cfq-iosched: Introduce CFQ group hierarchical scheduling and &#34;use_hierarchy&#34; interface

---
 block/cfq-iosched.c |  118 ++++++++++++++++++++++++++++++++------------------
 1 files changed, 75 insertions(+), 43 deletions(-)

block/cfq-iosched.c +75 ~~-43~~

index dbf01f1..15344fb 100644
@@ -92,19 +92,29 @@ struct cfq_rb_root {
 			.count = 0, .min_vdisktime = 0, }
 
 /*
+ * This's the CFQ queue schedule entity which is scheduled on  service tree.
+ */
+struct cfq_entity {
+	/* service tree */
+	struct cfq_rb_root *service_tree;
+	/* service_tree member */
+	struct rb_node rb_node;
+	/* service_tree key, represent the position on the tree */
+	unsigned long rb_key;
+};
+
+/*
  * Per process-grouping structure
  */
 struct cfq_queue {
+	/* The schedule entity */
+	struct cfq_entity cfqe;
 	/* reference count */
 	int ref;
 	/* various state flags, see below */
 	unsigned int flags;
 	/* parent cfq_data */
 	struct cfq_data *cfqd;
-	/* service_tree member */
-	struct rb_node rb_node;
-	/* service_tree key */
-	unsigned long rb_key;
 	/* prio tree member */
 	struct rb_node p_node;
 	/* prio tree root we belong to, if any */

@@ -143,7 +153,6 @@ struct cfq_queue {
 	u32 seek_history;
 	sector_t last_request_pos;
 
-	struct cfq_rb_root *service_tree;
 	struct cfq_queue *new_cfqq;
 	struct cfq_group *cfqg;
 	struct cfq_group *orig_cfqg;

@@ -302,6 +311,15 @@ struct cfq_data {
 	struct rcu_head rcu;
 };
 
+static inline struct cfq_queue *
+cfqq_of_entity(struct cfq_entity *cfqe)
+{
+	if (cfqe)
+		return container_of(cfqe, struct cfq_queue, cfqe);
+
+	return NULL;
+}
+
 static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
 
 static struct cfq_rb_root *service_tree_for(struct cfq_group *cfqg,

@@ -751,7 +769,7 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2,
 /*
  * The below is leftmost cache rbtree addon
  */
-static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
+static struct cfq_entity *cfq_rb_first(struct cfq_rb_root *root)
 {
 	/* Service tree is empty */
 	if (!root->count)

@@ -761,7 +779,7 @@ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
 		root->left = rb_first(&root->rb);
 
 	if (root->left)
-		return rb_entry(root->left, struct cfq_queue, rb_node);
+		return rb_entry(root->left, struct cfq_entity, rb_node);
 
 	return NULL;
 }

@@ -1179,21 +1197,24 @@ static inline void cfq_put_cfqg(struct cfq_group *cfqg) {}
 static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 				 bool add_front)
 {
+	struct cfq_entity *cfqe;
 	struct rb_node **p, *parent;
-	struct cfq_queue *__cfqq;
+	struct cfq_entity *__cfqe;
 	unsigned long rb_key;
 	struct cfq_rb_root *service_tree;
 	int left;
 	int new_cfqq = 1;
 	int group_changed = 0;
 
+	cfqe = &cfqq->cfqe;
+
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 	if (!cfqd->cfq_group_isolation
 	    && cfqq_type(cfqq) == SYNC_NOIDLE_WORKLOAD
 	    && cfqq->cfqg && cfqq->cfqg != &cfqd->root_group) {
 		/* Move this cfq to root group */
 		cfq_log_cfqq(cfqd, cfqq, "moving to root group");
-		if (!RB_EMPTY_NODE(&cfqq->rb_node))
+		if (!RB_EMPTY_NODE(&cfqe->rb_node))
 			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
 		cfqq->orig_cfqg = cfqq->cfqg;
 		cfqq->cfqg = &cfqd->root_group;

@@ -1203,7 +1224,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		   && cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) {
 		/* cfqq is sequential now needs to go to its original group */
 		BUG_ON(cfqq->cfqg != &cfqd->root_group);
-		if (!RB_EMPTY_NODE(&cfqq->rb_node))
+		if (!RB_EMPTY_NODE(&cfqe->rb_node))
 			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
 		cfq_put_cfqg(cfqq->cfqg);
 		cfqq->cfqg = cfqq->orig_cfqg;

@@ -1218,9 +1239,9 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	if (cfq_class_idle(cfqq)) {
 		rb_key = CFQ_IDLE_DELAY;
 		parent = rb_last(&service_tree->rb);
-		if (parent && parent != &cfqq->rb_node) {
-			__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
-			rb_key += __cfqq->rb_key;
+		if (parent && parent != &cfqe->rb_node) {
+			__cfqe = rb_entry(parent, struct cfq_entity, rb_node);
+			rb_key += __cfqe->rb_key;
 		} else
 			rb_key += jiffies;
 	} else if (!add_front) {

@@ -1235,37 +1256,37 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		cfqq->slice_resid = 0;
 	} else {
 		rb_key = -HZ;
-		__cfqq = cfq_rb_first(service_tree);
-		rb_key += __cfqq ? __cfqq->rb_key : jiffies;
+		__cfqe = cfq_rb_first(service_tree);
+		rb_key += __cfqe ? __cfqe->rb_key : jiffies;
 	}
 
-	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
+	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
 		new_cfqq = 0;
 		/*
 		 * same position, nothing more to do
 		 */
-		if (rb_key == cfqq->rb_key &&
-		    cfqq->service_tree == service_tree)
+		if (rb_key == cfqe->rb_key &&
+		    cfqe->service_tree == service_tree)
 			return;
 
-		cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
-		cfqq->service_tree = NULL;
+		cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
+		cfqe->service_tree = NULL;
 	}
 
 	left = 1;
 	parent = NULL;
-	cfqq->service_tree = service_tree;
+	cfqe->service_tree = service_tree;
 	p = &service_tree->rb.rb_node;
 	while (*p) {
 		struct rb_node **n;
 
 		parent = *p;
-		__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
+		__cfqe = rb_entry(parent, struct cfq_entity, rb_node);
 
 		/*
 		 * sort by key, that represents service time.
 		 */
-		if (time_before(rb_key, __cfqq->rb_key))
+		if (time_before(rb_key, __cfqe->rb_key))
 			n = &(*p)->rb_left;
 		else {
 			n = &(*p)->rb_right;

@@ -1276,11 +1297,11 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	}
 
 	if (left)
-		service_tree->left = &cfqq->rb_node;
+		service_tree->left = &cfqe->rb_node;
 
-	cfqq->rb_key = rb_key;
-	rb_link_node(&cfqq->rb_node, parent, p);
-	rb_insert_color(&cfqq->rb_node, &service_tree->rb);
+	cfqe->rb_key = rb_key;
+	rb_link_node(&cfqe->rb_node, parent, p);
+	rb_insert_color(&cfqe->rb_node, &service_tree->rb);
 	service_tree->count++;
 	if ((add_front || !new_cfqq) && !group_changed)
 		return;

@@ -1382,13 +1403,16 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  */
 static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
+	struct cfq_entity *cfqe;
 	cfq_log_cfqq(cfqd, cfqq, "del_from_rr");
 	BUG_ON(!cfq_cfqq_on_rr(cfqq));
 	cfq_clear_cfqq_on_rr(cfqq);
 
-	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
-		cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
-		cfqq->service_tree = NULL;
+	cfqe = &cfqq->cfqe;
+
+	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
+		cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
+		cfqe->service_tree = NULL;
 	}
 	if (cfqq->p_root) {
 		rb_erase(&cfqq->p_node, cfqq->p_root);

@@ -1719,13 +1743,13 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
 		return NULL;
 	if (RB_EMPTY_ROOT(&service_tree->rb))
 		return NULL;
-	return cfq_rb_first(service_tree);
+	return cfqq_of_entity(cfq_rb_first(service_tree));
 }
 
 static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd)
 {
 	struct cfq_group *cfqg;
-	struct cfq_queue *cfqq;
+	struct cfq_entity *cfqe;
 	int i, j;
 	struct cfq_rb_root *st;

@@ -1736,9 +1760,11 @@ static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd)
 	if (!cfqg)
 		return NULL;
 
-	for_each_cfqg_st(cfqg, i, j, st)
-		if ((cfqq = cfq_rb_first(st)) != NULL)
-			return cfqq;
+	for_each_cfqg_st(cfqg, i, j, st) {
+		cfqe = cfq_rb_first(st);
+		if (cfqe != NULL)
+			return cfqq_of_entity(cfqe);
+	}
 	return NULL;
 }

@@ -1875,9 +1901,12 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
 
 static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
+	struct cfq_entity *cfqe;
 	enum wl_prio_t prio = cfqq_prio(cfqq);
-	struct cfq_rb_root *service_tree = cfqq->service_tree;
+	struct cfq_rb_root *service_tree;
 
+	cfqe = &cfqq->cfqe;
+	service_tree = cfqe->service_tree;
 	BUG_ON(!service_tree);
 	BUG_ON(!service_tree->count);

@@ -2087,7 +2116,7 @@ static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
 static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
 				struct cfq_group *cfqg, enum wl_prio_t prio)
 {
-	struct cfq_queue *queue;
+	struct cfq_entity *cfqe;
 	int i;
 	bool key_valid = false;
 	unsigned long lowest_key = 0;

@@ -2095,10 +2124,10 @@ static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
 
 	for (i = 0; i <= SYNC_WORKLOAD; ++i) {
 		/* select the one with lowest rb_key */
-		queue = cfq_rb_first(service_tree_for(cfqg, prio, i));
-		if (queue &&
-		    (!key_valid || time_before(queue->rb_key, lowest_key))) {
-			lowest_key = queue->rb_key;
+		cfqe = cfq_rb_first(service_tree_for(cfqg, prio, i));
+		if (cfqe &&
+		    (!key_valid || time_before(cfqe->rb_key, lowest_key))) {
+			lowest_key = cfqe->rb_key;
 			cur_best = i;
 			key_valid = true;
 		}

@@ -2846,7 +2875,10 @@ static void cfq_ioc_set_ioprio(struct io_context *ioc)
 static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			  pid_t pid, bool is_sync)
 {
-	RB_CLEAR_NODE(&cfqq->rb_node);
+	struct cfq_entity *cfqe;
+
+	cfqe = &cfqq->cfqe;
+	RB_CLEAR_NODE(&cfqe->rb_node);
 	RB_CLEAR_NODE(&cfqq->p_node);
 	INIT_LIST_HEAD(&cfqq->fifo);

@@ -3255,7 +3287,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	/* Allow preemption only if we are idling on sync-noidle tree */
 	if (cfqd->serving_type == SYNC_NOIDLE_WORKLOAD &&
 	    cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD &&
-	    new_cfqq->service_tree->count == 2 &&
+	    new_cfqq->cfqe.service_tree->count == 2 &&
 	    RB_EMPTY_ROOT(&cfqq->sort_list))
 		return true;

Signature · 1 line

1.7.1

Gui Jianfeng

author

2011-02-23 03:08 UTC #4 lore raw

PATCH v5 2/6 cfq-iosched: Introduce cfq_entity for CFQ group

Introduce cfq_entity for CFQ group

---
 block/cfq-iosched.c |  111 +++++++++++++++++++++++++++++++--------------------
 1 files changed, 67 insertions(+), 44 deletions(-)

block/cfq-iosched.c +67 ~~-44~~

index 15344fb..98a39eb 100644
@@ -73,7 +73,7 @@ static DEFINE_IDA(cic_index_ida);
 #define cfq_class_rt(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
 
 #define sample_valid(samples)	((samples) > 80)
-#define rb_entry_cfqg(node)	rb_entry((node), struct cfq_group, rb_node)
+#define rb_entry_entity(node)	rb_entry((node), struct cfq_entity, rb_node)
 
 /*
  * Most of our rbtree usage is for sorting with min extraction, so

@@ -101,6 +101,11 @@ struct cfq_entity {
 	struct rb_node rb_node;
 	/* service_tree key, represent the position on the tree */
 	unsigned long rb_key;
+
+	/* group service_tree key */
+	u64 vdisktime;
+	bool is_group_entity;
+	unsigned int weight;
 };
 
 /*

@@ -182,12 +187,8 @@ enum wl_type_t {
 
 /* This is per cgroup per device grouping structure */
 struct cfq_group {
-	/* group service_tree member */
-	struct rb_node rb_node;
-
-	/* group service_tree key */
-	u64 vdisktime;
-	unsigned int weight;
+	/* cfq group sched entity */
+	struct cfq_entity cfqe;
 
 	/* number of cfqq currently on this group */
 	int nr_cfqq;

@@ -314,12 +315,22 @@ struct cfq_data {
 static inline struct cfq_queue *
 cfqq_of_entity(struct cfq_entity *cfqe)
 {
-	if (cfqe)
+	if (cfqe && !cfqe->is_group_entity)
 		return container_of(cfqe, struct cfq_queue, cfqe);
 
 	return NULL;
 }
 
+static inline struct cfq_group *
+cfqg_of_entity(struct cfq_entity *cfqe)
+{
+	if (cfqe && cfqe->is_group_entity)
+		return container_of(cfqe, struct cfq_group, cfqe);
+
+	return NULL;
+}
+
+
 static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
 
 static struct cfq_rb_root *service_tree_for(struct cfq_group *cfqg,

@@ -547,12 +558,12 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
 }
 
-static inline u64 cfq_scale_slice(unsigned long delta, struct cfq_group *cfqg)
+static inline u64 cfq_scale_slice(unsigned long delta, struct cfq_entity *cfqe)
 {
 	u64 d = delta << CFQ_SERVICE_SHIFT;
 
 	d = d * BLKIO_WEIGHT_DEFAULT;
-	do_div(d, cfqg->weight);
+	do_div(d, cfqe->weight);
 	return d;
 }

@@ -577,11 +588,11 @@ static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime)
 static void update_min_vdisktime(struct cfq_rb_root *st)
 {
 	u64 vdisktime = st->min_vdisktime;
-	struct cfq_group *cfqg;
+	struct cfq_entity *cfqe;
 
 	if (st->left) {
-		cfqg = rb_entry_cfqg(st->left);
-		vdisktime = min_vdisktime(vdisktime, cfqg->vdisktime);
+		cfqe = rb_entry_entity(st->left);
+		vdisktime = min_vdisktime(vdisktime, cfqe->vdisktime);
 	}
 
 	st->min_vdisktime = max_vdisktime(st->min_vdisktime, vdisktime);

@@ -612,8 +623,9 @@ static inline unsigned
 cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
+	struct cfq_entity *cfqe = &cfqg->cfqe;
 
-	return cfq_target_latency * cfqg->weight / st->total_weight;
+	return cfq_target_latency * cfqe->weight / st->total_weight;
 }
 
 static inline unsigned

@@ -784,13 +796,13 @@ static struct cfq_entity *cfq_rb_first(struct cfq_rb_root *root)
 	return NULL;
 }
 
-static struct cfq_group *cfq_rb_first_group(struct cfq_rb_root *root)
+static struct cfq_entity *cfq_rb_first_entity(struct cfq_rb_root *root)
 {
 	if (!root->left)
 		root->left = rb_first(&root->rb);
 
 	if (root->left)
-		return rb_entry_cfqg(root->left);
+		return rb_entry_entity(root->left);
 
 	return NULL;
 }

@@ -847,9 +859,9 @@ static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
 }
 
 static inline s64
-cfqg_key(struct cfq_rb_root *st, struct cfq_group *cfqg)
+entity_key(struct cfq_rb_root *st, struct cfq_entity *entity)
 {
-	return cfqg->vdisktime - st->min_vdisktime;
+	return entity->vdisktime - st->min_vdisktime;
 }
 
 static void

@@ -857,15 +869,16 @@ __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 {
 	struct rb_node **node = &st->rb.rb_node;
 	struct rb_node *parent = NULL;
-	struct cfq_group *__cfqg;
-	s64 key = cfqg_key(st, cfqg);
+	struct cfq_entity *__cfqe;
+	struct cfq_entity *cfqe = &cfqg->cfqe;
+	s64 key = entity_key(st, cfqe);
 	int left = 1;
 
 	while (*node != NULL) {
 		parent = *node;
-		__cfqg = rb_entry_cfqg(parent);
+		__cfqe = rb_entry_entity(parent);
 
