mm/page-writeback: introduce tracepoint for wait_on_page_writeback()

Recently there have been some hung tasks on our server due to
wait_on_page_writeback(), and we want to know the details of this
PG_writeback, i.e.  this page is writing back to which device.  But it is
not so convenient to get the details.

I think it would be better to introduce a tracepoint for diagnosing the
writeback details.

Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Yafang Shao <[email protected]>
Reviewed-by: Andrew Morton <[email protected]>
Cc: Jan Kara <[email protected]>
Cc: Michal Hocko <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

1 files changed, 15 insertions, 1 deletions

diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 32db72c7c055..aa7f3aeac740 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -53,7 +53,7 @@ WB_WORK_REASON
 
 struct wb_writeback_work;
 
-TRACE_EVENT(writeback_dirty_page,
+DECLARE_EVENT_CLASS(writeback_page_template,
 
 	TP_PROTO(struct page *page, struct address_space *mapping),
 
@@ -79,6 +79,20 @@ TRACE_EVENT(writeback_dirty_page,
 	)
 );
 
+DEFINE_EVENT(writeback_page_template, writeback_dirty_page,
+
+	TP_PROTO(struct page *page, struct address_space *mapping),
+
+	TP_ARGS(page, mapping)
+);
+
+DEFINE_EVENT(writeback_page_template, wait_on_page_writeback,
+
+	TP_PROTO(struct page *page, struct address_space *mapping),
+
+	TP_ARGS(page, mapping)
+);
+
 DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
 
 	TP_PROTO(struct inode *inode, int flags),