..21e0ace 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3261,9 +3261,15 @@ int memcg_kmem_update_lru_size(struct list_lru *lru, int num_groups,
* either follow the new array or the old one and they contain
* exactly the same information. The new space in the end is
* always empty anyway.
+ *
+ * We do have to make sure that no more users of the old
+ * memcg_lrus array exist before we free, and this is achieved
+ * by rcu. Since it would be too slow to synchronize RCU for
+ * every LRU, we store the pointer and let the LRU code free
+ * all of them when all LRUs are updated.
*/
if (lru->memcg_lrus)
- kfree(old_array);
+ lru->old_array = old_array;
}
if (lru->memcg_lrus) {
@@ -3407,6 +3413,22 @@ static inline void memcg_resume_kmem_account(void)
current->memcg_kmem_skip_account--;
}
+struct mem_cgroup *mem_cgroup_from_kmem_page(struct page *page)
+{
+ struct page_cgroup *pc;
+ struct mem_cgroup *memcg = NULL;
+
+ pc = lookup_page_cgroup(page);
+ if (!PageCgroupUsed(pc))
+ return NULL;
+
+ lock_page_cgroup(pc);
+ if (PageCgroupUsed(pc))
+ memcg = pc->mem_cgroup;
+ unlock_page_cgroup(pc);
+ return memcg;
+}
+
static void kmem_cache_destroy_work_func(struct work_struct *w)
{
struct kmem_cache *cachep;
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 24/31] list_lru: per-memcg walks
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (22 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 23/31] lru: add an element to a memcg list Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 25/31] memcg: per-memcg kmem shrinking Glauber Costa
` (7 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Dave Chinner,
Mel Gorman, Rik van Riel, Hugh Dickins
This patch extend the list_lru interfaces to allow for a memcg
parameter. Because most of its users won't need it, instead of
modifying the function signatures we create a new set of _memcg()
functions and write the old API ontop of that.
Signed-off-by: Glauber Costa <glommer@openvz.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/list_lru.h | 25 ++++++++---
include/linux/memcontrol.h | 2 +
lib/list_lru.c | 102 +++++++++++++++++++++++++++++++++++----------
3 files changed, 102 insertions(+), 27 deletions(-)
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 753f0bc..c70f518 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -89,21 +89,36 @@ static inline int list_lru_init_memcg(struct list_lru *lru)
int list_lru_add(struct list_lru *lru, struct list_head *item);
int list_lru_del(struct list_lru *lru, struct list_head *item);
-long list_lru_count_nodemask(struct list_lru *lru, nodemask_t *nodes_to_count);
+
+long list_lru_count_nodemask_memcg(struct list_lru *lru,
+ nodemask_t *nodes_to_count, struct mem_cgroup *memcg);
+
+static inline long
+list_lru_count_nodemask(struct list_lru *lru, nodemask_t *nodes_to_count)
+{
+ return list_lru_count_nodemask_memcg(lru, nodes_to_count, NULL);
+}
static inline long list_lru_count(struct list_lru *lru)
{
return list_lru_count_nodemask(lru, &lru->active_nodes);
}
-
typedef enum lru_status
(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
-
typedef void (*list_lru_dispose_cb)(struct list_head *dispose_list);
-long list_lru_walk_nodemask(struct list_lru *lru, list_lru_walk_cb isolate,
- void *cb_arg, long nr_to_walk, nodemask_t *nodes_to_walk);
+long list_lru_walk_nodemask_memcg(struct list_lru *lru,
+ list_lru_walk_cb isolate, void *cb_arg, long nr_to_walk,
+ nodemask_t *nodes_to_walk, struct mem_cgroup *memcg);
+
+static inline long list_lru_walk_nodemask(struct list_lru *lru,
+ list_lru_walk_cb isolate, void *cb_arg, long nr_to_walk,
+ nodemask_t *nodes_to_walk)
+{
+ return list_lru_walk_nodemask_memcg(lru, isolate, cb_arg, nr_to_walk,
+ &lru->active_nodes, NULL);
+}
static inline long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
void *cb_arg, long nr_to_walk)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1e74610..6dc1d7a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -592,6 +592,8 @@ static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
#define for_each_memcg_cache_index(_idx) \
for (; NULL; )
+#define memcg_limited_groups_array_size 0
+
static inline bool memcg_kmem_enabled(void)
{
return false;
diff --git a/lib/list_lru.c b/lib/list_lru.c
index 01f843f..85d7b7f 100644
--- a/lib/list_lru.c
+++ b/lib/list_lru.c
@@ -72,6 +72,23 @@ memcg_kmem_lru_of_page(struct list_lru *lru, struct page *page)
return lru_node_of_index(lru, memcg_id, nid);
}
+/*
+ * This helper will loop through all node-data in the LRU, either global or
+ * per-memcg. If memcg is either not present or not used,
+ * memcg_limited_groups_array_size will be 0. _idx starts at -1, and it will
+ * still be allowed to execute once.
+ *
+ * We convention that for _idx = -1, the global node info should be used.
+ * After that, we will go through each of the memcgs, starting at 0.
+ *
+ * We don't need any kind of locking for the loop because
+ * memcg_limited_groups_array_size can only grow, gaining new fields at the
+ * end. The old ones are just copied, and any interesting manipulation happen
+ * in the node list itself, and we already lock the list.
+ */
+#define for_each_memcg_lru_index(_idx) \
+ for ((_idx) = -1; ((_idx) < memcg_limited_groups_array_size); (_idx)++)
+
int
list_lru_add(
struct list_lru *lru,
@@ -131,15 +148,29 @@ list_lru_del(
EXPORT_SYMBOL_GPL(list_lru_del);
long
-list_lru_count_nodemask(
+list_lru_count_nodemask_memcg(
struct list_lru *lru,
- nodemask_t *nodes_to_count)
+ nodemask_t *nodes_to_count,
+ struct mem_cgroup *memcg)
{
long count = 0;
int nid;
+ nodemask_t nodes;
+ int memcg_id = -1;
- for_each_node_mask(nid, *nodes_to_count) {
- struct list_lru_node *nlru = &lru->node[nid];
+ if (memcg && memcg_kmem_is_active(memcg))
+ memcg_id = memcg_cache_id(memcg);
+ /*
+ * Conservative code can call this setting nodes with node_setall.
+ * This will generate an out of bound access for memcg.
+ */
+ nodes_and(nodes, *nodes_to_count, node_online_map);
+
+ for_each_node_mask(nid, nodes) {
+ struct list_lru_node *nlru;
+ nlru = lru_node_of_index(lru, memcg_id, nid);
+ if (!nlru)
+ continue;
spin_lock(&nlru->lock);
BUG_ON(nlru->nr_items < 0);
@@ -149,17 +180,17 @@ list_lru_count_nodemask(
return count;
}
-EXPORT_SYMBOL_GPL(list_lru_count_nodemask);
+EXPORT_SYMBOL_GPL(list_lru_count_nodemask_memcg);
static long
list_lru_walk_node(
struct list_lru *lru,
+ struct list_lru_node *nlru,
int nid,
list_lru_walk_cb isolate,
void *cb_arg,
long *nr_to_walk)
{
- struct list_lru_node *nlru = &lru->node[nid];
struct list_head *item, *n;
long isolated = 0;
@@ -196,25 +227,41 @@ restart:
}
long
-list_lru_walk_nodemask(
+list_lru_walk_nodemask_memcg(
struct list_lru *lru,
list_lru_walk_cb isolate,
void *cb_arg,
long nr_to_walk,
- nodemask_t *nodes_to_walk)
+ nodemask_t *nodes_to_walk,
+ struct mem_cgroup *memcg)
{
long isolated = 0;
int nid;
+ nodemask_t nodes;
+ int memcg_id = -1;
+ struct list_lru_node *nlru;
+
+ if (memcg && memcg_kmem_is_active(memcg))
+ memcg_id = memcg_cache_id(memcg);
+ /*
+ * Conservative code can call this setting nodes with node_setall.
+ * This will generate an out of bound access for memcg.
