writeback: trace event writeback_queue_io

Note that it adds a little overheads to account the moved/enqueued
inodes from b_dirty to b_io. The "moved" accounting may be later used to
limit the number of inodes that can be moved in one shot, in order to
keep spinlock hold time under control.

Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>

2 files changed, 35 insertions, 4 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 5185fad48b6..6caa98247a5 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -248,15 +248,16 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
 /*
  * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
  */
-static void move_expired_inodes(struct list_head *delaying_queue,
+static int move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
-				unsigned long *older_than_this)
+			       unsigned long *older_than_this)
 {
 	LIST_HEAD(tmp);
 	struct list_head *pos, *node;
 	struct super_block *sb = NULL;
 	struct inode *inode;
 	int do_sb_sort = 0;
+	int moved = 0;
 
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
@@ -267,12 +268,13 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 			do_sb_sort = 1;
 		sb = inode->i_sb;
 		list_move(&inode->i_wb_list, &tmp);
+		moved++;
 	}
 
 	/* just one sb in list, splice to dispatch_queue and we're done */
 	if (!do_sb_sort) {
 		list_splice(&tmp, dispatch_queue);
-		return;
+		goto out;
 	}
 
 	/* Move inodes from one superblock together */
@@ -284,6 +286,8 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 				list_move(&inode->i_wb_list, dispatch_queue);
 		}
 	}
+out:
+	return moved;
 }
 
 /*
@@ -299,9 +303,11 @@ static void move_expired_inodes(struct list_head *delaying_queue,
  */
 static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
 {
+	int moved;
 	assert_spin_locked(&wb->list_lock);
 	list_splice_init(&wb->b_more_io, &wb->b_io);
-	move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
+	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
+	trace_writeback_queue_io(wb, older_than_this, moved);
 }
 
 static int write_inode(struct inode *inode, struct writeback_control *wbc)
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 898277bc89b..205d14919ef 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -162,6 +162,31 @@ DEFINE_WBC_EVENT(wbc_balance_dirty_written);
 DEFINE_WBC_EVENT(wbc_balance_dirty_wait);
 DEFINE_WBC_EVENT(wbc_writepage);
 
+TRACE_EVENT(writeback_queue_io,
+	TP_PROTO(struct bdi_writeback *wb,
+		 unsigned long *older_than_this,
+		 int moved),
+	TP_ARGS(wb, older_than_this, moved),
+	TP_STRUCT__entry(
+		__array(char,		name, 32)
+		__field(unsigned long,	older)
+		__field(long,		age)
+		__field(int,		moved)
+	),
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
+		__entry->older	= older_than_this ?  *older_than_this : 0;
+		__entry->age	= older_than_this ?
+				  (jiffies - *older_than_this) * 1000 / HZ : -1;
+		__entry->moved	= moved;
+	),
+	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d",
+		__entry->name,
+		__entry->older,	/* older_than_this in jiffies */
+		__entry->age,	/* older_than_this in relative milliseconds */
+		__entry->moved)
+);
+
 DECLARE_EVENT_CLASS(writeback_congest_waited_template,
 
 	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),