-		if (key < cfqg_key(st, __cfqg))
+		if (key < entity_key(st, __cfqe))
 			node = &parent->rb_left;
 		else {
 			node = &parent->rb_right;

@@ -874,21 +887,22 @@ __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 	}
 
 	if (left)
-		st->left = &cfqg->rb_node;
+		st->left = &cfqe->rb_node;
 
-	rb_link_node(&cfqg->rb_node, parent, node);
-	rb_insert_color(&cfqg->rb_node, &st->rb);
+	rb_link_node(&cfqe->rb_node, parent, node);
+	rb_insert_color(&cfqe->rb_node, &st->rb);
 }
 
 static void
 cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
-	struct cfq_group *__cfqg;
+	struct cfq_entity *cfqe = &cfqg->cfqe;
+	struct cfq_entity *__cfqe;
 	struct rb_node *n;
 
 	cfqg->nr_cfqq++;
-	if (!RB_EMPTY_NODE(&cfqg->rb_node))
+	if (!RB_EMPTY_NODE(&cfqe->rb_node))
 		return;
 
 	/*

@@ -898,19 +912,20 @@ cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	 */
 	n = rb_last(&st->rb);
 	if (n) {
-		__cfqg = rb_entry_cfqg(n);
-		cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
+		__cfqe = rb_entry_entity(n);
+		cfqe->vdisktime = __cfqe->vdisktime + CFQ_IDLE_DELAY;
 	} else
-		cfqg->vdisktime = st->min_vdisktime;
+		cfqe->vdisktime = st->min_vdisktime;
 
 	__cfq_group_service_tree_add(st, cfqg);
-	st->total_weight += cfqg->weight;
+	st->total_weight += cfqe->weight;
 }
 
 static void
 cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
+	struct cfq_entity *cfqe = &cfqg->cfqe;
 
 	BUG_ON(cfqg->nr_cfqq < 1);
 	cfqg->nr_cfqq--;

@@ -920,9 +935,9 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		return;
 
 	cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
-	st->total_weight -= cfqg->weight;
-	if (!RB_EMPTY_NODE(&cfqg->rb_node))
-		cfq_rb_erase(&cfqg->rb_node, st);
+	st->total_weight -= cfqe->weight;
+	if (!RB_EMPTY_NODE(&cfqe->rb_node))
+		cfq_rb_erase(&cfqe->rb_node, st);
 	cfqg->saved_workload_slice = 0;
 	cfq_blkiocg_update_dequeue_stats(&cfqg->blkg, 1);
 }

@@ -960,6 +975,7 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 	unsigned int used_sl, charge;
 	int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
 			- cfqg->service_tree_idle.count;
+	struct cfq_entity *cfqe = &cfqg->cfqe;
 
 	BUG_ON(nr_sync < 0);
 	used_sl = charge = cfq_cfqq_slice_usage(cfqq);

@@ -970,8 +986,8 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 		charge = 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(charge, cfqg);
+	cfq_rb_erase(&cfqe->rb_node, st);
+	cfqe->vdisktime += cfq_scale_slice(charge, cfqe);
 	__cfq_group_service_tree_add(st, cfqg);
 
 	/* This group is being expired. Save the context */

@@ -983,8 +999,8 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 	} else
 		cfqg->saved_workload_slice = 0;
 
-	cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
-					st->min_vdisktime);
+	cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu",
+		     cfqe->vdisktime, st->min_vdisktime);
 	cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u disp=%u charge=%u iops=%u"
 			" sect=%u", used_sl, cfqq->slice_dispatch, charge,
 			iops_mode(cfqd), cfqq->nr_sectors);

@@ -1003,7 +1019,7 @@ static inline struct cfq_group *cfqg_of_blkg(struct blkio_group *blkg)
 void cfq_update_blkio_group_weight(void *key, struct blkio_group *blkg,
 					unsigned int weight)
 {
-	cfqg_of_blkg(blkg)->weight = weight;
+	cfqg_of_blkg(blkg)->cfqe.weight = weight;
 }
 
 static struct cfq_group *

@@ -1032,7 +1048,9 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 
 	for_each_cfqg_st(cfqg, i, j, st)
 		*st = CFQ_RB_ROOT;
-	RB_CLEAR_NODE(&cfqg->rb_node);
+	RB_CLEAR_NODE(&cfqg->cfqe.rb_node);
+
+	cfqg->cfqe.is_group_entity = true;
 
 	/*
 	 * Take the initial reference that will be released on destroy

@@ -1056,7 +1074,7 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
 					0);
 
-	cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
+	cfqg->cfqe.weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
 
 	/* Add group on cfqd list */
 	hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);

@@ -2220,10 +2238,13 @@ static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
 	struct cfq_group *cfqg;
+	struct cfq_entity *cfqe;
 
 	if (RB_EMPTY_ROOT(&st->rb))
 		return NULL;
-	cfqg = cfq_rb_first_group(st);
+	cfqe = cfq_rb_first_entity(st);
+	cfqg = cfqg_of_entity(cfqe);
+	BUG_ON(!cfqg);
 	update_min_vdisktime(st);
 	return cfqg;
 }

@@ -2882,6 +2903,7 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	RB_CLEAR_NODE(&cfqq->p_node);
 	INIT_LIST_HEAD(&cfqq->fifo);
 
+	cfqe->is_group_entity = false;
 	cfqq->ref = 0;
 	cfqq->cfqd = cfqd;

@@ -3931,10 +3953,11 @@ static void *cfq_init_queue(struct request_queue *q)
 	cfqg = &cfqd->root_group;
 	for_each_cfqg_st(cfqg, i, j, st)
 		*st = CFQ_RB_ROOT;
-	RB_CLEAR_NODE(&cfqg->rb_node);
+	RB_CLEAR_NODE(&cfqg->cfqe.rb_node);
 
 	/* Give preference to root group over other groups */
-	cfqg->weight = 2*BLKIO_WEIGHT_DEFAULT;
+	cfqg->cfqe.weight = 2*BLKIO_WEIGHT_DEFAULT;
+	cfqg->cfqe.is_group_entity = true;
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 	/*

Signature · 1 line

1.7.1

Gui Jianfeng

author

2011-02-23 03:09 UTC #5 lore raw

PATCH v5 3/6 cfq-iosched: Introduce vdisktime and io weight for CFQ queue

Introduce vdisktime and io weight for CFQ queue scheduling. Currently, io priority maps to a range [100,1000]. It also gets rid of cfq_slice_offset() logic and makes use the same scheduling algorithm as CFQ group does. This helps for CFQ queue and group scheduling on the same service tree.

---
 block/cfq-iosched.c |  210 ++++++++++++++++++++++++++++++++++++++-------------
 1 files changed, 158 insertions(+), 52 deletions(-)

block/cfq-iosched.c +158 ~~-52~~

index 98a39eb..2cceeb1 100644
@@ -40,6 +40,13 @@ static const int cfq_hist_divisor = 4;
 #define CFQ_IDLE_DELAY		(HZ / 5)
 
 /*
+ * The base boosting value.
+ */
+#define CFQ_BOOST_SYNC_BASE          ((HZ / 10) / 4)
+#define CFQ_BOOST_ASYNC_BASE          ((HZ / 25) / 4)
+
+
+/*
  * below this threshold, we consider thinktime immediate
  */
 #define CFQ_MIN_TT		(2)

@@ -99,10 +106,7 @@ struct cfq_entity {
 	struct cfq_rb_root *service_tree;
 	/* service_tree member */
 	struct rb_node rb_node;
-	/* service_tree key, represent the position on the tree */
-	unsigned long rb_key;
-
-	/* group service_tree key */
+	/* service_tree key */
 	u64 vdisktime;
 	bool is_group_entity;
 	unsigned int weight;

@@ -114,6 +118,8 @@ struct cfq_entity {
 struct cfq_queue {
 	/* The schedule entity */
 	struct cfq_entity cfqe;
+	/* Position time */
+	unsigned long position_time;
 	/* reference count */
 	int ref;
 	/* various state flags, see below */

@@ -312,6 +318,24 @@ struct cfq_data {
 	struct rcu_head rcu;
 };
 
+/*
+ * Map io priority(7 ~ 0) to io weight(100 ~ 1000) as follows
+ *     prio       0    1     2    3    4    5    6     7
+ *     weight  1000  868   740  612  484  356  228   100
+ */
+static inline unsigned int cfq_prio_to_weight(unsigned short ioprio)
+{
+	unsigned int step;
+
+	BUG_ON(ioprio >= IOPRIO_BE_NR);
+
+	step = (BLKIO_WEIGHT_MAX - BLKIO_WEIGHT_MIN) / (IOPRIO_BE_NR - 1);
+	if (ioprio == 0)
+		return BLKIO_WEIGHT_MAX;
+
+	return BLKIO_WEIGHT_MIN + (IOPRIO_BE_NR - ioprio - 1) * step;
+}
+
 static inline struct cfq_queue *
 cfqq_of_entity(struct cfq_entity *cfqe)
 {

@@ -848,16 +872,6 @@ cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	return cfq_choose_req(cfqd, next, prev, blk_rq_pos(last));
 }
 
-static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
-				      struct cfq_queue *cfqq)
-{
-	/*
-	 * just an approximation, should be ok.
-	 */
-	return (cfqq->cfqg->nr_cfqq - 1) * (cfq_prio_slice(cfqd, 1, 0) -
-		       cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio));
-}
-
 static inline s64
 entity_key(struct cfq_rb_root *st, struct cfq_entity *entity)
 {

@@ -1207,6 +1221,15 @@ static inline void cfq_put_cfqg(struct cfq_group *cfqg) {}
 
 #endif /* GROUP_IOSCHED */
 
+static inline u64 cfq_get_boost(struct cfq_data *cfqd,
+				 struct cfq_queue *cfqq)
+{
+	if (cfq_cfqq_sync(cfqq))
+		return cfq_scale_slice(CFQ_BOOST_SYNC_BASE, &cfqq->cfqe);
+	else
+		return cfq_scale_slice(CFQ_BOOST_ASYNC_BASE, &cfqq->cfqe);
+}
+
 /*
  * The cfqd->service_trees holds all pending cfq_queue's that have
  * requests waiting to be processed. It is sorted in the order that

@@ -1218,13 +1241,14 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	struct cfq_entity *cfqe;
 	struct rb_node **p, *parent;
 	struct cfq_entity *__cfqe;
-	unsigned long rb_key;
-	struct cfq_rb_root *service_tree;
+	struct cfq_rb_root *service_tree, *orig_st;
 	int left;
 	int new_cfqq = 1;
 	int group_changed = 0;
+	s64 key;
 
 	cfqe = &cfqq->cfqe;
+	orig_st = cfqe->service_tree;
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 	if (!cfqd->cfq_group_isolation

@@ -1232,8 +1256,15 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	    && cfqq->cfqg && cfqq->cfqg != &cfqd->root_group) {
 		/* Move this cfq to root group */
 		cfq_log_cfqq(cfqd, cfqq, "moving to root group");
-		if (!RB_EMPTY_NODE(&cfqe->rb_node))
+		if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
 			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
+			/*
+			 * Group changed, dequeue this CFQ queue from the
+			 * original service tree.
+			 */
+			cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
+			orig_st->total_weight -= cfqe->weight;
+		}
 		cfqq->orig_cfqg = cfqq->cfqg;
 		cfqq->cfqg = &cfqd->root_group;
 		cfqd->root_group.ref++;

@@ -1242,8 +1273,15 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		   && cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) {
 		/* cfqq is sequential now needs to go to its original group */
 		BUG_ON(cfqq->cfqg != &cfqd->root_group);
-		if (!RB_EMPTY_NODE(&cfqe->rb_node))
+		if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
 			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
+			/*
+			 * Group changed, dequeue this CFQ queue from the
+			 * original service tree.
+			 */
+			cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
+			orig_st->total_weight -= cfqe->weight;
+		}
 		cfq_put_cfqg(cfqq->cfqg);
 		cfqq->cfqg = cfqq->orig_cfqg;
 		cfqq->orig_cfqg = NULL;

@@ -1254,47 +1292,65 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 
 	service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq),
 						cfqq_type(cfqq));
+	if (RB_EMPTY_NODE(&cfqe->rb_node)) {
+		/*
+		 * If this CFQ queue moves to another group, the original
+		 * vdisktime makes no sense any more, reset the vdisktime
+		 * here.
+		 */
+		parent = rb_last(&service_tree->rb);
+		if (parent) {
+			u64 pos_offset;
+
+			/*
+			 * Estimate the position according to its weight and
+			 * ioprio.
+			 */
+			pos_offset = cfq_get_boost(cfqd, cfqq);
+			cfqe->vdisktime = service_tree->min_vdisktime +
+						pos_offset;
+		} else
+			cfqe->vdisktime = service_tree->min_vdisktime;
+
+		goto insert;
+	}
+
+	/*
+	 * Ok, we get here, this CFQ queue is on the service tree, dequeue it
+	 * firstly.
+	 */
+	cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
+	orig_st->total_weight -= cfqe->weight;
+
+	new_cfqq = 0;
+
 	if (cfq_class_idle(cfqq)) {
-		rb_key = CFQ_IDLE_DELAY;
 		parent = rb_last(&service_tree->rb);
 		if (parent && parent != &cfqe->rb_node) {
 			__cfqe = rb_entry(parent, struct cfq_entity, rb_node);
-			rb_key += __cfqe->rb_key;
+			cfqe->vdisktime = __cfqe->vdisktime + CFQ_IDLE_DELAY;
 		} else
-			rb_key += jiffies;
+			cfqe->vdisktime = service_tree->min_vdisktime;
 	} else if (!add_front) {
 		/*
-		 * Get our rb key offset. Subtract any residual slice
-		 * value carried from last service. A negative resid
-		 * count indicates slice overrun, and this should position
-		 * the next service time further away in the tree.
+		 * We charge the CFQ queue by the time this queue runs, and
+		 * repsition it on the service tree.
 		 */
-		rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
-		rb_key -= cfqq->slice_resid;
+		unsigned int used_sl;
+
+		used_sl = cfq_cfqq_slice_usage(cfqq);
+		cfqe->vdisktime += cfq_scale_slice(used_sl, cfqe);
 		cfqq->slice_resid = 0;
 	} else {
-		rb_key = -HZ;
-		__cfqe = cfq_rb_first(service_tree);
-		rb_key += __cfqe ? __cfqe->rb_key : jiffies;
-	}
-
-	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
-		new_cfqq = 0;
-		/*
-		 * same position, nothing more to do
-		 */
-		if (rb_key == cfqe->rb_key &&
-		    cfqe->service_tree == service_tree)
-			return;
-
-		cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
-		cfqe->service_tree = NULL;
+		cfqe->vdisktime = service_tree->min_vdisktime;
 	}
 
+insert:
 	left = 1;
 	parent = NULL;
 	cfqe->service_tree = service_tree;
 	p = &service_tree->rb.rb_node;
+	key = entity_key(service_tree, cfqe);
 	while (*p) {
 		struct rb_node **n;

@@ -1304,7 +1360,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		/*
 		 * sort by key, that represents service time.
 		 */
-		if (time_before(rb_key, __cfqe->rb_key))
+		if (key < entity_key(service_tree, __cfqe))
 			n = &(*p)->rb_left;
 		else {
 			n = &(*p)->rb_right;

@@ -1317,10 +1373,12 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	if (left)
 		service_tree->left = &cfqe->rb_node;
 
-	cfqe->rb_key = rb_key;
 	rb_link_node(&cfqe->rb_node, parent, p);
 	rb_insert_color(&cfqe->rb_node, &service_tree->rb);
+	update_min_vdisktime(service_tree);
 	service_tree->count++;
+	service_tree->total_weight += cfqe->weight;
+	cfqq->position_time = jiffies;
 	if ((add_front || !new_cfqq) && !group_changed)
 		return;
 	cfq_group_service_tree_add(cfqd, cfqq->cfqg);

