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 <[e-mail]>
Cc: Johannes Weiner <[e-mail]>
Cc: Minchan Kim <[e-mail]>
Cc: Wu Fengguang <[e-mail]>
Cc: KAMEZAWA Hiroyuki <[e-mail]>
Cc: KOSAKI Motohiro <[e-mail]>
Cc: Rik van Riel <[e-mail]>
Cc: Jens Axboe <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

include/linux/backing-dev.h

···
 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)
 {

include/linux/mmzone.h

···
 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)
···
 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)

include/trace/events/writeback.h

···
 	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 */

mm/backing-dev.c

···
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
 	};
+static atomic_t nr_bdi_congested[2];
 
 void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
···
 	wait_queue_head_t *wqh = &congestion_wqh[sync];
 
 	bit = sync ? BDI_sync_congested : BDI_async_congested;
-	clear_bit(bit, &bdi->state);
+	if (test_and_clear_bit(bit, &bdi->state))
+		atomic_dec(&nr_bdi_congested[sync]);
 	smp_mb__after_clear_bit();
 	if (waitqueue_active(wqh))
 		wake_up(wqh);
···
 	enum bdi_state bit;
 
 	bit = sync ? BDI_sync_congested : BDI_async_congested;
-	set_bit(bit, &bdi->state);
+	if (!test_and_set_bit(bit, &bdi->state))
+		atomic_inc(&nr_bdi_congested[sync]);
 }
 EXPORT_SYMBOL(set_bdi_congested);
 
···
 }
 EXPORT_SYMBOL(congestion_wait);
 
+/**
+ * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes
+ * @zone: A zone to check if it is heavily congested
+ * @sync: SYNC or ASYNC IO
+ * @timeout: timeout in jiffies
+ *
+ * In the event of a congested backing_dev (any backing_dev) and the given
+ * @zone has experienced recent congestion, this waits for up to @timeout
+ * jiffies for either a BDI to exit congestion of the given @sync queue
+ * or a write to complete.
+ *
+ * In the absense of zone congestion, cond_resched() is called to yield
+ * the processor if necessary but otherwise does not sleep.
+ *
+ * The return value is 0 if the sleep is for the full timeout. Otherwise,
+ * it is the number of jiffies that were still remaining when the function
+ * returned. return_value == timeout implies the function did not sleep.
+ */
+long wait_iff_congested(struct zone *zone, int sync, long timeout)
+{
+	long ret;
+	unsigned long start = jiffies;
+	DEFINE_WAIT(wait);
+	wait_queue_head_t *wqh = &congestion_wqh[sync];
+
+	/*
+	 * If there is no congestion, or heavy congestion is not being
+	 * encountered in the current zone, yield if necessary instead
+	 * of sleeping on the congestion queue
+	 */
+	if (atomic_read(&nr_bdi_congested[sync]) == 0 ||
+			!zone_is_reclaim_congested(zone)) {
+		cond_resched();
+
+		/* In case we scheduled, work out time remaining */
+		ret = timeout - (jiffies - start);
+		if (ret < 0)
+			ret = 0;
+
+		goto out;
+	}
+
+	/* Sleep until uncongested or a write happens */
+	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+	ret = io_schedule_timeout(timeout);
+	finish_wait(wqh, &wait);
+
+out:
+	trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout),
+					jiffies_to_usecs(jiffies - start));
+
+	return ret;
+}
+EXPORT_SYMBOL(wait_iff_congested);

mm/page_alloc.c

···
 			preferred_zone, migratetype);
 
 		if (!page && gfp_mask & __GFP_NOFAIL)
-			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
 	} while (!page && (gfp_mask & __GFP_NOFAIL));
 
 	return page;
···
 	pages_reclaimed += did_some_progress;
 	if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
 		/* Wait for some write requests to complete then retry */
-		congestion_wait(BLK_RW_ASYNC, HZ/50);
+		wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
 		goto rebalance;
 	}
 