+ */
+ nodes_and(nodes, *nodes_to_walk, node_online_map);
+
+ for_each_node_mask(nid, nodes) {
+ nlru = lru_node_of_index(lru, memcg_id, nid);
+ if (!nlru)
+ continue;
- for_each_node_mask(nid, *nodes_to_walk) {
- isolated += list_lru_walk_node(lru, nid, isolate,
+ isolated += list_lru_walk_node(lru, nlru, nid, isolate,
cb_arg, &nr_to_walk);
if (nr_to_walk <= 0)
break;
}
return isolated;
}
-EXPORT_SYMBOL_GPL(list_lru_walk_nodemask);
+EXPORT_SYMBOL_GPL(list_lru_walk_nodemask_memcg);
static long
list_lru_dispose_all_node(
@@ -222,23 +269,34 @@ list_lru_dispose_all_node(
int nid,
list_lru_dispose_cb dispose)
{
- struct list_lru_node *nlru = &lru->node[nid];
+ struct list_lru_node *nlru;
LIST_HEAD(dispose_list);
long disposed = 0;
+ int idx;
- spin_lock(&nlru->lock);
- while (!list_empty(&nlru->list)) {
- list_splice_init(&nlru->list, &dispose_list);
- disposed += nlru->nr_items;
- nlru->nr_items = 0;
- node_clear(nid, lru->active_nodes);
- spin_unlock(&nlru->lock);
-
- dispose(&dispose_list);
+ for_each_memcg_lru_index(idx) {
+ nlru = lru_node_of_index(lru, idx, nid);
+ if (!nlru)
+ continue;
spin_lock(&nlru->lock);
+ while (!list_empty(&nlru->list)) {
+ list_splice_init(&nlru->list, &dispose_list);
+
+ if (atomic_long_sub_and_test(nlru->nr_items,
+ &lru->node_totals[nid]))
+ node_clear(nid, lru->active_nodes);
+ disposed += nlru->nr_items;
+ nlru->nr_items = 0;
+ spin_unlock(&nlru->lock);
+
+ dispose(&dispose_list);
+
+ spin_lock(&nlru->lock);
+ }
+ spin_unlock(&nlru->lock);
}
- spin_unlock(&nlru->lock);
+
return disposed;
}
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 25/31] memcg: per-memcg kmem shrinking
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (23 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 24/31] list_lru: per-memcg walks Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 26/31] memcg: scan cache objects hierarchically Glauber Costa
` (6 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Dave Chinner,
Mel Gorman, Rik van Riel, Hugh Dickins
If the kernel limit is smaller than the user limit, we will have
situations in which our allocations fail but freeing user pages will buy
us nothing. In those, we would like to call a specialized memcg
reclaimer that only frees kernel memory and leave the user memory alone.
Those are also expected to fail when we account memcg->kmem, instead of
when we account memcg->res. Based on that, this patch implements a
memcg-specific reclaimer, that only shrinks kernel objects, withouth
touching user pages.
There might be situations in which there are plenty of objects to
shrink, but we can't do it because the __GFP_FS flag is not set.
Although they can happen with user pages, they are a lot more common
with fs-metadata: this is the case with almost all inode allocation.
Those allocations are, however, capable of waiting. So we can just span
a worker, let it finish its job and proceed with the allocation. As slow
as it is, at this point we are already past any hopes anyway.
[ v2: moved congestion_wait call to vmscan.c ]
Signed-off-by: Glauber Costa <glommer@openvz.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/swap.h | 2 +
mm/memcontrol.c | 180 ++++++++++++++++++++++++++++++++++++++++-----------
mm/vmscan.c | 44 ++++++++++++-
3 files changed, 187 insertions(+), 39 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index ca031f7..5a0ef45 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -268,6 +268,8 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
gfp_t gfp_mask, bool noswap);
+extern unsigned long try_to_free_mem_cgroup_kmem(struct mem_cgroup *mem,
+ gfp_t gfp_mask);
extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
gfp_t gfp_mask, bool noswap,
struct zone *zone,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 21e0ace..39b9ffe 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -363,7 +363,8 @@ struct mem_cgroup {
atomic_t numainfo_events;
atomic_t numainfo_updating;
#endif
-
+ /* when kmem shrinkers can sleep but can't proceed due to context */
+ struct work_struct kmemcg_shrink_work;
/*
* Per cgroup active and inactive list, similar to the
* per zone LRU lists.
@@ -380,11 +381,14 @@ static size_t memcg_size(void)
nr_node_ids * sizeof(struct mem_cgroup_per_node);
}
+static DEFINE_MUTEX(set_limit_mutex);
+
/* internal only representation about the status of kmem accounting. */
enum {
KMEM_ACCOUNTED_ACTIVE = 0, /* accounted by this cgroup itself */
KMEM_ACCOUNTED_ACTIVATED, /* static key enabled. */
KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */
+ KMEM_MAY_SHRINK, /* kmem limit < mem limit, shrink kmem only */
};
/* We account when limit is on, but only after call sites are patched */
@@ -423,6 +427,31 @@ static bool memcg_kmem_test_and_clear_dead(struct mem_cgroup *memcg)
return test_and_clear_bit(KMEM_ACCOUNTED_DEAD,
&memcg->kmem_account_flags);
}
+
+/*
+ * If the kernel limit is smaller than the user limit, we will have situations
+ * in which our allocations fail but freeing user pages will buy us nothing.
+ * In those, we would like to call a specialized memcg reclaimer that only
+ * frees kernel memory and leave the user memory alone.
+ *
+ * This test exists so we can differentiate between those. Everytime one of the
+ * limits is updated, we need to run it. The set_limit_mutex must be held, so
+ * they don't change again.
+ */
+static void memcg_update_shrink_status(struct mem_cgroup *memcg)
+{
+ mutex_lock(&set_limit_mutex);
+ if (res_counter_read_u64(&memcg->kmem, RES_LIMIT) <
+ res_counter_read_u64(&memcg->res, RES_LIMIT))
+ set_bit(KMEM_MAY_SHRINK, &memcg->kmem_account_flags);
+ else
+ clear_bit(KMEM_MAY_SHRINK, &memcg->kmem_account_flags);
+ mutex_unlock(&set_limit_mutex);
+}
+#else
+static void memcg_update_shrink_status(struct mem_cgroup *memcg)
+{
+}
#endif
/* Stuffs for move charges at task migration. */
@@ -2939,8 +2968,6 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
memcg_check_events(memcg, page);
}
-static DEFINE_MUTEX(set_limit_mutex);
-
#ifdef CONFIG_MEMCG_KMEM
static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg)
{
@@ -2982,16 +3009,91 @@ static int mem_cgroup_slabinfo_read(struct cgroup *cont, struct cftype *cft,
}
#endif
+/*
+ * During the creation a new cache, we need to disable our accounting mechanism
+ * altogether. This is true even if we are not creating, but rather just
+ * enqueing new caches to be created.
+ *
+ * This is because that process will trigger allocations; some visible, like
+ * explicit kmallocs to auxiliary data structures, name strings and internal
+ * cache structures; some well concealed, like INIT_WORK() that can allocate
+ * objects during debug.
+ *
+ * If any allocation happens during memcg_kmem_get_cache, we will recurse back
+ * to it. This may not be a bounded recursion: since the first cache creation
+ * failed to complete (waiting on the allocation), we'll just try to create the
+ * cache again, failing at the same point.
+ *
+ * memcg_kmem_get_cache is prepared to abort after seeing a positive count of
+ * memcg_kmem_skip_account. So we enclose anything that might allocate memory
+ * inside the following two functions.
+ */
+static inline void memcg_stop_kmem_account(void)
+{
+ VM_BUG_ON(!current->mm);
+ current->memcg_kmem_skip_account++;
+}
+
+static inline void memcg_resume_kmem_account(void)
+{
+ VM_BUG_ON(!current->mm);
+ current->memcg_kmem_skip_account--;
+}
+
+static int memcg_try_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
+{
+ int retries = MEM_CGROUP_RECLAIM_RETRIES;
+ struct res_counter *fail_res;
+ int ret;
+
+ do {
+ ret = res_counter_charge(&memcg->kmem, size, &fail_res);
+ if (!ret)
+ return ret;
+
+ if (!(gfp & __GFP_WAIT))
+ return ret;
+
+ /*
+ * We will try to shrink kernel memory present in caches. We
+ * are sure that we can wait, so we will. The duration of our
+ * wait is determined by congestion, the same way as vmscan.c
+ *
+ * If we are in FS context, though, then although we can wait,
+ * we cannot call the shrinkers. Most fs shrinkers (which
+ * comprises most of our kmem data) will not run without
+ * __GFP_FS since they can deadlock. The solution is to
+ * synchronously run that in a different context.