@@ -1422,14 +1480,18 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	struct cfq_entity *cfqe;
+	struct cfq_rb_root *service_tree;
+
 	cfq_log_cfqq(cfqd, cfqq, "del_from_rr");
 	BUG_ON(!cfq_cfqq_on_rr(cfqq));
 	cfq_clear_cfqq_on_rr(cfqq);
 
 	cfqe = &cfqq->cfqe;
+	service_tree = cfqe->service_tree;
 
 	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
 		cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
+		service_tree->total_weight -= cfqe->weight;
 		cfqe->service_tree = NULL;
 	}
 	if (cfqq->p_root) {

@@ -2131,23 +2193,36 @@ static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
 	}
 }
 
+/*
+ * The time when a CFQ queue is put onto a service tree is recoreded in
+ * cfqq->position_time. Currently, we check the first priority CFQ queues
+ * on each service tree, and select the workload type that contains the lowest
+ * position_time CFQ queue among them.
+ */
 static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
 				struct cfq_group *cfqg, enum wl_prio_t prio)
 {
 	struct cfq_entity *cfqe;
+	struct cfq_queue *cfqq;
+	unsigned long lowest_start_time;
 	int i;
-	bool key_valid = false;
-	unsigned long lowest_key = 0;
+	bool time_valid = false;
 	enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD;
 
+	/*
+	 * TODO: We may take io priority and io class into account when
+	 * choosing a workload type. But for the time being just make use of
+	 * position_time only.
+	 */
 	for (i = 0; i <= SYNC_WORKLOAD; ++i) {
-		/* select the one with lowest rb_key */
 		cfqe = cfq_rb_first(service_tree_for(cfqg, prio, i));
-		if (cfqe &&
-		    (!key_valid || time_before(cfqe->rb_key, lowest_key))) {
-			lowest_key = cfqe->rb_key;
+		cfqq = cfqq_of_entity(cfqe);
+		if (cfqe && (!time_valid ||
+			     time_before(cfqq->position_time,
+					 lowest_start_time))) {
+			lowest_start_time = cfqq->position_time;
 			cur_best = i;
-			key_valid = true;
+			time_valid = true;
 		}
 	}

@@ -2819,10 +2894,13 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc)
 {
 	struct task_struct *tsk = current;
 	int ioprio_class;
+	struct cfq_entity *cfqe;
 
 	if (!cfq_cfqq_prio_changed(cfqq))
 		return;
 
+	cfqe = &cfqq->cfqe;
+
 	ioprio_class = IOPRIO_PRIO_CLASS(ioc->ioprio);
 	switch (ioprio_class) {
 	default:

@@ -2849,6 +2927,17 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc)
 		break;
 	}
 
+	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
+		/*
+		 * If this CFQ entity is already on service tree, we need to
+		 * adjust service tree's total weight accordingly.
+		 */
+		cfqe->service_tree->total_weight -= cfqe->weight;
+		cfqe->weight = cfq_prio_to_weight(cfqq->ioprio);
+		cfqe->service_tree->total_weight += cfqe->weight;
+	} else
+		cfqe->weight = cfq_prio_to_weight(cfqq->ioprio);
+
 	/*
 	 * keep track of original prio settings in case we have to temporarily
 	 * elevate the priority of this queue

@@ -3596,6 +3685,9 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
  */
 static void cfq_prio_boost(struct cfq_queue *cfqq)
 {
+	struct cfq_entity *cfqe;
+
+	cfqe = &cfqq->cfqe;
 	if (has_fs_excl()) {
 		/*
 		 * boost idle prio on transactions that would lock out other

@@ -3612,6 +3704,20 @@ static void cfq_prio_boost(struct cfq_queue *cfqq)
 		cfqq->ioprio_class = cfqq->org_ioprio_class;
 		cfqq->ioprio = cfqq->org_ioprio;
 	}
+
+	/*
+	 * update the io weight if io priority gets changed.
+	 */
+	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
+		/*
+		 * If this CFQ entity is already on service tree, we need to
+		 * adjust service tree's total weight accordingly.
+		 */
+		cfqe->service_tree->total_weight -= cfqe->weight;
+		cfqe->weight = cfq_prio_to_weight(cfqq->ioprio);
+		cfqe->service_tree->total_weight += cfqe->weight;
+	} else
+		cfqe->weight = cfq_prio_to_weight(cfqq->ioprio);
 }
 
 static inline int __cfq_may_queue(struct cfq_queue *cfqq)

Signature · 1 line

1.7.1

Gui Jianfeng

author

2011-02-23 03:10 UTC #6 lore raw

PATCH v5 4/6 cfq-iosched: Extract some common code of service tree handling for CFQ queue and CFQ group.

Extract some common code of service tree handling for CFQ queue and CFQ group. This helps when CFQ queue and CFQ group are scheduling together.

---
 block/cfq-iosched.c |   86 +++++++++++++++++++++-----------------------------
 1 files changed, 36 insertions(+), 50 deletions(-)

block/cfq-iosched.c +36 ~~-50~~

index 2cceeb1..d10f776 100644
@@ -879,12 +879,11 @@ entity_key(struct cfq_rb_root *st, struct cfq_entity *entity)
 }
 
 static void
-__cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
+__cfq_entity_service_tree_add(struct cfq_rb_root *st, struct cfq_entity *cfqe)
 {
 	struct rb_node **node = &st->rb.rb_node;
 	struct rb_node *parent = NULL;
 	struct cfq_entity *__cfqe;
-	struct cfq_entity *cfqe = &cfqg->cfqe;
 	s64 key = entity_key(st, cfqe);
 	int left = 1;

@@ -908,6 +907,14 @@ __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 }
 
 static void
+cfq_entity_service_tree_add(struct cfq_rb_root *st, struct cfq_entity *cfqe)
+{
+	__cfq_entity_service_tree_add(st, cfqe);
+	st->count++;
+	st->total_weight += cfqe->weight;
+}
+
+static void
 cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;

@@ -931,8 +938,23 @@ cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	} else
 		cfqe->vdisktime = st->min_vdisktime;
 
-	__cfq_group_service_tree_add(st, cfqg);
-	st->total_weight += cfqe->weight;
+	cfq_entity_service_tree_add(st, cfqe);
+}
+
+static void
+__cfq_entity_service_tree_del(struct cfq_rb_root *st, struct cfq_entity *cfqe)
+{
+	cfq_rb_erase(&cfqe->rb_node, st);
+}
+
+static void
+cfq_entity_service_tree_del(struct cfq_rb_root *st, struct cfq_entity *cfqe)
+{
+	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
+		__cfq_entity_service_tree_del(st, cfqe);
+		st->total_weight -= cfqe->weight;
+		cfqe->service_tree = NULL;
+	}
 }
 
 static void

@@ -949,9 +971,7 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		return;
 
 	cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
-	st->total_weight -= cfqe->weight;
-	if (!RB_EMPTY_NODE(&cfqe->rb_node))
-		cfq_rb_erase(&cfqe->rb_node, st);
+	cfq_entity_service_tree_del(st, cfqe);
 	cfqg->saved_workload_slice = 0;
 	cfq_blkiocg_update_dequeue_stats(&cfqg->blkg, 1);
 }

@@ -1000,9 +1020,9 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 		charge = cfqq->allocated_slice;
 
 	/* Can't update vdisktime while group is on service tree */
-	cfq_rb_erase(&cfqe->rb_node, st);
+	__cfq_entity_service_tree_del(st, cfqe);
 	cfqe->vdisktime += cfq_scale_slice(charge, cfqe);
-	__cfq_group_service_tree_add(st, cfqg);
+	__cfq_entity_service_tree_add(st, cfqe);
 
 	/* This group is being expired. Save the context */
 	if (time_after(cfqd->workload_expires, jiffies)) {

@@ -1239,13 +1259,11 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 				 bool add_front)
 {
 	struct cfq_entity *cfqe;
-	struct rb_node **p, *parent;
+	struct rb_node *parent;
 	struct cfq_entity *__cfqe;
 	struct cfq_rb_root *service_tree, *orig_st;
-	int left;
 	int new_cfqq = 1;
 	int group_changed = 0;
-	s64 key;
 
 	cfqe = &cfqq->cfqe;
 	orig_st = cfqe->service_tree;

@@ -1262,8 +1280,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			 * Group changed, dequeue this CFQ queue from the
 			 * original service tree.
 			 */
-			cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
-			orig_st->total_weight -= cfqe->weight;
+			cfq_entity_service_tree_del(orig_st, cfqe);
 		}
 		cfqq->orig_cfqg = cfqq->cfqg;
 		cfqq->cfqg = &cfqd->root_group;

@@ -1279,8 +1296,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			 * Group changed, dequeue this CFQ queue from the
 			 * original service tree.
 			 */
-			cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
-			orig_st->total_weight -= cfqe->weight;
+			cfq_entity_service_tree_del(orig_st, cfqe);
 		}
 		cfq_put_cfqg(cfqq->cfqg);
 		cfqq->cfqg = cfqq->orig_cfqg;

@@ -1319,8 +1335,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	 * Ok, we get here, this CFQ queue is on the service tree, dequeue it
 	 * firstly.
 	 */
-	cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
-	orig_st->total_weight -= cfqe->weight;
+	cfq_entity_service_tree_del(orig_st, cfqe);
 
 	new_cfqq = 0;

@@ -1346,38 +1361,11 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	}
 
 insert:
-	left = 1;
-	parent = NULL;
 	cfqe->service_tree = service_tree;
-	p = &service_tree->rb.rb_node;
-	key = entity_key(service_tree, cfqe);
-	while (*p) {
-		struct rb_node **n;
-
-		parent = *p;
-		__cfqe = rb_entry(parent, struct cfq_entity, rb_node);
-
-		/*
-		 * sort by key, that represents service time.
-		 */
-		if (key < entity_key(service_tree, __cfqe))
-			n = &(*p)->rb_left;
-		else {
-			n = &(*p)->rb_right;
-			left = 0;
-		}
-
-		p = n;
-	}
 
-	if (left)
-		service_tree->left = &cfqe->rb_node;
-
-	rb_link_node(&cfqe->rb_node, parent, p);
-	rb_insert_color(&cfqe->rb_node, &service_tree->rb);
+	/* Add cfqq onto service tree. */
+	cfq_entity_service_tree_add(service_tree, cfqe);
 	update_min_vdisktime(service_tree);
-	service_tree->count++;
-	service_tree->total_weight += cfqe->weight;
 	cfqq->position_time = jiffies;
 	if ((add_front || !new_cfqq) && !group_changed)
 		return;

@@ -1490,9 +1478,7 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	service_tree = cfqe->service_tree;
 
 	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
-		cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
-		service_tree->total_weight -= cfqe->weight;
-		cfqe->service_tree = NULL;
+		cfq_entity_service_tree_del(service_tree, cfqe);
 	}
 	if (cfqq->p_root) {
 		rb_erase(&cfqq->p_node, cfqq->p_root);

Signature · 1 line

1.7.1

Gui Jianfeng

author

2011-02-23 03:10 UTC #7 lore raw

PATCH v5 5/6 cfq-iosched: CFQ group hierarchical scheduling and use_hierarchy interface.

CFQ group hierarchical scheduling and use_hierarchy interface.

---
 block/blk-cgroup.c  |   61 +++++-
 block/blk-cgroup.h  |    3 +
 block/cfq-iosched.c |  596 +++++++++++++++++++++++++++++++++++++--------------
 3 files changed, 496 insertions(+), 164 deletions(-)

block/blk-cgroup.c +59 -2

index 455768a..c55fecd 100644
@@ -25,7 +25,10 @@
 static DEFINE_SPINLOCK(blkio_list_lock);
 static LIST_HEAD(blkio_list);
 
-struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
+struct blkio_cgroup blkio_root_cgroup = {
+	.weight = 2*BLKIO_WEIGHT_DEFAULT,
+	.use_hierarchy = 0
+};
 EXPORT_SYMBOL_GPL(blkio_root_cgroup);
 
 static struct cgroup_subsys_state *blkiocg_create(struct cgroup_subsys *,

@@ -454,6 +457,7 @@ static void __blkiocg_del_blkio_group(struct blkio_group *blkg)
 	blkg->blkcg_id = 0;
 }
 
+
 /*
  * returns 0 if blkio_group was still on cgroup list. Otherwise returns 1
  * indicating that blk_group was unhashed by the time we got to it.

@@ -765,6 +769,12 @@ unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
 }
 EXPORT_SYMBOL_GPL(blkcg_get_weight);
 
+unsigned int blkcg_get_use_hierarchy(struct blkio_cgroup *blkcg)
+{
+	return blkcg->use_hierarchy;
+}
+EXPORT_SYMBOL_GPL(blkcg_get_use_hierarchy);
+
 uint64_t blkcg_get_read_bps(struct blkio_cgroup *blkcg, dev_t dev)
 {
 	struct blkio_policy_node *pn;

@@ -1202,6 +1212,8 @@ static u64 blkiocg_file_read_u64 (struct cgroup *cgrp, struct cftype *cft) {
 		switch(name) {
 		case BLKIO_PROP_weight:
 			return (u64)blkcg->weight;
+		case BLKIO_PROP_use_hierarchy:
+			return (u64)blkcg->use_hierarchy;
 		}
 		break;
 	default:

@@ -1210,6 +1222,36 @@ static u64 blkiocg_file_read_u64 (struct cgroup *cgrp, struct cftype *cft) {
 	return 0;
 }
 
+static int blkio_use_hierarchy_write(struct cgroup *cgrp, u64 val)
+{
+	struct cgroup *parent = cgrp->parent;
+	struct blkio_cgroup *blkcg, *parent_blkcg = NULL;
+	int ret = 0;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	blkcg = cgroup_to_blkio_cgroup(cgrp);
+	if (parent)
+		parent_blkcg = cgroup_to_blkio_cgroup(parent);
+
+	cgroup_lock();
+	/*
+	 * If parent's use_hierarchy is set, we can't make any modifications
+	 * in the child subtrees. If it is unset, then the change can occur,
+	 * provided the current cgroup has no children.
+	 */
+	if (!parent_blkcg || !parent_blkcg->use_hierarchy) {
+		if (list_empty(&cgrp->children))
+			blkcg->use_hierarchy = val;
+		else
+			ret = -EBUSY;
+	} else
+		ret = -EINVAL;
+	cgroup_unlock();
+	return ret;
+}
+
 static int
 blkiocg_file_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
 {

@@ -1224,6 +1266,8 @@ blkiocg_file_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
 		switch(name) {
 		case BLKIO_PROP_weight:
 			return blkio_weight_write(blkcg, val);
+		case BLKIO_PROP_use_hierarchy:
+			return blkio_use_hierarchy_write(cgrp, val);
 		}
 		break;
 	default:

@@ -1301,6 +1345,13 @@ struct cftype blkio_files[] = {
 		.name = "reset_stats",
 		.write_u64 = blkiocg_reset_stats,
 	},
+	{
+		.name = "use_hierarchy",
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+					     BLKIO_PROP_use_hierarchy),
+		.read_u64 = blkiocg_file_read_u64,
+		.write_u64 = blkiocg_file_write_u64,
+	},
 #ifdef CONFIG_BLK_DEV_THROTTLING
 	{
 		.name = "throttle.read_bps_device",

@@ -1444,7 +1495,7 @@ static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 static struct cgroup_subsys_state *
 blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 {
-	struct blkio_cgroup *blkcg;
+	struct blkio_cgroup *blkcg, *parent_blkcg = NULL;
 	struct cgroup *parent = cgroup->parent;
 
 	if (!parent) {

@@ -1452,6 +1503,7 @@ blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 		goto done;
 	}
 
+	parent_blkcg = cgroup_to_blkio_cgroup(parent);
 	blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
 	if (!blkcg)
 		return ERR_PTR(-ENOMEM);

@@ -1462,6 +1514,11 @@ done:
 	INIT_HLIST_HEAD(&blkcg->blkg_list);
 
 	INIT_LIST_HEAD(&blkcg->policy_list);
+	if (parent)
+		blkcg->use_hierarchy = parent_blkcg->use_hierarchy;
+	else
+		blkcg->use_hierarchy = 0;
+
 	return &blkcg->css;
 }

block/blk-cgroup.h +3 -0

index ea4861b..5b4b351 100644
@@ -90,6 +90,7 @@ enum blkcg_file_name_prop {
 	BLKIO_PROP_idle_time,
 	BLKIO_PROP_empty_time,
 	BLKIO_PROP_dequeue,
+	BLKIO_PROP_use_hierarchy,
 };
 
 /* cgroup files owned by throttle policy */

@@ -105,6 +106,7 @@ enum blkcg_file_name_throtl {
 struct blkio_cgroup {
 	struct cgroup_subsys_state css;
 	unsigned int weight;
+	bool use_hierarchy;
 	spinlock_t lock;
 	struct hlist_head blkg_list;
 	struct list_head policy_list; /* list of blkio_policy_node */

@@ -179,6 +181,7 @@ struct blkio_policy_node {
 
 extern unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
 				     dev_t dev);
+extern unsigned int blkcg_get_use_hierarchy(struct blkio_cgroup *blkcg);
 extern uint64_t blkcg_get_read_bps(struct blkio_cgroup *blkcg,
 				     dev_t dev);
 extern uint64_t blkcg_get_write_bps(struct blkio_cgroup *blkcg,

block/cfq-iosched.c +434 ~~-162~~

872 lines not on this page · raw message

Signature · 1 line

1.7.1

Gui Jianfeng

author

2011-02-23 03:11 UTC #8 lore raw

PATCH v5 6/6 blkio-cgroup: Document for blkio.use_hierarchy interface

Document for blkio.use_hierarchy interface

---
 Documentation/cgroups/blkio-controller.txt |   81 +++++++++++++++++++++-------
 1 files changed, 62 insertions(+), 19 deletions(-)

Documentation/cgroups/blkio-controller.txt +62 ~~-19~~

index 4ed7b5c..24399f4 100644
@@ -91,30 +91,62 @@ Throttling/Upper Limit policy
 
 Hierarchical Cgroups
 ====================
-- Currently none of the IO control policy supports hierarhical groups. But
-  cgroup interface does allow creation of hierarhical cgroups and internally
-  IO policies treat them as flat hierarchy.
+- Cgroup interface allows creation of hierarchical cgroups. Currently,
+  internally IO policies are able to treat them as flat hierarchy or
+  hierarchical hierarchy. Both hierarchical bandwidth division and flat
+  bandwidth division are supported. "blkio.use_hierarchy" can be used to
+  switch between flat mode and hierarchical mode.
 
