1 files changed, 77 insertions, 6 deletions

diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 5639921dfa92..f10c2a0d18d4 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -131,6 +131,20 @@ static u8 dd_rq_ioclass(struct request *rq)
 }
 
 /*
+ * get the request before `rq' in sector-sorted order
+ */
+static inline struct request *
+deadline_earlier_request(struct request *rq)
+{
+	struct rb_node *node = rb_prev(&rq->rb_node);
+
+	if (node)
+		return rb_entry_rq(node);
+
+	return NULL;
+}
+
+/*
  * get the request after `rq' in sector-sorted order
  */
 static inline struct request *
@@ -278,6 +292,39 @@ static inline int deadline_check_fifo(struct dd_per_prio *per_prio,
 }
 
 /*
+ * Check if rq has a sequential request preceding it.
+ */
+static bool deadline_is_seq_write(struct deadline_data *dd, struct request *rq)
+{
+	struct request *prev = deadline_earlier_request(rq);
+
+	if (!prev)
+		return false;
+
+	return blk_rq_pos(prev) + blk_rq_sectors(prev) == blk_rq_pos(rq);
+}
+
+/*
+ * Skip all write requests that are sequential from @rq, even if we cross
+ * a zone boundary.
+ */
+static struct request *deadline_skip_seq_writes(struct deadline_data *dd,
+						struct request *rq)
+{
+	sector_t pos = blk_rq_pos(rq);
+	sector_t skipped_sectors = 0;
+
+	while (rq) {
+		if (blk_rq_pos(rq) != pos + skipped_sectors)
+			break;
+		skipped_sectors += blk_rq_sectors(rq);
+		rq = deadline_latter_request(rq);
+	}
+
+	return rq;
+}
+
+/*
  * For the specified data direction, return the next request to
  * dispatch using arrival ordered lists.
  */
@@ -297,11 +344,16 @@ deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
 
 	/*
 	 * Look for a write request that can be dispatched, that is one with
-	 * an unlocked target zone.
+	 * an unlocked target zone. For some HDDs, breaking a sequential
+	 * write stream can lead to lower throughput, so make sure to preserve
+	 * sequential write streams, even if that stream crosses into the next
+	 * zones and these zones are unlocked.
 	 */
 	spin_lock_irqsave(&dd->zone_lock, flags);
 	list_for_each_entry(rq, &per_prio->fifo_list[DD_WRITE], queuelist) {
-		if (blk_req_can_dispatch_to_zone(rq))
+		if (blk_req_can_dispatch_to_zone(rq) &&
+		    (blk_queue_nonrot(rq->q) ||
+		     !deadline_is_seq_write(dd, rq)))
 			goto out;
 	}
 	rq = NULL;
@@ -331,13 +383,19 @@ deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
 
 	/*
 	 * Look for a write request that can be dispatched, that is one with
-	 * an unlocked target zone.
+	 * an unlocked target zone. For some HDDs, breaking a sequential
+	 * write stream can lead to lower throughput, so make sure to preserve
+	 * sequential write streams, even if that stream crosses into the next
+	 * zones and these zones are unlocked.
 	 */
 	spin_lock_irqsave(&dd->zone_lock, flags);
 	while (rq) {
 		if (blk_req_can_dispatch_to_zone(rq))
 			break;
-		rq = deadline_latter_request(rq);
+		if (blk_queue_nonrot(rq->q))
+			rq = deadline_latter_request(rq);
+		else
+			rq = deadline_skip_seq_writes(dd, rq);
 	}
 	spin_unlock_irqrestore(&dd->zone_lock, flags);
 
@@ -789,6 +847,18 @@ static void dd_prepare_request(struct request *rq)
 	rq->elv.priv[0] = NULL;
 }
 
+static bool dd_has_write_work(struct blk_mq_hw_ctx *hctx)
+{
+	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
+	enum dd_prio p;
+
+	for (p = 0; p <= DD_PRIO_MAX; p++)
+		if (!list_empty_careful(&dd->per_prio[p].fifo_list[DD_WRITE]))
+			return true;
+
+	return false;
+}
+
 /*
  * Callback from inside blk_mq_free_request().
  *
@@ -828,9 +898,10 @@ static void dd_finish_request(struct request *rq)
 
 		spin_lock_irqsave(&dd->zone_lock, flags);
 		blk_req_zone_write_unlock(rq);
-		if (!list_empty(&per_prio->fifo_list[DD_WRITE]))
-			blk_mq_sched_mark_restart_hctx(rq->mq_hctx);
 		spin_unlock_irqrestore(&dd->zone_lock, flags);
+
+		if (dd_has_write_work(rq->mq_hctx))
+			blk_mq_sched_mark_restart_hctx(rq->mq_hctx);
 	}
 }