+ */
+ if (!(gfp & __GFP_FS)) {
+ /*
+ * we are already short on memory, every queue
+ * allocation is likely to fail
+ */
+ memcg_stop_kmem_account();
+ schedule_work(&memcg->kmemcg_shrink_work);
+ flush_work(&memcg->kmemcg_shrink_work);
+ memcg_resume_kmem_account();
+ } else
+ try_to_free_mem_cgroup_kmem(memcg, gfp);
+ } while (retries--);
+
+ return ret;
+}
+
static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
{
struct res_counter *fail_res;
struct mem_cgroup *_memcg;
int ret = 0;
bool may_oom;
+ bool kmem_first = test_bit(KMEM_MAY_SHRINK, &memcg->kmem_account_flags);
- ret = res_counter_charge(&memcg->kmem, size, &fail_res);
- if (ret)
- return ret;
+ if (kmem_first) {
+ ret = memcg_try_charge_kmem(memcg, gfp, size);
+ if (ret)
+ return ret;
+ }
/*
* Conditions under which we can wait for the oom_killer. Those are
@@ -3024,12 +3126,41 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
res_counter_charge_nofail(&memcg->memsw, size,
&fail_res);
ret = 0;
- } else if (ret)
+ if (!kmem_first)
+ res_counter_charge_nofail(&memcg->kmem, size, &fail_res);
+ } else if (ret && kmem_first)
res_counter_uncharge(&memcg->kmem, size);
+ if (!kmem_first) {
+ ret = memcg_try_charge_kmem(memcg, gfp, size);
+ if (!ret)
+ return ret;
+
+ res_counter_uncharge(&memcg->res, size);
+ if (do_swap_account)
+ res_counter_uncharge(&memcg->memsw, size);
+ }
+
return ret;
}
+/*
+ * There might be situations in which there are plenty of objects to shrink,
+ * but we can't do it because the __GFP_FS flag is not set. This is the case
+ * with almost all inode allocation. They do are, however, capable of waiting.
+ * So we can just span a worker, let it finish its job and proceed with the
+ * allocation. As slow as it is, at this point we are already past any hopes
+ * anyway.
+ */
+static void kmemcg_shrink_work_fn(struct work_struct *w)
+{
+ struct mem_cgroup *memcg;
+
+ memcg = container_of(w, struct mem_cgroup, kmemcg_shrink_work);
+ try_to_free_mem_cgroup_kmem(memcg, GFP_KERNEL);
+}
+
+
static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size)
{
res_counter_uncharge(&memcg->res, size);
@@ -3106,6 +3237,7 @@ int memcg_update_cache_sizes(struct mem_cgroup *memcg)
memcg_update_array_size(num + 1);
INIT_LIST_HEAD(&memcg->memcg_slab_caches);
+ INIT_WORK(&memcg->kmemcg_shrink_work, kmemcg_shrink_work_fn);
mutex_init(&memcg->slab_caches_mutex);
return 0;
@@ -3382,37 +3514,6 @@ out:
kfree(s->memcg_params);
}
-/*
- * During the creation a new cache, we need to disable our accounting mechanism
- * altogether. This is true even if we are not creating, but rather just
- * enqueing new caches to be created.
- *
- * This is because that process will trigger allocations; some visible, like
- * explicit kmallocs to auxiliary data structures, name strings and internal
- * cache structures; some well concealed, like INIT_WORK() that can allocate
- * objects during debug.
- *
- * If any allocation happens during memcg_kmem_get_cache, we will recurse back
- * to it. This may not be a bounded recursion: since the first cache creation
- * failed to complete (waiting on the allocation), we'll just try to create the
- * cache again, failing at the same point.
- *
- * memcg_kmem_get_cache is prepared to abort after seeing a positive count of
- * memcg_kmem_skip_account. So we enclose anything that might allocate memory
- * inside the following two functions.
- */
-static inline void memcg_stop_kmem_account(void)
-{
- VM_BUG_ON(!current->mm);
- current->memcg_kmem_skip_account++;
-}
-
-static inline void memcg_resume_kmem_account(void)
-{
- VM_BUG_ON(!current->mm);
- current->memcg_kmem_skip_account--;
-}
-
struct mem_cgroup *mem_cgroup_from_kmem_page(struct page *page)
{
struct page_cgroup *pc;
@@ -5374,6 +5475,9 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
ret = memcg_update_kmem_limit(cont, val);
else
return -EINVAL;
+
+ if (!ret)
+ memcg_update_shrink_status(memcg);
break;
case RES_SOFT_LIMIT:
ret = res_counter_memparse_write_strategy(buffer, &val);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 0319dd2..1ac47b5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2512,7 +2512,49 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
return nr_reclaimed;
}
-#endif
+
+#ifdef CONFIG_MEMCG_KMEM
+/*
+ * This function is called when we are under kmem-specific pressure. It will
+ * only trigger in environments with kmem.limit_in_bytes < limit_in_bytes, IOW,
+ * with a lower kmem allowance than the memory allowance.
+ *
+ * In this situation, freeing user pages from the cgroup won't do us any good.
+ * What we really need is to call the memcg-aware shrinkers, in the hope of
+ * freeing pages holding kmem objects. It may also be that we won't be able to
+ * free any pages, but will get rid of old objects opening up space for new
+ * ones.
+ */
+unsigned long try_to_free_mem_cgroup_kmem(struct mem_cgroup *memcg,
+ gfp_t gfp_mask)
+{
+ long freed;
+
+ struct shrink_control shrink = {
+ .gfp_mask = gfp_mask,
+ .target_mem_cgroup = memcg,
+ };
+
+ if (!(gfp_mask & __GFP_WAIT))
+ return 0;
+
+ /*
+ * memcg pressure is always global */
+ nodes_setall(shrink.nodes_to_scan);
+
+ /*
+ * We haven't scanned any user LRU, so we basically come up with
+ * crafted values of nr_scanned and LRU page (1 and 0 respectively).
+ * This should be enough to tell shrink_slab that the freeing
+ * responsibility is all on himself.
+ */
+ freed = shrink_slab(&shrink, 1, 0);
+ if (!freed)
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
+ return freed;
+}
+#endif /* CONFIG_MEMCG_KMEM */
+#endif /* CONFIG_MEMCG */
static void age_active_anon(struct zone *zone, struct scan_control *sc)
{
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 26/31] memcg: scan cache objects hierarchically
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (24 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 25/31] memcg: per-memcg kmem shrinking Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 27/31] super: targeted memcg reclaim Glauber Costa
` (5 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Dave Chinner,
Mel Gorman, Rik van Riel, Hugh Dickins
When reaching shrink_slab, we should descent in children memcg searching
for objects that could be shrunk. This is true even if the memcg does
not have kmem limits on, since the kmem res_counter will also be billed
against the user res_counter of the parent.
It is possible that we will free objects and not free any pages, that
will just harm the child groups without helping the parent group at all.
But at this point, we basically are prepared to pay the price.
Signed-off-by: Glauber Costa <glommer@openvz.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/memcontrol.h | 6 ++
mm/memcontrol.c | 13 +++
mm/vmscan.c | 208 ++++++++++++++++++++++++++-------------------
3 files changed, 140 insertions(+), 87 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6dc1d7a..782dcbf 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -440,6 +440,7 @@ static inline bool memcg_kmem_enabled(void)
return static_key_false(&memcg_kmem_enabled_key);
}
+bool memcg_kmem_should_reclaim(struct mem_cgroup *memcg);
bool memcg_kmem_is_active(struct mem_cgroup *memcg);
/*
@@ -584,6 +585,11 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
}
#else
+static inline bool memcg_kmem_should_reclaim(struct mem_cgroup *memcg)
+{
+ return false;
+}
+
static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
{
return false;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 39b9ffe..f45da3c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2969,6 +2969,19 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
}
#ifdef CONFIG_MEMCG_KMEM
+bool memcg_kmem_should_reclaim(struct mem_cgroup *memcg)
+{
+ struct mem_cgroup *iter;
+
+ for_each_mem_cgroup_tree(iter, memcg) {
+ if (memcg_kmem_is_active(iter)) {
+ mem_cgroup_iter_break(memcg, iter);
+ return true;
+ }
+ }
+ return false;
+}
+
static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg)
{
return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg) &&
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1ac47b5..d07edfc 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -148,7 +148,7 @@ static bool global_reclaim(struct scan_control *sc)
static bool has_kmem_reclaim(struct scan_control *sc)
{
return !sc->target_mem_cgroup ||
- memcg_kmem_is_active(sc->target_mem_cgroup);
+ memcg_kmem_should_reclaim(sc->target_mem_cgroup);
}
static unsigned long
@@ -228,12 +228,108 @@ EXPORT_SYMBOL(unregister_shrinker);
*
* Returns the number of slab objects which we shrunk.
*/
+unsigned long
+shrink_slab_one(struct shrinker *shrinker, struct shrink_control *sc,
+ unsigned long nr_pages_scanned, unsigned long lru_pages)
+{
+ unsigned long freed = 0;
+ unsigned long long delta;
+ long total_scan;
+ long max_pass;
+ long nr;
+ long new_nr;
+ long batch_size = shrinker->batch ? shrinker->batch
+ : SHRINK_BATCH;
+
+ max_pass = shrinker->count_objects(shrinker, sc);
+ WARN_ON(max_pass < 0);
+ if (max_pass <= 0)
+ return 0;
+
+ /*
+ * copy the current shrinker scan count into a local variable
+ * and zero it so that other concurrent shrinker invocations
+ * don't also do this scanning work.