-  So this patch will allow creation of cgroup hierarhcy but at the backend
-  everything will be treated as flat. So if somebody created a hierarchy like
-  as follows.
+  Note: Currently, "blkio.use_hierarchy" only effects proportional bandwidth
+  division. For Throttling logic, it still continues to treat everything as flat.
 
-			root
-			/  \
-		     test1 test2
-			|
-		     test3
+  Consider the following CGroup hierarchy:
 
-  CFQ and throttling will practically treat all groups at same level.
+			  Root
+			/  |   \
+		     Grp1  Grp2 tsk1
+	            /  \
+		 Grp3 tsk2
 
-				pivot
-			     /  |   \  \
-			root  test1 test2  test3
+  If blkio.use_hierarchy is disabled in all CGroups, CFQ will practically treat all groups
+  at the same level.
 
-  Down the line we can implement hierarchical accounting/control support
-  and also introduce a new cgroup file "use_hierarchy" which will control
-  whether cgroup hierarchy is viewed as flat or hierarchical by the policy..
-  This is how memory controller also has implemented the things.
+			     Pivot tree
+			    /  |   |   \
+			Root Grp1 Grp2 Grp3
+			 /     |
+			tsk1  tsk2
+
+  If blkio.use_hierarchy is enabled in Root group, then all children will inherit it, thus
+  all children group have use_hierarchy=1 set automatically and looks as follows.
+
+		       Pivot tree
+			   |
+			  Root
+			/  |   \
+		     Grp1  Grp2 tsk1
+	            /  \
+		 Grp3 tsk2
+
+  If blkio.use_hierarchy is enabled in Grp1 and Grp3, CFQ will treat groups and tasks as the
+  same view in CGroup hierarchy, it looks as follows.
+
+
+			     Pivot tree
+			    /    |    \
+			  Root  Grp1  Grp2
+			  /     /  \
+		       tsk1   Grp3 tsk2
+
+  Root, Grp1 and Grp2 are treated at the same level under Pivot tree. tsk1 stays under Root.
+  Grp3 and tsk2 are treated at the same level under Grp1. Below is the mapping between
+  task io priority and io weight:
+
+	    prio       0    1     2    3    4    5    6     7
+	    weight  1000  868   740  612  484  356  228   100
+
+  Note: Regardless of the use_hierarchy setting in Root group, Root group is always put onto
+  Pivot tree.
 
 Various user visible config options
 ===================================

@@ -169,6 +201,17 @@ Proportional weight policy files
 	  dev     weight
 	  8:16    300
 
+- blkio.use_hierarchy
+	- Switch between hierarchical mode and flat mode as stated above.
+	  blkio.use_hierarchy == 1 means hierarchical mode is enabled.
+	  blkio.use_hierarchy == 0 means flat mode is enabled.
+	  You can set this interface only if there isn't any child CGroup under
+	  this CGroup. If one CGroup's blkio.use_hierarchy is set, the created
+	  children will inherit it. it's not allowed to unset it in children.
+	  The default mode in Root CGroup is flat.
+	  blkio.use_hierarchy only works for proportional bandwidth division
+	  as of today and doesn't have any effect on throttling logic.
+
 - blkio.time
 	- disk time allocated to cgroup per device in milliseconds. First
 	  two fields specify the major and minor number of the device and

Signature · 1 line

1.7.1

Vivek Goyal

2011-02-24 18:11 UTC #9 lore raw

Quoted 8 lines · Gui Jianfeng

Hi
I rebase this series on top of *for-next* branch, it will make merging life easier.
Previously, I posted a patchset to add support of CFQ group hierarchical scheduling in the way that it puts all CFQ queues in a hidden group and schedules with other CFQ group under their parent. The patchset is available here,
http://lkml.org/lkml/2010/8/30/30

Gui,

I was running some tests (iostest) with these patches and my system crashed after a while.

To be precise I was running "brrmmap" test of iostest.

train.lab.bos.redhat.com login: [72194.404201] EXT4-fs (dm-1): mounted filesystem with ordered data mode. Opts: (null)

[72642.818976] EXT4-fs (dm-1): mounted filesystem with ordered data mode.
Opts: (null)
[72931.409460] BUG: unable to handle kernel NULL pointer dereference at
0000000000000010
[72931.410216] IP: [<ffffffff812265ff>] __rb_rotate_left+0xb/0x64
[72931.410216] PGD 134d80067 PUD 12f524067 PMD 0 
[72931.410216] Oops: 0000 [#1] SMP 
[72931.410216] last sysfs file:
/sys/devices/system/cpu/cpu0/cache/index0/coherency_line_size
[72931.410216] CPU 3 
[72931.410216] Modules linked in: kvm_intel kvm qla2xxx scsi_transport_fc
[last unloaded: scsi_wait_scan]
[72931.410216] 
[72931.410216] Pid: 18675, comm: sh Not tainted 2.6.38-rc4+ #3 0A98h/HP
xw8600 Workstation
[72931.410216] RIP: 0010:[<ffffffff812265ff>]  [<ffffffff812265ff>]
__rb_rotate_left+0xb/0x64
[72931.410216] RSP: 0000:ffff88012f461480  EFLAGS: 00010086
[72931.410216] RAX: 0000000000000000 RBX: ffff880135f40c00 RCX:
ffffffffffffdcc8
[72931.410216] RDX: ffff880135f43800 RSI: ffff880135f43000 RDI:
ffff880135f42c00
[72931.410216] RBP: ffff88012f461480 R08: ffff880135f40c00 R09:
ffff880135f43018
[72931.410216] R10: 0000000000000000 R11: 0000001000000000 R12:
ffff880135f42c00
[72931.410216] R13: ffff880135f41808 R14: ffff880135f43000 R15:
ffff880135f40c00
[72931.410216] FS:  0000000000000000(0000) GS:ffff8800bfcc0000(0000)
knlGS:0000000000000000
[72931.410216] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[72931.410216] CR2: 0000000000000010 CR3: 000000013774f000 CR4:
00000000000006e0
[72931.410216] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
0000000000000000
[72931.410216] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7:
0000000000000400
[72931.410216] Process sh (pid: 18675, threadinfo ffff88012f460000, task
ffff8801376e6f90)
[72931.410216] Stack:
[72931.410216]  ffff88012f4614b8 ffffffff81226778 ffff880135f43000
ffff880135f43000
[72931.410216]  ffff88011c5bed00 0000000000000000 0000000000000001
ffff88012f4614d8
[72931.410216]  ffffffff8121c521 0000001000000000 ffff880135f41800
ffff88012f461528
[72931.410216] Call Trace:
[72931.410216]  [<ffffffff81226778>] rb_insert_color+0xbc/0xe5
[72931.410216]  [<ffffffff8121c521>]
__cfq_entity_service_tree_add+0x76/0xa5
[72931.410216]  [<ffffffff8121cb28>] cfq_service_tree_add+0x383/0x3eb
[72931.410216]  [<ffffffff8121cbaa>] cfq_resort_rr_list+0x1a/0x2a
[72931.410216]  [<ffffffff8121eb06>] cfq_add_rq_rb+0xbd/0xff
[72931.410216]  [<ffffffff8121ec0a>] cfq_insert_request+0xc2/0x556
[72931.410216]  [<ffffffff8120a44c>] elv_insert+0x118/0x188
[72931.410216]  [<ffffffff8120a52a>] __elv_add_request+0x6e/0x75
[72931.410216]  [<ffffffff812102d0>] __make_request+0x3ac/0x42f
[72931.410216]  [<ffffffff8120e9ca>] generic_make_request+0x2ec/0x356
[72931.410216]  [<ffffffff8120eb05>] submit_bio+0xd1/0xdc
[72931.410216]  [<ffffffff8110bea3>] submit_bh+0xe6/0x108
[72931.410216]  [<ffffffff8110eb9d>] __bread+0x4c/0x6f
[72931.410216]  [<ffffffff811453ab>] ext3_get_branch+0x64/0xdf
[72931.410216]  [<ffffffff81146f5c>] ext3_get_blocks_handle+0x9b/0x90b
[72931.410216]  [<ffffffff81147882>] ext3_get_block+0xb6/0xf6
[72931.410216]  [<ffffffff81113520>] do_mpage_readpage+0x198/0x4bd
[72931.410216]  [<ffffffff810c01b2>] ? __inc_zone_page_state+0x29/0x2b
[72931.410216]  [<ffffffff810ab6e4>] ? add_to_page_cache_locked+0xb6/0x10d
[72931.410216]  [<ffffffff81113980>] mpage_readpages+0xd6/0x123
[72931.410216]  [<ffffffff811477cc>] ? ext3_get_block+0x0/0xf6
[72931.410216]  [<ffffffff811477cc>] ? ext3_get_block+0x0/0xf6
[72931.410216]  [<ffffffff810da750>] ? alloc_pages_current+0xa2/0xc5
[72931.410216]  [<ffffffff81145a6a>] ext3_readpages+0x18/0x1a
[72931.410216]  [<ffffffff810b31fc>] __do_page_cache_readahead+0x111/0x1a7
[72931.410216]  [<ffffffff810b32ae>] ra_submit+0x1c/0x20
[72931.410216]  [<ffffffff810acb1b>] filemap_fault+0x165/0x35b
[72931.410216]  [<ffffffff810c6ce1>] __do_fault+0x50/0x3e2
[72931.410216]  [<ffffffff810c7cf8>] handle_pte_fault+0x2ff/0x779
[72931.410216]  [<ffffffff810b05c9>] ? __free_pages+0x1b/0x24
[72931.410216]  [<ffffffff810c82d1>] handle_mm_fault+0x15f/0x173
[72931.410216]  [<ffffffff815b0963>] do_page_fault+0x348/0x36a
[72931.410216]  [<ffffffff810f21c5>] ? path_put+0x1d/0x21
[72931.410216]  [<ffffffff810f21c5>] ? path_put+0x1d/0x21
[72931.410216]  [<ffffffff815adf1f>] page_fault+0x1f/0x30
[72931.410216] Code: 48 83 c4 18 44 89 e8 5b 41 5c 41 5d c9 c3 48 83 7b 18
00 0f 84 71 ff ff ff e9 77 ff ff ff 90 90 48 8b 47 08 55 48 8b 17 48 89 e5
<48> 8b 48 10 48 83 e2 fc 48 85 c9 48 89 4f 08 74 10 4c 8b 40 10 
[72931.410216] RIP  [<ffffffff812265ff>] __rb_rotate_left+0xb/0x64
[72931.410216]  RSP <ffff88012f461480>
[72931.410216] CR2: 0000000000000010
[72931.410216] ---[ end trace cddc7a4456407f6a ]---

Thanks
Vivek

Quoted 59 lines

Vivek think this approach isn't so instinct that we should treat CFQ queues and groups at the same level. Here is the new approach for hierarchical scheduling based on Vivek's suggestion. The most big change of CFQ is that it gets rid of cfq_slice_offset logic, and makes use of vdisktime for CFQ queue scheduling just like CFQ group does. But I still give cfqq some jump in vdisktime based on ioprio, thanks for Vivek to point out this. Now CFQ queue and CFQ group use the same scheduling algorithm.
"use_hierarchy" interface is now added to switch between hierarchical mode and flat mode. It works as memcg.
V4 -> V5 Changes:
- Change boosting base to a smaller value.
- Rename repostion_time to position_time
- Replace duplicated code by calling cfq_scale_slice()
- Remove redundant use_hierarchy in cfqd
- Fix grp_service_tree comment
- Rename init_cfqe() to init_group_cfqe()
--
V3 -> V4 Changes:
- Take io class into account when calculating the boost value.
- Refine the vtime boosting logic as Vivek's Suggestion.
- Make the calculation of group slice cross all service trees under a group.
- Modify Documentation in terms of Vivek's comments.
--
V2 -> V3 Changes:
- Starting from cfqd->grp_service_tree for both hierarchical mode and flat mode
- Avoid recursion when allocating cfqg and force dispatch logic
- Fix a bug when boosting vdisktime
- Adjusting total_weight accordingly when changing weight
- Change group slice calculation into a hierarchical way
- Keep flat mode rather than deleting it first then adding it later
- kfree the parent cfqg if there nobody references to it
- Simplify select_queue logic by using some wrap function
- Make "use_hierarchy" interface work as memcg
- Make use of time_before() for vdisktime compare
- Update Document
- Fix some code style problems
--
V1 -> V2 Changes:
- Raname "struct io_sched_entity" to "struct cfq_entity" and don't differentiate queue_entity and group_entity, just use cfqe instead.
- Give newly added cfqq a small vdisktime jump accord to its ioprio.
- Make flat mode as default CFQ group scheduling mode.
- Introduce "use_hierarchy" interface.
- Update blkio cgroup documents
 Documentation/cgroups/blkio-controller.txt |   81 +-
 block/blk-cgroup.c                         |   61 +
 block/blk-cgroup.h                         |    3
 block/cfq-iosched.c                        |  959 ++++++++++++++++++++---------
 4 files changed, 815 insertions(+), 289 deletions(-)
Thanks,
Gui

Gui Jianfeng

author

2011-02-25 01:55 UTC #10 lore raw

Quoted 10 lines · Vivek Goyal

Quoted 8 lines · Gui Jianfeng
Hi
I rebase this series on top of *for-next* branch, it will make merging life easier.
Previously, I posted a patchset to add support of CFQ group hierarchical scheduling in the way that it puts all CFQ queues in a hidden group and schedules with other CFQ group under their parent. The patchset is available here,
http://lkml.org/lkml/2010/8/30/30

Quoted 6 lines

Gui,
I was running some tests (iostest) with these patches and my system crashed after a while.
To be precise I was running "brrmmap" test of iostest.

Vivek,

I simply run iostest with brrmmap mode, I can't reproduce this bug. Would you give more details.
Can you tell me the iostest command line options?
Did you enable use_hierarchy in root group?

