diff mbox

[4/5] writeback: introduce super_operations->write_metadata

Message ID 1477420904-1399-5-git-send-email-jbacik@fb.com (mailing list archive)
State New, archived
Headers show

Commit Message

Josef Bacik Oct. 25, 2016, 6:41 p.m. UTC 
Now that we have metadata counters in the VM, we need to provide a way to kick
writeback on dirty metadata.  Introduce super_operations->write_metadata.  This
allows file systems to deal with writing back any dirty metadata we need based
on the writeback needs of the system.  Since there is no inode to key off of we
need a list in the bdi for dirty super blocks to be added.  From there we can
find any dirty sb's on the bdi we are currently doing writeback on and call into
their ->write_metadata callback.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 fs/fs-writeback.c                | 72 ++++++++++++++++++++++++++++++++++++----
 fs/super.c                       |  7 ++++
 include/linux/backing-dev-defs.h |  2 ++
 include/linux/fs.h               |  4 +++
 mm/backing-dev.c                 |  2 ++
 5 files changed, 81 insertions(+), 6 deletions(-)

Comments

Tejun Heo Oct. 25, 2016, 8 p.m. UTC | #1 
Hello,

On Tue, Oct 25, 2016 at 02:41:43PM -0400, Josef Bacik wrote:
> Now that we have metadata counters in the VM, we need to provide a way to kick
> writeback on dirty metadata.  Introduce super_operations->write_metadata.  This
> allows file systems to deal with writing back any dirty metadata we need based
> on the writeback needs of the system.  Since there is no inode to key off of we
> need a list in the bdi for dirty super blocks to be added.  From there we can
> find any dirty sb's on the bdi we are currently doing writeback on and call into
> their ->write_metadata callback.
> 
> Signed-off-by: Josef Bacik <jbacik@fb.com>
> Reviewed-by: Jan Kara <jack@suse.cz>

Reviewed-by: Tejun Heo <tj@kernel.org>

> @@ -1491,6 +1516,7 @@ static long writeback_sb_inodes(struct super_block *sb,
>  	unsigned long start_time = jiffies;
>  	long write_chunk;
>  	long wrote = 0;  /* count both pages and inodes */
> +	bool done = false;
>  
>  	while (!list_empty(&wb->b_io)) {
>  		struct inode *inode = wb_inode(wb->b_io.prev);
> @@ -1607,12 +1633,18 @@ static long writeback_sb_inodes(struct super_block *sb,
>  		 * background threshold and other termination conditions.
>  		 */
>  		if (wrote) {
> -			if (time_is_before_jiffies(start_time + HZ / 10UL))
> -				break;
> -			if (work->nr_pages <= 0)
> +			if (time_is_before_jiffies(start_time + HZ / 10UL) ||
> +			    work->nr_pages <= 0) {
> +				done = true;
>  				break;
> +			}
>  		}
>  	}
> +	if (!done && sb->s_op->write_metadata) {
> +		spin_unlock(&wb->list_lock);
> +		wrote += writeback_sb_metadata(sb, wb, work);
> +		spin_lock(&wb->list_lock);

So, here and below, we're writing out metadata only after finishing
writing out data if the writeout budget is limited.  It'd be great to
document the behavior and why it's so in the callback definition.

Thanks.
diff mbox

Patch

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index a5cb1dd..8e392b2 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1465,6 +1465,31 @@  static long writeback_chunk_size(struct bdi_writeback *wb,
 	return pages;
 }
 
+static long writeback_sb_metadata(struct super_block *sb,
+				  struct bdi_writeback *wb,
+				  struct wb_writeback_work *work)
+{
+	struct writeback_control wbc = {
+		.sync_mode		= work->sync_mode,
+		.tagged_writepages	= work->tagged_writepages,
+		.for_kupdate		= work->for_kupdate,
+		.for_background		= work->for_background,
+		.for_sync		= work->for_sync,
+		.range_cyclic		= work->range_cyclic,
+		.range_start		= 0,
+		.range_end		= LLONG_MAX,
+	};
+	long write_chunk;
+
+	write_chunk = writeback_chunk_size(wb, work);
+	wbc.nr_to_write = write_chunk;
+	sb->s_op->write_metadata(sb, &wbc);
+	work->nr_pages -= write_chunk - wbc.nr_to_write;
+
+	return write_chunk - wbc.nr_to_write;
+}
+
+
 /*
  * Write a portion of b_io inodes which belong to @sb.
  *
@@ -1491,6 +1516,7 @@  static long writeback_sb_inodes(struct super_block *sb,
 	unsigned long start_time = jiffies;
 	long write_chunk;
 	long wrote = 0;  /* count both pages and inodes */
+	bool done = false;
 
 	while (!list_empty(&wb->b_io)) {
 		struct inode *inode = wb_inode(wb->b_io.prev);
@@ -1607,12 +1633,18 @@  static long writeback_sb_inodes(struct super_block *sb,
 		 * background threshold and other termination conditions.
 		 */
 		if (wrote) {
-			if (time_is_before_jiffies(start_time + HZ / 10UL))
-				break;
-			if (work->nr_pages <= 0)
+			if (time_is_before_jiffies(start_time + HZ / 10UL) ||
+			    work->nr_pages <= 0) {
+				done = true;
 				break;
+			}
 		}
 	}
+	if (!done && sb->s_op->write_metadata) {
+		spin_unlock(&wb->list_lock);
+		wrote += writeback_sb_metadata(sb, wb, work);
+		spin_lock(&wb->list_lock);
+	}
 	return wrote;
 }
 