+ */
+ nr = atomic_long_xchg(&shrinker->nr_in_batch, 0);
+
+ total_scan = nr;
+ delta = (4 * nr_pages_scanned) / shrinker->seeks;
+ delta *= max_pass;
+ do_div(delta, lru_pages + 1);
+ total_scan += delta;
+ if (total_scan < 0) {
+ printk(KERN_ERR
+ "shrink_slab: %pF negative objects to delete nr=%ld\n",
+ shrinker->scan_objects, total_scan);
+ total_scan = max_pass;
+ }
+
+ /*
+ * We need to avoid excessive windup on filesystem shrinkers
+ * due to large numbers of GFP_NOFS allocations causing the
+ * shrinkers to return -1 all the time. This results in a large
+ * nr being built up so when a shrink that can do some work
+ * comes along it empties the entire cache due to nr >>>
+ * max_pass. This is bad for sustaining a working set in
+ * memory.
+ *
+ * Hence only allow the shrinker to scan the entire cache when
+ * a large delta change is calculated directly.
+ */
+ if (delta < max_pass / 4)
+ total_scan = min(total_scan, max_pass / 2);
+
+ /*
+ * Avoid risking looping forever due to too large nr value:
+ * never try to free more than twice the estimate number of
+ * freeable entries.
+ */
+ if (total_scan > max_pass * 2)
+ total_scan = max_pass * 2;
+
+ trace_mm_shrink_slab_start(shrinker, sc, nr,
+ nr_pages_scanned, lru_pages,
+ max_pass, delta, total_scan);
+
+ do {
+ long ret;
+
+ sc->nr_to_scan = batch_size;
+ ret = shrinker->scan_objects(shrinker, sc);
+ if (ret == -1)
+ break;
+ freed += ret;
+
+ count_vm_events(SLABS_SCANNED, batch_size);
+ total_scan -= batch_size;
+
+ cond_resched();
+ } while (total_scan >= batch_size);
+
+ /*
+ * move the unused scan count back into the shrinker in a
+ * manner that handles concurrent updates. If we exhausted the
+ * scan, there is no need to do an update.
+ */
+ if (total_scan > 0)
+ new_nr = atomic_long_add_return(total_scan,
+ &shrinker->nr_in_batch);
+ else
+ new_nr = atomic_long_read(&shrinker->nr_in_batch);
+
+ trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr);
+
+ return freed;
+}
+
unsigned long shrink_slab(struct shrink_control *sc,
unsigned long nr_pages_scanned,
unsigned long lru_pages)
{
struct shrinker *shrinker;
unsigned long freed = 0;
+ struct mem_cgroup *root = sc->target_mem_cgroup;
if (nr_pages_scanned == 0)
nr_pages_scanned = SWAP_CLUSTER_MAX;
@@ -245,101 +341,39 @@ unsigned long shrink_slab(struct shrink_control *sc,
}
list_for_each_entry(shrinker, &shrinker_list, list) {
- unsigned long long delta;
- long total_scan;
- long max_pass;
- long nr;
- long new_nr;
- long batch_size = shrinker->batch ? shrinker->batch
- : SHRINK_BATCH;
-
+ struct mem_cgroup *memcg;
/*
* If we don't have a target mem cgroup, we scan them all.
* Otherwise we will limit our scan to shrinkers marked as
* memcg aware
*/
- if (sc->target_mem_cgroup && !shrinker->memcg_shrinker)
- continue;
-
- max_pass = shrinker->count_objects(shrinker, sc);
- WARN_ON(max_pass < 0);
- if (max_pass <= 0)
+ if (root && !shrinker->memcg_shrinker)
continue;
- /*
- * copy the current shrinker scan count into a local variable
- * and zero it so that other concurrent shrinker invocations
- * don't also do this scanning work.
- */
- nr = atomic_long_xchg(&shrinker->nr_in_batch, 0);
-
- total_scan = nr;
- delta = (4 * nr_pages_scanned) / shrinker->seeks;
- delta *= max_pass;
- do_div(delta, lru_pages + 1);
- total_scan += delta;
- if (total_scan < 0) {
- printk(KERN_ERR
- "shrink_slab: %pF negative objects to delete nr=%ld\n",
- shrinker->scan_objects, total_scan);
- total_scan = max_pass;
- }
-
- /*
- * We need to avoid excessive windup on filesystem shrinkers
- * due to large numbers of GFP_NOFS allocations causing the
- * shrinkers to return -1 all the time. This results in a large
- * nr being built up so when a shrink that can do some work
- * comes along it empties the entire cache due to nr >>>
- * max_pass. This is bad for sustaining a working set in
- * memory.
- *
- * Hence only allow the shrinker to scan the entire cache when
- * a large delta change is calculated directly.
- */
- if (delta < max_pass / 4)
- total_scan = min(total_scan, max_pass / 2);
-
- /*
- * Avoid risking looping forever due to too large nr value:
- * never try to free more than twice the estimate number of
- * freeable entries.
- */
- if (total_scan > max_pass * 2)
- total_scan = max_pass * 2;
-
- trace_mm_shrink_slab_start(shrinker, sc, nr,
- nr_pages_scanned, lru_pages,
- max_pass, delta, total_scan);
-
+ memcg = mem_cgroup_iter(root, NULL, NULL);
do {
- long ret;
-
- sc->nr_to_scan = batch_size;
- ret = shrinker->scan_objects(shrinker, sc);
- if (ret == -1)
- break;
- freed += ret;
-
- count_vm_events(SLABS_SCANNED, batch_size);
- total_scan -= batch_size;
-
- cond_resched();
- } while (total_scan >= batch_size);
-
- /*
- * move the unused scan count back into the shrinker in a
- * manner that handles concurrent updates. If we exhausted the
- * scan, there is no need to do an update.
- */
- if (total_scan > 0)
- new_nr = atomic_long_add_return(total_scan,
- &shrinker->nr_in_batch);
- else
- new_nr = atomic_long_read(&shrinker->nr_in_batch);
-
- trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr);
+ sc->target_mem_cgroup = memcg;
+ /*
+ * In a hierarchical chain, it might be that not all
+ * memcgs are kmem active. kmemcg design mandates that
+ * when one memcg is active, its children will be
+ * active as well. But it is perfectly possible that
+ * its parent is not.
+ *
+ * We also need to make sure we scan at least once, for
+ * the global case. So if we don't have a target memcg
+ * (saved in root), we proceed normally and expect to
+ * break in the next round.
+ */
+ if (!root || memcg_kmem_is_active(memcg))
+ freed += shrink_slab_one(shrinker, sc,
+ nr_pages_scanned, lru_pages);
+ memcg = mem_cgroup_iter(root, memcg, NULL);
+ } while (memcg);
}
+
+ /* restore original state */
+ sc->target_mem_cgroup = root;
up_read(&shrinker_rwsem);
out:
cond_resched();
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 27/31] super: targeted memcg reclaim
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (25 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 26/31] memcg: scan cache objects hierarchically Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 28/31] memcg: move initialization to memcg creation Glauber Costa
` (4 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Dave Chinner,
Mel Gorman, Rik van Riel, Hugh Dickins
We now have all our dentries and inodes placed in memcg-specific LRU
lists. All we have to do is restrict the reclaim to the said lists in
case of memcg pressure.
That can't be done so easily for the fs_objects part of the equation,
since this is heavily fs-specific. What we do is pass on the context,
and let the filesystems decide if they ever chose or want to. At this
time, we just don't shrink them in memcg pressure (none is supported),
leaving that for global pressure only.
Marking the superblock shrinker and its LRUs as memcg-aware will
guarantee that the shrinkers will get invoked during targetted reclaim.
Signed-off-by: Glauber Costa <glommer@openvz.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
fs/dcache.c | 6 +++---
fs/inode.c | 6 +++---
fs/internal.h | 5 +++--
fs/super.c | 39 +++++++++++++++++++++++++++------------
4 files changed, 36 insertions(+), 20 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index 60b34fc..ee2de31 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -898,13 +898,13 @@ dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
* use.
*/
long prune_dcache_sb(struct super_block *sb, long nr_to_scan,
- nodemask_t *nodes_to_walk)
+ nodemask_t *nodes_to_walk, struct mem_cgroup *memcg)
{
LIST_HEAD(dispose);
long freed;
- freed = list_lru_walk_nodemask(&sb->s_dentry_lru, dentry_lru_isolate,
- &dispose, nr_to_scan, nodes_to_walk);
+ freed = list_lru_walk_nodemask_memcg(&sb->s_dentry_lru,
+ dentry_lru_isolate, &dispose, nr_to_scan, nodes_to_walk, memcg);
shrink_dentry_list(&dispose);
return freed;
}
diff --git a/fs/inode.c b/fs/inode.c
index dd1f6e9..83ee324 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -747,13 +747,13 @@ inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
* then are freed outside inode_lock by dispose_list().