Thanks,
Gui

Quoted 156 lines

train.lab.bos.redhat.com login: [72194.404201] EXT4-fs (dm-1): mounted filesystem with ordered data mode. Opts: (null)
[72642.818976] EXT4-fs (dm-1): mounted filesystem with ordered data mode.
Opts: (null)
[72931.409460] BUG: unable to handle kernel NULL pointer dereference at
0000000000000010
[72931.410216] IP: [<ffffffff812265ff>] __rb_rotate_left+0xb/0x64
[72931.410216] PGD 134d80067 PUD 12f524067 PMD 0 
[72931.410216] Oops: 0000 [#1] SMP 
[72931.410216] last sysfs file:
/sys/devices/system/cpu/cpu0/cache/index0/coherency_line_size
[72931.410216] CPU 3 
[72931.410216] Modules linked in: kvm_intel kvm qla2xxx scsi_transport_fc
[last unloaded: scsi_wait_scan]
[72931.410216] 
[72931.410216] Pid: 18675, comm: sh Not tainted 2.6.38-rc4+ #3 0A98h/HP
xw8600 Workstation
[72931.410216] RIP: 0010:[<ffffffff812265ff>]  [<ffffffff812265ff>]
__rb_rotate_left+0xb/0x64
[72931.410216] RSP: 0000:ffff88012f461480  EFLAGS: 00010086
[72931.410216] RAX: 0000000000000000 RBX: ffff880135f40c00 RCX:
ffffffffffffdcc8
[72931.410216] RDX: ffff880135f43800 RSI: ffff880135f43000 RDI:
ffff880135f42c00
[72931.410216] RBP: ffff88012f461480 R08: ffff880135f40c00 R09:
ffff880135f43018
[72931.410216] R10: 0000000000000000 R11: 0000001000000000 R12:
ffff880135f42c00
[72931.410216] R13: ffff880135f41808 R14: ffff880135f43000 R15:
ffff880135f40c00
[72931.410216] FS:  0000000000000000(0000) GS:ffff8800bfcc0000(0000)
knlGS:0000000000000000
[72931.410216] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[72931.410216] CR2: 0000000000000010 CR3: 000000013774f000 CR4:
00000000000006e0
[72931.410216] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
0000000000000000
[72931.410216] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7:
0000000000000400
[72931.410216] Process sh (pid: 18675, threadinfo ffff88012f460000, task
ffff8801376e6f90)
[72931.410216] Stack:
[72931.410216]  ffff88012f4614b8 ffffffff81226778 ffff880135f43000
ffff880135f43000
[72931.410216]  ffff88011c5bed00 0000000000000000 0000000000000001
ffff88012f4614d8
[72931.410216]  ffffffff8121c521 0000001000000000 ffff880135f41800
ffff88012f461528
[72931.410216] Call Trace:
[72931.410216]  [<ffffffff81226778>] rb_insert_color+0xbc/0xe5
[72931.410216]  [<ffffffff8121c521>]
__cfq_entity_service_tree_add+0x76/0xa5
[72931.410216]  [<ffffffff8121cb28>] cfq_service_tree_add+0x383/0x3eb
[72931.410216]  [<ffffffff8121cbaa>] cfq_resort_rr_list+0x1a/0x2a
[72931.410216]  [<ffffffff8121eb06>] cfq_add_rq_rb+0xbd/0xff
[72931.410216]  [<ffffffff8121ec0a>] cfq_insert_request+0xc2/0x556
[72931.410216]  [<ffffffff8120a44c>] elv_insert+0x118/0x188
[72931.410216]  [<ffffffff8120a52a>] __elv_add_request+0x6e/0x75
[72931.410216]  [<ffffffff812102d0>] __make_request+0x3ac/0x42f
[72931.410216]  [<ffffffff8120e9ca>] generic_make_request+0x2ec/0x356
[72931.410216]  [<ffffffff8120eb05>] submit_bio+0xd1/0xdc
[72931.410216]  [<ffffffff8110bea3>] submit_bh+0xe6/0x108
[72931.410216]  [<ffffffff8110eb9d>] __bread+0x4c/0x6f
[72931.410216]  [<ffffffff811453ab>] ext3_get_branch+0x64/0xdf
[72931.410216]  [<ffffffff81146f5c>] ext3_get_blocks_handle+0x9b/0x90b
[72931.410216]  [<ffffffff81147882>] ext3_get_block+0xb6/0xf6
[72931.410216]  [<ffffffff81113520>] do_mpage_readpage+0x198/0x4bd
[72931.410216]  [<ffffffff810c01b2>] ? __inc_zone_page_state+0x29/0x2b
[72931.410216]  [<ffffffff810ab6e4>] ? add_to_page_cache_locked+0xb6/0x10d
[72931.410216]  [<ffffffff81113980>] mpage_readpages+0xd6/0x123
[72931.410216]  [<ffffffff811477cc>] ? ext3_get_block+0x0/0xf6
[72931.410216]  [<ffffffff811477cc>] ? ext3_get_block+0x0/0xf6
[72931.410216]  [<ffffffff810da750>] ? alloc_pages_current+0xa2/0xc5
[72931.410216]  [<ffffffff81145a6a>] ext3_readpages+0x18/0x1a
[72931.410216]  [<ffffffff810b31fc>] __do_page_cache_readahead+0x111/0x1a7
[72931.410216]  [<ffffffff810b32ae>] ra_submit+0x1c/0x20
[72931.410216]  [<ffffffff810acb1b>] filemap_fault+0x165/0x35b
[72931.410216]  [<ffffffff810c6ce1>] __do_fault+0x50/0x3e2
[72931.410216]  [<ffffffff810c7cf8>] handle_pte_fault+0x2ff/0x779
[72931.410216]  [<ffffffff810b05c9>] ? __free_pages+0x1b/0x24
[72931.410216]  [<ffffffff810c82d1>] handle_mm_fault+0x15f/0x173
[72931.410216]  [<ffffffff815b0963>] do_page_fault+0x348/0x36a
[72931.410216]  [<ffffffff810f21c5>] ? path_put+0x1d/0x21
[72931.410216]  [<ffffffff810f21c5>] ? path_put+0x1d/0x21
[72931.410216]  [<ffffffff815adf1f>] page_fault+0x1f/0x30
[72931.410216] Code: 48 83 c4 18 44 89 e8 5b 41 5c 41 5d c9 c3 48 83 7b 18
00 0f 84 71 ff ff ff e9 77 ff ff ff 90 90 48 8b 47 08 55 48 8b 17 48 89 e5
<48> 8b 48 10 48 83 e2 fc 48 85 c9 48 89 4f 08 74 10 4c 8b 40 10 
[72931.410216] RIP  [<ffffffff812265ff>] __rb_rotate_left+0xb/0x64
[72931.410216]  RSP <ffff88012f461480>
[72931.410216] CR2: 0000000000000010
[72931.410216] ---[ end trace cddc7a4456407f6a ]---
Thanks
Vivek
Quoted 58 lines
Vivek think this approach isn't so instinct that we should treat CFQ queues and groups at the same level. Here is the new approach for hierarchical scheduling based on Vivek's suggestion. The most big change of CFQ is that it gets rid of cfq_slice_offset logic, and makes use of vdisktime for CFQ queue scheduling just like CFQ group does. But I still give cfqq some jump in vdisktime based on ioprio, thanks for Vivek to point out this. Now CFQ queue and CFQ group use the same scheduling algorithm.
"use_hierarchy" interface is now added to switch between hierarchical mode and flat mode. It works as memcg.
V4 -> V5 Changes:
- Change boosting base to a smaller value.
- Rename repostion_time to position_time
- Replace duplicated code by calling cfq_scale_slice()
- Remove redundant use_hierarchy in cfqd
- Fix grp_service_tree comment
- Rename init_cfqe() to init_group_cfqe()
--
V3 -> V4 Changes:
- Take io class into account when calculating the boost value.
- Refine the vtime boosting logic as Vivek's Suggestion.
- Make the calculation of group slice cross all service trees under a group.
- Modify Documentation in terms of Vivek's comments.
--
V2 -> V3 Changes:
- Starting from cfqd->grp_service_tree for both hierarchical mode and flat mode
- Avoid recursion when allocating cfqg and force dispatch logic
- Fix a bug when boosting vdisktime
- Adjusting total_weight accordingly when changing weight
- Change group slice calculation into a hierarchical way
- Keep flat mode rather than deleting it first then adding it later
- kfree the parent cfqg if there nobody references to it
- Simplify select_queue logic by using some wrap function
- Make "use_hierarchy" interface work as memcg
- Make use of time_before() for vdisktime compare
- Update Document
- Fix some code style problems
--
V1 -> V2 Changes:
- Raname "struct io_sched_entity" to "struct cfq_entity" and don't differentiate queue_entity and group_entity, just use cfqe instead.
- Give newly added cfqq a small vdisktime jump accord to its ioprio.
- Make flat mode as default CFQ group scheduling mode.
- Introduce "use_hierarchy" interface.
- Update blkio cgroup documents
 Documentation/cgroups/blkio-controller.txt |   81 +-
 block/blk-cgroup.c                         |   61 +
 block/blk-cgroup.h                         |    3
 block/cfq-iosched.c                        |  959 ++++++++++++++++++++---------
 4 files changed, 815 insertions(+), 289 deletions(-)
Thanks,
Gui

Signature · 2 lines

Regards
Gui Jianfeng

Vivek Goyal

2011-02-27 23:16 UTC #11 lore raw

Quoted 16 lines · Gui Jianfeng

Quoted 15 lines · Vivek Goyal
Quoted 8 lines · Gui Jianfeng
Hi
I rebase this series on top of *for-next* branch, it will make merging life easier.
Previously, I posted a patchset to add support of CFQ group hierarchical scheduling in the way that it puts all CFQ queues in a hidden group and schedules with other CFQ group under their parent. The patchset is available here,
http://lkml.org/lkml/2010/8/30/30
Gui,
I was running some tests (iostest) with these patches and my system crashed after a while.

Quoted 7 lines

Quoted 1 line
To be precise I was running "brrmmap" test of iostest.
Vivek,
I simply run iostest with brrmmap mode, I can't reproduce this bug. Would you give more details.
Can you tell me the iostest command line options?

iostest /dev/dm-1 -G --nrgrp 4 -m 8 --cgtime --io_serviced --dequeue --total

I was actually trying to run all the workloads defined but after running 2 workloads it crashed on 3rd workload.

Now I tried to re-run brrmmap and it did not crash. So I am trying to run all the inbuilt workloads again.

Quoted 1 line

Did you enable use_hierarchy in root group?

No I did not. Trying to test the flat setup first.

Thanks
Vivek

Vivek Goyal

2011-02-28 00:15 UTC #12 lore raw

Quoted 30 lines · Vivek Goyal

Quoted 16 lines · Gui Jianfeng
Quoted 15 lines · Vivek Goyal
Quoted 8 lines · Gui Jianfeng
Hi
I rebase this series on top of *for-next* branch, it will make merging life easier.
Previously, I posted a patchset to add support of CFQ group hierarchical scheduling in the way that it puts all CFQ queues in a hidden group and schedules with other CFQ group under their parent. The patchset is available here,
http://lkml.org/lkml/2010/8/30/30
Gui,
I was running some tests (iostest) with these patches and my system crashed after a while.
Quoted 7 lines
Quoted 1 line
To be precise I was running "brrmmap" test of iostest.
Vivek,
I simply run iostest with brrmmap mode, I can't reproduce this bug. Would you give more details.
Can you tell me the iostest command line options?
iostest /dev/dm-1 -G --nrgrp 4 -m 8 --cgtime --io_serviced --dequeue --total
I was actually trying to run all the workloads defined but after running 2 workloads it crashed on 3rd workload.

Quoted 6 lines

Now I tried to re-run brrmmap and it did not crash. So I am trying to run all the inbuilt workloads again.
Quoted 1 line
Did you enable use_hierarchy in root group?
No I did not. Trying to test the flat setup first.

Again was running above job and after 3 workloads it ran into a different BUG_ON().

Thanks
Vivek

[277063.539001] kernel BUG at block/cfq-iosched.c:1407!
[277063.539001] invalid opcode: 0000 [#1] SMP 
[277063.539001] last sysfs file: /sys/devices/virtual/block/dm-1/queue/scheduler
[277063.539001] CPU 2 
[277063.539001] Modules linked in: kvm_intel kvm qla2xxx scsi_transport_fc [last unloaded: scsi_wait_scan]
[277063.539001] 
[277063.539001] Pid: 24628, comm: iostest Not tainted 2.6.38-rc4+ #3 0A98h/HP xw8600 Workstation
[277063.539001] RIP: 0010:[<ffffffff8121c6f0>]  [<ffffffff8121c6f0>] cfq_put_cfqg+0x13/0xc8
[277063.539001] RSP: 0018:ffff880129a81d48  EFLAGS: 00010046
[277063.539001] RAX: 0000000000000000 RBX: ffff880135e4b800 RCX: ffff88012b9d8ed0
[277063.539001] RDX: ffff880135e4be30 RSI: ffff880135070c00 RDI: ffff880135070c00
[277063.539001] RBP: ffff880129a81d58 R08: ffff880135e4bbc8 R09: ffffffff81ad76d0
[277063.539001] R10: ffff880129a81d48 R11: ffff880129a81d78 R12: ffff880135e4bc18
[277063.539001] R13: ffff880135e4bbc8 R14: ffff8801359c3020 R15: ffff880135033310
[277063.539001] FS:  00007f1329ed4700(0000) GS:ffff8800bfc80000(0000) knlGS:0000000000000000
[277063.539001] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[277063.539001] CR2: 0000000000b89c08 CR3: 00000001230a5000 CR4: 00000000000006e0
[277063.539001] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[277063.539001] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[277063.539001] Process iostest (pid: 24628, threadinfo ffff880129a80000, task ffff880131394a60)
[277063.539001] Stack:
[277063.539001]  ffff880135e4b800 ffff880135e4b800 ffff880129a81d68 ffffffff8121d0a0
[277063.539001]  ffff880129a81db8 ffffffff8121d6b6 ffff880133af1850 ffff880135070c00
[277063.539001]  ffff880129a81db8 ffff88012c908900 ffff88012c908958 ffff880133af1840
[277063.539001] Call Trace:
[277063.539001]  [<ffffffff8121d0a0>] cfq_destroy_cfqg+0x45/0x47
[277063.539001]  [<ffffffff8121d6b6>] cfq_exit_queue+0xcc/0x164
[277063.539001]  [<ffffffff81209f19>] elevator_exit+0x2a/0x47
[277063.539001]  [<ffffffff8120a8cc>] elevator_change+0x12f/0x1b7
[277063.539001]  [<ffffffff8120a976>] elv_iosched_store+0x22/0x4c
[277063.539001]  [<ffffffff812111f2>] queue_attr_store+0x6a/0x89
[277063.539001]  [<ffffffff8113e093>] sysfs_write_file+0xfc/0x138
[277063.539001]  [<ffffffff810e9fd4>] vfs_write+0xa9/0x105
[277063.539001]  [<ffffffff810ea0e9>] sys_write+0x45/0x6c
[277063.539001]  [<ffffffff8100293b>] system_call_fastpath+0x16/0x1b
[277063.539001] Code: 75 09 48 85 db 0f 85 77 ff ff ff 41 5c 5b 41 5c 41 5d 41 5e 41 5f c9 c3 55 48 89 e5 53 48 83 ec 08 8b 87 20 03 00 00 85 c0 7f 04 <0f> 0b eb fe ff c8 85 c0 89 87 20 03 00 00 0f 85 9d 00 00 00 4c 
[277063.539001] RIP  [<ffffffff8121c6f0>] cfq_put_cfqg+0x13/0xc8
[277063.539001]  RSP <ffff880129a81d48>
[277063.539001] ---[ end trace d7596ee55221d6a7 ]---

Gui Jianfeng

author

2011-02-28 09:34 UTC #13 lore raw

Quoted 34 lines · Vivek Goyal

Quoted 24 lines · Vivek Goyal
Quoted 15 lines · Gui Jianfeng
Quoted 14 lines · Vivek Goyal
Quoted 8 lines · Gui Jianfeng
Hi
I rebase this series on top of *for-next* branch, it will make merging life easier.
Previously, I posted a patchset to add support of CFQ group hierarchical scheduling in the way that it puts all CFQ queues in a hidden group and schedules with other CFQ group under their parent. The patchset is available here,
http://lkml.org/lkml/2010/8/30/30
Gui,
I was running some tests (iostest) with these patches and my system crashed after a while.
Quoted 6 lines
Quoted 1 line
To be precise I was running "brrmmap" test of iostest.
Vivek,
I simply run iostest with brrmmap mode, I can't reproduce this bug. Would you give more details.
Can you tell me the iostest command line options?
iostest /dev/dm-1 -G --nrgrp 4 -m 8 --cgtime --io_serviced --dequeue --total
Quoted 8 lines
I was actually trying to run all the workloads defined but after running 2 workloads it crashed on 3rd workload.
Now I tried to re-run brrmmap and it did not crash. So I am trying to run all the inbuilt workloads again.
Quoted 1 line
Did you enable use_hierarchy in root group?
No I did not. Trying to test the flat setup first.

