---

yaml
---
r: 272129
b: refs/heads/master
c: 92df3a7
h: refs/heads/master
i:
  272127: f5e194b
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: f84f6e2b0868f198f97a32ba503d6f9f319a249a
+refs/heads/master: 92df3a723f84cdf8133560bbff950a7a99e92bc9

trunk/mm/vmscan.c

@@ -751,14 +751,17 @@ static noinline_for_stack void free_page_list(struct list_head *free_pages)
 static unsigned long shrink_page_list(struct list_head *page_list,
 				      struct zone *zone,
 				      struct scan_control *sc,
-				      int priority)
+				      int priority,
+				      unsigned long *ret_nr_dirty,
+				      unsigned long *ret_nr_writeback)
 {
 	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;
+	unsigned long nr_writeback = 0;
 
 	cond_resched();
 
@@ -795,6 +798,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
 
 		if (PageWriteback(page)) {
+			nr_writeback++;
 			/*
 			 * Synchronous reclaim cannot queue pages for
 			 * writeback due to the possibility of stack overflow
@@ -1000,6 +1004,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 	list_splice(&ret_pages, page_list);
 	count_vm_events(PGACTIVATE, pgactivate);
+	*ret_nr_dirty += nr_dirty;
+	*ret_nr_writeback += nr_writeback;
 	return nr_reclaimed;
 }
 
@@ -1460,6 +1466,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 	unsigned long nr_taken;
 	unsigned long nr_anon;
 	unsigned long nr_file;
+	unsigned long nr_dirty = 0;
+	unsigned long nr_writeback = 0;
 	isolate_mode_t reclaim_mode = ISOLATE_INACTIVE;
 
 	while (unlikely(too_many_isolated(zone, file, sc))) {
@@ -1512,12 +1520,14 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 
 	spin_unlock_irq(&zone->lru_lock);
 
-	nr_reclaimed = shrink_page_list(&page_list, zone, sc, priority);
+	nr_reclaimed = shrink_page_list(&page_list, zone, sc, priority,
+						&nr_dirty, &nr_writeback);
 
 	/* Check if we should syncronously wait for writeback */
 	if (should_reclaim_stall(nr_taken, nr_reclaimed, priority, sc)) {
 		set_reclaim_mode(priority, sc, true);
-		nr_reclaimed += shrink_page_list(&page_list, zone, sc, priority);
+		nr_reclaimed += shrink_page_list(&page_list, zone, sc,
+					priority, &nr_dirty, &nr_writeback);
 	}
 
 	local_irq_disable();
@@ -1527,6 +1537,32 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 
 	putback_lru_pages(zone, sc, nr_anon, nr_file, &page_list);
 
+	/*
+	 * If reclaim is isolating dirty pages under writeback, it implies
+	 * that the long-lived page allocation rate is exceeding the page
+	 * laundering rate. Either the global limits are not being effective
+	 * at throttling processes due to the page distribution throughout
+	 * zones or there is heavy usage of a slow backing device. The
+	 * only option is to throttle from reclaim context which is not ideal
+	 * as there is no guarantee the dirtying process is throttled in the
+	 * same way balance_dirty_pages() manages.
+	 *
+	 * This scales the number of dirty pages that must be under writeback
+	 * before throttling depending on priority. It is a simple backoff
+	 * function that has the most effect in the range DEF_PRIORITY to
+	 * DEF_PRIORITY-2 which is the priority reclaim is considered to be
+	 * in trouble and reclaim is considered to be in trouble.
+	 *
+	 * DEF_PRIORITY   100% isolated pages must be PageWriteback to throttle
+	 * DEF_PRIORITY-1  50% must be PageWriteback
+	 * DEF_PRIORITY-2  25% must be PageWriteback, kswapd in trouble
+	 * ...
+	 * DEF_PRIORITY-6 For SWAP_CLUSTER_MAX isolated pages, throttle if any
+	 *                     isolated page is PageWriteback
+	 */
+	if (nr_writeback && nr_writeback >= (nr_taken >> (DEF_PRIORITY-priority)))
+		wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10);
+
 	trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id,
 		zone_idx(zone),
 		nr_scanned, nr_reclaimed,