block: attempt to merge with existing requests on plug flush

One of the disadvantages of on-stack plugging is that we potentially
lose out on merging since all pending IO isn't always visible to
everybody. When we flush the on-stack plugs, right now we don't do
any checks to see if potential merge candidates could be utilized.

Correct this by adding a new insert variant, ELEVATOR_INSERT_SORT_MERGE.
It works just ELEVATOR_INSERT_SORT, but first checks whether we can
merge with an existing request before doing the insertion (if we fail
merging).

This fixes a regression with multiple processes issuing IO that
can be merged.

Thanks to Shaohua Li <shaohua.li@intel.com> for testing and fixing
an accounting bug.
Signed-off-by: NJens Axboe <jaxboe@fusionio.com>

block/blk-core.c

@@ -2685,7 +2685,7 @@ static void flush_plug_list(struct blk_plug *plug)
 		/*
 		 * rq is already accounted, so use raw insert
 		 */
-		__elv_add_request(q, rq, ELEVATOR_INSERT_SORT);
+		__elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE);
 	}
 
 	if (q) {

block/blk-merge.c

@@ -465,3 +465,9 @@ int attempt_front_merge(struct request_queue *q, struct request *rq)
 
 	return 0;
 }
+
+int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
+			  struct request *next)
+{
+	return attempt_merge(q, rq, next);
+}

block/blk.h

@@ -103,6 +103,8 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 		      struct bio *bio);
 int attempt_back_merge(struct request_queue *q, struct request *rq);
 int attempt_front_merge(struct request_queue *q, struct request *rq);
+int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
+				struct request *next);
 void blk_recalc_rq_segments(struct request *rq);
 void blk_rq_set_mixed_merge(struct request *rq);
 

block/elevator.c

@@ -521,6 +521,40 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	return ELEVATOR_NO_MERGE;
 }
 
+/*
+ * Attempt to do an insertion back merge. Only check for the case where
+ * we can append 'rq' to an existing request, so we can throw 'rq' away
+ * afterwards.
+ *
+ * Returns true if we merged, false otherwise
+ */
+static bool elv_attempt_insert_merge(struct request_queue *q,
+				     struct request *rq)
+{
+	struct request *__rq;
+
+	if (blk_queue_nomerges(q))
+		return false;
+
+	/*
+	 * First try one-hit cache.
+	 */
+	if (q->last_merge && blk_attempt_req_merge(q, q->last_merge, rq))
+		return true;
+
+	if (blk_queue_noxmerges(q))
+		return false;
+
+	/*
+	 * See if our hash lookup can find a potential backmerge.
+	 */
+	__rq = elv_rqhash_find(q, blk_rq_pos(rq));
+	if (__rq && blk_attempt_req_merge(q, __rq, rq))
+		return true;
+
+	return false;
+}
+
 void elv_merged_request(struct request_queue *q, struct request *rq, int type)
 {
 	struct elevator_queue *e = q->elevator;
@@ -538,14 +572,18 @@ void elv_merge_requests(struct request_queue *q, struct request *rq,
 			     struct request *next)
 {
 	struct elevator_queue *e = q->elevator;
+	const int next_sorted = next->cmd_flags & REQ_SORTED;
 
-	if (e->ops->elevator_merge_req_fn)
+	if (next_sorted && e->ops->elevator_merge_req_fn)
 		e->ops->elevator_merge_req_fn(q, rq, next);
 
 	elv_rqhash_reposition(q, rq);
-	elv_rqhash_del(q, next);
 
-	q->nr_sorted--;
+	if (next_sorted) {
+		elv_rqhash_del(q, next);
+		q->nr_sorted--;
+	}
+
 	q->last_merge = rq;
 }
 
@@ -647,6 +685,14 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 		__blk_run_queue(q, false);
 		break;
 
+	case ELEVATOR_INSERT_SORT_MERGE:
+		/*
+		 * If we succeed in merging this request with one in the
+		 * queue already, we are done - rq has now been freed,
+		 * so no need to do anything further.
+		 */
+		if (elv_attempt_insert_merge(q, rq))
+			break;
 	case ELEVATOR_INSERT_SORT:
 		BUG_ON(rq->cmd_type != REQ_TYPE_FS &&
 		       !(rq->cmd_flags & REQ_DISCARD));

include/linux/elevator.h

@@ -166,6 +166,7 @@ extern struct request *elv_rb_find(struct rb_root *, sector_t);
 #define ELEVATOR_INSERT_SORT	3
 #define ELEVATOR_INSERT_REQUEUE	4
 #define ELEVATOR_INSERT_FLUSH	5
+#define ELEVATOR_INSERT_SORT_MERGE	6
 
 /*
  * return values from elevator_may_queue_fn