From: Glauber Costa <glommer@openvz.org>
To: linux-mm@kvack.org
Cc: 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>,
Glauber Costa <glommer@openvz.org>
Subject: [PATCH v4 10/31] dcache: convert to use new lru list infrastructure
Date: Sat, 27 Apr 2013 03:19:06 +0400 [thread overview]
Message-ID: <1367018367-11278-11-git-send-email-glommer@openvz.org> (raw)
In-Reply-To: <1367018367-11278-1-git-send-email-glommer@openvz.org>
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>
next prev parent reply other threads:[~2013-04-26 23:19 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
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
2013-04-30 13:03 ` Mel Gorman
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
2013-04-30 15:37 ` Mel Gorman
2013-05-07 13:35 ` Glauber Costa
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
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
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
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
2013-04-30 15:32 ` Mel Gorman
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
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
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
2013-04-26 23:19 ` Glauber Costa [this message]
2013-04-30 16:04 ` [PATCH v4 10/31] dcache: convert to use new lru list infrastructure Mel Gorman
2013-04-30 16:13 ` Glauber Costa
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
2013-04-26 23:19 ` [PATCH v4 12/31] shrinker: add node awareness 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
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
2013-04-26 23:19 ` [PATCH v4 15/31] xfs: convert dquot cache lru to list_lru Glauber Costa
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 ` [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
2013-05-02 9:37 ` Mel Gorman
2013-05-02 13:37 ` Glauber Costa
2013-05-01 15:26 ` Daniel Vetter
2013-05-02 9:31 ` Mel Gorman
2013-04-26 23:19 ` [PATCH v4 18/31] shrinker: convert remaining shrinkers to " Glauber Costa
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 ` [PATCH v4 20/31] shrinker: Kill old ->shrink API 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
2013-04-26 23:19 ` [PATCH v4 22/31] memcg,list_lru: duplicate LRUs upon kmemcg creation Glauber Costa
2013-04-26 23:19 ` [PATCH v4 23/31] lru: add an element to a memcg list Glauber Costa
2013-04-26 23:19 ` [PATCH v4 24/31] list_lru: per-memcg walks Glauber Costa
2013-04-26 23:19 ` [PATCH v4 25/31] memcg: per-memcg kmem shrinking Glauber Costa
2013-04-26 23:19 ` [PATCH v4 26/31] memcg: scan cache objects hierarchically Glauber Costa
2013-04-26 23:19 ` [PATCH v4 27/31] super: targeted memcg reclaim Glauber Costa
2013-04-26 23:19 ` [PATCH v4 28/31] memcg: move initialization to memcg creation Glauber Costa
2013-04-26 23:19 ` [PATCH v4 29/31] vmpressure: in-kernel notifications Glauber Costa
2013-04-26 23:19 ` [PATCH v4 30/31] memcg: reap dead memcgs upon global memory pressure 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
2013-05-01 9:05 ` Mel Gorman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1367018367-11278-11-git-send-email-glommer@openvz.org \
--to=glommer@openvz.org \
--cc=akpm@linux-foundation.org \
--cc=cgroups@vger.kernel.org \
--cc=dchinner@redhat.com \
--cc=gthelen@google.com \
--cc=hannes@cmpxchg.org \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.cz \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).