[PATCH 05/16] blkio: Implement per cfq group latency target and busy queue avg

[Vivek Goyal <vgoyal@redhat.com>]

o So far we had 300ms soft target latency system wide. Now with the
  introduction of cfq groups, divide that latency by number of groups so
  that one can come up with group target latency which will be helpful
  in determining the workload slice with-in group and also the dynamic
  slice length of the cfq queue.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
---
 block/cfq-iosched.c |   48 ++++++++++++++++++++++++++++++------------------
 1 files changed, 30 insertions(+), 18 deletions(-)

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 33c3e62..f8688b4 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -167,6 +167,8 @@ struct cfq_group {
 	/* number of cfqq currently on this group */
 	int nr_cfqq;
 
+	/* Per group busy queus average. Useful for workload slice calc. */
+	unsigned int busy_queues_avg[2];
 	/*
 	 * rr lists of queues with requests, onle rr for each priority class.
 	 * Counts are embedded in the cfq_rb_root
@@ -184,6 +186,8 @@ struct cfq_data {
 	/* Root service tree for cfq_groups */
 	struct cfq_rb_root grp_service_tree;
 	struct cfq_group root_group;
+	/* Number of active cfq groups on group service tree */
+	int nr_groups;
 
 	/*
 	 * The priority currently being served
@@ -201,7 +205,6 @@ struct cfq_data {
 	struct rb_root prio_trees[CFQ_PRIO_LISTS];
 
 	unsigned int busy_queues;
-	unsigned int busy_queues_avg[2];
 
 	int rq_in_driver[2];
 	int sync_flight;
@@ -330,10 +333,10 @@ static enum wl_type_t cfqq_type(struct cfq_queue *cfqq)
 	return SYNC_WORKLOAD;
 }
 
-static inline int cfq_busy_queues_wl(enum wl_prio_t wl, struct cfq_data *cfqd)
+static inline int cfq_group_busy_queues_wl(enum wl_prio_t wl,
+					struct cfq_data *cfqd,
+					struct cfq_group *cfqg)
 {
-	struct cfq_group *cfqg = &cfqd->root_group;
-
 	if (wl == IDLE_WORKLOAD)
 		return cfqg->service_tree_idle.count;
 
@@ -420,18 +423,19 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  * to quickly follows sudden increases and decrease slowly
  */
 
-static inline unsigned cfq_get_avg_queues(struct cfq_data *cfqd, bool rt)
+static inline unsigned cfq_group_get_avg_queues(struct cfq_data *cfqd,
+					struct cfq_group *cfqg, bool rt)
 {
 	unsigned min_q, max_q;
 	unsigned mult  = cfq_hist_divisor - 1;
 	unsigned round = cfq_hist_divisor / 2;
-	unsigned busy = cfq_busy_queues_wl(rt, cfqd);
+	unsigned busy = cfq_group_busy_queues_wl(rt, cfqd, cfqg);
 
-	min_q = min(cfqd->busy_queues_avg[rt], busy);
-	max_q = max(cfqd->busy_queues_avg[rt], busy);
-	cfqd->busy_queues_avg[rt] = (mult * max_q + min_q + round) /
+	min_q = min(cfqg->busy_queues_avg[rt], busy);
+	max_q = max(cfqg->busy_queues_avg[rt], busy);
+	cfqg->busy_queues_avg[rt] = (mult * max_q + min_q + round) /
 		cfq_hist_divisor;
-	return cfqd->busy_queues_avg[rt];
+	return cfqg->busy_queues_avg[rt];
 }
 
 static inline void
@@ -441,10 +445,13 @@ cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	if (cfqd->cfq_latency) {
 		/* interested queues (we consider only the ones with the same
 		 * priority class) */
-		unsigned iq = cfq_get_avg_queues(cfqd, cfq_class_rt(cfqq));
+		unsigned iq = cfq_group_get_avg_queues(cfqd, cfqq->cfqg,
+						cfq_class_rt(cfqq));
 		unsigned sync_slice = cfqd->cfq_slice[1];
 		unsigned expect_latency = sync_slice * iq;
-		if (expect_latency > cfq_target_latency) {
+		unsigned group_target_lat = cfq_target_latency/cfqd->nr_groups;
+
+		if (expect_latency > group_target_lat) {
 			unsigned base_low_slice = 2 * cfqd->cfq_slice_idle;
 			/* scale low_slice according to IO priority
 			 * and sync vs async */
@@ -452,7 +459,7 @@ cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 				min(slice, base_low_slice * slice / sync_slice);
 			/* the adapted slice value is scaled to fit all iqs
 			 * into the target latency */
-			slice = max(slice * cfq_target_latency / expect_latency,
+			slice = max(slice * group_target_lat / expect_latency,
 				    low_slice);
 		}
 	}
@@ -703,6 +710,7 @@ cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 
 	__cfq_group_service_tree_add(st, cfqg);
 	cfqg->on_st = true;
+	cfqd->nr_groups++;
 }
 
 static void
@@ -717,6 +725,7 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		return;
 
 	cfqg->on_st = false;
+	cfqd->nr_groups--;
 	if (!RB_EMPTY_NODE(&cfqg->rb_node))
 		cfq_rb_erase(&cfqg->rb_node, st);
 }
@@ -1588,6 +1597,7 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	unsigned slice;
 	unsigned count;
 	struct cfq_rb_root *st;
+	int group_target_latency;
 
 	if (!cfqg) {
 		cfqd->serving_prio = IDLE_WORKLOAD;
@@ -1596,9 +1606,9 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	}
 
 	/* Choose next priority. RT > BE > IDLE */
-	if (cfq_busy_queues_wl(RT_WORKLOAD, cfqd))
+	if (cfq_group_busy_queues_wl(RT_WORKLOAD, cfqd, cfqg))
 		cfqd->serving_prio = RT_WORKLOAD;
-	else if (cfq_busy_queues_wl(BE_WORKLOAD, cfqd))
+	else if (cfq_group_busy_queues_wl(BE_WORKLOAD, cfqd, cfqg))
 		cfqd->serving_prio = BE_WORKLOAD;
 	else {
 		cfqd->serving_prio = IDLE_WORKLOAD;
@@ -1636,9 +1646,11 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	 * proportional to the number of queues in that workload, over
 	 * all the queues in the same priority class
 	 */
-	slice = cfq_target_latency * count /
-		max_t(unsigned, cfqd->busy_queues_avg[cfqd->serving_prio],
-		      cfq_busy_queues_wl(cfqd->serving_prio, cfqd));
+	group_target_latency = cfq_target_latency/cfqd->nr_groups;
+
+	slice = group_target_latency * count /
+		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)
 		/* async workload slice is scaled down according to
-- 
1.6.2.5