writeback: make writeback_control.nr_to_write straight

Pass struct wb_writeback_work all the way down to writeback_sb_inodes(),
and initialize the struct writeback_control there.

struct writeback_control is basically designed to control writeback of a
single file, but we keep abuse it for writing multiple files in
writeback_sb_inodes() and its callers.

It immediately clean things up, e.g. suddenly wbc.nr_to_write vs
work->nr_pages starts to make sense, and instead of saving and restoring
pages_skipped in writeback_sb_inodes it can always start with a clean
zero value.

It also makes a neat IO pattern change: large dirty files are now
written in the full 4MB writeback chunk size, rather than whatever
remained quota in wbc->nr_to_write.

Acked-by: Jan Kara <jack@suse.cz>
Proposed-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>

2 files changed, 29 insertions, 16 deletions

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 2f1b512..df1b7f1 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -24,12 +24,9 @@ enum writeback_sync_modes {
  */
 struct writeback_control {
 	enum writeback_sync_modes sync_mode;
-	unsigned long *older_than_this;	/* If !NULL, only write back inodes
-					   older than this */
 	long nr_to_write;		/* Write this many pages, and decrement
 					   this for each page written */
 	long pages_skipped;		/* Pages which were not written */
-	long inodes_written;		/* # of inodes written (at least) */
 
 	/*
 	 * For a_ops->writepages(): is start or end are non-zero then this is
@@ -56,8 +53,7 @@ void writeback_inodes_sb_nr(struct super_block *, unsigned long nr);
 int writeback_inodes_sb_if_idle(struct super_block *);
 int writeback_inodes_sb_nr_if_idle(struct super_block *, unsigned long nr);
 void sync_inodes_sb(struct super_block *);
-void writeback_inodes_wb(struct bdi_writeback *wb,
-		struct writeback_control *wbc);
+long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages);
 long wb_do_writeback(struct bdi_writeback *wb, int force_wait);
 void wakeup_flusher_threads(long nr_pages);
 
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 205d149..3e7662a 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -62,6 +62,9 @@ DEFINE_EVENT(writeback_work_class, name, \
 DEFINE_WRITEBACK_WORK_EVENT(writeback_nothread);
 DEFINE_WRITEBACK_WORK_EVENT(writeback_queue);
 DEFINE_WRITEBACK_WORK_EVENT(writeback_exec);
+DEFINE_WRITEBACK_WORK_EVENT(writeback_start);
+DEFINE_WRITEBACK_WORK_EVENT(writeback_written);
+DEFINE_WRITEBACK_WORK_EVENT(writeback_wait);
 
 TRACE_EVENT(writeback_pages_written,
 	TP_PROTO(long pages_written),
@@ -101,6 +104,30 @@ DEFINE_WRITEBACK_EVENT(writeback_bdi_register);
 DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister);
 DEFINE_WRITEBACK_EVENT(writeback_thread_start);
 DEFINE_WRITEBACK_EVENT(writeback_thread_stop);
+DEFINE_WRITEBACK_EVENT(balance_dirty_start);
+DEFINE_WRITEBACK_EVENT(balance_dirty_wait);
+
+TRACE_EVENT(balance_dirty_written,
+
+	TP_PROTO(struct backing_dev_info *bdi, int written),
+
+	TP_ARGS(bdi, written),
+
+	TP_STRUCT__entry(
+		__array(char,	name, 32)
+		__field(int,	written)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		__entry->written = written;
+	),
+
+	TP_printk("bdi %s written %d",
+		  __entry->name,
+		  __entry->written
+	)
+);
 
 DECLARE_EVENT_CLASS(wbc_class,
 	TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi),
@@ -114,7 +141,6 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__field(int, for_background)
 		__field(int, for_reclaim)
 		__field(int, range_cyclic)
-		__field(unsigned long, older_than_this)
 		__field(long, range_start)
 		__field(long, range_end)
 	),
@@ -128,14 +154,12 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->for_background	= wbc->for_background;
 		__entry->for_reclaim	= wbc->for_reclaim;
 		__entry->range_cyclic	= wbc->range_cyclic;
-		__entry->older_than_this = wbc->older_than_this ?
-						*wbc->older_than_this : 0;
 		__entry->range_start	= (long)wbc->range_start;
 		__entry->range_end	= (long)wbc->range_end;
 	),
 
 	TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d "
-		"bgrd=%d reclm=%d cyclic=%d older=0x%lx "
+		"bgrd=%d reclm=%d cyclic=%d "
 		"start=0x%lx end=0x%lx",
 		__entry->name,
 		__entry->nr_to_write,
@@ -145,7 +169,6 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->for_background,
 		__entry->for_reclaim,
 		__entry->range_cyclic,
-		__entry->older_than_this,
 		__entry->range_start,
 		__entry->range_end)
 )
@@ -154,12 +177,6 @@ DECLARE_EVENT_CLASS(wbc_class,
 DEFINE_EVENT(wbc_class, name, \
 	TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), \
 	TP_ARGS(wbc, bdi))
-DEFINE_WBC_EVENT(wbc_writeback_start);
-DEFINE_WBC_EVENT(wbc_writeback_written);
-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);
 
 TRACE_EVENT(writeback_queue_io,