[dm-devel] [PATCH 07/25] io-controller: core bfq scheduler changes for hierarchical setup

[Vivek Goyal <vgoyal redhat com>]

o Some of the core bfq scheduler changes for hiearchical groups.

Signed-off-by: Fabio Checconi <fabio gandalf sssup it>
Signed-off-by: Paolo Valente <paolo valente unimore it>
Signed-off-by: Nauman Rafique <nauman google com>
Signed-off-by: Vivek Goyal <vgoyal redhat com>
---
 block/elevator-fq.c |  169 ++++++++++++++++++++++++++++++++++++++++++++++-----
 block/elevator-fq.h |    4 +
 init/Kconfig        |    8 +++
 3 files changed, 165 insertions(+), 16 deletions(-)

diff --git a/block/elevator-fq.c b/block/elevator-fq.c
index 67c02b9..0acfa2c 100644
--- a/block/elevator-fq.c
+++ b/block/elevator-fq.c
@@ -42,6 +42,69 @@ static int elv_rate_sampling_window = HZ / 10;
  */
 #define WFQ_SERVICE_SHIFT	22
 
+#ifdef CONFIG_GROUP_IOSCHED
+#define for_each_entity(entity)	\
+	for (; entity != NULL; entity = entity->parent)
+
+#define for_each_entity_safe(entity, parent) \
+	for (; entity && ({ parent = entity->parent; 1; }); entity = parent)
+
+
+static struct io_entity *bfq_lookup_next_entity(struct io_sched_data *sd,
+						 int extract);
+
+static int bfq_update_next_active(struct io_sched_data *sd)
+{
+	struct io_group *iog;
+	struct io_entity *entity, *next_active;
+
+	if (sd->active_entity != NULL)
+		/* will update/requeue at the end of service */
+		return 0;
+
+	/*
+	 * NOTE: this can be improved in may ways, such as returning
+	 * 1 (and thus propagating upwards the update) only when the
+	 * budget changes, or caching the bfqq that will be scheduled
+	 * next from this subtree.  By now we worry more about
+	 * correctness than about performance...
+	 */
+	next_active = bfq_lookup_next_entity(sd, 0);
+	sd->next_active = next_active;
+
+	if (next_active != NULL) {
+		iog = container_of(sd, struct io_group, sched_data);
+		entity = iog->my_entity;
+		if (entity != NULL)
+			entity->budget = next_active->budget;
+	}
+
+	return 1;
+}
+
+static inline void bfq_check_next_active(struct io_sched_data *sd,
+					 struct io_entity *entity)
+{
+	BUG_ON(sd->next_active != entity);
+}
+#else /* GROUP_IOSCHED */
+#define for_each_entity(entity)	\
+	for (; entity != NULL; entity = NULL)
+
+#define for_each_entity_safe(entity, parent) \
+	for (parent = NULL; entity != NULL; entity = parent)
+
+static inline int bfq_update_next_active(struct io_sched_data *sd)
+{
+	return 0;
+}
+
+static inline void bfq_check_next_active(struct io_sched_data *sd,
+					 struct io_entity *entity)
+{
+}
+#endif /* GROUP_IOSCHED */
+
 static inline int elv_prio_slice(struct elv_fq_data *efqd, int sync,
 					unsigned short prio)
 {
@@ -587,8 +650,10 @@ static struct io_entity *bfq_lookup_next_entity(struct io_sched_data *sd,
 		entity = __bfq_lookup_next_entity(st);
 		if (entity != NULL) {
 			if (extract) {
+				bfq_check_next_active(sd, entity);
 				bfq_active_remove(st, entity);
 				sd->active_entity = entity;
+				sd->next_active = NULL;
 			}
 			break;
 		}
@@ -661,11 +726,8 @@ static void __bfq_activate_entity(struct io_entity *entity, int add_front)
 	if (add_front) {
 		struct io_entity *next_entity;
 
-		/*
-		 * Determine the entity which will be dispatched next
-		 * Use sd->next_active once hierarchical patch is applied
-		 */
-		next_entity = bfq_lookup_next_entity(sd, 0);
+		/* Determine the entity which will be dispatched next */
+		next_entity = sd->next_active;
 
 		if (next_entity && next_entity != entity) {
 			struct io_service_tree *new_st;
@@ -697,7 +759,21 @@ static void __bfq_activate_entity(struct io_entity *entity, int add_front)
  */
 static void bfq_activate_entity(struct io_entity *entity, int add_front)
 {
-	__bfq_activate_entity(entity, add_front);
+	struct io_sched_data *sd;
+
+	for_each_entity(entity) {
+		__bfq_activate_entity(entity, add_front);
+
+		add_front = 0;
+		sd = entity->sched_data;
+		if (!bfq_update_next_active(sd))
+			/*
+			 * No need to propagate the activation to the
+			 * upper entities, as they will be updated when
+			 * the active entity is rescheduled.
+			 */
+			break;
+	}
 }
 
