From: zwu.kernel@gmail.com
To: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, viro@zeniv.linux.org.uk,
david@fromorbit.com, dave@jikos.cz, darrick.wong@oracle.com,
andi@firstfloor.org, hch@infradead.org,
linuxram@linux.vnet.ibm.com, zwu.kernel@gmail.com,
wuzhy@linux.vnet.ibm.com
Subject: [PATCH RESEND v1 03/16] vfs: add I/O frequency update function
Date: Thu, 20 Dec 2012 22:43:22 +0800 [thread overview]
Message-ID: <1356014615-15073-4-git-send-email-zwu.kernel@gmail.com> (raw)
In-Reply-To: <1356014615-15073-1-git-send-email-zwu.kernel@gmail.com>
From: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
Add some util helpers to update access frequencies
for one file or its range.
Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
---
fs/hot_tracking.c | 178 ++++++++++++++++++++++++++++++++++++++++++
fs/hot_tracking.h | 5 +
include/linux/hot_tracking.h | 4 +
3 files changed, 187 insertions(+), 0 deletions(-)
diff --git a/fs/hot_tracking.c b/fs/hot_tracking.c
index a73477c..6f587fa 100644
--- a/fs/hot_tracking.c
+++ b/fs/hot_tracking.c
@@ -164,6 +164,135 @@ static void hot_inode_tree_exit(struct hot_info *root)
spin_unlock(&root->lock);
}
+struct hot_inode_item
+*hot_inode_item_lookup(struct hot_info *root, u64 ino)
+{
+ struct rb_node **p = &root->hot_inode_tree.map.rb_node;
+ struct rb_node *parent = NULL;
+ struct hot_comm_item *ci;
+ struct hot_inode_item *entry;
+
+ /* walk tree to find insertion point */
+ spin_lock(&root->lock);
+ while (*p) {
+ parent = *p;
+ ci = rb_entry(parent, struct hot_comm_item, rb_node);
+ entry = container_of(ci, struct hot_inode_item, hot_inode);
+ if (ino < entry->i_ino)
+ p = &(*p)->rb_left;
+ else if (ino > entry->i_ino)
+ p = &(*p)->rb_right;
+ else {
+ spin_unlock(&root->lock);
+ kref_get(&entry->hot_inode.refs);
+ return entry;
+ }
+ }
+ spin_unlock(&root->lock);
+
+ entry = kmem_cache_zalloc(hot_inode_item_cachep, GFP_NOFS);
+ if (!entry)
+ return ERR_PTR(-ENOMEM);
+
+ spin_lock(&root->lock);
+ hot_inode_item_init(entry, ino, &root->hot_inode_tree);
+ rb_link_node(&entry->hot_inode.rb_node, parent, p);
+ rb_insert_color(&entry->hot_inode.rb_node,
+ &root->hot_inode_tree.map);
+ spin_unlock(&root->lock);
+
+ kref_get(&entry->hot_inode.refs);
+ return entry;
+}
+EXPORT_SYMBOL_GPL(hot_inode_item_lookup);
+
+static loff_t hot_range_end(struct hot_range_item *hr)
+{
+ if (hr->start + hr->len < hr->start)
+ return (loff_t)-1;
+
+ return hr->start + hr->len - 1;
+}
+
+static struct hot_range_item
+*hot_range_item_lookup(struct hot_inode_item *he,
+ loff_t start)
+{
+ struct rb_node **p = &he->hot_range_tree.map.rb_node;
+ struct rb_node *parent = NULL;
+ struct hot_comm_item *ci;
+ struct hot_range_item *entry;
+
+ /* walk tree to find insertion point */
+ spin_lock(&he->lock);
+ while (*p) {
+ parent = *p;
+ ci = rb_entry(parent, struct hot_comm_item, rb_node);
+ entry = container_of(ci, struct hot_range_item, hot_range);
+ if (start < entry->start)
+ p = &(*p)->rb_left;
+ else if (start > hot_range_end(entry))
+ p = &(*p)->rb_right;
+ else {
+ spin_unlock(&he->lock);
+ kref_get(&entry->hot_range.refs);
+ return entry;
+ }
+ }
+ spin_unlock(&he->lock);
+
+ entry = kmem_cache_zalloc(hot_range_item_cachep, GFP_NOFS);
+ if (!entry)
+ return ERR_PTR(-ENOMEM);
+
+ spin_lock(&he->lock);
+ hot_range_item_init(entry, start, he);
+ rb_link_node(&entry->hot_range.rb_node, parent, p);
+ rb_insert_color(&entry->hot_range.rb_node,
+ &he->hot_range_tree.map);
+ spin_unlock(&he->lock);
+
+ kref_get(&entry->hot_range.refs);
+ return entry;
+}
+
+/*
+ * This function does the actual work of updating
+ * the frequency numbers, whatever they turn out to be.