Quoted 8 lines

Again was running above job and after 3 workloads it ran into a different BUG_ON().
Thanks
Vivek
login: [277063.539001] ------------[ cut here ]------------
[277063.539001] kernel BUG at block/cfq-iosched.c:1407!

Vivek,

It seems there's something wrong when handling cfqg's reference counter. But I'm not sure why for the moment, I'll try to reproduce it and figure out the reason.
Would you help to take a look also.

Thanks,
Gui

Quoted 44 lines

[277063.539001] invalid opcode: 0000 [#1] SMP 
[277063.539001] last sysfs file: /sys/devices/virtual/block/dm-1/queue/scheduler
[277063.539001] CPU 2 
[277063.539001] Modules linked in: kvm_intel kvm qla2xxx scsi_transport_fc [last unloaded: scsi_wait_scan]
[277063.539001] 
[277063.539001] Pid: 24628, comm: iostest Not tainted 2.6.38-rc4+ #3 0A98h/HP xw8600 Workstation
[277063.539001] RIP: 0010:[<ffffffff8121c6f0>]  [<ffffffff8121c6f0>] cfq_put_cfqg+0x13/0xc8
[277063.539001] RSP: 0018:ffff880129a81d48  EFLAGS: 00010046
[277063.539001] RAX: 0000000000000000 RBX: ffff880135e4b800 RCX: ffff88012b9d8ed0
[277063.539001] RDX: ffff880135e4be30 RSI: ffff880135070c00 RDI: ffff880135070c00
[277063.539001] RBP: ffff880129a81d58 R08: ffff880135e4bbc8 R09: ffffffff81ad76d0
[277063.539001] R10: ffff880129a81d48 R11: ffff880129a81d78 R12: ffff880135e4bc18
[277063.539001] R13: ffff880135e4bbc8 R14: ffff8801359c3020 R15: ffff880135033310
[277063.539001] FS:  00007f1329ed4700(0000) GS:ffff8800bfc80000(0000) knlGS:0000000000000000
[277063.539001] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[277063.539001] CR2: 0000000000b89c08 CR3: 00000001230a5000 CR4: 00000000000006e0
[277063.539001] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[277063.539001] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[277063.539001] Process iostest (pid: 24628, threadinfo ffff880129a80000, task ffff880131394a60)
[277063.539001] Stack:
[277063.539001]  ffff880135e4b800 ffff880135e4b800 ffff880129a81d68 ffffffff8121d0a0
[277063.539001]  ffff880129a81db8 ffffffff8121d6b6 ffff880133af1850 ffff880135070c00
[277063.539001]  ffff880129a81db8 ffff88012c908900 ffff88012c908958 ffff880133af1840
[277063.539001] Call Trace:
[277063.539001]  [<ffffffff8121d0a0>] cfq_destroy_cfqg+0x45/0x47
[277063.539001]  [<ffffffff8121d6b6>] cfq_exit_queue+0xcc/0x164
[277063.539001]  [<ffffffff81209f19>] elevator_exit+0x2a/0x47
[277063.539001]  [<ffffffff8120a8cc>] elevator_change+0x12f/0x1b7
[277063.539001]  [<ffffffff8120a976>] elv_iosched_store+0x22/0x4c
[277063.539001]  [<ffffffff812111f2>] queue_attr_store+0x6a/0x89
[277063.539001]  [<ffffffff8113e093>] sysfs_write_file+0xfc/0x138
[277063.539001]  [<ffffffff810e9fd4>] vfs_write+0xa9/0x105
[277063.539001]  [<ffffffff810ea0e9>] sys_write+0x45/0x6c
[277063.539001]  [<ffffffff8100293b>] system_call_fastpath+0x16/0x1b
[277063.539001] Code: 75 09 48 85 db 0f 85 77 ff ff ff 41 5c 5b 41 5c 41 5d 41 5e 41 5f c9 c3 55 48 89 e5 53 48 83 ec 08 8b 87 20 03 00 00 85 c0 7f 04 <0f> 0b eb fe ff c8 85 c0 89 87 20 03 00 00 0f 85 9d 00 00 00 4c 
[277063.539001] RIP  [<ffffffff8121c6f0>] cfq_put_cfqg+0x13/0xc8
[277063.539001]  RSP <ffff880129a81d48>
[277063.539001] ---[ end trace d7596ee55221d6a7 ]---

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Gui Jianfeng

author

2011-03-02 10:01 UTC #14 lore raw

In reply to Vivek Goyal

Quoted 28 lines · Vivek Goyal

Quoted 27 lines · Vivek Goyal
Quoted 15 lines · Gui Jianfeng
Quoted 14 lines · Vivek Goyal
Quoted 8 lines · Gui Jianfeng
Hi
I rebase this series on top of *for-next* branch, it will make merging life easier.
Previously, I posted a patchset to add support of CFQ group hierarchical scheduling in the way that it puts all CFQ queues in a hidden group and schedules with other CFQ group under their parent. The patchset is available here,
http://lkml.org/lkml/2010/8/30/30
Gui,
I was running some tests (iostest) with these patches and my system crashed after a while.
Quoted 6 lines
Quoted 1 line
To be precise I was running "brrmmap" test of iostest.
Vivek,
I simply run iostest with brrmmap mode, I can't reproduce this bug. Would you give more details.
Can you tell me the iostest command line options?
iostest /dev/dm-1 -G --nrgrp 4 -m 8 --cgtime --io_serviced --dequeue --total
I was actually trying to run all the workloads defined but after running 2 workloads it crashed on 3rd workload.

Quoted 8 lines

Quoted 5 lines
Now I tried to re-run brrmmap and it did not crash. So I am trying to run all the inbuilt workloads again.
Quoted 1 line
Did you enable use_hierarchy in root group?
No I did not. Trying to test the flat setup first.
Again was running above job and after 3 workloads it ran into a different BUG_ON().

Vivek,

It seems there's a race.
Would you try the following patch. This patch seems working for me.

block/cfq-iosched.c +3 -2

index 380d667..abbbb0e 100644
@@ -4126,11 +4126,12 @@ new_queue:
 	cfqq->allocated[rw]++;
 	cfqq->ref++;
 
-	spin_unlock_irqrestore(q->queue_lock, flags);
-
 	rq->elevator_private[0] = cic;
 	rq->elevator_private[1] = cfqq;
 	rq->elevator_private[2] = cfq_ref_get_cfqg(cfqq->cfqg);
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
 	return 0;
 
 queue_fail:

Thanks
Gui

Quoted 50 lines

Thanks
Vivek

[277063.539001] kernel BUG at block/cfq-iosched.c:1407!
[277063.539001] invalid opcode: 0000 [#1] SMP 
[277063.539001] last sysfs file: /sys/devices/virtual/block/dm-1/queue/scheduler
[277063.539001] CPU 2 
[277063.539001] Modules linked in: kvm_intel kvm qla2xxx scsi_transport_fc [last unloaded: scsi_wait_scan]
[277063.539001] 
[277063.539001] Pid: 24628, comm: iostest Not tainted 2.6.38-rc4+ #3 0A98h/HP xw8600 Workstation
[277063.539001] RIP: 0010:[<ffffffff8121c6f0>]  [<ffffffff8121c6f0>] cfq_put_cfqg+0x13/0xc8
[277063.539001] RSP: 0018:ffff880129a81d48  EFLAGS: 00010046
[277063.539001] RAX: 0000000000000000 RBX: ffff880135e4b800 RCX: ffff88012b9d8ed0
[277063.539001] RDX: ffff880135e4be30 RSI: ffff880135070c00 RDI: ffff880135070c00
[277063.539001] RBP: ffff880129a81d58 R08: ffff880135e4bbc8 R09: ffffffff81ad76d0
[277063.539001] R10: ffff880129a81d48 R11: ffff880129a81d78 R12: ffff880135e4bc18
[277063.539001] R13: ffff880135e4bbc8 R14: ffff8801359c3020 R15: ffff880135033310
[277063.539001] FS:  00007f1329ed4700(0000) GS:ffff8800bfc80000(0000) knlGS:0000000000000000
[277063.539001] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[277063.539001] CR2: 0000000000b89c08 CR3: 00000001230a5000 CR4: 00000000000006e0
[277063.539001] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[277063.539001] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[277063.539001] Process iostest (pid: 24628, threadinfo ffff880129a80000, task ffff880131394a60)
[277063.539001] Stack:
[277063.539001]  ffff880135e4b800 ffff880135e4b800 ffff880129a81d68 ffffffff8121d0a0
[277063.539001]  ffff880129a81db8 ffffffff8121d6b6 ffff880133af1850 ffff880135070c00
[277063.539001]  ffff880129a81db8 ffff88012c908900 ffff88012c908958 ffff880133af1840
[277063.539001] Call Trace:
[277063.539001]  [<ffffffff8121d0a0>] cfq_destroy_cfqg+0x45/0x47
[277063.539001]  [<ffffffff8121d6b6>] cfq_exit_queue+0xcc/0x164
[277063.539001]  [<ffffffff81209f19>] elevator_exit+0x2a/0x47
[277063.539001]  [<ffffffff8120a8cc>] elevator_change+0x12f/0x1b7
[277063.539001]  [<ffffffff8120a976>] elv_iosched_store+0x22/0x4c
[277063.539001]  [<ffffffff812111f2>] queue_attr_store+0x6a/0x89
[277063.539001]  [<ffffffff8113e093>] sysfs_write_file+0xfc/0x138
[277063.539001]  [<ffffffff810e9fd4>] vfs_write+0xa9/0x105
[277063.539001]  [<ffffffff810ea0e9>] sys_write+0x45/0x6c
[277063.539001]  [<ffffffff8100293b>] system_call_fastpath+0x16/0x1b
[277063.539001] Code: 75 09 48 85 db 0f 85 77 ff ff ff 41 5c 5b 41 5c 41 5d 41 5e 41 5f c9 c3 55 48 89 e5 53 48 83 ec 08 8b 87 20 03 00 00 85 c0 7f 04 <0f> 0b eb fe ff c8 85 c0 89 87 20 03 00 00 0f 85 9d 00 00 00 4c 
[277063.539001] RIP  [<ffffffff8121c6f0>] cfq_put_cfqg+0x13/0xc8
[277063.539001]  RSP <ffff880129a81d48>
[277063.539001] ---[ end trace d7596ee55221d6a7 ]---

Gui Jianfeng

author

2011-03-04 04:34 UTC #15 lore raw

Quoted 62 lines · Gui Jianfeng

Quoted 28 lines · Vivek Goyal
Quoted 27 lines · Vivek Goyal
Quoted 15 lines · Gui Jianfeng
Quoted 14 lines · Vivek Goyal
Quoted 8 lines · Gui Jianfeng
Hi
I rebase this series on top of *for-next* branch, it will make merging life easier.
Previously, I posted a patchset to add support of CFQ group hierarchical scheduling in the way that it puts all CFQ queues in a hidden group and schedules with other CFQ group under their parent. The patchset is available here,
http://lkml.org/lkml/2010/8/30/30
Gui,
I was running some tests (iostest) with these patches and my system crashed after a while.
Quoted 6 lines
Quoted 1 line
To be precise I was running "brrmmap" test of iostest.
Vivek,
I simply run iostest with brrmmap mode, I can't reproduce this bug. Would you give more details.
Can you tell me the iostest command line options?
iostest /dev/dm-1 -G --nrgrp 4 -m 8 --cgtime --io_serviced --dequeue --total
I was actually trying to run all the workloads defined but after running 2 workloads it crashed on 3rd workload.
Quoted 7 lines
Quoted 5 lines
Now I tried to re-run brrmmap and it did not crash. So I am trying to run all the inbuilt workloads again.
Quoted 1 line
Did you enable use_hierarchy in root group?
No I did not. Trying to test the flat setup first.
Again was running above job and after 3 workloads it ran into a different BUG_ON().
Vivek,
It seems there's a race.
Would you try the following patch. This patch seems working for me.
block/cfq-iosched.c +3 -2
index 380d667..abbbb0e 100644
@@ -4126,11 +4126,12 @@ new_queue:
 	cfqq->allocated[rw]++;
 	cfqq->ref++;
 
-	spin_unlock_irqrestore(q->queue_lock, flags);
-
 	rq->elevator_private[0] = cic;
 	rq->elevator_private[1] = cfqq;
 	rq->elevator_private[2] = cfq_ref_get_cfqg(cfqq->cfqg);
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
 	return 0;
 
 queue_fail:

Quoted 3 lines

Thanks
Gui

Jens,

This bug seems being introduced in commmit 763414b in for-next branch when merging for-2.6.39/core branch.
Would you apply the above patch?

Vivek, can you try the patchset again with this fix? It works fine for me now.

Thanks,
Gui

Quoted 57 lines

Quoted 45 lines

Thanks
Vivek

[277063.539001] kernel BUG at block/cfq-iosched.c:1407!
[277063.539001] invalid opcode: 0000 [#1] SMP 
[277063.539001] last sysfs file: /sys/devices/virtual/block/dm-1/queue/scheduler
[277063.539001] CPU 2 
[277063.539001] Modules linked in: kvm_intel kvm qla2xxx scsi_transport_fc [last unloaded: scsi_wait_scan]
[277063.539001] 
[277063.539001] Pid: 24628, comm: iostest Not tainted 2.6.38-rc4+ #3 0A98h/HP xw8600 Workstation
[277063.539001] RIP: 0010:[<ffffffff8121c6f0>]  [<ffffffff8121c6f0>] cfq_put_cfqg+0x13/0xc8
[277063.539001] RSP: 0018:ffff880129a81d48  EFLAGS: 00010046
[277063.539001] RAX: 0000000000000000 RBX: ffff880135e4b800 RCX: ffff88012b9d8ed0
[277063.539001] RDX: ffff880135e4be30 RSI: ffff880135070c00 RDI: ffff880135070c00
[277063.539001] RBP: ffff880129a81d58 R08: ffff880135e4bbc8 R09: ffffffff81ad76d0
[277063.539001] R10: ffff880129a81d48 R11: ffff880129a81d78 R12: ffff880135e4bc18
[277063.539001] R13: ffff880135e4bbc8 R14: ffff8801359c3020 R15: ffff880135033310
[277063.539001] FS:  00007f1329ed4700(0000) GS:ffff8800bfc80000(0000) knlGS:0000000000000000
[277063.539001] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[277063.539001] CR2: 0000000000b89c08 CR3: 00000001230a5000 CR4: 00000000000006e0
[277063.539001] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[277063.539001] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[277063.539001] Process iostest (pid: 24628, threadinfo ffff880129a80000, task ffff880131394a60)
[277063.539001] Stack:
[277063.539001]  ffff880135e4b800 ffff880135e4b800 ffff880129a81d68 ffffffff8121d0a0
[277063.539001]  ffff880129a81db8 ffffffff8121d6b6 ffff880133af1850 ffff880135070c00
[277063.539001]  ffff880129a81db8 ffff88012c908900 ffff88012c908958 ffff880133af1840
[277063.539001] Call Trace:
[277063.539001]  [<ffffffff8121d0a0>] cfq_destroy_cfqg+0x45/0x47
[277063.539001]  [<ffffffff8121d6b6>] cfq_exit_queue+0xcc/0x164
[277063.539001]  [<ffffffff81209f19>] elevator_exit+0x2a/0x47
[277063.539001]  [<ffffffff8120a8cc>] elevator_change+0x12f/0x1b7
[277063.539001]  [<ffffffff8120a976>] elv_iosched_store+0x22/0x4c
[277063.539001]  [<ffffffff812111f2>] queue_attr_store+0x6a/0x89
[277063.539001]  [<ffffffff8113e093>] sysfs_write_file+0xfc/0x138
[277063.539001]  [<ffffffff810e9fd4>] vfs_write+0xa9/0x105
[277063.539001]  [<ffffffff810ea0e9>] sys_write+0x45/0x6c
[277063.539001]  [<ffffffff8100293b>] system_call_fastpath+0x16/0x1b
[277063.539001] Code: 75 09 48 85 db 0f 85 77 ff ff ff 41 5c 5b 41 5c 41 5d 41 5e 41 5f c9 c3 55 48 89 e5 53 48 83 ec 08 8b 87 20 03 00 00 85 c0 7f 04 <0f> 0b eb fe ff c8 85 c0 89 87 20 03 00 00 0f 85 9d 00 00 00 4c 
[277063.539001] RIP  [<ffffffff8121c6f0>] cfq_put_cfqg+0x13/0xc8
[277063.539001]  RSP <ffff880129a81d48>
[277063.539001] ---[ end trace d7596ee55221d6a7 ]---

