blkio: Determine async workload length based on total number of queues

o Async queues are not per group. Instead these are system wide and maintained
  in root group. Hence their workload slice length should be calculated
  based on total number of queues in the system and not just queues in the
  root group.

o As root group's default weight is 1000, make sure to charge async queue
  more in terms of vtime so that it does not get more time on disk because
  root group has higher weight.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 1cc1048..b9e483d 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -408,6 +408,13 @@
 		+ cfqg->service_trees[wl][SYNC_WORKLOAD].count;
 }
 
+static inline int cfqg_busy_async_queues(struct cfq_data *cfqd,
+					struct cfq_group *cfqg)
+{
+	return cfqg->service_trees[RT_WORKLOAD][ASYNC_WORKLOAD].count
+		+ cfqg->service_trees[BE_WORKLOAD][ASYNC_WORKLOAD].count;
+}
+
 static void cfq_dispatch_insert(struct request_queue *, struct request *);
 static struct cfq_queue *cfq_get_queue(struct cfq_data *, bool,
 				       struct io_context *, gfp_t);
@@ -895,13 +902,19 @@
 				struct cfq_queue *cfqq)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
-	unsigned int used_sl;
+	unsigned int used_sl, charge_sl;
+	int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
+			- cfqg->service_tree_idle.count;
 
-	used_sl = cfq_cfqq_slice_usage(cfqq);
+	BUG_ON(nr_sync < 0);
+	used_sl = charge_sl = cfq_cfqq_slice_usage(cfqq);
+
+	if (!cfq_cfqq_sync(cfqq) && !nr_sync)
+		charge_sl = cfqq->allocated_slice;
 
 	/* Can't update vdisktime while group is on service tree */
 	cfq_rb_erase(&cfqg->rb_node, st);
-	cfqg->vdisktime += cfq_scale_slice(used_sl, cfqg);
+	cfqg->vdisktime += cfq_scale_slice(charge_sl, cfqg);
 	__cfq_group_service_tree_add(st, cfqg);
 
 	/* This group is being expired. Save the context */
@@ -2016,11 +2029,24 @@
 		max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_prio],
 		      cfq_group_busy_queues_wl(cfqd->serving_prio, cfqd, cfqg));
 
-	if (cfqd->serving_type == ASYNC_WORKLOAD)
+	if (cfqd->serving_type == ASYNC_WORKLOAD) {
+		unsigned int tmp;
+
+		/*
+		 * Async queues are currently system wide. Just taking
+		 * proportion of queues with-in same group will lead to higher
+		 * async ratio system wide as generally root group is going
+		 * to have higher weight. A more accurate thing would be to
+		 * calculate system wide asnc/sync ratio.
+		 */
+		tmp = cfq_target_latency * cfqg_busy_async_queues(cfqd, cfqg);
+		tmp = tmp/cfqd->busy_queues;
+		slice = min_t(unsigned, slice, tmp);
+
 		/* async workload slice is scaled down according to
 		 * the sync/async slice ratio. */
 		slice = slice * cfqd->cfq_slice[0] / cfqd->cfq_slice[1];
-	else
+	} else
 		/* sync workload slice is at least 2 * cfq_slice_idle */
 		slice = max(slice, 2 * cfqd->cfq_slice_idle);