*/
long prune_icache_sb(struct super_block *sb, long nr_to_scan,
- nodemask_t *nodes_to_walk)
+ nodemask_t *nodes_to_walk, struct mem_cgroup *memcg)
{
LIST_HEAD(freeable);
long freed;
- freed = list_lru_walk_nodemask(&sb->s_inode_lru, inode_lru_isolate,
- &freeable, nr_to_scan, nodes_to_walk);
+ freed = list_lru_walk_nodemask_memcg(&sb->s_inode_lru,
+ inode_lru_isolate, &freeable, nr_to_scan, nodes_to_walk, memcg);
dispose_list(&freeable);
return freed;
}
diff --git a/fs/internal.h b/fs/internal.h
index 552cdd6..64d95e4 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -16,6 +16,7 @@ struct file_system_type;
struct linux_binprm;
struct path;
struct mount;
+struct mem_cgroup;
/*
* block_dev.c
@@ -111,7 +112,7 @@ extern int open_check_o_direct(struct file *f);
*/
extern spinlock_t inode_sb_list_lock;
extern long prune_icache_sb(struct super_block *sb, long nr_to_scan,
- nodemask_t *nodes_to_scan);
+ nodemask_t *nodes_to_scan, struct mem_cgroup *memcg);
extern void inode_add_lru(struct inode *inode);
/*
@@ -128,7 +129,7 @@ extern int invalidate_inodes(struct super_block *, bool);
*/
extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
extern long prune_dcache_sb(struct super_block *sb, long nr_to_scan,
- nodemask_t *nodes_to_scan);
+ nodemask_t *nodes_to_scan, struct mem_cgroup *memcg);
/*
* read_write.c
diff --git a/fs/super.c b/fs/super.c
index 5c7b879..e92ebcb 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -34,6 +34,7 @@
#include <linux/cleancache.h>
#include <linux/fsnotify.h>
#include <linux/lockdep.h>
+#include <linux/memcontrol.h>
#include "internal.h"
@@ -56,6 +57,7 @@ static char *sb_writers_name[SB_FREEZE_LEVELS] = {
static long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
{
struct super_block *sb;
+ struct mem_cgroup *memcg = sc->target_mem_cgroup;
long fs_objects = 0;
long total_objects;
long freed = 0;
@@ -74,11 +76,13 @@ static long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
if (!grab_super_passive(sb))
return -1;
- if (sb->s_op && sb->s_op->nr_cached_objects)
+ if (sb->s_op && sb->s_op->nr_cached_objects && !memcg)
fs_objects = sb->s_op->nr_cached_objects(sb, &sc->nodes_to_scan);
- inodes = list_lru_count_nodemask(&sb->s_inode_lru, &sc->nodes_to_scan);
- dentries = list_lru_count_nodemask(&sb->s_dentry_lru, &sc->nodes_to_scan);
+ inodes = list_lru_count_nodemask_memcg(&sb->s_inode_lru,
+ &sc->nodes_to_scan, memcg);
+ dentries = list_lru_count_nodemask_memcg(&sb->s_dentry_lru,
+ &sc->nodes_to_scan, memcg);
total_objects = dentries + inodes + fs_objects + 1;
/* proportion the scan between the caches */
@@ -89,8 +93,8 @@ static long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
* prune the dcache first as the icache is pinned by it, then
* prune the icache, followed by the filesystem specific caches
*/
- freed = prune_dcache_sb(sb, dentries, &sc->nodes_to_scan);
- freed += prune_icache_sb(sb, inodes, &sc->nodes_to_scan);
+ freed = prune_dcache_sb(sb, dentries, &sc->nodes_to_scan, memcg);
+ freed += prune_icache_sb(sb, inodes, &sc->nodes_to_scan, memcg);
if (fs_objects) {
fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
@@ -107,20 +111,26 @@ static long super_cache_count(struct shrinker *shrink, struct shrink_control *sc
{
struct super_block *sb;
long total_objects = 0;
+ struct mem_cgroup *memcg = sc->target_mem_cgroup;
sb = container_of(shrink, struct super_block, s_shrink);
if (!grab_super_passive(sb))
return -1;
- if (sb->s_op && sb->s_op->nr_cached_objects)
+ /*
+ * Ideally we would pass memcg to nr_cached_objects, and
+ * let the underlying filesystem decide. Most likely the
+ * path will be if (!memcg) return;, but even then.
+ */
+ if (sb->s_op && sb->s_op->nr_cached_objects && !memcg)
total_objects = sb->s_op->nr_cached_objects(sb,
&sc->nodes_to_scan);
- total_objects += list_lru_count_nodemask(&sb->s_dentry_lru,
- &sc->nodes_to_scan);
- total_objects += list_lru_count_nodemask(&sb->s_inode_lru,
- &sc->nodes_to_scan);
+ total_objects += list_lru_count_nodemask_memcg(&sb->s_dentry_lru,
+ &sc->nodes_to_scan, memcg);
+ total_objects += list_lru_count_nodemask_memcg(&sb->s_inode_lru,
+ &sc->nodes_to_scan, memcg);
total_objects = vfs_pressure_ratio(total_objects);
drop_super(sb);
@@ -199,8 +209,10 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
INIT_HLIST_NODE(&s->s_instances);
INIT_HLIST_BL_HEAD(&s->s_anon);
INIT_LIST_HEAD(&s->s_inodes);
- list_lru_init(&s->s_dentry_lru);
- list_lru_init(&s->s_inode_lru);
+
+ list_lru_init_memcg(&s->s_dentry_lru);
+ list_lru_init_memcg(&s->s_inode_lru);
+
INIT_LIST_HEAD(&s->s_mounts);
init_rwsem(&s->s_umount);
lockdep_set_class(&s->s_umount, &type->s_umount_key);
@@ -236,6 +248,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
s->s_shrink.scan_objects = super_cache_scan;
s->s_shrink.count_objects = super_cache_count;
s->s_shrink.batch = 1024;
+ s->s_shrink.memcg_shrinker = true;
}
out:
return s;
@@ -318,6 +331,8 @@ void deactivate_locked_super(struct super_block *s)
/* caches are now gone, we can safely kill the shrinker now */
unregister_shrinker(&s->s_shrink);
+ list_lru_destroy(&s->s_dentry_lru);
+ list_lru_destroy(&s->s_inode_lru);
put_filesystem(fs);
put_super(s);
} else {
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 28/31] memcg: move initialization to memcg creation
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (26 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 27/31] super: targeted memcg reclaim Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 29/31] vmpressure: in-kernel notifications Glauber Costa
` (3 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Dave Chinner,
Mel Gorman, Rik van Riel, Hugh Dickins
Those structures are only used for memcgs that are effectively using
kmemcg. However, in a later patch I intend to use scan that list
inconditionally (list empty meaning no kmem caches present), which
simplifies the code a lot.
So move the initialization to early kmem creation.
Signed-off-by: Glauber Costa <glommer@openvz.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
mm/memcontrol.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f45da3c..f95debc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3249,9 +3249,7 @@ int memcg_update_cache_sizes(struct mem_cgroup *memcg)
memcg_update_array_size(num + 1);
- INIT_LIST_HEAD(&memcg->memcg_slab_caches);
INIT_WORK(&memcg->kmemcg_shrink_work, kmemcg_shrink_work_fn);
- mutex_init(&memcg->slab_caches_mutex);
return 0;
out:
@@ -6121,6 +6119,8 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
int ret;
+ INIT_LIST_HEAD(&memcg->memcg_slab_caches);
+ mutex_init(&memcg->slab_caches_mutex);
memcg->kmemcg_id = -1;
ret = memcg_propagate_kmem(memcg);
if (ret)
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 29/31] vmpressure: in-kernel notifications
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (27 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 28/31] memcg: move initialization to memcg creation Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 30/31] memcg: reap dead memcgs upon global memory pressure Glauber Costa
` (2 subsequent siblings)
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Dave Chinner,
John Stultz, Joonsoo Kim
From: Glauber Costa <glommer@parallels.com>
During the past weeks, it became clear to us that the shrinker interface
we have right now works very well for some particular types of users,
but not that well for others. The later are usually people interested in
one-shot notifications, that were forced to adapt themselves to the
count+scan behavior of shrinkers. To do so, they had no choice than to
greatly abuse the shrinker interface producing little monsters all over.
During LSF/MM, one of the proposals that popped out during our session
was to reuse Anton Voronstsov's vmpressure for this. They are designed
for userspace consumption, but also provide a well-stablished,
cgroup-aware entry point for notifications.
