writeback: trace event balance_dirty_pages

Useful for analyzing the dynamics of the throttling algorithms and
debugging user reported problems.

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

2 files changed, 95 insertions, 0 deletions

diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index ffb5deb..0ce9f06 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -271,6 +271,79 @@ TRACE_EVENT(bdi_dirty_ratelimit,
 	)
 );
 
+TRACE_EVENT(balance_dirty_pages,
+
+	TP_PROTO(struct backing_dev_info *bdi,
+		 unsigned long thresh,
+		 unsigned long bg_thresh,
+		 unsigned long dirty,
+		 unsigned long bdi_thresh,
+		 unsigned long bdi_dirty,
+		 unsigned long dirty_ratelimit,
+		 unsigned long task_ratelimit,
+		 unsigned long dirtied,
+		 long pause,
+		 unsigned long start_time),
+
+	TP_ARGS(bdi, thresh, bg_thresh, dirty, bdi_thresh, bdi_dirty,
+		dirty_ratelimit, task_ratelimit,
+		dirtied, pause, start_time),
+
+	TP_STRUCT__entry(
+		__array(	 char,	bdi, 32)
+		__field(unsigned long,	limit)
+		__field(unsigned long,	setpoint)
+		__field(unsigned long,	dirty)
+		__field(unsigned long,	bdi_setpoint)
+		__field(unsigned long,	bdi_dirty)
+		__field(unsigned long,	dirty_ratelimit)
+		__field(unsigned long,	task_ratelimit)
+		__field(unsigned int,	dirtied)
+		__field(unsigned int,	dirtied_pause)
+		__field(unsigned long,	paused)
+		__field(	 long,	pause)
+	),
+
+	TP_fast_assign(
+		unsigned long freerun = (thresh + bg_thresh) / 2;
+		strlcpy(__entry->bdi, dev_name(bdi->dev), 32);
+
+		__entry->limit		= global_dirty_limit;
+		__entry->setpoint	= (global_dirty_limit + freerun) / 2;
+		__entry->dirty		= dirty;
+		__entry->bdi_setpoint	= __entry->setpoint *
+						bdi_thresh / (thresh + 1);
+		__entry->bdi_dirty	= bdi_dirty;
+		__entry->dirty_ratelimit = KBps(dirty_ratelimit);
+		__entry->task_ratelimit	= KBps(task_ratelimit);
+		__entry->dirtied	= dirtied;
+		__entry->dirtied_pause	= current->nr_dirtied_pause;
+		__entry->pause		= pause * 1000 / HZ;
+		__entry->paused		= (jiffies - start_time) * 1000 / HZ;
+	),
+
+
+	TP_printk("bdi %s: "
+		  "limit=%lu setpoint=%lu dirty=%lu "
+		  "bdi_setpoint=%lu bdi_dirty=%lu "
+		  "dirty_ratelimit=%lu task_ratelimit=%lu "
+		  "dirtied=%u dirtied_pause=%u "
+		  "paused=%lu pause=%ld",
+		  __entry->bdi,
+		  __entry->limit,
+		  __entry->setpoint,
+		  __entry->dirty,
+		  __entry->bdi_setpoint,
+		  __entry->bdi_dirty,
+		  __entry->dirty_ratelimit,
+		  __entry->task_ratelimit,
+		  __entry->dirtied,
+		  __entry->dirtied_pause,
+		  __entry->paused,	/* ms */
+		  __entry->pause	/* ms */
+	  )
+);
+
 DECLARE_EVENT_CLASS(writeback_congest_waited_template,
 
 	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index e3c2d8b..45d36f7 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1103,12 +1103,34 @@ static void balance_dirty_pages(struct address_space *mapping,
 					pos_ratio >> RATELIMIT_CALC_SHIFT;
 		pause = (HZ * pages_dirtied) / (task_ratelimit | 1);
 		if (unlikely(pause <= 0)) {
+			trace_balance_dirty_pages(bdi,
+						  dirty_thresh,
+						  background_thresh,
+						  nr_dirty,
+						  bdi_thresh,
+						  bdi_dirty,
+						  dirty_ratelimit,
+						  task_ratelimit,
+						  pages_dirtied,
+						  pause,
+						  start_time);
 			pause = 1; /* avoid resetting nr_dirtied_pause below */
 			break;
 		}
 		pause = min(pause, max_pause);
 
 pause:
+		trace_balance_dirty_pages(bdi,
+					  dirty_thresh,
+					  background_thresh,
+					  nr_dirty,
+					  bdi_thresh,
+					  bdi_dirty,
+					  dirty_ratelimit,
+					  task_ratelimit,
+					  pages_dirtied,
+					  pause,
+					  start_time);
 		__set_current_state(TASK_UNINTERRUPTIBLE);
 		io_schedule_timeout(pause);