writeback: Tracing support V2

index c8471b3..767898b 100644
@@ -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_wb_sched_queue(bdi, work);
+
 	spin_lock(&bdi->wb_lock);
 	list_add_tail(&work->list, &bdi->work_list);
 	spin_unlock(&bdi->wb_lock);

@@ -74,12 +85,16 @@ 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_wb_sched_default(bdi, work);
 		wake_up_process(default_backing_dev_info.wb.task);
 	} else {
 		struct bdi_writeback *wb = &bdi->wb;
 
-		if (wb->task)
+		if (wb->task) {
+			trace_wb_sched_task(bdi, work);
 			wake_up_process(wb->task);
+		} else
+			trace_wb_sched_notask(bdi, work);
 	}
 }
 

@@ -95,8 +110,10 @@ __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_wb_sched_nowork(bdi, work);
 			wake_up_process(bdi->wb.task);
+		}
 		return;
 	}
 

@@ -751,6 +768,8 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 		if (force_wait)
 			work->sync_mode = WB_SYNC_ALL;
 
+		trace_wb_sched_exec(bdi, work);
+
 		wrote += wb_writeback(wb, work);
 
 		/*

@@ -805,9 +824,13 @@ int bdi_writeback_thread(void *data)
 	smp_mb__after_clear_bit();
 	wake_up_bit(&bdi->state, BDI_pending);
 
+	trace_wb_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 +868,8 @@ int bdi_writeback_thread(void *data)
 	 */
 	if (!list_empty(&bdi->work_list))
 		wb_do_writeback(wb, 1);
+
+	trace_wb_thread_stop(bdi);
 	return 0;
 }
 

93 lines not on this page · raw message

index bceac64..e0411a6 100644
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/writeback.h>
 #include <linux/device.h>
+#include <trace/events/writeback.h>
 
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 

@@ -518,6 +519,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 
 	bdi_debug_register(bdi, dev_name(dev));
 	set_bit(BDI_registered, &bdi->state);
+	trace_wb_bdi_register(bdi);
 exit:
 	return ret;
 }

@@ -578,6 +580,7 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 void bdi_unregister(struct backing_dev_info *bdi)
 {
 	if (bdi->dev) {
+		trace_wb_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
 
 		if (!bdi_cap_flush_forker(bdi))

index 767898b..3e9d221 100644
@@ -659,10 +659,14 @@ static long wb_writeback(struct bdi_writeback *wb,
 		wbc.more_io = 0;
 		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
 		wbc.pages_skipped = 0;
+
+		trace_wbc_writeback_start(&wbc, wb->bdi);
 		if (work->sb)
 			__writeback_inodes_sb(work->sb, wb, &wbc);
 		else
 			writeback_inodes_wb(wb, &wbc);
+		trace_wbc_writeback_written(&wbc, wb->bdi);
+
 		work->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
 		wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
 

@@ -690,6 +694,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 		if (!list_empty(&wb->b_more_io))  {
 			inode = list_entry(wb->b_more_io.prev,
 						struct inode, i_list);
+			trace_wbc_writeback_wait(&wbc, wb->bdi);
 			inode_wait_for_writeback(inode);
 		}
 		spin_unlock(&inode_lock);

75 lines not on this page · raw message

index 37498ef..d556cd8 100644
@@ -34,6 +34,7 @@
 #include <linux/syscalls.h>
 #include <linux/buffer_head.h>
 #include <linux/pagevec.h>
+#include <trace/events/writeback.h>
 
 /*
  * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited

@@ -535,11 +536,13 @@ static void balance_dirty_pages(struct address_space *mapping,
 		 * threshold otherwise wait until the disk writes catch
 		 * up.
 		 */
+		trace_wbc_balance_dirty_start(&wbc, bdi);
 		if (bdi_nr_reclaimable > bdi_thresh) {
 			writeback_inodes_wb(&bdi->wb, &wbc);
 			pages_written += write_chunk - wbc.nr_to_write;
 			get_dirty_limits(&background_thresh, &dirty_thresh,
 				       &bdi_thresh, bdi);
+			trace_wbc_balance_dirty_written(&wbc, bdi);
 		}
 
 		/*

@@ -565,6 +568,7 @@ static void balance_dirty_pages(struct address_space *mapping,
 		if (pages_written >= write_chunk)
 			break;		/* We've done our duty */
 
+		trace_wbc_balance_dirty_wait(&wbc, bdi);
 		__set_current_state(TASK_INTERRUPTIBLE);
 		io_schedule_timeout(pause);
 

index 4e219e2..9d8460e 100644
@@ -155,6 +155,7 @@ DEFINE_WBC_EVENT(wbc_writeback_wait);
 DEFINE_WBC_EVENT(wbc_balance_dirty_start);
 DEFINE_WBC_EVENT(wbc_balance_dirty_written);
 DEFINE_WBC_EVENT(wbc_balance_dirty_wait);
+DEFINE_WBC_EVENT(wbc_writepage);
 
 #endif /* _TRACE_WRITEBACK_H */
 

index d556cd8..3d2111a 100644
@@ -933,6 +933,7 @@ continue_unlock:
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
+			trace_wbc_writepage(wbc, mapping->backing_dev_info);
 			ret = (*writepage)(page, wbc, data);
 			if (unlikely(ret)) {
 				if (ret == AOP_WRITEPAGE_ACTIVATE) {