This patch extends that to also support in-kernel users. Events that
should be generated for in-kernel consumption will be marked as such,
and for those, we will call a registered function instead of triggering
an eventfd notification.
Please note that due to my lack of understanding of each shrinker user,
I will stay away from converting the actual users, you are all welcome
to do so.
Signed-off-by: Glauber Costa <glommer@openvz.org>
Acked-by: Anton Vorontsov <anton@enomsg.org>
Acked-by: Pekka Enberg <penberg@kernel.org>
Reviewed-by: Greg Thelen <gthelen@google.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
---
include/linux/vmpressure.h | 6 ++++++
mm/vmpressure.c | 52 +++++++++++++++++++++++++++++++++++++++++++---
2 files changed, 55 insertions(+), 3 deletions(-)
diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h
index 76be077..3131e72 100644
--- a/include/linux/vmpressure.h
+++ b/include/linux/vmpressure.h
@@ -19,6 +19,9 @@ struct vmpressure {
/* Have to grab the lock on events traversal or modifications. */
struct mutex events_lock;
+ /* False if only kernel users want to be notified, true otherwise. */
+ bool notify_userspace;
+
struct work_struct work;
};
@@ -36,6 +39,9 @@ extern struct vmpressure *css_to_vmpressure(struct cgroup_subsys_state *css);
extern int vmpressure_register_event(struct cgroup *cg, struct cftype *cft,
struct eventfd_ctx *eventfd,
const char *args);
+
+extern int vmpressure_register_kernel_event(struct cgroup *cg,
+ void (*fn)(void));
extern void vmpressure_unregister_event(struct cgroup *cg, struct cftype *cft,
struct eventfd_ctx *eventfd);
#else
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 736a601..e16256e 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -135,8 +135,12 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned,
}
struct vmpressure_event {
- struct eventfd_ctx *efd;
+ union {
+ struct eventfd_ctx *efd;
+ void (*fn)(void);
+ };
enum vmpressure_levels level;
+ bool kernel_event;
struct list_head node;
};
@@ -152,12 +156,15 @@ static bool vmpressure_event(struct vmpressure *vmpr,
mutex_lock(&vmpr->events_lock);
list_for_each_entry(ev, &vmpr->events, node) {
- if (level >= ev->level) {
+ if (ev->kernel_event) {
+ ev->fn();
+ } else if (vmpr->notify_userspace && level >= ev->level) {
eventfd_signal(ev->efd, 1);
signalled = true;
}
}
+ vmpr->notify_userspace = false;
mutex_unlock(&vmpr->events_lock);
return signalled;
@@ -227,7 +234,7 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg,
* we account it too.
*/
if (!(gfp & (__GFP_HIGHMEM | __GFP_MOVABLE | __GFP_IO | __GFP_FS)))
- return;
+ goto schedule;
/*
* If we got here with no pages scanned, then that is an indicator
@@ -244,8 +251,15 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg,
vmpr->scanned += scanned;
vmpr->reclaimed += reclaimed;
scanned = vmpr->scanned;
+ /*
+ * If we didn't reach this point, only kernel events will be triggered.
+ * It is the job of the worker thread to clean this up once the
+ * notifications are all delivered.
+ */
+ vmpr->notify_userspace = true;
mutex_unlock(&vmpr->sr_lock);
+schedule:
if (scanned < vmpressure_win || work_pending(&vmpr->work))
return;
schedule_work(&vmpr->work);
@@ -328,6 +342,38 @@ int vmpressure_register_event(struct cgroup *cg, struct cftype *cft,
}
/**
+ * vmpressure_register_kernel_event() - Register kernel-side notification
+ * @cg: cgroup that is interested in vmpressure notifications
+ * @fn: function to be called when pressure happens
+ *
+ * This function register in-kernel users interested in receiving notifications
+ * about pressure conditions. Pressure notifications will be triggered at the
+ * same time as userspace notifications (with no particular ordering relative
+ * to it).
+ *
+ * Pressure notifications are a alternative method to shrinkers and will serve
+ * well users that are interested in a one-shot notification, with a
+ * well-defined cgroup aware interface.
+ */
+int vmpressure_register_kernel_event(struct cgroup *cg, void (*fn)(void))
+{
+ struct vmpressure *vmpr = cg_to_vmpressure(cg);
+ struct vmpressure_event *ev;
+
+ ev = kzalloc(sizeof(*ev), GFP_KERNEL);
+ if (!ev)
+ return -ENOMEM;
+
+ ev->kernel_event = true;
+ ev->fn = fn;
+
+ mutex_lock(&vmpr->events_lock);
+ list_add(&ev->node, &vmpr->events);
+ mutex_unlock(&vmpr->events_lock);
+ return 0;
+}
+
+/**
* vmpressure_unregister_event() - Unbind eventfd from vmpressure
* @cg: cgroup handle
* @cft: cgroup control files handle
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 30/31] memcg: reap dead memcgs upon global memory pressure.
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (28 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 29/31] vmpressure: in-kernel notifications Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-26 23:19 ` [PATCH v4 31/31] memcg: debugging facility to access dangling memcgs Glauber Costa
2013-04-30 22:47 ` [PATCH v4 00/31] kmemcg shrinkers Mel Gorman
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa, Dave Chinner,
Mel Gorman, Rik van Riel, Hugh Dickins
When we delete kmem-enabled memcgs, they can still be zombieing
around for a while. The reason is that the objects may still be alive,
and we won't be able to delete them at destruction time.
The only entry point for that, though, are the shrinkers. The
shrinker interface, however, is not exactly tailored to our needs. It
could be a little bit better by using the API Dave Chinner proposed, but
it is still not ideal since we aren't really a count-and-scan event, but
more a one-off flush-all-you-can event that would have to abuse that
somehow.
Signed-off-by: Glauber Costa <glommer@openvz.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
mm/memcontrol.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 73 insertions(+), 3 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f95debc..434bb5c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -319,8 +319,16 @@ struct mem_cgroup {
/* thresholds for mem+swap usage. RCU-protected */
struct mem_cgroup_thresholds memsw_thresholds;
- /* For oom notifier event fd */
- struct list_head oom_notify;
+ union {
+ /* For oom notifier event fd */
+ struct list_head oom_notify;
+ /*
+ * we can only trigger an oom event if the memcg is alive.
+ * so we will reuse this field to hook the memcg in the list
+ * of dead memcgs.
+ */
+ struct list_head dead;
+ };
/*
* Should we move charges of a task when a task is moved into this
@@ -383,6 +391,24 @@ static size_t memcg_size(void)
static DEFINE_MUTEX(set_limit_mutex);
+static LIST_HEAD(dangling_memcgs);
+static DEFINE_MUTEX(dangling_memcgs_mutex);
+
+static inline void memcg_dangling_free(struct mem_cgroup *memcg)
+{
+ mutex_lock(&dangling_memcgs_mutex);
+ list_del(&memcg->dead);
+ mutex_unlock(&dangling_memcgs_mutex);
+}
+
+static inline void memcg_dangling_add(struct mem_cgroup *memcg)
+{
+ INIT_LIST_HEAD(&memcg->dead);
+ mutex_lock(&dangling_memcgs_mutex);
+ list_add(&memcg->dead, &dangling_memcgs);
+ mutex_unlock(&dangling_memcgs_mutex);
+}
+
/* internal only representation about the status of kmem accounting. */
enum {
KMEM_ACCOUNTED_ACTIVE = 0, /* accounted by this cgroup itself */
@@ -6115,6 +6141,41 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
}
#ifdef CONFIG_MEMCG_KMEM
+static void memcg_vmpressure_shrink_dead(void)
+{
+ struct memcg_cache_params *params, *tmp;
+ struct kmem_cache *cachep;
+ struct mem_cgroup *memcg;
+
+ mutex_lock(&dangling_memcgs_mutex);
+ list_for_each_entry(memcg, &dangling_memcgs, dead) {
+ mutex_lock(&memcg->slab_caches_mutex);
+ /* The element may go away as an indirect result of shrink */
+ list_for_each_entry_safe(params, tmp,
+ &memcg->memcg_slab_caches, list) {
+ cachep = memcg_params_to_cache(params);
+ /*
+ * the cpu_hotplug lock is taken in kmem_cache_create
+ * outside the slab_caches_mutex manipulation. It will
+ * be taken by kmem_cache_shrink to flush the cache.
+ * So we need to drop the lock. It is all right because
+ * the lock only protects elements moving in and out the
+ * list.
