From: Zhi Yong Wu <wu...@linux.vnet.ibm.com>
Add some util helpers to update access frequencies
for one file or its range.
Signed-off-by: Zhi Yong Wu <wu...@linux.vnet.ibm.com>
---
fs/hot_tracking.c | 174 ++++++++++++++++++++++++++++++++++++++++++
fs/hot_tracking.h | 5 +
include/linux/hot_tracking.h | 4 +
3 files changed, 183 insertions(+), 0 deletions(-)
diff --git a/fs/hot_tracking.c b/fs/hot_tracking.c
index 3118c0b..1142ef1 100644
--- a/fs/hot_tracking.c
+++ b/fs/hot_tracking.c
@@ -173,6 +173,131 @@ static void hot_inode_tree_exit(struct hot_info *root)
}
}
+struct hot_inode_item
+*hot_inode_item_lookup(struct hot_info *root, unsigned long ino)
+{
+ struct hot_inode_item *he;
+ int ret;
+
+again:
+ spin_lock(&root->lock);
+ he = radix_tree_lookup(&root->hot_inode_tree, ino);
+ if (he) {
+ kref_get(&he->hot_inode.refs);
+ spin_unlock(&root->lock);
+ return he;
+ }
+ spin_unlock(&root->lock);
+
+ he = kmem_cache_zalloc(hot_inode_item_cachep, GFP_NOFS);
+ if (!he)
+ return ERR_PTR(-ENOMEM);
+
+ hot_inode_item_init(he, ino, &root->hot_inode_tree);
+
+ ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+ if (ret) {
+ kmem_cache_free(hot_inode_item_cachep, he);
+ return ERR_PTR(ret);
+ }
+
+ spin_lock(&root->lock);
+ ret = radix_tree_insert(&root->hot_inode_tree, ino, he);
+ if (ret == -EEXIST) {
+ kmem_cache_free(hot_inode_item_cachep, he);
+ spin_unlock(&root->lock);
+ radix_tree_preload_end();
+ goto again;
+ }
+ spin_unlock(&root->lock);
+ radix_tree_preload_end();
+
+ kref_get(&he->hot_inode.refs);
+ return he;
+}
+EXPORT_SYMBOL_GPL(hot_inode_item_lookup);
+
+static struct hot_range_item
+*hot_range_item_lookup(struct hot_inode_item *he,
+ loff_t start)
+{
+ struct hot_range_item *hr;
+ int ret;
+
+again:
+ spin_lock(&he->lock);
+ hr = radix_tree_lookup(&he->hot_range_tree, start);
+ if (hr) {
+ kref_get(&hr->hot_range.refs);
+ spin_unlock(&he->lock);
+ return hr;
+ }
+ spin_unlock(&he->lock);
+
+ hr = kmem_cache_zalloc(hot_range_item_cachep, GFP_NOFS);
+ if (!hr)
+ return ERR_PTR(-ENOMEM);
+
+ hot_range_item_init(hr, start, he);
+
+ ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+ if (ret) {
+ kmem_cache_free(hot_range_item_cachep, hr);
+ return ERR_PTR(ret);
+ }
+
+ spin_lock(&he->lock);
+ ret = radix_tree_insert(&he->hot_range_tree, start, hr);
+ if (ret == -EEXIST) {
+ kmem_cache_free(hot_range_item_cachep, hr);
+ spin_unlock(&he->lock);
+ radix_tree_preload_end();
+ goto again;
+ }
+ spin_unlock(&he->lock);
+ radix_tree_preload_end();
+
+ kref_get(&hr->hot_range.refs);
+ return hr;
+}
+
+/*
+ * 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.
*/
@@ -200,6 +325,55 @@ 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 febf699..7f279af 100644
--- a/fs/hot_tracking.h
+++ b/fs/hot_tracking.h
@@ -20,4 +20,9 @@
#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 1c364f6..3797cf0 100644
--- a/include/linux/hot_tracking.h
+++ b/include/linux/hot_tracking.h
@@ -72,5 +72,9 @@ 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,
+ unsigned long ino);
#endif /* _LINUX_HOTTRACK_H */
--
1.7.6.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
