linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Glauber Costa <glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
To: Andrew Morton <akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
Cc: <linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	Mel Gorman <mgorman-l3A5Bk7waGM@public.gmane.org>,
	Dave Chinner <david-FqsqvQoI3Ljby3iVrkZq2A@public.gmane.org>,
	<linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org>,
	<cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	<kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>,
	Michal Hocko <mhocko-AlSwsSmVLrQ@public.gmane.org>,
	Johannes Weiner <hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org>,
	hughd-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org,
	Greg Thelen <gthelen-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
	Dave Chinner <dchinner-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	Glauber Costa <glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
Subject: [PATCH v9 10/35] dcache: convert to use new lru list infrastructure
Date: Thu, 30 May 2013 14:35:56 +0400	[thread overview]
Message-ID: <1369910181-20026-11-git-send-email-glommer@openvz.org> (raw)
In-Reply-To: <1369910181-20026-1-git-send-email-glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>

From: Dave Chinner <dchinner-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>

[ glommer: don't reintroduce double decrement of nr_unused_dentries,
  adapted for new LRU return codes ]
Signed-off-by: Dave Chinner <dchinner-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Signed-off-by: Glauber Costa <glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
---
 fs/dcache.c        | 165 ++++++++++++++++++++++++-----------------------------
 fs/super.c         |  11 ++--
 include/linux/fs.h |  15 +++--
 3 files changed, 87 insertions(+), 104 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index f048f95..30731d3 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"
 
@@ -319,20 +320,8 @@ 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);
 }
 
 /*
@@ -350,26 +339,8 @@ static void dentry_lru_del(struct dentry *dentry)
 		return;
 	}
 
-	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);
-	}
-}
-
-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_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);
 }
 
 /**
@@ -844,12 +815,72 @@ 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.
  *
@@ -858,45 +889,12 @@ static void shrink_dentry_list(struct list_head *list)
  */
 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);
-	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(&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;
 }
 
@@ -930,24 +928,10 @@ 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)) {
-		/*
-		 * account for removal here so we don't need to handle it later
-		 * even though the dentry is no longer on the lru list.
-		 */
-		list_splice_init(&sb->s_dentry_lru, &tmp);
-		this_cpu_sub(nr_dentry_unused, sb->s_nr_dentry_unused);
-		sb->s_nr_dentry_unused = 0;
-		spin_unlock(&sb->s_dentry_lru_lock);
+	long disposed;
 
-		shrink_dcache_list(&tmp);
-
-		spin_lock(&sb->s_dentry_lru_lock);
-	}
-	spin_unlock(&sb->s_dentry_lru_lock);
+	disposed = list_lru_dispose_all(&sb->s_dentry_lru, shrink_dcache_list);
+	this_cpu_sub(nr_dentry_unused, disposed);
 }
 EXPORT_SYMBOL(shrink_dcache_sb);
 
@@ -1220,7 +1204,8 @@ 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 83f6eb4..8d8a62c 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 06695d7..0d05a98 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 */
-	long			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

