[PATCH 1/7] writeback: introduce queue b_more_io_wait

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

[-- Attachment #1: writeback-more_io_wait.patch --]
[-- Type: text/plain, Size: 5373 bytes --]

The problem is, redirty_tail() may update i_dirtied_when and result in
30s max delay. If redirty_tail() is called often enough, some inode may
even be delayed for ever.

So introduce the b_more_io_wait queue to park inodes that for some
reason cannot be synced immediately. The inodes will be sent to b_io at
the next b_io refill time, however won't be busy retried as b_more_io:
when the redirtied inodes are all in b_more_io_wait, wb_writeback() will
see empty b_more_io and hence break out of the loop.

This would be the new data flow after converting all redirty_tail()
calls to requeue_io_wait():

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

Cc: Jan Kara <jack@suse.cz>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
 fs/fs-writeback.c           |   16 ++++++++++++++++
 include/linux/backing-dev.h |    8 +++++---
 mm/backing-dev.c            |   10 ++++++++--
 3 files changed, 29 insertions(+), 5 deletions(-)

--- linux-next.orig/fs/fs-writeback.c	2011-10-20 23:13:48.000000000 +0800
+++ linux-next/fs/fs-writeback.c	2011-10-20 23:19:12.000000000 +0800
@@ -234,6 +234,21 @@ 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.
+ *
+ * The only difference between b_more_io and b_more_io_wait is:
+ * wb_writeback() won't quit as long as b_more_io is not empty.  When
+ * wb_writeback() quit on empty b_more_io and non-empty b_more_io_wait,
+ * the kupdate work will wakeup more frequently to retry the inodes in
+ * b_more_io_wait.
+ */
+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)
 {
 	/*
@@ -321,6 +336,7 @@ 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, work);
 	trace_writeback_queue_io(wb, work, moved);
 }
--- linux-next.orig/include/linux/backing-dev.h	2011-10-20 23:13:48.000000000 +0800
+++ linux-next/include/linux/backing-dev.h	2011-10-20 23:13:50.000000000 +0800
@@ -59,6 +59,7 @@ 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 */
 };
 
@@ -133,9 +134,10 @@ 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-next.orig/mm/backing-dev.c	2011-10-20 23:13:48.000000000 +0800
+++ linux-next/mm/backing-dev.c	2011-10-20 23:13:50.000000000 +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);
@@ -103,6 +105,7 @@ 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)),
@@ -116,6 +119,7 @@ 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
 
@@ -651,6 +655,7 @@ 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);
 }
@@ -718,6 +723,7 @@ 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);
 	}