+ */
+static void hot_rw_freq_calc(struct timespec old_atime,
+ struct timespec cur_time, u64 *avg)
+{
+ struct timespec delta_ts;
+ u64 new_delta;
+
+ delta_ts = timespec_sub(cur_time, old_atime);
+ new_delta = timespec_to_ns(&delta_ts) >> FREQ_POWER;
+
+ *avg = (*avg << FREQ_POWER) - *avg + new_delta;
+ *avg = *avg >> FREQ_POWER;
+}
+
+static void hot_freq_data_update(struct hot_freq_data *freq_data, bool write)
+{
+ struct timespec cur_time = current_kernel_time();
+
+ if (write) {
+ freq_data->nr_writes += 1;
+ hot_rw_freq_calc(freq_data->last_write_time,
+ cur_time,
+ &freq_data->avg_delta_writes);
+ freq_data->last_write_time = cur_time;
+ } else {
+ freq_data->nr_reads += 1;
+ hot_rw_freq_calc(freq_data->last_read_time,
+ freq_data->last_read_time,
+ cur_time,
+ &freq_data->avg_delta_reads);
+ freq_data->last_read_time = cur_time;
+ }
+}
+
/*
* Initialize kmem cache for hot_inode_item and hot_range_item.
*/
@@ -191,6 +320,55 @@ err:
EXPORT_SYMBOL_GPL(hot_cache_init);
/*
+ * Main function to update access frequency from read/writepage(s) hooks
+ */
+void hot_update_freqs(struct inode *inode, loff_t start,
+ size_t len, int rw)
+{
+ struct hot_info *root = inode->i_sb->s_hot_root;
+ struct hot_inode_item *he;
+ struct hot_range_item *hr;
+ loff_t cur, end;
+
+ if (!root || (len == 0))
+ return;
+
+ he = hot_inode_item_lookup(root, inode->i_ino);
+ if (IS_ERR(he)) {
+ WARN_ON(1);
+ return;
+ }
+
+ spin_lock(&he->hot_inode.lock);
+ hot_freq_data_update(&he->hot_inode.hot_freq_data, rw);
+ spin_unlock(&he->hot_inode.lock);
+
+ /*
+ * Align ranges on RANGE_SIZE boundary
+ * to prevent proliferation of range structs
+ */
+ end = (start + len + RANGE_SIZE - 1) >> RANGE_BITS;
+ for (cur = (start >> RANGE_BITS); cur < end; cur++) {
+ hr = hot_range_item_lookup(he, cur);
+ if (IS_ERR(hr)) {
+ WARN(1, "hot_range_item_lookup returns %ld\n",
+ PTR_ERR(hr));
+ hot_inode_item_put(he);
+ return;
+ }
+
+ spin_lock(&hr->hot_range.lock);
+ hot_freq_data_update(&hr->hot_range.hot_freq_data, rw);
+ spin_unlock(&hr->hot_range.lock);
+
+ hot_range_item_put(hr);
+ }
+
+ hot_inode_item_put(he);
+}
+EXPORT_SYMBOL_GPL(hot_update_freqs);
+
+/*
* Initialize the data structures for hot data tracking.
