writeback: do not sleep on the congestion queue if there are no congested BDIs or if significant congestion is not being encountered in the current zone

If congestion_wait() is called with no BDI congested, the caller will
sleep for the full timeout and this may be an unnecessary sleep.  This
patch adds a wait_iff_congested() that checks congestion and only sleeps
if a BDI is congested else, it calls cond_resched() to ensure the caller
is not hogging the CPU longer than its quota but otherwise will not sleep.

This is aimed at reducing some of the major desktop stalls reported during
IO.  For example, while kswapd is operating, it calls congestion_wait()
but it could just have been reclaiming clean page cache pages with no
congestion.  Without this patch, it would sleep for a full timeout but
after this patch, it'll just call schedule() if it has been on the CPU too
long.  Similar logic applies to direct reclaimers that are not making
enough progress.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 16 insertions, 1 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 35b0074..f1b402a 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -285,7 +285,7 @@ enum {
 void clear_bdi_congested(struct backing_dev_info *bdi, int sync);
 void set_bdi_congested(struct backing_dev_info *bdi, int sync);
 long congestion_wait(int sync, long timeout);
-
+long wait_iff_congested(struct zone *zone, int sync, long timeout);
 
 static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
 {
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index c3c17fb..39c24eb 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -423,6 +423,9 @@ struct zone {
 typedef enum {
 	ZONE_RECLAIM_LOCKED,		/* prevents concurrent reclaim */
 	ZONE_OOM_LOCKED,		/* zone is in OOM killer zonelist */
+	ZONE_CONGESTED,			/* zone has many dirty pages backed by
+					 * a congested BDI
+					 */
 } zone_flags_t;
 
 static inline void zone_set_flag(struct zone *zone, zone_flags_t flag)
@@ -440,6 +443,11 @@ static inline void zone_clear_flag(struct zone *zone, zone_flags_t flag)
 	clear_bit(flag, &zone->flags);
 }
 
+static inline int zone_is_reclaim_congested(const struct zone *zone)
+{
+	return test_bit(ZONE_CONGESTED, &zone->flags);
+}
+
 static inline int zone_is_reclaim_locked(const struct zone *zone)
 {
 	return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags);
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index d2b2654..89a2b2d 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -179,6 +179,13 @@ DEFINE_EVENT(writeback_congest_waited_template, writeback_congestion_wait,
 	TP_ARGS(usec_timeout, usec_delayed)
 );
 
+DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested,
+
+	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),
+
+	TP_ARGS(usec_timeout, usec_delayed)
+);
+
 #endif /* _TRACE_WRITEBACK_H */
 
 /* This part must be outside protection */