+ */
+ mutex_unlock(&memcg->slab_caches_mutex);
+ kmem_cache_shrink(cachep);
+ mutex_lock(&memcg->slab_caches_mutex);
+ }
+ mutex_unlock(&memcg->slab_caches_mutex);
+ }
+ mutex_unlock(&dangling_memcgs_mutex);
+}
+
+static void memcg_register_kmem_events(struct cgroup *cont)
+{
+ vmpressure_register_kernel_event(cont, memcg_vmpressure_shrink_dead);
+}
+
static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
int ret;
@@ -6150,6 +6211,10 @@ static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
}
}
#else
+static inline void memcg_register_kmem_events(struct cgroup *cont)
+{
+}
+
static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
return 0;
@@ -6415,6 +6480,8 @@ static void free_work(struct work_struct *work)
struct mem_cgroup *memcg;
memcg = container_of(work, struct mem_cgroup, work_freeing);
+
+ memcg_dangling_free(memcg);
__mem_cgroup_free(memcg);
}
@@ -6525,8 +6592,10 @@ mem_cgroup_css_online(struct cgroup *cont)
struct mem_cgroup *memcg, *parent;
int error = 0;
- if (!cont->parent)
+ if (!cont->parent) {
+ memcg_register_kmem_events(cont);
return 0;
+ }
mutex_lock(&memcg_create_mutex);
memcg = mem_cgroup_from_cont(cont);
@@ -6609,6 +6678,7 @@ static void mem_cgroup_css_free(struct cgroup *cont)
kmem_cgroup_destroy(memcg);
+ memcg_dangling_add(memcg);
mem_cgroup_put(memcg);
}
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* [PATCH v4 31/31] memcg: debugging facility to access dangling memcgs
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (29 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 30/31] memcg: reap dead memcgs upon global memory pressure Glauber Costa
@ 2013-04-26 23:19 ` Glauber Costa
2013-04-30 22:47 ` [PATCH v4 00/31] kmemcg shrinkers Mel Gorman
31 siblings, 0 replies; 63+ messages in thread
From: Glauber Costa @ 2013-04-26 23:19 UTC (permalink / raw)
To: linux-mm
Cc: cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner, Glauber Costa
If memcg is tracking anything other than plain user memory (swap,
tcp buf mem, or slab memory), it is possible - and normal - that a
reference will be held by the group after it is dead. Still, for
developers, it would be extremely useful to be able to query about those
states during debugging.
This patch provides a debugging facility in the root memcg, so we
can inspect which memcgs still have pending objects, and what is the
cause of this state.
[akpm@linux-foundation.org: fix up Kconfig text]
Signed-off-by: Glauber Costa <glommer@openvz.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
---
This is a debug-only patch, intended for -mm only
---
Documentation/cgroups/memory.txt | 16 ++++
init/Kconfig | 17 +++++
mm/memcontrol.c | 160 +++++++++++++++++++++++++++++++++++++--
3 files changed, 187 insertions(+), 6 deletions(-)
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 09027a9..1178e23 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -72,6 +72,7 @@ Brief summary of control files.
memory.move_charge_at_immigrate # set/show controls of moving charges
memory.oom_control # set/show oom controls.
memory.numa_stat # show the number of memory usage per numa node
+ memory.dangling_memcgs # show debugging information about dangling groups
memory.kmem.limit_in_bytes # set/show hard limit for kernel memory
memory.kmem.usage_in_bytes # show current kernel memory allocation
@@ -579,6 +580,21 @@ unevictable=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ...
And we have total = file + anon + unevictable.
+5.7 dangling_memcgs
+
+This file will only be ever present in the root cgroup, if the option
+CONFIG_MEMCG_DEBUG_ASYNC_DESTROY is set. When a memcg is destroyed, the memory
+consumed by it may not be immediately freed. This is because when some
+extensions are used, such as swap or kernel memory, objects can outlive the
+group and hold a reference to it.
+
+If this is the case, the dangling_memcgs file will show information about what
+are the memcgs still alive, and which references are still preventing it to be
+freed. There is nothing wrong with that, but it is very useful when debugging,
+to know where this memory is being held. This is a developer-oriented debugging
+facility only, and no guarantees of interface stability will be given. The file
+is read-only, and has the sole purpose of displaying information.
+
6. Hierarchy support
The memory controller supports a deep hierarchy and hierarchical accounting.
diff --git a/init/Kconfig b/init/Kconfig
index 6e47c09..346cd1b 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -946,6 +946,23 @@ config MEMCG_KMEM
the kmem extension can use it to guarantee that no group of processes
will ever exhaust kernel resources alone.
+config MEMCG_DEBUG_ASYNC_DESTROY
+ bool "Memory Resource Controller Debug asynchronous object destruction"
+ depends on MEMCG_KMEM || MEMCG_SWAP
+ default n
+ help
+ When a memcg is destroyed, the memory consumed by it may not be
+ immediately freed. This is because when some extensions are used, such
+ as swap or kernel memory, objects can outlive the group and hold a
+ reference to it.
+
+ If this is the case, the dangling_memcgs file will show information
+ about what are the memcgs still alive, and which references are still
+ preventing it to be freed. There is nothing wrong with that, but it is
+ very useful when debugging, to know where this memory is being held.
+ This is a developer-oriented debugging facility only, and no
+ guarantees of interface stability will be given.
+
config CGROUP_HUGETLB
bool "HugeTLB Resource Controller for Control Groups"
depends on RESOURCE_COUNTERS && HUGETLB_PAGE
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 434bb5c..06f3f18 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -330,11 +330,20 @@ struct mem_cgroup {
struct list_head dead;
};
- /*
- * Should we move charges of a task when a task is moved into this
- * mem_cgroup ? And what type of charges should we move ?
- */
- unsigned long move_charge_at_immigrate;
+ union {
+ /*
+ * Should we move charges of a task when a task is moved into
+ * this mem_cgroup ? And what type of charges should we move ?
+ */
+ unsigned long move_charge_at_immigrate;
+
+ /*
+ * We are no longer concerned about moving charges after memcg
+ * is dead. So we will fill this up with its name, to aid
+ * debugging.
+ */
+ char *memcg_name;
+ };
/*
* set > 0 if pages under this cgroup are moving to other cgroup.
*/
@@ -399,10 +408,40 @@ static inline void memcg_dangling_free(struct mem_cgroup *memcg)
mutex_lock(&dangling_memcgs_mutex);
list_del(&memcg->dead);
mutex_unlock(&dangling_memcgs_mutex);
+#ifdef CONFIG_MEMCG_DEBUG_ASYNC_DESTROY
+ free_pages((unsigned long)memcg->memcg_name, 0);
+#endif
}
static inline void memcg_dangling_add(struct mem_cgroup *memcg)
{
+#ifdef CONFIG_MEMCG_DEBUG_ASYNC_DESTROY
+ /*
+ * cgroup.c will do page-sized allocations most of the time,
+ * so we'll just follow the pattern. Also, __get_free_pages
+ * is a better interface than kmalloc for us here, because
+ * we'd like this memory to be always billed to the root cgroup,
+ * not to the process removing the memcg. While kmalloc would
+ * require us to wrap it into memcg_stop/resume_kmem_account,
+ * with __get_free_pages we just don't pass the memcg flag.
+ */
+ memcg->memcg_name = (char *)__get_free_pages(GFP_KERNEL, 0);
+
+ /*
+ * we will, in general, just ignore failures. No need to go crazy,
+ * being this just a debugging interface. It is nice to copy a memcg
+ * name over, but if we (unlikely) can't, just the address will do
+ */
+ if (!memcg->memcg_name)
+ goto add_list;
+
+ if (cgroup_path(memcg->css.cgroup, memcg->memcg_name, PAGE_SIZE) < 0) {
+ free_pages((unsigned long)memcg->memcg_name, 0);
+ memcg->memcg_name = NULL;
+ }
+
+add_list:
+#endif
INIT_LIST_HEAD(&memcg->dead);
mutex_lock(&dangling_memcgs_mutex);
list_add(&memcg->dead, &dangling_memcgs);
@@ -3594,7 +3633,7 @@ static void kmem_cache_destroy_work_func(struct work_struct *w)
*/
if (atomic_read(&cachep->memcg_params->nr_pages) != 0) {
kmem_cache_shrink(cachep);
- if (atomic_read(&cachep->memcg_params->nr_pages) == 0)
+ if (atomic_read(&cachep->memcg_params->nr_pages) != 0)
return;
} else
kmem_cache_destroy(cachep);
@@ -5384,6 +5423,107 @@ static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
return simple_read_from_buffer(buf, nbytes, ppos, str, len);
}
+#ifdef CONFIG_MEMCG_DEBUG_ASYNC_DESTROY
+static void
+mem_cgroup_dangling_swap(struct mem_cgroup *memcg, struct seq_file *m)
+{
+#ifdef CONFIG_MEMCG_SWAP
+ u64 kmem;
+ u64 memsw;
+
+ /*
+ * kmem will also propagate here, so we are only interested in the
+ * difference. See comment in mem_cgroup_reparent_charges for details.