Quoted 6 lines

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Vivek Goyal

2011-03-04 19:15 UTC #16 lore raw

Quoted 69 lines · Gui Jianfeng

Quoted 62 lines · Gui Jianfeng
Quoted 28 lines · Vivek Goyal
Quoted 27 lines · Vivek Goyal
Quoted 15 lines · Gui Jianfeng
Quoted 14 lines · Vivek Goyal
Quoted 8 lines · Gui Jianfeng
Hi
I rebase this series on top of *for-next* branch, it will make merging life easier.
Previously, I posted a patchset to add support of CFQ group hierarchical scheduling in the way that it puts all CFQ queues in a hidden group and schedules with other CFQ group under their parent. The patchset is available here,
http://lkml.org/lkml/2010/8/30/30
Gui,
I was running some tests (iostest) with these patches and my system crashed after a while.
Quoted 6 lines
Quoted 1 line
To be precise I was running "brrmmap" test of iostest.
Vivek,
I simply run iostest with brrmmap mode, I can't reproduce this bug. Would you give more details.
Can you tell me the iostest command line options?
iostest /dev/dm-1 -G --nrgrp 4 -m 8 --cgtime --io_serviced --dequeue --total
I was actually trying to run all the workloads defined but after running 2 workloads it crashed on 3rd workload.
Quoted 7 lines
Quoted 5 lines
Now I tried to re-run brrmmap and it did not crash. So I am trying to run all the inbuilt workloads again.
Quoted 1 line
Did you enable use_hierarchy in root group?
No I did not. Trying to test the flat setup first.
Again was running above job and after 3 workloads it ran into a different BUG_ON().
Vivek,
It seems there's a race.
Would you try the following patch. This patch seems working for me.
block/cfq-iosched.c +3 -2
index 380d667..abbbb0e 100644
@@ -4126,11 +4126,12 @@ new_queue:
 	cfqq->allocated[rw]++;
 	cfqq->ref++;
 
-	spin_unlock_irqrestore(q->queue_lock, flags);
-
 	rq->elevator_private[0] = cic;
 	rq->elevator_private[1] = cfqq;
 	rq->elevator_private[2] = cfq_ref_get_cfqg(cfqq->cfqg);
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
 	return 0;
 
 queue_fail:
Quoted 3 lines
Thanks
Gui
Jens,

Quoted 5 lines

This bug seems being introduced in commmit 763414b in for-next branch when merging for-2.6.39/core branch.
Would you apply the above patch?
Vivek, can you try the patchset again with this fix? It works fine for me now.

Gui,

Ok, I ran iostest with this fix and it seems to have worked. I need to run it for some more time. And I also need to spend more time reviewing your patchset. There are so many details to it. Soon I will spare some time to review it more and also test it bit more.

Of the top of my head I have one concern.

- How to map iopriority to weights. I am thinking that currently weight range is 100-1000. If we decide to extend the range in current scheme, it will change the ioprio entity weight also and effectively the service differentiation between ioprio level will change. I am wondering if this is a concern and how cpu scheduler has managed it

Thanks
Vivek

Gui Jianfeng

author

2011-03-05 05:25 UTC #17 lore raw

Quoted 72 lines · Vivek Goyal

Quoted 71 lines · Gui Jianfeng
Quoted 61 lines · Gui Jianfeng
Quoted 28 lines · Vivek Goyal
Quoted 27 lines · Vivek Goyal
Quoted 15 lines · Gui Jianfeng
Quoted 14 lines · Vivek Goyal
Quoted 8 lines · Gui Jianfeng
Hi
I rebase this series on top of *for-next* branch, it will make merging life easier.
Previously, I posted a patchset to add support of CFQ group hierarchical scheduling in the way that it puts all CFQ queues in a hidden group and schedules with other CFQ group under their parent. The patchset is available here,
http://lkml.org/lkml/2010/8/30/30
Gui,
I was running some tests (iostest) with these patches and my system crashed after a while.
Quoted 6 lines
Quoted 1 line
To be precise I was running "brrmmap" test of iostest.
Vivek,
I simply run iostest with brrmmap mode, I can't reproduce this bug. Would you give more details.
Can you tell me the iostest command line options?
iostest /dev/dm-1 -G --nrgrp 4 -m 8 --cgtime --io_serviced --dequeue --total
I was actually trying to run all the workloads defined but after running 2 workloads it crashed on 3rd workload.
Quoted 7 lines
Quoted 5 lines
Now I tried to re-run brrmmap and it did not crash. So I am trying to run all the inbuilt workloads again.
Quoted 1 line
Did you enable use_hierarchy in root group?
No I did not. Trying to test the flat setup first.
Again was running above job and after 3 workloads it ran into a different BUG_ON().
Vivek,
It seems there's a race.
Would you try the following patch. This patch seems working for me.
block/cfq-iosched.c +3 -2
index 380d667..abbbb0e 100644
@@ -4126,11 +4126,12 @@ new_queue:
 	cfqq->allocated[rw]++;
 	cfqq->ref++;
 
-	spin_unlock_irqrestore(q->queue_lock, flags);
-
 	rq->elevator_private[0] = cic;
 	rq->elevator_private[1] = cfqq;
 	rq->elevator_private[2] = cfq_ref_get_cfqg(cfqq->cfqg);
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
 	return 0;
 
 queue_fail:
Quoted 3 lines
Thanks
Gui
Jens,
This bug seems being introduced in commmit 763414b in for-next branch when merging for-2.6.39/core branch.
Would you apply the above patch?

Quoted 8 lines

Quoted 1 line
Vivek, can you try the patchset again with this fix? It works fine for me now.
Gui,
Ok, I ran iostest with this fix and it seems to have worked. I need to run it for some more time. And I also need to spend more time reviewing your patchset. There are so many details to it. Soon I will spare some time to review it more and also test it bit more.

Vivek,

Ok, thanks.

Quoted 8 lines

Of the top of my head I have one concern.
- How to map iopriority to weights. I am thinking that currently weight range is 100-1000. If we decide to extend the range in current scheme, it will change the ioprio entity weight also and effectively the service differentiation between ioprio level will change. I am wondering if this is a concern and how cpu scheduler has managed it

Isn't it enought for ten times of weight difference? The old ioprio scheme has only 4.5 times service difference. So I think we don't need to extend the range for the time being.

Thanks,
Gui

Quoted 4 lines

Thanks
Vivek

Vivek Goyal

2011-03-07 14:28 UTC #18 lore raw

On Sat, Mar 05, 2011 at 01:16:08PM +0800, Gui Jianfeng wrote:

[..]

Quoted 26 lines

Quoted 4 lines
Quoted 4 lines
This bug seems being introduced in commmit 763414b in for-next branch when merging for-2.6.39/core branch.
Would you apply the above patch?
Quoted 8 lines
Quoted 1 line
Vivek, can you try the patchset again with this fix? It works fine for me now.
Gui,
Ok, I ran iostest with this fix and it seems to have worked. I need to run it for some more time. And I also need to spend more time reviewing your patchset. There are so many details to it. Soon I will spare some time to review it more and also test it bit more.
Vivek,
Ok, thanks.
Quoted 8 lines
Of the top of my head I have one concern.
- How to map iopriority to weights. I am thinking that currently weight range is 100-1000. If we decide to extend the range in current scheme, it will change the ioprio entity weight also and effectively the service differentiation between ioprio level will change. I am wondering if this is a concern and how cpu scheduler has managed it

Quoted 3 lines

Isn't it enought for ten times of weight difference? The old ioprio scheme has only 4.5 times service difference. So I think we don't need to extend the range for the time being.

Well, never say never. I think google guys are already using minimum weight of 10. So don't rule it out.

Secondly, because we might not idle all the time the effective service differentiation might be much less than a factor of 10. In that case to get effective 10, one might have to go for wider range of weights.

Thanks
Vivek

Justin TerAvest

2011-03-07 18:08 UTC #19 lore raw

Quoted 29 lines · Vivek Goyal

On Sat, Mar 05, 2011 at 01:16:08PM +0800, Gui Jianfeng wrote:
[..]
Quoted 26 lines
Quoted 4 lines
Quoted 4 lines
This bug seems being introduced in commmit 763414b in for-next branch when merging for-2.6.39/core branch.
Would you apply the above patch?
Quoted 8 lines
Quoted 1 line
Vivek, can you try the patchset again with this fix? It works fine for me now.
Gui,
Ok, I ran iostest with this fix and it seems to have worked. I need to run it for some more time. And I also need to spend more time reviewing your patchset. There are so many details to it. Soon I will spare some time to review it more and also test it bit more.
Vivek,
Ok, thanks.
Quoted 8 lines
Of the top of my head I have one concern.
- How to map iopriority to weights. I am thinking that currently weight range is 100-1000. If we decide to extend the range in current scheme, it will change the ioprio entity weight also and effectively the service differentiation between ioprio level will change. I am wondering if this is a concern and how cpu scheduler has managed it

Quoted 6 lines

Quoted 3 lines
Isn't it enought for ten times of weight difference? The old ioprio scheme has only 4.5 times service difference. So I think we don't need to extend the range for the time being.
Well, never say never. I think google guys are already using minimum weight of 10. So don't rule it out.

Yes, we're using a minimum weight of 10. We still see good isolation with the minimum that low.

Thanks,
Justin

Quoted 8 lines

Secondly, because we might not idle all the time the effective service differentiation might be much less than a factor of 10. In that case to get effective 10, one might have to go for wider range of weights.
Thanks
Vivek

Gui Jianfeng

author

2011-02-21 06:10 UTC #20 lore raw

PATCH v5 1/6 cfq-iosched: Introduce cfq_entity for CFQ queue

Introduce cfq_entity for CFQ queue

---
 block/cfq-iosched.c |  118 ++++++++++++++++++++++++++++++++------------------
 1 files changed, 75 insertions(+), 43 deletions(-)

block/cfq-iosched.c +75 ~~-43~~

index f083bda..939c6a6 100644
@@ -92,19 +92,29 @@ struct cfq_rb_root {
 			.count = 0, .min_vdisktime = 0, }
 
 /*
+ * This's the CFQ queue schedule entity which is scheduled on  service tree.
+ */
+struct cfq_entity {
+	/* service tree */
+	struct cfq_rb_root *service_tree;
+	/* service_tree member */
+	struct rb_node rb_node;
+	/* service_tree key, represent the position on the tree */
+	unsigned long rb_key;
+};
+
+/*
  * Per process-grouping structure
  */
 struct cfq_queue {
+	/* The schedule entity */
+	struct cfq_entity cfqe;
 	/* reference count */
 	int ref;
 	/* various state flags, see below */
 	unsigned int flags;
 	/* parent cfq_data */
 	struct cfq_data *cfqd;
-	/* service_tree member */
-	struct rb_node rb_node;
-	/* service_tree key */
-	unsigned long rb_key;
 	/* prio tree member */
 	struct rb_node p_node;
 	/* prio tree root we belong to, if any */

@@ -143,7 +153,6 @@ struct cfq_queue {
 	u32 seek_history;
 	sector_t last_request_pos;
 
-	struct cfq_rb_root *service_tree;
 	struct cfq_queue *new_cfqq;
 	struct cfq_group *cfqg;
 	struct cfq_group *orig_cfqg;

@@ -302,6 +311,15 @@ struct cfq_data {
 	struct rcu_head rcu;
 };
 
+static inline struct cfq_queue *
+cfqq_of_entity(struct cfq_entity *cfqe)
+{
+	if (cfqe)
+		return container_of(cfqe, struct cfq_queue, cfqe);
+
+	return NULL;
+}
+
 static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
 
 static struct cfq_rb_root *service_tree_for(struct cfq_group *cfqg,

@@ -743,7 +761,7 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2,
 /*
  * The below is leftmost cache rbtree addon
  */
-static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
+static struct cfq_entity *cfq_rb_first(struct cfq_rb_root *root)
 {
 	/* Service tree is empty */
 	if (!root->count)

@@ -753,7 +771,7 @@ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
 		root->left = rb_first(&root->rb);
 
 	if (root->left)
-		return rb_entry(root->left, struct cfq_queue, rb_node);
+		return rb_entry(root->left, struct cfq_entity, rb_node);
 
 	return NULL;
 }

@@ -1171,21 +1189,24 @@ static inline void cfq_put_cfqg(struct cfq_group *cfqg) {}
 static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 				 bool add_front)
 {
+	struct cfq_entity *cfqe;
 	struct rb_node **p, *parent;
-	struct cfq_queue *__cfqq;
+	struct cfq_entity *__cfqe;
 	unsigned long rb_key;
 	struct cfq_rb_root *service_tree;
 	int left;
 	int new_cfqq = 1;
 	int group_changed = 0;
 
+	cfqe = &cfqq->cfqe;
+
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 	if (!cfqd->cfq_group_isolation
 	    && cfqq_type(cfqq) == SYNC_NOIDLE_WORKLOAD
 	    && cfqq->cfqg && cfqq->cfqg != &cfqd->root_group) {
 		/* Move this cfq to root group */
 		cfq_log_cfqq(cfqd, cfqq, "moving to root group");
-		if (!RB_EMPTY_NODE(&cfqq->rb_node))
+		if (!RB_EMPTY_NODE(&cfqe->rb_node))
 			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
 		cfqq->orig_cfqg = cfqq->cfqg;
 		cfqq->cfqg = &cfqd->root_group;

@@ -1195,7 +1216,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		   && cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) {
 		/* cfqq is sequential now needs to go to its original group */
 		BUG_ON(cfqq->cfqg != &cfqd->root_group);
-		if (!RB_EMPTY_NODE(&cfqq->rb_node))
+		if (!RB_EMPTY_NODE(&cfqe->rb_node))
 			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
 		cfq_put_cfqg(cfqq->cfqg);
 		cfqq->cfqg = cfqq->orig_cfqg;

@@ -1210,9 +1231,9 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	if (cfq_class_idle(cfqq)) {
 		rb_key = CFQ_IDLE_DELAY;
 		parent = rb_last(&service_tree->rb);
-		if (parent && parent != &cfqq->rb_node) {
-			__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
-			rb_key += __cfqq->rb_key;
+		if (parent && parent != &cfqe->rb_node) {
+			__cfqe = rb_entry(parent, struct cfq_entity, rb_node);
+			rb_key += __cfqe->rb_key;
 		} else
 			rb_key += jiffies;
 	} else if (!add_front) {

@@ -1227,37 +1248,37 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		cfqq->slice_resid = 0;
 	} else {
 		rb_key = -HZ;
-		__cfqq = cfq_rb_first(service_tree);
-		rb_key += __cfqq ? __cfqq->rb_key : jiffies;
+		__cfqe = cfq_rb_first(service_tree);
+		rb_key += __cfqe ? __cfqe->rb_key : jiffies;
 	}
 
-	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
+	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
 		new_cfqq = 0;
 		/*
 		 * same position, nothing more to do
 		 */
-		if (rb_key == cfqq->rb_key &&
-		    cfqq->service_tree == service_tree)
+		if (rb_key == cfqe->rb_key &&
+		    cfqe->service_tree == service_tree)
 			return;
 
