Re: xfstests 073 regression

[Wu Fengguang <fengguang.wu@intel.com>]

> --- linux.orig/fs/fs-writeback.c	2011-07-29 22:14:18.000000000 +0800
> +++ linux/fs/fs-writeback.c	2011-07-31 17:04:25.000000000 +0800
> @@ -618,7 +618,12 @@ static long __writeback_inodes_wb(struct
>  		struct super_block *sb = inode->i_sb;
>  
>  		if (!grab_super_passive(sb)) {
> -			requeue_io(inode, wb);
> +			/*
> +			 * grab_super_passive() may fail consistently due to
> +			 * s_umount being grabbed by someone else. So redirty
> +			 * the inode to avoid busy loop.
> +			 */
> +			redirty_tail(inode, wb);
>  			continue;
>  		}
>  		wrote += writeback_sb_inodes(sb, wb, work);

Or we could fix it by moving the inode into b_more_io_wait. This
avoids introducing possible delays to the inode, as well as makes
it possible to eliminate extra sync works by setting the sync works'
work->older_than_this to the sync() _syscall_ time instead of the
current sync work _execution_ time.

Thanks,
Fengguang
---

Subject: writeback: introduce queue b_more_io_wait
Date: Sun Jul 31 18:44:44 CST 2011

Introduce the b_more_io_wait queue to park inodes that for some reason
cannot be synced immediately. They will be enqueued at the next b_io
refill time and won't be busy retried as b_more_io.

The new data flow after this patchset:

b_dirty --> b_io --> b_more_io/b_more_io_wait --+
             ^                                  |
	     |                                  |
	     +----------------------------------+

The rational is to address two issues:

- the 30s max delay of redirty_tail() may be too long

- redirty_tail() may update i_dirtied_when. With b_more_io_wait, we'll
  be able to avoid extra sync() works by excluding any inodes from being
  synced if its dirty time is after the sync() _syscall_ time.

Cc: Jan Kara <jack@suse.cz>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Michael Rubin <mrubin@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
 fs/fs-writeback.c           |   10 ++++++++++
 include/linux/backing-dev.h |    8 +++++---
 mm/backing-dev.c            |   10 ++++++++--
 3 files changed, 23 insertions(+), 5 deletions(-)

--- linux.orig/fs/fs-writeback.c	2011-07-31 18:39:19.000000000 +0800
+++ linux/fs/fs-writeback.c	2011-07-31 19:03:28.000000000 +0800
@@ -220,6 +220,15 @@ static void requeue_io(struct inode *ino
 	list_move(&inode->i_wb_list, &wb->b_more_io);
 }
 
+/*
+ * The inode should be retried in an opportunistic way.
+ */
+static void requeue_io_wait(struct inode *inode, struct bdi_writeback *wb)
+{
+	assert_spin_locked(&wb->list_lock);
+	list_move(&inode->i_wb_list, &wb->b_more_io_wait);
+}
+
 static void inode_sync_complete(struct inode *inode)
 {
 	/*
@@ -307,6 +316,7 @@ static void queue_io(struct bdi_writebac
 	int moved;
 	assert_spin_locked(&wb->list_lock);
 	list_splice_init(&wb->b_more_io, &wb->b_io);
+	list_splice_init(&wb->b_more_io_wait, &wb->b_io);
 	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
 	trace_writeback_queue_io(wb, older_than_this, moved);
 }
--- linux.orig/include/linux/backing-dev.h	2011-07-31 18:39:20.000000000 +0800
+++ linux/include/linux/backing-dev.h	2011-07-31 18:42:18.000000000 +0800
@@ -58,6 +58,7 @@ struct bdi_writeback {
 	struct list_head b_dirty;	/* dirty inodes */
 	struct list_head b_io;		/* parked for writeback */
 	struct list_head b_more_io;	/* parked for more writeback */
+	struct list_head b_more_io_wait;/* opportunistic retry io */
 	spinlock_t list_lock;		/* protects the b_* lists */
 };
 
@@ -121,9 +122,10 @@ extern struct list_head bdi_pending_list
 
 static inline int wb_has_dirty_io(struct bdi_writeback *wb)
 {
-	return !list_empty(&wb->b_dirty) ||
-	       !list_empty(&wb->b_io) ||
-	       !list_empty(&wb->b_more_io);
+	return !list_empty(&wb->b_dirty)	||
+	       !list_empty(&wb->b_io)		||
+	       !list_empty(&wb->b_more_io)	||
+	       !list_empty(&wb->b_more_io_wait);
 }
 
 static inline void __add_bdi_stat(struct backing_dev_info *bdi,
--- linux.orig/mm/backing-dev.c	2011-07-31 18:39:19.000000000 +0800
+++ linux/mm/backing-dev.c	2011-07-31 18:44:26.000000000 +0800
@@ -74,10 +74,10 @@ static int bdi_debug_stats_show(struct s
 	unsigned long background_thresh;
 	unsigned long dirty_thresh;
 	unsigned long bdi_thresh;
-	unsigned long nr_dirty, nr_io, nr_more_io;
+	unsigned long nr_dirty, nr_io, nr_more_io, nr_more_io_wait;
 	struct inode *inode;
 
-	nr_dirty = nr_io = nr_more_io = 0;
+	nr_dirty = nr_io = nr_more_io = nr_more_io_wait = 0;
 	spin_lock(&wb->list_lock);
 	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
 		nr_dirty++;
@@ -85,6 +85,8 @@ static int bdi_debug_stats_show(struct s
 		nr_io++;
 	list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
 		nr_more_io++;
+	list_for_each_entry(inode, &wb->b_more_io_wait, i_wb_list)
+		nr_more_io_wait++;
 	spin_unlock(&wb->list_lock);
 
 	global_dirty_limits(&background_thresh, &dirty_thresh);
@@ -102,6 +104,7 @@ static int bdi_debug_stats_show(struct s
 		   "b_dirty:            %10lu\n"
 		   "b_io:               %10lu\n"
 		   "b_more_io:          %10lu\n"
+		   "b_more_io_wait:     %10lu\n"
 		   "bdi_list:           %10u\n"
 		   "state:              %10lx\n",
 		   (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
@@ -114,6 +117,7 @@ static int bdi_debug_stats_show(struct s
 		   nr_dirty,
 		   nr_io,
 		   nr_more_io,
+		   nr_more_io_wait,
 		   !list_empty(&bdi->bdi_list), bdi->state);
 #undef K
 
@@ -637,6 +641,7 @@ static void bdi_wb_init(struct bdi_write
 	INIT_LIST_HEAD(&wb->b_dirty);
 	INIT_LIST_HEAD(&wb->b_io);
 	INIT_LIST_HEAD(&wb->b_more_io);
+	INIT_LIST_HEAD(&wb->b_more_io_wait);
 	spin_lock_init(&wb->list_lock);
 	setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi);
 }
@@ -702,6 +707,7 @@ void bdi_destroy(struct backing_dev_info
 		list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
 		list_splice(&bdi->wb.b_io, &dst->b_io);
 		list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
+		list_splice(&bdi->wb.b_more_io_wait, &dst->b_more_io_wait);
 		spin_unlock(&bdi->wb.list_lock);
 		spin_unlock(&dst->list_lock);
 	}