All of lore.kernel.org
 help / color / mirror / Atom feed
From: zwu.kernel@gmail.com
To: viro@zeniv.linux.org.uk
Cc: linux-fsdevel@vger.kernel.org, sekharan@us.ibm.com,
	Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
Subject: [PATCH v4 04/10] VFS hot tracking: Add shrinker functionality to curtail memory usage
Date: Mon,  5 Aug 2013 22:49:54 +0800	[thread overview]
Message-ID: <1375714200-23944-5-git-send-email-zwu.kernel@gmail.com> (raw)
In-Reply-To: <1375714200-23944-1-git-send-email-zwu.kernel@gmail.com>

From: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>

Register a shrinker to control the amount of memory that
is used in tracking hot regions. If we are throwing inodes
out of memory due to memory pressure, we most definitely are
going to need to reduce the amount of memory the tracking
code is using, even if it means losing useful information.

Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com>
Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
---
 fs/hot_tracking.c            | 74 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/hot_tracking.h |  2 ++
 2 files changed, 76 insertions(+)

diff --git a/fs/hot_tracking.c b/fs/hot_tracking.c
index 857d423..037d5db 100644
--- a/fs/hot_tracking.c
+++ b/fs/hot_tracking.c
@@ -40,13 +40,16 @@ static void hot_range_item_init(struct hot_range_item *hr,
 	hr->start = start;
 	hr->len = hot_bit_shift(1, RANGE_BITS, true);
 	hr->hot_inode = he;
+	atomic_long_inc(&he->hot_root->hot_cnt);
 }
 
 static void hot_range_item_free_cb(struct rcu_head *head)
 {
 	struct hot_range_item *hr = container_of(head,
 				struct hot_range_item, rcu);
+	struct hot_info *root = hr->hot_inode->hot_root;
 
+	atomic_long_dec(&root->hot_cnt);
 	kmem_cache_free(hot_range_item_cachep, hr);
 }
 
@@ -231,13 +234,16 @@ static void hot_inode_item_init(struct hot_inode_item *he,
 	he->i_ino = ino;
 	he->hot_root = root;
 	spin_lock_init(&he->i_lock);
+	atomic_long_inc(&root->hot_cnt);
 }
 
 static void hot_inode_item_free_cb(struct rcu_head *head)
 {
 	struct hot_inode_item *he = container_of(head,
 				struct hot_inode_item, rcu);
+	struct hot_info *root = he->hot_root;
 
+	atomic_long_dec(&root->hot_cnt);
 	kmem_cache_free(hot_inode_item_cachep, he);
 }
 
@@ -517,6 +523,39 @@ u32 hot_temp_calc(struct hot_freq *freq)
 	return result;
 }
 
+static void hot_item_evict(struct hot_info *root, unsigned long work,
+			unsigned long (*work_get)(struct hot_info *root))
+{
+	int i;
+
+	if (work <= 0)
+		return;
+
+	for (i = 0; i < MAP_SIZE; i++) {
+		struct hot_inode_item *he, *next;
+		unsigned long work_prev;
+
+		spin_lock(&root->t_lock);
+		if (list_empty(&root->hot_map[TYPE_INODE][i])) {
+			spin_unlock(&root->t_lock);
+			continue;
+		}
+
+		list_for_each_entry_safe(he, next,
+			&root->hot_map[TYPE_INODE][i], track_list) {
+			work_prev = work_get(root);
+			hot_inode_item_put(he);
+			work -= (work_prev - work_get(root));
+			if (work <= 0)
+				break;
+		}
+		spin_unlock(&root->t_lock);
+
+		if (work <= 0)
+			break;
+	}
+}
+
 /*
  * Every sync period we update temperatures for
  * each hot inode item and hot range item for aging
@@ -579,6 +618,34 @@ void __init hot_cache_init(void)
 }
 EXPORT_SYMBOL_GPL(hot_cache_init);
 
