linux-fsdevel.vger.kernel.org archive mirror
 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 07/10] VFS hot tracking: Add two /proc interfaces to control memory usage
Date: Mon,  5 Aug 2013 22:49:57 +0800	[thread overview]
Message-ID: <1375714200-23944-8-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>

Introduce two proc interfaces hot-mem-high-thresh and
hot-mem-low-thresh to cap the memory which is consumed by
hot_inode_item and hot_range_item, and they will be in
the unit of 1M bytes.

Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com>
Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
---
 fs/hot_tracking.c            | 32 ++++++++++++++++++++++++++++++++
 fs/hot_tracking.h            | 23 +++++++++++++++++++++++
 include/linux/hot_tracking.h |  4 ++++
 kernel/sysctl.c              | 14 ++++++++++++++
 4 files changed, 73 insertions(+)

diff --git a/fs/hot_tracking.c b/fs/hot_tracking.c
index a3742b7..3a08b66 100644
--- a/fs/hot_tracking.c
+++ b/fs/hot_tracking.c
@@ -15,6 +15,12 @@
 #include <linux/list_sort.h>
 #include "hot_tracking.h"
 
+int sysctl_hot_mem_high_thresh __read_mostly = 0;
+EXPORT_SYMBOL_GPL(sysctl_hot_mem_high_thresh);
+
+int sysctl_hot_mem_low_thresh __read_mostly = 0;
+EXPORT_SYMBOL_GPL(sysctl_hot_mem_low_thresh);
+
 int sysctl_hot_update_interval __read_mostly = 150;
 EXPORT_SYMBOL_GPL(sysctl_hot_update_interval);
 
@@ -44,6 +50,7 @@ static void hot_range_item_init(struct hot_range_item *hr,
 	hr->len = hot_bit_shift(1, RANGE_BITS, true);
 	hr->hot_inode = he;
 	atomic_long_inc(&he->hot_root->hot_cnt);
+	hot_mem_limit_add(he->hot_root, sizeof(struct hot_range_item));
 }
 
 static void hot_range_item_free_cb(struct rcu_head *head)
@@ -53,6 +60,7 @@ static void hot_range_item_free_cb(struct rcu_head *head)
 	struct hot_info *root = hr->hot_inode->hot_root;
 
 	atomic_long_dec(&root->hot_cnt);
+	hot_mem_limit_sub(root, sizeof(struct hot_range_item));
 	kmem_cache_free(hot_range_item_cachep, hr);
 }
 
@@ -238,6 +246,7 @@ static void hot_inode_item_init(struct hot_inode_item *he,
 	he->hot_root = root;
 	spin_lock_init(&he->i_lock);
 	atomic_long_inc(&root->hot_cnt);
+	hot_mem_limit_add(root, sizeof(struct hot_inode_item));
 }
 
 static void hot_inode_item_free_cb(struct rcu_head *head)
@@ -247,6 +256,7 @@ static void hot_inode_item_free_cb(struct rcu_head *head)
 	struct hot_info *root = he->hot_root;
 
 	atomic_long_dec(&root->hot_cnt);
+	hot_mem_limit_sub(root, sizeof(struct hot_inode_item));
 	kmem_cache_free(hot_inode_item_cachep, he);
 }
 
@@ -559,6 +569,25 @@ static void hot_item_evict(struct hot_info *root, unsigned long work,
 	}
 }
 
+static void hot_mem_evict(struct hot_info *root)
+{
+	unsigned long sum, thresh;
+
+	if (sysctl_hot_mem_low_thresh == 0 ||
+		sysctl_hot_mem_high_thresh == 0 ||
+		(sysctl_hot_mem_high_thresh < sysctl_hot_mem_low_thresh))
+		return;
+
+	sum = hot_mem_limit_sum(root);
+	/* Note: sysctl_** is in the unit of 1M bytes */
+	thresh = sysctl_hot_mem_high_thresh;
+	thresh *= 1024 * 1024;
+	if (sum <= thresh)
+		return;
+
+	hot_item_evict(root, sum - thresh, hot_mem_limit_sum);
+}
+
 /*
  * Every sync period we update temperatures for
  * each hot inode item and hot range item for aging
@@ -572,6 +601,8 @@ static void hot_update_worker(struct work_struct *work)
 	struct rb_node *node;
 	int i;
 
+	hot_mem_evict(root);
+
 	rcu_read_lock();
 	node = rb_first(&root->hot_inode_tree);
 	while (node) {
@@ -785,6 +816,7 @@ int hot_track_init(struct super_block *sb)
 		goto err;
 	}
 
+	hot_mem_limit_init(root);
 	sb->s_hot_root = root;
 
 	printk(KERN_INFO "VFS: Turning on hot tracking\n");
diff --git a/fs/hot_tracking.h b/fs/hot_tracking.h
index 23b1339..c9efa5b 100644
--- a/fs/hot_tracking.h
+++ b/fs/hot_tracking.h
@@ -40,4 +40,27 @@
 #define AVW_DIVIDER_POWER 40 /* AVW - average delta between recent writes(ns) */
 #define AVW_COEFF_POWER 0
 
+/* Memory Tracking Functions. */
+static inline unsigned long hot_mem_limit_sum(struct hot_info *root)
+{
+	return atomic_long_read(&root->mem);
+}
+
+static inline void hot_mem_limit_sub(struct hot_info *root,
+				unsigned long count)
+{
+	atomic_long_sub(count, &root->mem);
+}
+
+static inline void hot_mem_limit_add(struct hot_info *root,
+				unsigned long count)
+{
+	atomic_long_add(count, &root->mem);
+}
+
+static inline void hot_mem_limit_init(struct hot_info *root)
+{
+	atomic_long_set(&root->mem, 0);
+}
+
 #endif /* __HOT_TRACKING__ */
diff --git a/include/linux/hot_tracking.h b/include/linux/hot_tracking.h
index 92e3547..64e1c8a 100644
--- a/include/linux/hot_tracking.h
+++ b/include/linux/hot_tracking.h
@@ -99,10 +99,14 @@ struct hot_info {
 	struct workqueue_struct *update_wq;
 	struct delayed_work update_work;
 	struct shrinker hot_shrink;
+	atomic_long_t mem;
 };
 
 /* set how often to update temperatures (seconds) */
 extern int sysctl_hot_update_interval;
+/* note: sysctl_** is in the unit of 1M bytes */
+extern int sysctl_hot_mem_high_thresh;
+extern int sysctl_hot_mem_low_thresh;
 
 /*
  * Hot data tracking ioctls:
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 398cc05..c56aa34 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1632,6 +1632,20 @@ static struct ctl_table fs_table[] = {
 		.extra1		= &pipe_min_size,
 	},
 	{
+		.procname       = "hot-mem-high-thresh",
+		.data           = &sysctl_hot_mem_high_thresh,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{
+		.procname       = "hot-mem-low-thresh",
+		.data           = &sysctl_hot_mem_low_thresh,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{
 		.procname	= "hot-update-interval",
 		.data		= &sysctl_hot_update_interval,
 		.maxlen		= sizeof(int),
-- 
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 ` [PATCH v4 04/10] VFS hot tracking: Add shrinker functionality to curtail memory usage zwu.kernel
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 ` zwu.kernel [this message]
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=1375714200-23944-8-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 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).