@@ -1621,6 +1653,7 @@  static long __writeback_inodes_wb(struct bdi_writeback *wb,
 {
 	unsigned long start_time = jiffies;
 	long wrote = 0;
+	bool done = false;
 
 	while (!list_empty(&wb->b_io)) {
 		struct inode *inode = wb_inode(wb->b_io.prev);
@@ -1640,12 +1673,39 @@  static long __writeback_inodes_wb(struct bdi_writeback *wb,
 
 		/* refer to the same tests at the end of writeback_sb_inodes */
 		if (wrote) {
-			if (time_is_before_jiffies(start_time + HZ / 10UL))
-				break;
-			if (work->nr_pages <= 0)
+			if (time_is_before_jiffies(start_time + HZ / 10UL) ||
+			    work->nr_pages <= 0) {
+				done = true;
 				break;
+			}
 		}
 	}
+
+	if (!done && wb_stat(wb, WB_METADATA_DIRTY_BYTES)) {
+		LIST_HEAD(list);
+
+		spin_unlock(&wb->list_lock);
+		spin_lock(&wb->bdi->sb_list_lock);
+		list_splice_init(&wb->bdi->dirty_sb_list, &list);
+		while (!list_empty(&list)) {
+			struct super_block *sb;
+
+			sb = list_first_entry(&list, struct super_block,
+					      s_bdi_dirty_list);
+			list_move_tail(&sb->s_bdi_dirty_list,
+				       &wb->bdi->dirty_sb_list);
+			if (!sb->s_op->write_metadata)
+				continue;
+			if (!trylock_super(sb))
+				continue;
+			spin_unlock(&wb->bdi->sb_list_lock);
+			wrote += writeback_sb_metadata(sb, wb, work);
+			spin_lock(&wb->bdi->sb_list_lock);
+			up_read(&sb->s_umount);
+		}
+		spin_unlock(&wb->bdi->sb_list_lock);
+		spin_lock(&wb->list_lock);
+	}
 	/* Leave any unwritten inodes on b_io */
 	return wrote;
 }
diff --git a/fs/super.c b/fs/super.c
index c2ff475..eb32913 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -215,6 +215,7 @@  static struct super_block *alloc_super(struct file_system_type *type, int flags,
 	spin_lock_init(&s->s_inode_list_lock);
 	INIT_LIST_HEAD(&s->s_inodes_wb);
 	spin_lock_init(&s->s_inode_wblist_lock);
+	INIT_LIST_HEAD(&s->s_bdi_dirty_list);
 
 	if (list_lru_init_memcg(&s->s_dentry_lru))
 		goto fail;
@@ -305,6 +306,8 @@  void deactivate_locked_super(struct super_block *s)
 {
 	struct file_system_type *fs = s->s_type;
 	if (atomic_dec_and_test(&s->s_active)) {
+		struct backing_dev_info *bdi = s->s_bdi;
+
 		cleancache_invalidate_fs(s);
 		unregister_shrinker(&s->s_shrink);
 		fs->kill_sb(s);
@@ -317,6 +320,10 @@  void deactivate_locked_super(struct super_block *s)
 		list_lru_destroy(&s->s_dentry_lru);
 		list_lru_destroy(&s->s_inode_lru);
 
+		spin_lock(&bdi->sb_list_lock);
+		list_del_init(&s->s_bdi_dirty_list);
+		spin_unlock(&bdi->sb_list_lock);
+
 		put_filesystem(fs);
 		put_super(s);
 	} else {
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index b1f8f70..8758d31 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -169,6 +169,8 @@  struct backing_dev_info {
 
 	struct timer_list laptop_mode_wb_timer;
 
+	spinlock_t sb_list_lock;
+	struct list_head dirty_sb_list;
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debug_dir;
 	struct dentry *debug_stats;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 901e25d..0217820 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1431,6 +1431,8 @@  struct super_block {
 
 	spinlock_t		s_inode_wblist_lock;
 	struct list_head	s_inodes_wb;	/* writeback inodes */
+
+	struct list_head	s_bdi_dirty_list;
 };
 
 /* Helper functions so that in most cases filesystems will
@@ -1806,6 +1808,8 @@  struct super_operations {
 				  struct shrink_control *);
 	long (*free_cached_objects)(struct super_block *,
 				    struct shrink_control *);
+	void (*write_metadata)(struct super_block *sb,
+			       struct writeback_control *wbc);
 };
 
 /*
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index da3f68b..10d9286 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -785,6 +785,8 @@  int bdi_init(struct backing_dev_info *bdi)
 	bdi->max_prop_frac = FPROP_FRAC_BASE;
 	INIT_LIST_HEAD(&bdi->bdi_list);
 	INIT_LIST_HEAD(&bdi->wb_list);
+	INIT_LIST_HEAD(&bdi->dirty_sb_list);
+	spin_lock_init(&bdi->sb_list_lock);
 	init_waitqueue_head(&bdi->wb_waitq);
 
 	ret = cgwb_bdi_init(bdi);