[PATCH 01/16] vfs: kill write_super and sync_supers

[Artem Bityutskiy]

From: Artem Bityutskiy <artem.bityutskiy@xxxxxxxxxxxxxxx>

Finally we can kill the 'sync_supers' kernel thread along with the
'->write_super()' superblock operation because all the users are gone.
Now every file-system is supposed to self-manage own superblock and
its dirty state.

The nice thing about killing this thread is that it improves power management.
Indeed, 'sync_supers' is a source of monotonic system wake-ups - it woke up
every 5 seconds no matter what - even if there were no dirty superblocks and
even if there were no file-systems using this service (e.g., btrfs and
journalled ext4 do not need it). So it was wasting power most of the time. And
because the thread was in the core of the kernel, all systems had to have it.
So I am quite happy to make it go away.

Interestingly, this thread is a left-over from the pdflush kernel thread which
was a self-forking kernel thread responsible for all the write-back in old
Linux kernels. It was turned into per-block device BDI threads, and
'sync_supers' was a left-over. Thus, R.I.P, pdflush as well.

Signed-off-by: Artem Bityutskiy <artem.bityutskiy@xxxxxxxxxxxxxxx>
---
 fs/super.c                  |   40 ---------------------------------
 include/linux/backing-dev.h |    1 -
 include/linux/fs.h          |    3 ---
 mm/backing-dev.c            |   52 -------------------------------------------
 mm/page-writeback.c         |    1 -
 5 files changed, 97 deletions(-)

diff --git a/fs/super.c b/fs/super.c
index cf00177..c8ca90c 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -484,46 +484,6 @@ void drop_super(struct super_block *sb)
 EXPORT_SYMBOL(drop_super);
 
 /**
- * sync_supers - helper for periodic superblock writeback
- *
- * Call the write_super method if present on all dirty superblocks in
- * the system.  This is for the periodic writeback used by most older
- * filesystems.  For data integrity superblock writeback use
- * sync_filesystems() instead.
- *
- * Note: check the dirty flag before waiting, so we don't
- * hold up the sync while mounting a device. (The newly
- * mounted device won't need syncing.)
- */
-void sync_supers(void)
-{
-	struct super_block *sb, *p = NULL;
-
-	spin_lock(&sb_lock);
-	list_for_each_entry(sb, &super_blocks, s_list) {
-		if (hlist_unhashed(&sb->s_instances))
-			continue;
-		if (sb->s_op->write_super && sb->s_dirt) {
-			sb->s_count++;
-			spin_unlock(&sb_lock);
-
-			down_read(&sb->s_umount);
-			if (sb->s_root && sb->s_dirt && (sb->s_flags & MS_BORN))
-				sb->s_op->write_super(sb);
-			up_read(&sb->s_umount);
-
-			spin_lock(&sb_lock);
-			if (p)
-				__put_super(p);
-			p = sb;
-		}
-	}
-	if (p)
-		__put_super(p);
-	spin_unlock(&sb_lock);
-}
-
-/**
  *	iterate_supers - call function for all active superblocks
  *	@f: function to call
  *	@arg: argument to pass to it
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index b1038bd..94143aa 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -123,7 +123,6 @@ void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 void bdi_start_background_writeback(struct backing_dev_info *bdi);
 int bdi_writeback_thread(void *data);
 int bdi_has_dirty_io(struct backing_dev_info *bdi);
-void bdi_arm_supers_timer(void);
 void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi);
 void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 17fd887..8878410 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1453,7 +1453,6 @@ extern spinlock_t sb_lock;
 struct super_block {
 	struct list_head	s_list;		/* Keep this first */
 	dev_t			s_dev;		/* search index; _not_ kdev_t */
-	unsigned char		s_dirt;
 	unsigned char		s_blocksize_bits;
 	unsigned long		s_blocksize;
 	loff_t			s_maxbytes;	/* Max file size */
@@ -1718,7 +1717,6 @@ struct super_operations {
 	int (*drop_inode) (struct inode *);
 	void (*evict_inode) (struct inode *);
 	void (*put_super) (struct super_block *);
-	void (*write_super) (struct super_block *);
 	int (*sync_fs)(struct super_block *sb, int wait);
 	int (*freeze_fs) (struct super_block *);
 	int (*unfreeze_fs) (struct super_block *);
@@ -2241,7 +2239,6 @@ extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
 			   int datasync);
 extern int vfs_fsync(struct file *file, int datasync);
 extern int generic_write_sync(struct file *file, loff_t pos, loff_t count);
-extern void sync_supers(void);
 extern void emergency_sync(void);
 extern void emergency_remount(void);
 #ifdef CONFIG_BLOCK
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index dd8e2aa..f34c4ca 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -39,12 +39,6 @@ DEFINE_SPINLOCK(bdi_lock);
 LIST_HEAD(bdi_list);
 LIST_HEAD(bdi_pending_list);
 
-static struct task_struct *sync_supers_tsk;
-static struct timer_list sync_supers_timer;
-
-static int bdi_sync_supers(void *);
-static void sync_supers_timer_fn(unsigned long);
-
 void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
 {
 	if (wb1 < wb2) {
@@ -250,12 +244,6 @@ static int __init default_bdi_init(void)
 {
 	int err;
 
-	sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers");
-	BUG_ON(IS_ERR(sync_supers_tsk));
-
-	setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0);
-	bdi_arm_supers_timer();
-
 	err = bdi_init(&default_backing_dev_info);
 	if (!err)
 		bdi_register(&default_backing_dev_info, NULL, "default");
@@ -270,46 +258,6 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi)
 	return wb_has_dirty_io(&bdi->wb);
 }
 
-/*
- * kupdated() used to do this. We cannot do it from the bdi_forker_thread()
- * or we risk deadlocking on ->s_umount. The longer term solution would be
- * to implement sync_supers_bdi() or similar and simply do it from the
- * bdi writeback thread individually.
- */
-static int bdi_sync_supers(void *unused)
-{
-	set_user_nice(current, 0);
-
-	while (!kthread_should_stop()) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		schedule();
-
-		/*
-		 * Do this periodically, like kupdated() did before.
-		 */
-		sync_supers();
-	}
-
-	return 0;
-}
-
-void bdi_arm_supers_timer(void)
-{
-	unsigned long next;
-
-	if (!dirty_writeback_interval)
-		return;
-
-	next = msecs_to_jiffies(dirty_writeback_interval * 10) + jiffies;
-	mod_timer(&sync_supers_timer, round_jiffies_up(next));
-}
-
-static void sync_supers_timer_fn(unsigned long unused)
-{
-	wake_up_process(sync_supers_tsk);
-	bdi_arm_supers_timer();
-}
-
 static void wakeup_timer_fn(unsigned long data)
 {
 	struct backing_dev_info *bdi = (struct backing_dev_info *)data;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 93d8d2f..cffc800 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1504,7 +1504,6 @@ int dirty_writeback_centisecs_handler(ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
 	proc_dointvec(table, write, buffer, length, ppos);
-	bdi_arm_supers_timer();
 	return 0;
 }
 
-- 
1.7.10

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/