+static inline unsigned long hot_cnt_get(struct hot_info *root)
+{
+	return (unsigned long)atomic_long_read(&root->hot_cnt);
+}
+
+static void hot_prune_map(struct hot_info *root, unsigned long nr)
+{
+	hot_item_evict(root, nr, hot_cnt_get);
+}
+
+/* The shrinker callback function */
+static int hot_track_prune(struct shrinker *shrink,
+			struct shrink_control *sc)
+{
+	struct hot_info *root =
+		container_of(shrink, struct hot_info, hot_shrink);
+
+	if (sc->nr_to_scan == 0)
+		return atomic_long_read(&root->hot_cnt) / 2;
+
+	if (!(sc->gfp_mask & __GFP_FS))
+		return -1;
+
+	hot_prune_map(root, sc->nr_to_scan);
+
+	return atomic_long_read(&root->hot_cnt);
+}
+
 /*
  * Main function to update i/o access frequencies, and it will be called
  * from read/writepages() hooks, which are read_pages(), do_writepages(),
@@ -643,6 +710,7 @@ static struct hot_info *hot_tree_init(struct super_block *sb)
 	root->hot_inode_tree = RB_ROOT;
 	spin_lock_init(&root->t_lock);
 	spin_lock_init(&root->m_lock);
+	atomic_long_set(&root->hot_cnt, 0);
 
 	for (i = 0; i < MAP_SIZE; i++) {
 		for (j = 0; j < MAX_TYPES; j++)
@@ -663,6 +731,11 @@ static struct hot_info *hot_tree_init(struct super_block *sb)
 	queue_delayed_work(root->update_wq, &root->update_work,
 		msecs_to_jiffies(HOT_UPDATE_INTERVAL * MSEC_PER_SEC));
 
+	/* Register a shrinker callback */
+	root->hot_shrink.shrink = hot_track_prune;
+	root->hot_shrink.seeks = DEFAULT_SEEKS;
+	register_shrinker(&root->hot_shrink);
+
 	return root;
 }
 
@@ -673,6 +746,7 @@ static void hot_tree_exit(struct hot_info *root)
 {
 	struct rb_node *node;
 
+	unregister_shrinker(&root->hot_shrink);
 	cancel_delayed_work_sync(&root->update_work);
 	destroy_workqueue(root->update_wq);
 
diff --git a/include/linux/hot_tracking.h b/include/linux/hot_tracking.h
index 9095859..adac767 100644
--- a/include/linux/hot_tracking.h
+++ b/include/linux/hot_tracking.h
@@ -82,8 +82,10 @@ struct hot_info {
 	struct list_head hot_map[MAX_TYPES][MAP_SIZE];	/* map of inode temp */
 	spinlock_t t_lock;		/* protect tree and map for inode item */
 	spinlock_t m_lock;		/* protect map for range item */
+	atomic_long_t hot_cnt;
 	struct workqueue_struct *update_wq;
 	struct delayed_work update_work;
+	struct shrinker hot_shrink;
 };
 
 extern void __init hot_cache_init(void);
-- 
1.7.11.7


  parent reply	other threads:[~2013-08-05 14:49 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-08-05 14:49 [PATCH v4 00/10] VFS hot tracking zwu.kernel
2013-08-05 14:49 ` [PATCH v4 01/10] VFS hot tracking: Define basic data structures and functions zwu.kernel
2013-08-05 14:49 ` [PATCH v4 02/10] VFS hot tracking: Track IO and record heat information zwu.kernel
2013-08-05 14:49 ` [PATCH v4 03/10] VFS hot tracking: Add a workqueue to move items between hot maps zwu.kernel
2013-08-05 14:49 ` zwu.kernel [this message]
2013-08-05 14:49 ` [PATCH v4 05/10] VFS hot tracking: Add an ioctl to get hot tracking information zwu.kernel
2013-08-05 14:49 ` [PATCH v4 06/10] VFS hot tracking: Add a /proc interface to make the interval tunable zwu.kernel
2013-08-05 14:49 ` [PATCH v4 07/10] VFS hot tracking: Add two /proc interfaces to control memory usage zwu.kernel
2013-08-05 14:49 ` [PATCH v4 08/10] VFS hot tracking: Add documentation zwu.kernel
2013-08-05 14:49 ` [PATCH v4 09/10] VFS hot tracking, btrfs: Add hot tracking support zwu.kernel
2013-08-05 14:50 ` [PATCH v4 10/10] VFS hot tracking, xfs: " zwu.kernel

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=1375714200-23944-5-git-send-email-zwu.kernel@gmail.com \
    --to=zwu.kernel@gmail.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=sekharan@us.ibm.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=wuzhy@linux.vnet.ibm.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.