  parent reply	other threads:[~2013-05-30 10:35 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-05-30 10:35 [PATCH v9 00/35] kmemcg shrinkers Glauber Costa
2013-05-30 10:35 ` [PATCH v9 02/35] super: fix calculation of shrinkable objects for small numbers Glauber Costa
     [not found] ` <1369910181-20026-1-git-send-email-glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
2013-05-30 10:35   ` [PATCH v9 01/35] fs: bump inode and dentry counters to long Glauber Costa
2013-05-30 10:35   ` [PATCH v9 03/35] dcache: convert dentry_stat.nr_unused to per-cpu counters Glauber Costa
2013-05-30 10:35   ` [PATCH v9 04/35] dentry: move to per-sb LRU locks Glauber Costa
2013-05-30 10:35   ` [PATCH v9 05/35] dcache: remove dentries from LRU before putting on dispose list Glauber Costa
2013-05-30 10:35   ` [PATCH v9 06/35] mm: new shrinker API Glauber Costa
2013-05-30 10:35   ` [PATCH v9 07/35] shrinker: convert superblock shrinkers to new API Glauber Costa
2013-05-30 10:35   ` [PATCH v9 08/35] list: add a new LRU list type Glauber Costa
2013-05-30 10:35   ` [PATCH v9 09/35] inode: convert inode lru list to generic lru list code Glauber Costa
2013-05-30 10:35   ` Glauber Costa [this message]
2013-05-30 10:35   ` [PATCH v9 11/35] list_lru: per-node list infrastructure Glauber Costa
2013-05-30 10:35   ` [PATCH v9 12/35] shrinker: add node awareness Glauber Costa
2013-05-30 10:35   ` [PATCH v9 13/35] vmscan: per-node deferred work Glauber Costa
2013-05-30 10:36   ` [PATCH v9 14/35] list_lru: per-node API Glauber Costa
2013-05-30 10:36   ` [PATCH v9 15/35] fs: convert inode and dentry shrinking to be node aware Glauber Costa
2013-05-30 10:36   ` [PATCH v9 16/35] xfs: convert buftarg LRU to generic code Glauber Costa
2013-05-30 10:36   ` [PATCH v9 17/35] xfs: rework buffer dispose list tracking Glauber Costa
2013-05-30 10:36   ` [PATCH v9 18/35] xfs: convert dquot cache lru to list_lru Glauber Costa
2013-05-30 10:36   ` [PATCH v9 19/35] fs: convert fs shrinkers to new scan/count API Glauber Costa
2013-05-30 10:36   ` [PATCH v9 21/35] i915: bail out earlier when shrinker cannot acquire mutex Glauber Costa
2013-05-30 10:36   ` [PATCH v9 22/35] shrinker: convert remaining shrinkers to count/scan API Glauber Costa
2013-05-30 10:36   ` [PATCH v9 23/35] hugepage: convert huge zero page shrinker to new shrinker API Glauber Costa
2013-05-30 10:36   ` [PATCH v9 24/35] shrinker: Kill old ->shrink API Glauber Costa
2013-05-30 10:36   ` [PATCH v9 25/35] vmscan: also shrink slab in memcg pressure Glauber Costa
2013-05-30 10:36   ` [PATCH v9 26/35] memcg,list_lru: duplicate LRUs upon kmemcg creation Glauber Costa
2013-05-30 10:36   ` [PATCH v9 27/35] lru: add an element to a memcg list Glauber Costa
2013-05-30 10:36   ` [PATCH v9 28/35] list_lru: per-memcg walks Glauber Costa
2013-05-30 10:36   ` [PATCH v9 29/35] memcg: per-memcg kmem shrinking Glauber Costa
2013-05-30 10:36   ` [PATCH v9 30/35] memcg: scan cache objects hierarchically Glauber Costa
2013-05-30 10:36   ` [PATCH v9 32/35] super: targeted memcg reclaim Glauber Costa
2013-05-30 10:36   ` [PATCH v9 33/35] memcg: move initialization to memcg creation Glauber Costa
2013-05-30 10:36   ` [PATCH v9 34/35] vmpressure: in-kernel notifications Glauber Costa
2013-05-30 10:36   ` [PATCH v9 35/35] memcg: reap dead memcgs upon global memory pressure Glauber Costa
2013-05-30 10:36 ` [PATCH v9 20/35] drivers: convert shrinkers to new count/scan API Glauber Costa
2013-05-30 10:36 ` [PATCH v9 31/35] vmscan: take at least one pass with shrinkers Glauber Costa

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=1369910181-20026-11-git-send-email-glommer@openvz.org \
    --to=glommer-gefaqzzx7r8dnm+yrofe0a@public.gmane.org \
    --cc=akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org \
    --cc=cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=david-FqsqvQoI3Ljby3iVrkZq2A@public.gmane.org \
    --cc=dchinner-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    --cc=gthelen-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
    --cc=hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org \
    --cc=hughd-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
    --cc=kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org \
    --cc=linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org \
    --cc=mgorman-l3A5Bk7waGM@public.gmane.org \
    --cc=mhocko-AlSwsSmVLrQ@public.gmane.org \
    /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).