[PATCH v3 11/11] blk-throttle: ignore idle cgroup limit

[Shaohua Li <shli@fb.com>]

Last patch introduces a way to detect idle cgroup. We use it to make
upgrade/downgrade decision.

Signed-off-by: Shaohua Li <shli@fb.com>
---
 block/blk-throttle.c | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index e8a2f31..c46d6e4 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -146,8 +146,6 @@ struct throtl_grp {
 
 	unsigned long last_check_time;
 
-	unsigned long last_dispatch_time[2];
-
 	/* When did we start a new slice */
 	unsigned long slice_start[2];
 	unsigned long slice_end[2];
@@ -489,8 +487,6 @@ static void throtl_pd_online(struct blkg_policy_data *pd)
 	 * Update has_rules[] after a new group is brought online.
 	 */
 	tg_update_has_rules(tg);
-	tg->last_dispatch_time[READ] = jiffies;
-	tg->last_dispatch_time[WRITE] = jiffies;
 }
 
 static void blk_throtl_update_valid_limit(struct throtl_data *td)
@@ -1664,9 +1660,8 @@ static bool throtl_upgrade_check_one(struct throtl_grp *tg)
 		return true;
 
 	if (time_after_eq(jiffies,
-	     tg->last_dispatch_time[READ] + tg->td->throtl_slice) &&
-	    time_after_eq(jiffies,
-	     tg->last_dispatch_time[WRITE] + tg->td->throtl_slice))
+		tg_last_high_overflow_time(tg) + tg->td->throtl_slice) &&
+	    throtl_tg_is_idle(tg))
 		return true;
 	return false;
 }
@@ -1715,6 +1710,19 @@ static bool throtl_can_upgrade(struct throtl_data *td,
 	return true;
 }
 
+static void throtl_upgrade_check(struct throtl_grp *tg)
+{
+	if (tg->td->limit_index != LIMIT_HIGH)
+		return;
+
+	if (!time_after_eq(jiffies,
+	     __tg_last_high_overflow_time(tg) + tg->td->throtl_slice))
+		return;
+
+	if (throtl_can_upgrade(tg->td, NULL))
+		throtl_upgrade_state(tg->td);
+}
+
 static void throtl_upgrade_state(struct throtl_data *td)
 {
 	struct cgroup_subsys_state *pos_css;
@@ -1749,15 +1757,14 @@ static bool throtl_downgrade_check_one(struct throtl_grp *tg)
 	struct throtl_data *td = tg->td;
 	unsigned long now = jiffies;
 
-	if (time_after_eq(now, tg->last_dispatch_time[READ] + td->throtl_slice) &&
-	    time_after_eq(now, tg->last_dispatch_time[WRITE] + td->throtl_slice))
-		return false;
 	/*
 	 * If cgroup is below high limit, consider downgrade and throttle other
 	 * cgroups
 	 */
 	if (time_after_eq(now, td->high_upgrade_time + td->throtl_slice) &&
-	    time_after_eq(now, tg_last_high_overflow_time(tg) + td->throtl_slice))
+	    time_after_eq(now, tg_last_high_overflow_time(tg) + td->throtl_slice) &&
+	    (!throtl_tg_is_idle(tg) ||
+	     !list_empty(&tg_to_blkg(tg)->blkcg->css.children)))
 		return true;
 	return false;
 }
@@ -1895,10 +1902,10 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 
 again:
 	while (true) {
-		tg->last_dispatch_time[rw] = jiffies;
 		if (tg->last_high_overflow_time[rw] == 0)
 			tg->last_high_overflow_time[rw] = jiffies;
 		throtl_downgrade_check(tg);
+		throtl_upgrade_check(tg);
 		/* throtl is FIFO - if bios are already queued, should queue */
 		if (sq->nr_queued[rw])
 			break;
-- 
2.9.3