[PATCH 32/47] writeback: extend balance_dirty_pages() trace event

[Wu Fengguang]

Make it more useful for analyzing the dynamics of the throttling
algorithms, and helpful for debugging user reported problems.

Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx>
---
 include/trace/events/writeback.h |   52 +++++++++++++++++++++--------
 mm/page-writeback.c              |   14 +++++++
 2 files changed, 53 insertions(+), 13 deletions(-)

--- linux-next.orig/include/trace/events/writeback.h	2010-12-09 12:21:04.000000000 +0800
+++ linux-next/include/trace/events/writeback.h	2010-12-09 12:24:49.000000000 +0800
@@ -149,35 +149,53 @@ DEFINE_WBC_EVENT(wbc_writeback_written);
 DEFINE_WBC_EVENT(wbc_writeback_wait);
 DEFINE_WBC_EVENT(wbc_writepage);
 
+#define KBps(x)			((x) << (PAGE_SHIFT - 10))
 #define BDP_PERCENT(a, b, c)	((__entry->a - __entry->b) * 100 * c + \
 				  __entry->bdi_limit/2) / (__entry->bdi_limit|1)
+
 TRACE_EVENT(balance_dirty_pages,
 
 	TP_PROTO(struct backing_dev_info *bdi,
 		 long bdi_dirty,
+		 long avg_dirty,
 		 long bdi_limit,
 		 long task_limit,
-		 long pages_dirtied,
+		 long dirtied,
+		 long task_bw,
+		 long period,
 		 long pause),
 
-	TP_ARGS(bdi, bdi_dirty, bdi_limit, task_limit,
-		pages_dirtied, pause),
+	TP_ARGS(bdi, bdi_dirty, avg_dirty, bdi_limit, task_limit,
+		dirtied, task_bw, period, pause),
 
 	TP_STRUCT__entry(
 		__array(char,	bdi, 32)
 		__field(long,	bdi_dirty)
+		__field(long,	avg_dirty)
 		__field(long,	bdi_limit)
 		__field(long,	task_limit)
-		__field(long,	pages_dirtied)
+		__field(long,	dirtied)
+		__field(long,	bdi_bw)
+		__field(long,	base_bw)
+		__field(long,	task_bw)
+		__field(long,	period)
+		__field(long,	think)
 		__field(long,	pause)
 	),
 
 	TP_fast_assign(
 		strlcpy(__entry->bdi, dev_name(bdi->dev), 32);
 		__entry->bdi_dirty	= bdi_dirty;
+		__entry->avg_dirty	= avg_dirty;
 		__entry->bdi_limit	= bdi_limit;
 		__entry->task_limit	= task_limit;
-		__entry->pages_dirtied	= pages_dirtied;
+		__entry->dirtied	= dirtied;
+		__entry->bdi_bw		= KBps(bdi->write_bandwidth);
+		__entry->base_bw	= KBps(bdi->throttle_bandwidth);
+		__entry->task_bw	= KBps(task_bw);
+		__entry->think		= current->paused_when == 0 ? 0 :
+			 (long)(jiffies - current->paused_when) * 1000 / HZ;
+		__entry->period		= period * 1000 / HZ;
 		__entry->pause		= pause * 1000 / HZ;
 	),
 
@@ -191,19 +209,27 @@ TRACE_EVENT(balance_dirty_pages,
 	 *
 	 * Reasonable large gaps help produce smooth pause times.
 	 */
-	TP_printk("bdi=%s bdi_dirty=%lu bdi_limit=%lu task_limit=%lu "
-		  "task_weight=%ld%% task_gap=%ld%% bdi_gap=%ld%% "
-		  "pages_dirtied=%lu pause=%lu",
+	TP_printk("bdi %s: "
+		  "bdi_limit=%lu task_limit=%lu bdi_dirty=%lu avg_dirty=%lu "
+		  "bdi_gap=%ld%% task_gap=%ld%% task_weight=%ld%% "
+		  "bdi_bw=%lu base_bw=%lu task_bw=%lu "
+		  "dirtied=%lu period=%lu think=%ld pause=%ld",
 		  __entry->bdi,
-		  __entry->bdi_dirty,
 		  __entry->bdi_limit,
 		  __entry->task_limit,
+		  __entry->bdi_dirty,
+		  __entry->avg_dirty,
+		  BDP_PERCENT(bdi_limit, bdi_dirty, BDI_SOFT_DIRTY_LIMIT),
+		  BDP_PERCENT(task_limit, avg_dirty, TASK_SOFT_DIRTY_LIMIT),
 		  /* task weight: proportion of recent dirtied pages */
 		  BDP_PERCENT(bdi_limit, task_limit, TASK_SOFT_DIRTY_LIMIT),
-		  BDP_PERCENT(task_limit, bdi_dirty, TASK_SOFT_DIRTY_LIMIT),
-		  BDP_PERCENT(bdi_limit, bdi_dirty, BDI_SOFT_DIRTY_LIMIT),
-		  __entry->pages_dirtied,
-		  __entry->pause
+		  __entry->bdi_bw,	/* bdi write bandwidth */
+		  __entry->base_bw,	/* bdi base throttle bandwidth */
+		  __entry->task_bw,	/* task throttle bandwidth */
+		  __entry->dirtied,
+		  __entry->period,	/* ms */
+		  __entry->think,	/* ms */
+		  __entry->pause	/* ms */
 		  )
 );
 
--- linux-next.orig/mm/page-writeback.c	2010-12-09 12:24:47.000000000 +0800
+++ linux-next/mm/page-writeback.c	2010-12-09 12:24:49.000000000 +0800
@@ -785,6 +785,8 @@ static void balance_dirty_pages(struct a
 		pause_max = max_pause(bdi_thresh);
 
 		if (avg_dirty >= task_thresh || nr_dirty > dirty_thresh) {
+			bw = 0;
+			period = 0;
 			pause = pause_max;
 			goto pause;
 		}
@@ -812,6 +814,15 @@ static void balance_dirty_pages(struct a
 		 * it may be a light dirtier.
 		 */
 		if (unlikely(-pause < HZ*10)) {
+			trace_balance_dirty_pages(bdi,
+						  bdi_dirty,
+						  avg_dirty,
+						  bdi_thresh,
+						  task_thresh,
+						  pages_dirtied,
+						  bw,
+						  period,
+						  pause);
 			if (-pause <= HZ/10)
 				current->paused_when += period;
 			else
@@ -824,9 +835,12 @@ static void balance_dirty_pages(struct a
 pause:
 		trace_balance_dirty_pages(bdi,
 					  bdi_dirty,
+					  avg_dirty,
 					  bdi_thresh,
 					  task_thresh,
 					  pages_dirtied,
+					  bw,
+					  period,
 					  pause);
 		current->paused_when = jiffies;
 		__set_current_state(TASK_UNINTERRUPTIBLE);


--
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/