diff --git a/include/linux/sched.h b/include/linux/sched.h
index 41d0237..a4a5582 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1525,6 +1525,13 @@
 	int make_it_fail;
 #endif
 	struct prop_local_single dirties;
+	/*
+	 * when (nr_dirtied >= nr_dirtied_pause), it's time to call
+	 * balance_dirty_pages() for some dirty throttling pause
+	 */
+	int nr_dirtied;
+	int nr_dirtied_pause;
+
 #ifdef CONFIG_LATENCYTOP
 	int latency_record_count;
 	struct latency_record latency_record[LT_SAVECOUNT];
diff --git a/kernel/fork.c b/kernel/fork.c
index 8e6b6f4..cc0815d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1302,6 +1302,9 @@
 	p->pdeath_signal = 0;
 	p->exit_state = 0;
 
+	p->nr_dirtied = 0;
+	p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
+
 	/*
 	 * Ok, make it visible to the rest of the system.
 	 * We dont wake it up yet.
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d4a6e91..daff320 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -54,20 +54,6 @@
  */
 static long ratelimit_pages = 32;
 
-/*
- * When balance_dirty_pages decides that the caller needs to perform some
- * non-background writeback, this is how many pages it will attempt to write.
- * It should be somewhat larger than dirtied pages to ensure that reasonably
- * large amounts of I/O are submitted.
- */
-static inline long sync_writeback_pages(unsigned long dirtied)
-{
-	if (dirtied < ratelimit_pages)
-		dirtied = ratelimit_pages;
-
-	return dirtied + dirtied / 2;
-}
-
 /* The following parameters are exported via /proc/sys/vm */
 
 /*
@@ -169,6 +155,8 @@
 	int shift = calc_period_shift();
 	prop_change_shift(&vm_completions, shift);
 	prop_change_shift(&vm_dirties, shift);
+
+	writeback_set_ratelimit();
 }
 
 int dirty_background_ratio_handler(struct ctl_table *table, int write,
@@ -979,6 +967,23 @@
 }
 
 /*
+ * After a task dirtied this many pages, balance_dirty_pages_ratelimited_nr()
+ * will look to see if it needs to start dirty throttling.
+ *
+ * If dirty_poll_interval is too low, big NUMA machines will call the expensive
+ * global_page_state() too often. So scale it near-sqrt to the safety margin
+ * (the number of pages we may dirty without exceeding the dirty limits).
+ */
+static unsigned long dirty_poll_interval(unsigned long dirty,
+					 unsigned long thresh)
+{
+	if (thresh > dirty)
+		return 1UL << (ilog2(thresh - dirty) >> 1);
+
+	return 1;
+}
+
+/*
  * balance_dirty_pages() must be called by processes which are generating dirty
  * data.  It looks at the number of dirty pages in the machine and will force
  * the caller to perform writeback if the system is over `vm_dirty_ratio'.
@@ -1112,6 +1117,9 @@
 	if (clear_dirty_exceeded && bdi->dirty_exceeded)
 		bdi->dirty_exceeded = 0;
 
+	current->nr_dirtied = 0;
+	current->nr_dirtied_pause = dirty_poll_interval(nr_dirty, dirty_thresh);
+
 	if (writeback_in_progress(bdi))
 		return;
 
@@ -1138,7 +1146,7 @@
 	}
 }
 
-static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;
+static DEFINE_PER_CPU(int, bdp_ratelimits);
 
 /**
  * balance_dirty_pages_ratelimited_nr - balance dirty memory state
@@ -1158,31 +1166,39 @@
 					unsigned long nr_pages_dirtied)
 {
 	struct backing_dev_info *bdi = mapping->backing_dev_info;
-	unsigned long ratelimit;
-	unsigned long *p;
+	int ratelimit;
+	int *p;
 
 	if (!bdi_cap_account_dirty(bdi))
 		return;
 
-	ratelimit = ratelimit_pages;
-	if (mapping->backing_dev_info->dirty_exceeded)
-		ratelimit = 8;
+	ratelimit = current->nr_dirtied_pause;
+	if (bdi->dirty_exceeded)
+		ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10));
 
-	/*
-	 * Check the rate limiting. Also, we do not want to throttle real-time
-	 * tasks in balance_dirty_pages(). Period.
-	 */
+	current->nr_dirtied += nr_pages_dirtied;
+
 	preempt_disable();
+	/*
+	 * This prevents one CPU to accumulate too many dirtied pages without
+	 * calling into balance_dirty_pages(), which can happen when there are
+	 * 1000+ tasks, all of them start dirtying pages at exactly the same
+	 * time, hence all honoured too large initial task->nr_dirtied_pause.
+	 */
 	p =  &__get_cpu_var(bdp_ratelimits);
-	*p += nr_pages_dirtied;
-	if (unlikely(*p >= ratelimit)) {
-		ratelimit = sync_writeback_pages(*p);
+	if (unlikely(current->nr_dirtied >= ratelimit))
 		*p = 0;
-		preempt_enable();
-		balance_dirty_pages(mapping, ratelimit);
-		return;
+	else {
+		*p += nr_pages_dirtied;
+		if (unlikely(*p >= ratelimit_pages)) {
+			*p = 0;
+			ratelimit = 0;
+		}
 	}
 	preempt_enable();
+
+	if (unlikely(current->nr_dirtied >= ratelimit))
+		balance_dirty_pages(mapping, current->nr_dirtied);
 }
 EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
 
@@ -1277,22 +1293,17 @@
  *
  * Here we set ratelimit_pages to a level which ensures that when all CPUs are
  * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory
- * thresholds before writeback cuts in.
- *
- * But the limit should not be set too high.  Because it also controls the
- * amount of memory which the balance_dirty_pages() caller has to write back.
- * If this is too large then the caller will block on the IO queue all the
- * time.  So limit it to four megabytes - the balance_dirty_pages() caller
- * will write six megabyte chunks, max.
+ * thresholds.
  */
 
 void writeback_set_ratelimit(void)
 {
-	ratelimit_pages = vm_total_pages / (num_online_cpus() * 32);
+	unsigned long background_thresh;
+	unsigned long dirty_thresh;
+	global_dirty_limits(&background_thresh, &dirty_thresh);
+	ratelimit_pages = dirty_thresh / (num_online_cpus() * 32);
 	if (ratelimit_pages < 16)
 		ratelimit_pages = 16;
-	if (ratelimit_pages * PAGE_CACHE_SIZE > 4096 * 1024)
-		ratelimit_pages = (4096 * 1024) / PAGE_CACHE_SIZE;
 }
 
 static int __cpuinit