mm/vmscan.c

···
 	}
 	if (mapping->a_ops->writepage == NULL)
 		return PAGE_ACTIVATE;
-	if (!may_write_to_queue(mapping->backing_dev_info, sc)) {
-		disable_lumpy_reclaim_mode(sc);
+	if (!may_write_to_queue(mapping->backing_dev_info, sc))
 		return PAGE_KEEP;
-	}
 
 	if (clear_page_dirty_for_io(page)) {
 		int res;
···
  * shrink_page_list() returns the number of reclaimed pages
  */
 static unsigned long shrink_page_list(struct list_head *page_list,
+				      struct zone *zone,
 				      struct scan_control *sc)
 {
 	LIST_HEAD(ret_pages);
 	LIST_HEAD(free_pages);
 	int pgactivate = 0;
+	unsigned long nr_dirty = 0;
+	unsigned long nr_congested = 0;
 	unsigned long nr_reclaimed = 0;
 
 	cond_resched();
···
 			goto keep;
 
 		VM_BUG_ON(PageActive(page));
+		VM_BUG_ON(page_zone(page) != zone);
 
 		sc->nr_scanned++;
 
···
 		}
 
 		if (PageDirty(page)) {
+			nr_dirty++;
+
 			if (references == PAGEREF_RECLAIM_CLEAN)
 				goto keep_locked;
 			if (!may_enter_fs)
···
 			/* Page is dirty, try to write it out here */
 			switch (pageout(page, mapping, sc)) {
 			case PAGE_KEEP:
+				nr_congested++;
 				goto keep_locked;
 			case PAGE_ACTIVATE:
 				goto activate_locked;
···
 		list_add(&page->lru, &ret_pages);
 		VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
 	}
+
+	/*
+	 * Tag a zone as congested if all the dirty pages encountered were
+	 * backed by a congested BDI. In this case, reclaimers should just
+	 * back off and wait for congestion to clear because further reclaim
+	 * will encounter the same problem
+	 */
+	if (nr_dirty == nr_congested)
+		zone_set_flag(zone, ZONE_CONGESTED);
 
 	free_page_list(&free_pages);
 
···
 
 	spin_unlock_irq(&zone->lru_lock);
 
-	nr_reclaimed = shrink_page_list(&page_list, sc);
+	nr_reclaimed = shrink_page_list(&page_list, zone, sc);
 
 	/* Check if we should syncronously wait for writeback */
 	if (should_reclaim_stall(nr_taken, nr_reclaimed, priority, sc)) {
 		set_lumpy_reclaim_mode(priority, sc, true);
-		nr_reclaimed += shrink_page_list(&page_list, sc);
+		nr_reclaimed += shrink_page_list(&page_list, zone, sc);
 	}
 
 	local_irq_disable();
···
 
 		/* Take a nap, wait for some writeback to complete */
 		if (!sc->hibernation_mode && sc->nr_scanned &&
-		    priority < DEF_PRIORITY - 2)
-			congestion_wait(BLK_RW_ASYNC, HZ/10);
+		    priority < DEF_PRIORITY - 2) {
+			struct zone *preferred_zone;
+
+			first_zones_zonelist(zonelist, gfp_zone(sc->gfp_mask),
+							NULL, &preferred_zone);
+			wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/10);
+		}
 	}
 
 out:
···
 				if (!zone_watermark_ok(zone, order,
 					    min_wmark_pages(zone), end_zone, 0))
 					has_under_min_watermark_zone = 1;
+			} else {
+				/*
+				 * If a zone reaches its high watermark,
+				 * consider it to be no longer congested. It's
+				 * possible there are dirty pages backed by
+				 * congested BDIs but as pressure is relieved,
+				 * spectulatively avoid congestion waits
+				 */
+				zone_clear_flag(zone, ZONE_CONGESTED);
 			}
 
 		}