[PATCH 35/51] writeback: make bdi->min/max_ratio handling cgroup writeback aware

[Tejun Heo]

bdi->min/max_ratio are user-configurable per-bdi knobs which regulate
dirty limit of each bdi.  For cgroup writeback, they need to be
further distributed across wb's (bdi_writeback's) belonging to the
configured bdi.

This patch introduces wb_min_max_ratio() which distributes
bdi->min/max_ratio according to a wb's proportion in the total active
bandwidth of its bdi.

v2: Update wb_min_max_ratio() to fix a bug where both min and max were
    assigned the min value and avoid calculations when possible.

Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
---
 mm/page-writeback.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 46 insertions(+), 4 deletions(-)

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 99b8846..9b55f12 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -155,6 +155,46 @@ static unsigned long writeout_period_time = 0;
  */
 #define VM_COMPLETIONS_PERIOD_LEN (3*HZ)
 
+#ifdef CONFIG_CGROUP_WRITEBACK
+
+static void wb_min_max_ratio(struct bdi_writeback *wb,
+			     unsigned long *minp, unsigned long *maxp)
+{
+	unsigned long this_bw = wb->avg_write_bandwidth;
+	unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth);
+	unsigned long long min = wb->bdi->min_ratio;
+	unsigned long long max = wb->bdi->max_ratio;
+
+	/*
+	 * @wb may already be clean by the time control reaches here and
+	 * the total may not include its bw.
+	 */
+	if (this_bw < tot_bw) {
+		if (min) {
+			min *= this_bw;
+			do_div(min, tot_bw);
+		}
+		if (max < 100) {
+			max *= this_bw;
+			do_div(max, tot_bw);
+		}
+	}
+
+	*minp = min;
+	*maxp = max;
+}
+
+#else	/* CONFIG_CGROUP_WRITEBACK */
+
+static void wb_min_max_ratio(struct bdi_writeback *wb,
+			     unsigned long *minp, unsigned long *maxp)
+{
+	*minp = wb->bdi->min_ratio;
+	*maxp = wb->bdi->max_ratio;
+}
+
+#endif	/* CONFIG_CGROUP_WRITEBACK */
+
 /*
  * In a memory zone, there is a certain amount of pages we consider
  * available for the page cache, which is essentially the number of
@@ -539,9 +579,9 @@ static unsigned long hard_dirty_limit(unsigned long thresh)
  */
 unsigned long wb_dirty_limit(struct bdi_writeback *wb, unsigned long dirty)
 {
-	struct backing_dev_info *bdi = wb->bdi;
 	u64 wb_dirty;
 	long numerator, denominator;
+	unsigned long wb_min_ratio, wb_max_ratio;
 
 	/*
 	 * Calculate this BDI's share of the dirty ratio.
@@ -552,9 +592,11 @@ unsigned long wb_dirty_limit(struct bdi_writeback *wb, unsigned long dirty)
 	wb_dirty *= numerator;
 	do_div(wb_dirty, denominator);
 
-	wb_dirty += (dirty * bdi->min_ratio) / 100;
-	if (wb_dirty > (dirty * bdi->max_ratio) / 100)
-		wb_dirty = dirty * bdi->max_ratio / 100;
+	wb_min_max_ratio(wb, &wb_min_ratio, &wb_max_ratio);
+
+	wb_dirty += (dirty * wb_min_ratio) / 100;
+	if (wb_dirty > (dirty * wb_max_ratio) / 100)
+		wb_dirty = dirty * wb_max_ratio / 100;
 
 	return wb_dirty;
 }
-- 
2.4.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/