shrinker: convert superblock shrinkers to new API
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@openvz.org: use mult_frac for fractional proportions, build fixes]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Arve Hjønnevåg <arve@android.com>
Cc: Carlos Maiolino <cmaiolino@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Rientjes <rientjes@google.com>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: J. Bruce Fields <bfields@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Kent Overstreet <koverstreet@google.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
diff --git a/fs/dcache.c b/fs/dcache.c
index 509b494..77d466b 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -913,11 +913,12 @@
* 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, unsigned long nr_to_scan)
{
struct dentry *dentry;
LIST_HEAD(referenced);
LIST_HEAD(tmp);
+ long freed = 0;
relock:
spin_lock(&sb->s_dentry_lru_lock);
@@ -942,7 +943,8 @@
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);
@@ -952,6 +954,7 @@
spin_unlock(&sb->s_dentry_lru_lock);
shrink_dentry_list(&tmp);
+ return freed;
}
/*
diff --git a/fs/inode.c b/fs/inode.c
index 2a3c37e..021d647 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -706,10 +706,11 @@
* 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, unsigned 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);
@@ -779,6 +780,7 @@
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);
@@ -789,6 +791,7 @@
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 b649565..cb83a34 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -114,6 +114,7 @@
* inode.c
*/
extern spinlock_t inode_sb_list_lock;
+extern long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan);
extern void inode_add_lru(struct inode *inode);
/*
@@ -130,6 +131,7 @@
*/
extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
extern int d_set_mounted(struct dentry *dentry);
+extern long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan);
/*
* read_write.c
diff --git a/fs/super.c b/fs/super.c
index 3c53186..8aa2660 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -53,11 +53,15 @@
* 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 unsigned 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);
@@ -65,11 +69,11 @@
* 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))
- return -1;
+ if (!(sc->gfp_mask & __GFP_FS))
+ return SHRINK_STOP;
if (!grab_super_passive(sb))
- return -1;
+ return SHRINK_STOP;
if (sb->s_op->nr_cached_objects)
fs_objects = sb->s_op->nr_cached_objects(sb);
@@ -77,33 +81,46 @@
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);
- /* 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);
+ /*
+ * 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 && 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;
+ 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 unsigned 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 0;
+
+ 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;
@@ -211,7 +228,8 @@
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 16219b9..73b62a2 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1167,7 +1167,7 @@
* 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)
@@ -1176,7 +1176,7 @@
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 8a89f7d..456f014 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -46,7 +46,7 @@
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 979a77d..71d7aae 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1535,19 +1535,19 @@
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 14a90f6..0ae0bc3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1335,10 +1335,6 @@
struct workqueue_struct *s_dio_done_wq;
};
-/* 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);
/*
@@ -1631,8 +1627,8 @@
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);
};
/*