[PATCH 7/7] blk-throtl: don't throttle the same IO multiple times

[Tejun Heo]

BIO_THROTTLED is used to mark already throttled bios so that a bio
doesn't get throttled multiple times.  The flag gets set when the bio
starts getting dispatched from blk-throtl and cleared when it leaves
blk-throtl.

Unfortunately, this doesn't work when the request_queue decides to
split or requeue the bio and ends up throttling the same IO multiple
times.  This condition gets easily triggered and often leads to
multiple times lower bandwidth limit being enforced than configured.

Fix it by always setting BIO_THROTTLED for bios recursing to the same
request_queue and clearing only when a bio leaves the current level.

Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
---
 block/blk-core.c           | 10 +++++++---
 block/blk-throttle.c       |  8 --------
 include/linux/blk-cgroup.h | 20 ++++++++++++++++++++
 3 files changed, 27 insertions(+), 11 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index ad23b96..f0e3157 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2216,11 +2216,15 @@ blk_qc_t generic_make_request(struct bio *bio)
 			 */
 			bio_list_init(&lower);
 			bio_list_init(&same);
-			while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
-				if (q == bio->bi_disk->queue)
+			while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL) {
+				if (q == bio->bi_disk->queue) {
+					blkcg_bio_repeat_q_level(bio);
 					bio_list_add(&same, bio);
-				else
+				} else {
+					blkcg_bio_leave_q_level(bio);
 					bio_list_add(&lower, bio);
+				}
+			}
 			/* now assemble so we handle the lowest level first */
 			bio_list_merge(&bio_list_on_stack[0], &lower);
 			bio_list_merge(&bio_list_on_stack[0], &same);
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 1e6916b..76579b2 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -2223,14 +2223,6 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 out_unlock:
 	spin_unlock_irq(q->queue_lock);
 out:
-	/*
-	 * As multiple blk-throtls may stack in the same issue path, we
-	 * don't want bios to leave with the flag set.  Clear the flag if
-	 * being issued.
-	 */
-	if (!throttled)
-		bio_clear_flag(bio, BIO_THROTTLED);
-
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 	if (throttled || !td->track_bio_latency)
 		bio->bi_issue_stat.stat |= SKIP_LATENCY;
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index f2f9691..bed0416 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -675,9 +675,29 @@ static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to,
 #ifdef CONFIG_BLK_DEV_THROTTLING
 extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 			   struct bio *bio);
+
+static inline void blkcg_bio_repeat_q_level(struct bio *bio)
+{
+	/*
+	 * @bio is queued while processing a previous bio which was already
+	 * throttled.  Don't throttle it again.
+	 */
+	bio_set_flag(bio, BIO_THROTTLED);
+}
+
+static inline void blkcg_bio_leave_q_level(struct bio *bio)
+{
+	/*
+	 * @bio may get throttled at multiple q levels, clear THROTTLED
+	 * when leaving the current one.
+	 */
+	bio_clear_flag(bio, BIO_THROTTLED);
+}
 #else
 static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 				  struct bio *bio) { return false; }
+static inline void blkcg_bio_repeat_q_level(struct bio *bio) { }
+static inline void biocg_bio_leave_q_level(struct bio *bio) { }
 #endif
 
 static inline struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
-- 
2.9.5