writeback: Initial tracing support

Trace queue/sched/exec parts of the writeback loop. This provides
insight into when and why flusher threads are scheduled to run. e.g
a sync invocation leaves traces like:

     sync-[...]: writeback_queue: bdi 8:0: sb_dev 8:1 nr_pages=7712 sync_mode=0 kupdate=0 range_cyclic=0 background=0
flush-8:0-[...]: writeback_exec: bdi 8:0: sb_dev 8:1 nr_pages=7712 sync_mode=0 kupdate=0 range_cyclic=0 background=0

This also lays the foundation for adding more writeback tracing to
provide deeper insight into the whole writeback path.

The original tracing code is from Jens Axboe, though this version is
a rewrite as a result of the code being traced changing
significantly.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

1 files changed, 30 insertions, 8 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index c8471b3ddcc..73acab4dc2b 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -26,15 +26,9 @@
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
+#include <linux/tracepoint.h>
 #include "internal.h"
 
-#define inode_to_bdi(inode)	((inode)->i_mapping->backing_dev_info)
-
-/*
- * We don't actually have pdflush, but this one is exported though /proc...
- */
-int nr_pdflush_threads;
-
 /*
  * Passed into wb_writeback(), essentially a subset of writeback_control
  */
@@ -50,6 +44,21 @@ struct wb_writeback_work {
 	struct completion *done;	/* set if the caller waits */
 };
 
+/*
+ * Include the creation of the trace points after defining the
+ * wb_writeback_work structure so that the definition remains local to this
+ * file.
+ */
+#define CREATE_TRACE_POINTS
+#include <trace/events/writeback.h>
+
+#define inode_to_bdi(inode)	((inode)->i_mapping->backing_dev_info)
+
+/*
+ * We don't actually have pdflush, but this one is exported though /proc...
+ */
+int nr_pdflush_threads;
+
 /**
  * writeback_in_progress - determine whether there is writeback in progress
  * @bdi: the device's backing_dev_info structure.
@@ -65,6 +74,8 @@ int writeback_in_progress(struct backing_dev_info *bdi)
 static void bdi_queue_work(struct backing_dev_info *bdi,
 		struct wb_writeback_work *work)
 {
+	trace_writeback_queue(bdi, work);
+
 	spin_lock(&bdi->wb_lock);
 	list_add_tail(&work->list, &bdi->work_list);
 	spin_unlock(&bdi->wb_lock);
@@ -74,6 +85,7 @@ static void bdi_queue_work(struct backing_dev_info *bdi,
 	 * it gets created and wakes up, we'll run this work.
 	 */
 	if (unlikely(!bdi->wb.task)) {
+		trace_writeback_nothread(bdi, work);
 		wake_up_process(default_backing_dev_info.wb.task);
 	} else {
 		struct bdi_writeback *wb = &bdi->wb;
@@ -95,8 +107,10 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	 */
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work) {
-		if (bdi->wb.task)
+		if (bdi->wb.task) {
+			trace_writeback_nowork(bdi);
 			wake_up_process(bdi->wb.task);
+		}
 		return;
 	}
 
@@ -751,6 +765,8 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 		if (force_wait)
 			work->sync_mode = WB_SYNC_ALL;
 
+		trace_writeback_exec(bdi, work);
+
 		wrote += wb_writeback(wb, work);
 
 		/*
@@ -805,9 +821,13 @@ int bdi_writeback_thread(void *data)
 	smp_mb__after_clear_bit();
 	wake_up_bit(&bdi->state, BDI_pending);
 
+	trace_writeback_thread_start(bdi);
+
 	while (!kthread_should_stop()) {
 		pages_written = wb_do_writeback(wb, 0);
 
+		trace_writeback_pages_written(pages_written);
+
 		if (pages_written)
 			last_active = jiffies;
 		else if (wait_jiffies != -1UL) {
@@ -845,6 +865,8 @@ int bdi_writeback_thread(void *data)
 	 */
 	if (!list_empty(&bdi->work_list))
 		wb_do_writeback(wb, 1);
+
+	trace_writeback_thread_stop(bdi);
 	return 0;
 }