 /**
@@ -732,6 +808,8 @@ static int __bfq_deactivate_entity(struct io_entity *entity, int requeue)
 		bfq_idle_remove(st, entity);
 	else if (entity->tree != NULL)
 		BUG();
+	if (was_active || sd->next_active == entity)
+		ret = bfq_update_next_active(sd);
 
 	if (!requeue || !bfq_gt(entity->finish, st->vtime))
 		bfq_forget_entity(st, entity);
@@ -739,6 +817,7 @@ static int __bfq_deactivate_entity(struct io_entity *entity, int requeue)
 		bfq_idle_insert(st, entity);
 
 	BUG_ON(sd->active_entity == entity);
+	BUG_ON(sd->next_active == entity);
 
 	return ret;
 }
@@ -750,18 +829,62 @@ static int __bfq_deactivate_entity(struct io_entity *entity, int requeue)
  */
 static void bfq_deactivate_entity(struct io_entity *entity, int requeue)
 {
-	__bfq_deactivate_entity(entity, requeue);
+	struct io_sched_data *sd;
+	struct io_entity *parent;
+
+	for_each_entity_safe(entity, parent) {
+		sd = entity->sched_data;
+
+		if (!__bfq_deactivate_entity(entity, requeue))
+			/*
+			 * The parent entity is still backlogged, and
+			 * we don't need to update it as it is still
+			 * under service.
+			 */
+			break;
+
+		if (sd->next_active != NULL) {
+			/*
+			 * The parent entity is still backlogged and
+			 * the budgets on the path towards the root
+			 * need to be updated.
+			 */
+			goto update;
+		}
+
+		/*
+		 * If we reach there the parent is no more backlogged and
+		 * we want to propagate the dequeue upwards.
+		 *
+		 */
+
+		requeue = 1;
+	}
+
+	return;
+
+update:
+	entity = parent;
+	for_each_entity(entity) {
+		__bfq_activate_entity(entity, 0);
+
+		sd = entity->sched_data;
+		if (!bfq_update_next_active(sd))
+			break;
+	}
 }
 
 static void entity_served(struct io_entity *entity, unsigned long served)
 {
 	struct io_service_tree *st;
 
-	st = io_entity_service_tree(entity);
-	entity->service += served;
-	BUG_ON(st->wsum == 0);
-	st->vtime += bfq_delta(served, st->wsum);
-	bfq_forget_idle(st);
+	for_each_entity(entity) {
+		st = io_entity_service_tree(entity);
+		entity->service += served;
+		BUG_ON(st->wsum == 0);
+		st->vtime += bfq_delta(served, st->wsum);
+		bfq_forget_idle(st);
+	}
 }
 
 /**
@@ -1154,11 +1277,25 @@ static struct io_queue *elv_get_next_ioq(struct request_queue *q, int extract)
 		return NULL;
 
 	sd = &efqd->root_group->sched_data;
-	entity = bfq_lookup_next_entity(sd, 1);
 
-	BUG_ON(!entity);
-	if (extract)
-		entity->service = 0;
+	for (; sd != NULL; sd = entity->my_sched_data) {
+		entity = bfq_lookup_next_entity(sd, 1);
+		/*
+		 * entity can be null despite the fact that there are busy
+		 * queues. if all the busy queues are under a group which is
+		 * currently under service.
+		 * So if we are just looking for next ioq while something is
+		 * being served, null entity is not an error.
+		 */
+		BUG_ON(!entity && extract);
+
+		if (extract)
+			entity->service = 0;
+
+		if (!entity)
+			return NULL;
+	}
+
 	ioq = io_entity_to_ioq(entity);
 
 	return ioq;
diff --git a/block/elevator-fq.h b/block/elevator-fq.h
index 4b69239..57207c4 100644
--- a/block/elevator-fq.h
+++ b/block/elevator-fq.h
@@ -72,6 +72,7 @@ struct io_service_tree {
  */
 struct io_sched_data {
 	struct io_entity *active_entity;
+	struct io_entity *next_active;
 	struct io_service_tree service_tree[IO_IOPRIO_CLASSES];
 };
 
@@ -181,7 +182,10 @@ struct io_queue {
 };
 
 struct io_group {
+	struct io_entity entity;
 	struct io_sched_data sched_data;
+	struct io_entity *my_entity;
+
 	/*
 	 * async queue for each priority case for RT and BE class.
 	 * Used only for cfq.
diff --git a/init/Kconfig b/init/Kconfig
index 1ce05a4..a380f46 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -612,6 +612,14 @@ config CGROUP_MEM_RES_CTLR_SWAP
 	  Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
 	  size is 4096bytes, 512k per 1Gbytes of swap.
 
+config GROUP_IOSCHED
+	bool "Group IO Scheduler"
+	depends on CGROUPS && ELV_FAIR_QUEUING
+	default n
+	---help---
+	  This feature lets IO scheduler recognize task groups and control
+	  disk bandwidth allocation to such task groups.
+
 endif # CGROUPS
 
 config MM_OWNER
-- 
1.6.0.6