*/
int hot_track_init(struct super_block *sb)
diff --git a/fs/hot_tracking.h b/fs/hot_tracking.h
index d58a461..8571186 100644
--- a/fs/hot_tracking.h
+++ b/fs/hot_tracking.h
@@ -19,4 +19,9 @@
#define FREQ_DATA_TYPE_INODE (1 << 0)
#define FREQ_DATA_TYPE_RANGE (1 << 1)
+/* size of sub-file ranges */
+#define RANGE_BITS 20
+#define RANGE_SIZE (1 << RANGE_BITS)
+#define FREQ_POWER 4
+
#endif /* __HOT_TRACKING__ */
diff --git a/include/linux/hot_tracking.h b/include/linux/hot_tracking.h
index 3b0dfcf..d555046 100644
--- a/include/linux/hot_tracking.h
+++ b/include/linux/hot_tracking.h
@@ -77,5 +77,9 @@ extern void __init hot_cache_init(void);
extern int hot_track_init(struct super_block *sb);
extern void hot_track_exit(struct super_block *sb);
extern void hot_inode_item_put(struct hot_inode_item *he);
+extern void hot_update_freqs(struct inode *inode, loff_t start,
+ size_t len, int rw);
+extern struct hot_inode_item *hot_inode_item_lookup(struct hot_info *root,
+ u64 ino);
#endif /* _LINUX_HOTTRACK_H */
--
1.7.6.5
next prev parent reply other threads:[~2012-12-20 14:44 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-12-20 14:43 [PATCH RESEND v1 00/16] vfs: hot data tracking zwu.kernel
2012-12-20 14:43 ` [PATCH RESEND v1 01/16] vfs: introduce some data structures zwu.kernel
2013-01-10 0:48 ` David Sterba
2013-01-10 6:24 ` Zhi Yong Wu
2012-12-20 14:43 ` [PATCH RESEND v1 02/16] vfs: add init and cleanup functions zwu.kernel
2013-01-10 0:48 ` David Sterba
2013-01-11 7:21 ` Zhi Yong Wu
2012-12-20 14:43 ` zwu.kernel [this message]
2013-01-10 0:51 ` [PATCH RESEND v1 03/16] vfs: add I/O frequency update function David Sterba
2013-01-11 7:38 ` Zhi Yong Wu
2013-01-11 14:27 ` David Sterba
2013-01-11 14:54 ` Zhi Yong Wu
2012-12-20 14:43 ` [PATCH RESEND v1 04/16] vfs: add two map arrays zwu.kernel
2013-01-10 0:51 ` David Sterba
2012-12-20 14:43 ` [PATCH RESEND v1 05/16] vfs: add hooks to enable hot tracking zwu.kernel
2013-01-10 0:52 ` David Sterba
2013-01-11 7:47 ` Zhi Yong Wu
2012-12-20 14:43 ` [PATCH RESEND v1 06/16] vfs: add temp calculation function zwu.kernel
2013-01-10 0:53 ` David Sterba
2013-01-11 8:08 ` Zhi Yong Wu
2012-12-20 14:43 ` [PATCH RESEND v1 07/16] vfs: add map info update function zwu.kernel
2012-12-20 14:43 ` [PATCH RESEND v1 08/16] vfs: add aging function zwu.kernel
2012-12-20 14:43 ` [PATCH RESEND v1 09/16] vfs: add one work queue zwu.kernel
2012-12-20 14:43 ` [PATCH RESEND v1 10/16] vfs: add FS hot type support zwu.kernel
2012-12-20 14:43 ` [PATCH RESEND v1 11/16] vfs: register one shrinker zwu.kernel
2012-12-20 14:43 ` [PATCH RESEND v1 12/16] vfs: add one ioctl interface zwu.kernel
2012-12-20 14:43 ` [PATCH RESEND v1 13/16] vfs: add debugfs support zwu.kernel
2012-12-20 14:43 ` [PATCH RESEND v1 14/16] proc: add two hot_track proc files zwu.kernel
2012-12-20 14:43 ` [PATCH RESEND v1 15/16] btrfs: add hot tracking support zwu.kernel
2012-12-20 14:43 ` [PATCH RESEND v1 16/16] vfs: add documentation zwu.kernel
2012-12-20 14:55 ` [PATCH RESEND v1 00/16] vfs: hot data tracking Zhi Yong Wu
2013-01-07 13:49 ` Zhi Yong Wu
2013-01-08 7:52 ` Zhi Yong Wu
2013-02-22 0:32 ` Zhi Yong Wu
2013-02-25 11:40 ` David Sterba
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=1356014615-15073-4-git-send-email-zwu.kernel@gmail.com \
--to=zwu.kernel@gmail.com \
--cc=andi@firstfloor.org \
--cc=darrick.wong@oracle.com \
--cc=dave@jikos.cz \
--cc=david@fromorbit.com \
--cc=hch@infradead.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxram@linux.vnet.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).