+ *
+ * We could save this value for later consumption by kmem reports, but
+ * there is not a lot of problem if the figures differ slightly.
+ */
+ kmem = res_counter_read_u64(&memcg->kmem, RES_USAGE);
+ memsw = res_counter_read_u64(&memcg->memsw, RES_USAGE) - kmem;
+ seq_printf(m, "\t%llu swap bytes\n", memsw);
+#endif
+}
+
+
+static void
+mem_cgroup_dangling_tcp(struct mem_cgroup *memcg, struct seq_file *m)
+{
+#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM)
+ struct tcp_memcontrol *tcp = &memcg->tcp_mem;
+ s64 tcp_socks;
+ u64 tcp_bytes;
+
+ tcp_socks = percpu_counter_sum_positive(&tcp->tcp_sockets_allocated);
+ tcp_bytes = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE);
+ seq_printf(m, "\t%llu tcp bytes", tcp_bytes);
+ /*
+ * if tcp_bytes == 0, tcp_socks != 0 is a bug. One more reason to print
+ * it!
+ */
+ if (tcp_bytes || tcp_socks)
+ seq_printf(m, ", in %lld sockets", tcp_socks);
+ seq_printf(m, "\n");
+
+#endif
+}
+
+static void
+mem_cgroup_dangling_kmem(struct mem_cgroup *memcg, struct seq_file *m)
+{
+#ifdef CONFIG_MEMCG_KMEM
+ u64 kmem;
+ struct memcg_cache_params *params;
+
+ kmem = res_counter_read_u64(&memcg->kmem, RES_USAGE);
+ seq_printf(m, "\t%llu kmem bytes", kmem);
+
+ /* list below may not be initialized, so not even try */
+ if (!kmem)
+ return;
+
+ seq_printf(m, " in caches");
+ mutex_lock(&memcg->slab_caches_mutex);
+ list_for_each_entry(params, &memcg->memcg_slab_caches, list) {
+ struct kmem_cache *s = memcg_params_to_cache(params);
+
+ seq_printf(m, " %s", s->name);
+ }
+ mutex_unlock(&memcg->slab_caches_mutex);
+ seq_printf(m, "\n");
+#endif
+}
+
+/*
+ * After a memcg is destroyed, it may still be kept around in memory.
+ * Currently, the two main reasons for it are swap entries, and kernel memory.
+ * Because they will be freed assynchronously, they will pin the memcg structure
+ * and its resources until the last reference goes away.
+ *
+ * This root-only file will show information about which users
+ */
+static int mem_cgroup_dangling_read(struct cgroup *cont, struct cftype *cft,
+ struct seq_file *m)
+{
+ struct mem_cgroup *memcg;
+
+ mutex_lock(&dangling_memcgs_mutex);
+
+ list_for_each_entry(memcg, &dangling_memcgs, dead) {
+ if (memcg->memcg_name)
+ seq_printf(m, "%s:\n", memcg->memcg_name);
+ else
+ seq_printf(m, "%p (name lost):\n", memcg);
+
+ mem_cgroup_dangling_swap(memcg, m);
+ mem_cgroup_dangling_tcp(memcg, m);
+ mem_cgroup_dangling_kmem(memcg, m);
+ }
+
+ mutex_unlock(&dangling_memcgs_mutex);
+ return 0;
+}
+#endif
+
static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
{
int ret = -EINVAL;
@@ -6331,6 +6471,14 @@ static struct cftype mem_cgroup_files[] = {
},
#endif
#endif
+
+#ifdef CONFIG_MEMCG_DEBUG_ASYNC_DESTROY
+ {
+ .name = "dangling_memcgs",
+ .read_seq_string = mem_cgroup_dangling_read,
+ .flags = CFTYPE_ONLY_ON_ROOT,
+ },
+#endif
{ }, /* terminate */
};
--
1.8.1.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 63+ messages in thread* Re: [PATCH v4 00/31] kmemcg shrinkers
2013-04-26 23:18 [PATCH v4 00/31] kmemcg shrinkers Glauber Costa
` (30 preceding siblings ...)
2013-04-26 23:19 ` [PATCH v4 31/31] memcg: debugging facility to access dangling memcgs Glauber Costa
@ 2013-04-30 22:47 ` Mel Gorman
2013-05-01 9:05 ` Mel Gorman
31 siblings, 1 reply; 63+ messages in thread
From: Mel Gorman @ 2013-04-30 22:47 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner
On Sat, Apr 27, 2013 at 03:18:56AM +0400, Glauber Costa wrote:
> Numbers (not updated since last time):
> ======================================
>
> I've run kernbench with 2Gb setups and 3 different kernels. All of them are
> capable of cgroup kmem accounting, but the first two ones won't be able to
> shrink it.
>
> Kernels
> -------
> base: the current -mm
> davelru: that + dave's patches applied
> fulllru: that + my patches applied.
>
> I've ran all of them in a 1st level cgroup. Please note that the first
> two kernels are not capable of shrinking metadata, so I had to select a
> size that is enough to be in relatively constant pressure, but at the
> same time not having that pressure to be exclusively from kernel memory.
> 2Gb did the job. This is a 2-node 24-way machine.
>
> Results:
> --------
>
> Base:
> Average Optimal load -j 24 Run (std deviation):
> Elapsed Time 415.988 (8.37909)
> User Time 4142 (759.964)
> System Time 418.483 (62.0377)
> Percent CPU 1030.7 (267.462)
> Context Switches 391509 (268361)
> Sleeps 738483 (149934)
>
This took longer than I expected and I ran out of beans by the time I hit
the memcg parts but I had started pagereclaim tests earlier and picked
up the results. There are some oddities in there that imply that slab
shrinkers are now way more aggressive, particularly when called from
kswapd. In some cases it looks like it's favouring shrinking slab over
pages which is not what I expected. I've no idea if the oddities were
introduced by the patches I reviewed and I missed (or miscalculated)
or in the later patches that I haven't read yet.
http://www.csn.ul.ie/~mel/postings/shrinker-20130430/report.html
This is based on the configs/config-global-dhp__pagereclaim-performance
from mmtests with alterations to run the test on a freshly created ext4
filesystem.
postmark
o Overall performance is good but ...
o kswapd pages scanned went from 9957291 to 4486. Thats a very
suspiciously high drop
o Same for kswapd pages reclaimed
o kswapd inode steals are through the roof
o graphs indicate almost no kswapd scanning activity
o free memory now has a very sawtooth pattern freeing pages in spikes
In combination this implies we are shrinking slab aggressively and
barely reclaiming user pages as the slab shrink is sufficient to free
enough memory.
largedd
o there is now direct reclaim activity
o kswapd scan and reclaim rates are again drastically altered
o slabs scanned is apparently through the roof
o memory is getting freed in LARGE chunks, look at the free memory
over time graph and look at the big sawtooth pattern for the patched
kernel
o kswapd CPU usage is highly variable. It might indicate a pattern of
sleep, WAKE UP RECLAIM EVERYTHING, sleep ages, ARGH WAKE UP KILL WORLD
fsmark-single
o very similar observations to largedd
micro
o slabs scanned looks a bit mental again
I've queued another test to run just the patches up to and including
"shrinker: Kill old ->shrink API".
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread* Re: [PATCH v4 00/31] kmemcg shrinkers
2013-04-30 22:47 ` [PATCH v4 00/31] kmemcg shrinkers Mel Gorman
@ 2013-05-01 9:05 ` Mel Gorman
0 siblings, 0 replies; 63+ messages in thread
From: Mel Gorman @ 2013-05-01 9:05 UTC (permalink / raw)
To: Glauber Costa
Cc: linux-mm, cgroups, Andrew Morton, Greg Thelen, kamezawa.hiroyu,
Michal Hocko, Johannes Weiner
On Tue, Apr 30, 2013 at 11:47:48PM +0100, Mel Gorman wrote:
> I've queued another test to run just the patches up to and including
> "shrinker: Kill old ->shrink API".
>
Oddities introduced prior to the memcg changes
In these, shrinker-v1r1 is the full series (middle column) and
nodeshrink-v1r1 is up to and including "shrinker: Kill old ->shrink API"
http://www.csn.ul.ie/~mel/postings/shrinker-20130501/global-dhp__pagereclaim-performance-ext3/hydra/report.html
http://www.csn.ul.ie/~mel/postings/shrinker-20130501/global-dhp__pagereclaim-performance-ext4/hydra/report.html
http://www.csn.ul.ie/~mel/postings/shrinker-20130501/global-dhp__pagereclaim-performance-xfs/hydra/report.html
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 63+ messages in thread