From: zwu.kernel@gmail.com
To: linux-fsdevel@vger.kernel.org
Cc: linux-ext4@vger.kernel.org, linux-btrfs@vger.kernel.org,
linux-kernel@vger.kernel.org, linuxram@linux.vnet.ibm.com,
viro@zeniv.linux.org.uk, david@fromorbit.com, tytso@mit.edu,
cmm@us.ibm.com, Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
Subject: [RFC v4 09/15] vfs,hot_track: register one memory shrinker
Date: Thu, 25 Oct 2012 23:09:01 +0800 [thread overview]
Message-ID: <1351177747-19389-10-git-send-email-zwu.kernel@gmail.com> (raw)
In-Reply-To: <1351177747-19389-1-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 (i.e. the shrinker
accelerates the aging process).
Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
---
fs/hot_tracking.c | 61 ++++++++++++++++++++++++++++++++++++++++++
include/linux/hot_tracking.h | 1 +
2 files changed, 62 insertions(+), 0 deletions(-)
diff --git a/fs/hot_tracking.c b/fs/hot_tracking.c
index d931083..7d2c53d 100644
--- a/fs/hot_tracking.c
+++ b/fs/hot_tracking.c
@@ -678,6 +678,61 @@ err:
kmem_cache_destroy(hot_inode_item_cachep);
}
+static int hot_track_prune_map(struct hot_map_head *map_head,
+ bool type, int nr)
+{
+ struct hot_comm_item *node;
+ int i;
+
+ for (i = 0; i < HEAT_MAP_SIZE; i++) {
+ while (!list_empty(&(map_head + i)->node_list)) {
+ if (nr-- <= 0)
+ break;
+
+ node = list_first_entry(&(map_head + i)->node_list,
+ struct hot_comm_item, n_list);
+ if (type) {
+ struct hot_inode_item *hot_inode =
+ container_of(node,
+ struct hot_inode_item, hot_inode);
+ hot_inode_item_put(hot_inode);
+ } else {
+ struct hot_range_item *hot_range =
+ container_of(node,
+ struct hot_range_item, hot_range);
+ hot_range_item_put(hot_range);
+ }
+ }
+ }
+
+ return nr;
+}
+
+/* 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);
+ int ret;
+
+ if (sc->nr_to_scan == 0)
+ return root->hot_map_nr;
+
+ if (!(sc->gfp_mask & __GFP_FS))
+ return -1;
+
+ ret = hot_track_prune_map(root->heat_range_map,
+ false, sc->nr_to_scan);
+ if (ret > 0)
+ ret = hot_track_prune_map(root->heat_inode_map,
+ true, ret);
+ if (ret > 0)
+ root->hot_map_nr -= (sc->nr_to_scan - ret);
+
+ return root->hot_map_nr;
+}
+
/*
* Main function to update access frequency from read/writepage(s) hooks
*/
@@ -758,6 +813,11 @@ int hot_track_init(struct super_block *sb)
queue_delayed_work(root->update_wq, &root->update_work,
msecs_to_jiffies(HEAT_UPDATE_DELAY * 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);
+
printk(KERN_INFO "VFS: Turning on hot data tracking\n");
return 0;
@@ -774,6 +834,7 @@ void hot_track_exit(struct super_block *sb)
{
struct hot_info *root = sb->s_hot_root;
+ unregister_shrinker(&root->hot_shrink);
cancel_delayed_work_sync(&root->update_work);
destroy_workqueue(root->update_wq);
hot_map_array_exit(root);
diff --git a/include/linux/hot_tracking.h b/include/linux/hot_tracking.h
index 4c5f5f3..446c99e 100644
--- a/include/linux/hot_tracking.h
+++ b/include/linux/hot_tracking.h
@@ -85,6 +85,7 @@ struct hot_info {
struct workqueue_struct *update_wq;
struct delayed_work update_work;
+ struct shrinker hot_shrink;
};
void __init hot_cache_init(void);
--
1.7.6.5
next prev parent reply other threads:[~2012-10-25 15:09 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-10-25 15:08 [RFC v4 00/15] vfs: hot data tracking zwu.kernel
2012-10-25 15:08 ` [RFC v4 01/15] vfs,hot_track: introduce private radix tree structures zwu.kernel
2012-10-25 15:08 ` [RFC v4 02/15] vfs,hot_track: initialize and free key data structures zwu.kernel
2012-10-25 15:08 ` [RFC v4 03/15] vfs,hot_track: add the function for collecting I/O frequency zwu.kernel
2012-10-28 7:55 ` Zheng Liu
2012-10-28 13:51 ` Zhi Yong Wu
2012-10-29 2:01 ` Dave Chinner
2012-10-29 2:14 ` Zhi Yong Wu
2012-10-25 15:08 ` [RFC v4 04/15] vfs,hot_track: add two map arrays zwu.kernel
2012-10-25 15:08 ` [RFC v4 05/15] vfs,hot_track: add hooks to enable hot data tracking zwu.kernel
2012-10-25 15:08 ` [RFC v4 06/15] vfs,hot_track: add the function for updating map arrays zwu.kernel
2012-10-25 15:08 ` [RFC v4 07/15] vfs,hot_track: add the aging function zwu.kernel
2012-10-25 15:09 ` [RFC v4 08/15] vfs,hot_track: add one work queue zwu.kernel
2012-10-25 15:09 ` zwu.kernel [this message]
2012-10-25 15:09 ` [RFC v4 10/15] vfs,hot_track: add one new ioctl interface zwu.kernel
2012-10-25 15:09 ` [RFC v4 11/15] vfs,hot_track: add debugfs support zwu.kernel
2012-10-25 15:09 ` [RFC v4 12/15] vfs,hot_track: turn some Micro into be tunable zwu.kernel
2012-10-25 15:09 ` [RFC v4 13/15] btrfs: add hot tracking support zwu.kernel
2012-10-25 15:09 ` [RFC v4 14/15] xfs: " zwu.kernel
2012-10-25 15:09 ` [RFC v4 15/15] vfs,hot_track: add the documentation zwu.kernel
2012-10-28 9:22 ` [PATCH] ext4: add hot tracking support Zheng Liu
2012-10-28 13:45 ` Zhi Yong Wu
2012-10-29 2:32 ` Zheng Liu
2012-10-29 2:24 ` Zhi Yong Wu
2012-11-07 8:37 ` Zhi Yong Wu
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=1351177747-19389-10-git-send-email-zwu.kernel@gmail.com \
--to=zwu.kernel@gmail.com \
--cc=cmm@us.ibm.com \
--cc=david@fromorbit.com \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxram@linux.vnet.ibm.com \
--cc=tytso@mit.edu \
--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).