Hi,
On Mon, 2012-10-29 at 12:30 +0800, zwu.kernel@xxxxxxxxx wrote:
> From: Zhi Yong Wu <wuzhy@xxxxxxxxxxxxxxxxxx>
>
> Add a per-superblock workqueue and a delayed_work
> to run periodic work to update map info on each superblock.
>
> Signed-off-by: Zhi Yong Wu <wuzhy@xxxxxxxxxxxxxxxxxx>
> ---
> fs/hot_tracking.c | 85 ++++++++++++++++++++++++++++++++++++++++++
> fs/hot_tracking.h | 3 +
> include/linux/hot_tracking.h | 3 +
> 3 files changed, 91 insertions(+), 0 deletions(-)
>
> diff --git a/fs/hot_tracking.c b/fs/hot_tracking.c
> index fff0038..0ef9cad 100644
> --- a/fs/hot_tracking.c
> +++ b/fs/hot_tracking.c
> @@ -15,9 +15,12 @@
> #include <linux/module.h>
> #include <linux/spinlock.h>
> #include <linux/hardirq.h>
> +#include <linux/kthread.h>
> +#include <linux/freezer.h>
> #include <linux/fs.h>
> #include <linux/blkdev.h>
> #include <linux/types.h>
> +#include <linux/list_sort.h>
> #include <linux/limits.h>
> #include "hot_tracking.h"
>
> @@ -557,6 +560,67 @@ static void hot_map_array_exit(struct hot_info *root)
> }
> }
>
> +/* Temperature compare function*/
> +static int hot_temp_cmp(void *priv, struct list_head *a,
> + struct list_head *b)
> +{
> + struct hot_comm_item *ap =
> + container_of(a, struct hot_comm_item, n_list);
> + struct hot_comm_item *bp =
> + container_of(b, struct hot_comm_item, n_list);
> +
> + int diff = ap->hot_freq_data.last_temp
> + - bp->hot_freq_data.last_temp;
> + if (diff > 0)
> + return -1;
> + if (diff < 0)
> + return 1;
> + return 0;
> +}
> +
> +/*
> + * Every sync period we update temperatures for
> + * each hot inode item and hot range item for aging
> + * purposes.
> + */
> +static void hot_update_worker(struct work_struct *work)
> +{
> + struct hot_info *root = container_of(to_delayed_work(work),
> + struct hot_info, update_work);
> + struct hot_inode_item *hi_nodes[8];
> + u64 ino = 0;
> + int i, n;
> +
> + while (1) {
> + n = radix_tree_gang_lookup(&root->hot_inode_tree,
> + (void **)hi_nodes, ino,
> + ARRAY_SIZE(hi_nodes));
> + if (!n)
> + break;
> +
> + ino = hi_nodes[n - 1]->i_ino + 1;
> + for (i = 0; i < n; i++) {
> + kref_get(&hi_nodes[i]->hot_inode.refs);
> + hot_map_array_update(
> + &hi_nodes[i]->hot_inode.hot_freq_data, root);
> + hot_range_update(hi_nodes[i], root);
> + hot_inode_item_put(hi_nodes[i]);
> + }
> + }
> +
> + /* Sort temperature map info */
> + for (i = 0; i < HEAT_MAP_SIZE; i++) {
> + list_sort(NULL, &root->heat_inode_map[i].node_list,
> + hot_temp_cmp);
> + list_sort(NULL, &root->heat_range_map[i].node_list,
> + hot_temp_cmp);
> + }
> +
If this list can potentially have one (or more) entries per inode, then
filesystems with a lot of inodes (millions) may potentially exceed the
max size of list which list_sort() can handle. If that happens it still
works, but you'll get a warning message and it won't be as efficient.
It is something that we've run into with list_sort() and GFS2, but it
only happens very rarely,
Steve.
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