-		cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
-		cfqq->service_tree = NULL;
+		cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
+		cfqe->service_tree = NULL;
 	}
 
 	left = 1;
 	parent = NULL;
-	cfqq->service_tree = service_tree;
+	cfqe->service_tree = service_tree;
 	p = &service_tree->rb.rb_node;
 	while (*p) {
 		struct rb_node **n;
 
 		parent = *p;
-		__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
+		__cfqe = rb_entry(parent, struct cfq_entity, rb_node);
 
 		/*
 		 * sort by key, that represents service time.
 		 */
-		if (time_before(rb_key, __cfqq->rb_key))
+		if (time_before(rb_key, __cfqe->rb_key))
 			n = &(*p)->rb_left;
 		else {
 			n = &(*p)->rb_right;

@@ -1268,11 +1289,11 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	}
 
 	if (left)
-		service_tree->left = &cfqq->rb_node;
+		service_tree->left = &cfqe->rb_node;
 
-	cfqq->rb_key = rb_key;
-	rb_link_node(&cfqq->rb_node, parent, p);
-	rb_insert_color(&cfqq->rb_node, &service_tree->rb);
+	cfqe->rb_key = rb_key;
+	rb_link_node(&cfqe->rb_node, parent, p);
+	rb_insert_color(&cfqe->rb_node, &service_tree->rb);
 	service_tree->count++;
 	if ((add_front || !new_cfqq) && !group_changed)
 		return;

@@ -1374,13 +1395,16 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  */
 static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
+	struct cfq_entity *cfqe;
 	cfq_log_cfqq(cfqd, cfqq, "del_from_rr");
 	BUG_ON(!cfq_cfqq_on_rr(cfqq));
 	cfq_clear_cfqq_on_rr(cfqq);
 
-	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
-		cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
-		cfqq->service_tree = NULL;
+	cfqe = &cfqq->cfqe;
+
+	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
+		cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
+		cfqe->service_tree = NULL;
 	}
 	if (cfqq->p_root) {
 		rb_erase(&cfqq->p_node, cfqq->p_root);

@@ -1708,13 +1732,13 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
 		return NULL;
 	if (RB_EMPTY_ROOT(&service_tree->rb))
 		return NULL;
-	return cfq_rb_first(service_tree);
+	return cfqq_of_entity(cfq_rb_first(service_tree));
 }
 
 static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd)
 {
 	struct cfq_group *cfqg;
-	struct cfq_queue *cfqq;
+	struct cfq_entity *cfqe;
 	int i, j;
 	struct cfq_rb_root *st;

@@ -1725,9 +1749,11 @@ static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd)
 	if (!cfqg)
 		return NULL;
 
-	for_each_cfqg_st(cfqg, i, j, st)
-		if ((cfqq = cfq_rb_first(st)) != NULL)
-			return cfqq;
+	for_each_cfqg_st(cfqg, i, j, st) {
+		cfqe = cfq_rb_first(st);
+		if (cfqe != NULL)
+			return cfqq_of_entity(cfqe);
+	}
 	return NULL;
 }

@@ -1864,9 +1890,12 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
 
 static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
+	struct cfq_entity *cfqe;
 	enum wl_prio_t prio = cfqq_prio(cfqq);
-	struct cfq_rb_root *service_tree = cfqq->service_tree;
+	struct cfq_rb_root *service_tree;
 
+	cfqe = &cfqq->cfqe;
+	service_tree = cfqe->service_tree;
 	BUG_ON(!service_tree);
 	BUG_ON(!service_tree->count);

@@ -2076,7 +2105,7 @@ static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
 static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
 				struct cfq_group *cfqg, enum wl_prio_t prio)
 {
-	struct cfq_queue *queue;
+	struct cfq_entity *cfqe;
 	int i;
 	bool key_valid = false;
 	unsigned long lowest_key = 0;

@@ -2084,10 +2113,10 @@ static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
 
 	for (i = 0; i <= SYNC_WORKLOAD; ++i) {
 		/* select the one with lowest rb_key */
-		queue = cfq_rb_first(service_tree_for(cfqg, prio, i));
-		if (queue &&
-		    (!key_valid || time_before(queue->rb_key, lowest_key))) {
-			lowest_key = queue->rb_key;
+		cfqe = cfq_rb_first(service_tree_for(cfqg, prio, i));
+		if (cfqe &&
+		    (!key_valid || time_before(cfqe->rb_key, lowest_key))) {
+			lowest_key = cfqe->rb_key;
 			cur_best = i;
 			key_valid = true;
 		}

@@ -2835,7 +2864,10 @@ static void cfq_ioc_set_ioprio(struct io_context *ioc)
 static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			  pid_t pid, bool is_sync)
 {
-	RB_CLEAR_NODE(&cfqq->rb_node);
+	struct cfq_entity *cfqe;
+
+	cfqe = &cfqq->cfqe;
+	RB_CLEAR_NODE(&cfqe->rb_node);
 	RB_CLEAR_NODE(&cfqq->p_node);
 	INIT_LIST_HEAD(&cfqq->fifo);

@@ -3244,7 +3276,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	/* Allow preemption only if we are idling on sync-noidle tree */
 	if (cfqd->serving_type == SYNC_NOIDLE_WORKLOAD &&
 	    cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD &&
-	    new_cfqq->service_tree->count == 2 &&
+	    new_cfqq->cfqe.service_tree->count == 2 &&
 	    RB_EMPTY_ROOT(&cfqq->sort_list))
 		return true;

-- 1.7.1

Gui Jianfeng

author

2011-02-21 06:12 UTC #21 lore raw

PATCH v5 2/6 cfq-iosched: Introduce cfq_entity for CFQ group

Introduce cfq_entity for CFQ group

---
 block/cfq-iosched.c |  111 +++++++++++++++++++++++++++++++--------------------
 1 files changed, 67 insertions(+), 44 deletions(-)

block/cfq-iosched.c +67 ~~-44~~

index 939c6a6..f3a126e 100644
@@ -73,7 +73,7 @@ static DEFINE_IDA(cic_index_ida);
 #define cfq_class_rt(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
 
 #define sample_valid(samples)	((samples) > 80)
-#define rb_entry_cfqg(node)	rb_entry((node), struct cfq_group, rb_node)
+#define rb_entry_entity(node)	rb_entry((node), struct cfq_entity, rb_node)
 
 /*
  * Most of our rbtree usage is for sorting with min extraction, so

@@ -101,6 +101,11 @@ struct cfq_entity {
 	struct rb_node rb_node;
 	/* service_tree key, represent the position on the tree */
 	unsigned long rb_key;
+
+	/* group service_tree key */
+	u64 vdisktime;
+	bool is_group_entity;
+	unsigned int weight;
 };
 
 /*

@@ -182,12 +187,8 @@ enum wl_type_t {
 
 /* This is per cgroup per device grouping structure */
 struct cfq_group {
-	/* group service_tree member */
-	struct rb_node rb_node;
-
-	/* group service_tree key */
-	u64 vdisktime;
-	unsigned int weight;
+	/* cfq group sched entity */
+	struct cfq_entity cfqe;
 
 	/* number of cfqq currently on this group */
 	int nr_cfqq;

@@ -314,12 +315,22 @@ struct cfq_data {
 static inline struct cfq_queue *
 cfqq_of_entity(struct cfq_entity *cfqe)
 {
-	if (cfqe)
+	if (cfqe && !cfqe->is_group_entity)
 		return container_of(cfqe, struct cfq_queue, cfqe);
 
 	return NULL;
 }
 
+static inline struct cfq_group *
+cfqg_of_entity(struct cfq_entity *cfqe)
+{
+	if (cfqe && cfqe->is_group_entity)
+		return container_of(cfqe, struct cfq_group, cfqe);
+
+	return NULL;
+}
+
+
 static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
 
 static struct cfq_rb_root *service_tree_for(struct cfq_group *cfqg,

@@ -547,12 +558,12 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
 }
 
-static inline u64 cfq_scale_slice(unsigned long delta, struct cfq_group *cfqg)
+static inline u64 cfq_scale_slice(unsigned long delta, struct cfq_entity *cfqe)
 {
 	u64 d = delta << CFQ_SERVICE_SHIFT;
 
 	d = d * BLKIO_WEIGHT_DEFAULT;
-	do_div(d, cfqg->weight);
+	do_div(d, cfqe->weight);
 	return d;
 }

@@ -577,11 +588,11 @@ static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime)
 static void update_min_vdisktime(struct cfq_rb_root *st)
 {
 	u64 vdisktime = st->min_vdisktime;
-	struct cfq_group *cfqg;
+	struct cfq_entity *cfqe;
 
 	if (st->left) {
-		cfqg = rb_entry_cfqg(st->left);
-		vdisktime = min_vdisktime(vdisktime, cfqg->vdisktime);
+		cfqe = rb_entry_entity(st->left);
+		vdisktime = min_vdisktime(vdisktime, cfqe->vdisktime);
 	}
 
 	st->min_vdisktime = max_vdisktime(st->min_vdisktime, vdisktime);

@@ -612,8 +623,9 @@ static inline unsigned
 cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
+	struct cfq_entity *cfqe = &cfqg->cfqe;
 
-	return cfq_target_latency * cfqg->weight / st->total_weight;
+	return cfq_target_latency * cfqe->weight / st->total_weight;
 }
 
 static inline void

@@ -776,13 +788,13 @@ static struct cfq_entity *cfq_rb_first(struct cfq_rb_root *root)
 	return NULL;
 }
 
-static struct cfq_group *cfq_rb_first_group(struct cfq_rb_root *root)
+static struct cfq_entity *cfq_rb_first_entity(struct cfq_rb_root *root)
 {
 	if (!root->left)
 		root->left = rb_first(&root->rb);
 
 	if (root->left)
-		return rb_entry_cfqg(root->left);
+		return rb_entry_entity(root->left);
 
 	return NULL;
 }

@@ -839,9 +851,9 @@ static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
 }
 
 static inline s64
-cfqg_key(struct cfq_rb_root *st, struct cfq_group *cfqg)
+entity_key(struct cfq_rb_root *st, struct cfq_entity *entity)
 {
-	return cfqg->vdisktime - st->min_vdisktime;
+	return entity->vdisktime - st->min_vdisktime;
 }
 
 static void

@@ -849,15 +861,16 @@ __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 {
 	struct rb_node **node = &st->rb.rb_node;
 	struct rb_node *parent = NULL;
-	struct cfq_group *__cfqg;
-	s64 key = cfqg_key(st, cfqg);
+	struct cfq_entity *__cfqe;
+	struct cfq_entity *cfqe = &cfqg->cfqe;
+	s64 key = entity_key(st, cfqe);
 	int left = 1;
 
 	while (*node != NULL) {
 		parent = *node;
-		__cfqg = rb_entry_cfqg(parent);
+		__cfqe = rb_entry_entity(parent);
 
-		if (key < cfqg_key(st, __cfqg))
+		if (key < entity_key(st, __cfqe))
 			node = &parent->rb_left;
 		else {
 			node = &parent->rb_right;

@@ -866,21 +879,22 @@ __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 	}
 
 	if (left)
-		st->left = &cfqg->rb_node;
+		st->left = &cfqe->rb_node;
 
-	rb_link_node(&cfqg->rb_node, parent, node);
-	rb_insert_color(&cfqg->rb_node, &st->rb);
+	rb_link_node(&cfqe->rb_node, parent, node);
+	rb_insert_color(&cfqe->rb_node, &st->rb);
 }
 
 static void
 cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
-	struct cfq_group *__cfqg;
+	struct cfq_entity *cfqe = &cfqg->cfqe;
+	struct cfq_entity *__cfqe;
 	struct rb_node *n;
 
 	cfqg->nr_cfqq++;
-	if (!RB_EMPTY_NODE(&cfqg->rb_node))
+	if (!RB_EMPTY_NODE(&cfqe->rb_node))
 		return;
 
 	/*

@@ -890,19 +904,20 @@ cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	 */
 	n = rb_last(&st->rb);
 	if (n) {
-		__cfqg = rb_entry_cfqg(n);
-		cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
+		__cfqe = rb_entry_entity(n);
+		cfqe->vdisktime = __cfqe->vdisktime + CFQ_IDLE_DELAY;
 	} else
-		cfqg->vdisktime = st->min_vdisktime;
+		cfqe->vdisktime = st->min_vdisktime;
 
 	__cfq_group_service_tree_add(st, cfqg);
-	st->total_weight += cfqg->weight;
+	st->total_weight += cfqe->weight;
 }
 
 static void
 cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
+	struct cfq_entity *cfqe = &cfqg->cfqe;
 
 	BUG_ON(cfqg->nr_cfqq < 1);
 	cfqg->nr_cfqq--;

@@ -912,9 +927,9 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		return;
 
 	cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
-	st->total_weight -= cfqg->weight;
-	if (!RB_EMPTY_NODE(&cfqg->rb_node))
-		cfq_rb_erase(&cfqg->rb_node, st);
+	st->total_weight -= cfqe->weight;
+	if (!RB_EMPTY_NODE(&cfqe->rb_node))
+		cfq_rb_erase(&cfqe->rb_node, st);
 	cfqg->saved_workload_slice = 0;
 	cfq_blkiocg_update_dequeue_stats(&cfqg->blkg, 1);
 }

@@ -952,6 +967,7 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 	unsigned int used_sl, charge;
 	int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
 			- cfqg->service_tree_idle.count;
+	struct cfq_entity *cfqe = &cfqg->cfqe;
 
 	BUG_ON(nr_sync < 0);
 	used_sl = charge = cfq_cfqq_slice_usage(cfqq);

@@ -962,8 +978,8 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 		charge = 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(charge, cfqg);
+	cfq_rb_erase(&cfqe->rb_node, st);
+	cfqe->vdisktime += cfq_scale_slice(charge, cfqe);
 	__cfq_group_service_tree_add(st, cfqg);
 
 	/* This group is being expired. Save the context */

@@ -975,8 +991,8 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 	} else
 		cfqg->saved_workload_slice = 0;
 
-	cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
-					st->min_vdisktime);
+	cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu",
+		     cfqe->vdisktime, st->min_vdisktime);
 	cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u disp=%u charge=%u iops=%u"
 			" sect=%u", used_sl, cfqq->slice_dispatch, charge,
 			iops_mode(cfqd), cfqq->nr_sectors);

@@ -995,7 +1011,7 @@ static inline struct cfq_group *cfqg_of_blkg(struct blkio_group *blkg)
 void cfq_update_blkio_group_weight(void *key, struct blkio_group *blkg,
 					unsigned int weight)
 {
-	cfqg_of_blkg(blkg)->weight = weight;
+	cfqg_of_blkg(blkg)->cfqe.weight = weight;
 }
 
 static struct cfq_group *

@@ -1024,7 +1040,9 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 
 	for_each_cfqg_st(cfqg, i, j, st)
 		*st = CFQ_RB_ROOT;
-	RB_CLEAR_NODE(&cfqg->rb_node);
+	RB_CLEAR_NODE(&cfqg->cfqe.rb_node);
+
+	cfqg->cfqe.is_group_entity = true;
 
 	/*
 	 * Take the initial reference that will be released on destroy

@@ -1048,7 +1066,7 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
 					0);
 
-	cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
+	cfqg->cfqe.weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
 
 	/* Add group on cfqd list */
 	hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);

@@ -2209,10 +2227,13 @@ static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
 	struct cfq_group *cfqg;
+	struct cfq_entity *cfqe;
 
 	if (RB_EMPTY_ROOT(&st->rb))
 		return NULL;
-	cfqg = cfq_rb_first_group(st);
+	cfqe = cfq_rb_first_entity(st);
+	cfqg = cfqg_of_entity(cfqe);
+	BUG_ON(!cfqg);
 	update_min_vdisktime(st);
 	return cfqg;
 }

@@ -2871,6 +2892,7 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	RB_CLEAR_NODE(&cfqq->p_node);
 	INIT_LIST_HEAD(&cfqq->fifo);
 
+	cfqe->is_group_entity = false;
 	cfqq->ref = 0;
 	cfqq->cfqd = cfqd;

@@ -3907,10 +3929,11 @@ static void *cfq_init_queue(struct request_queue *q)
 	cfqg = &cfqd->root_group;
 	for_each_cfqg_st(cfqg, i, j, st)
 		*st = CFQ_RB_ROOT;
-	RB_CLEAR_NODE(&cfqg->rb_node);
+	RB_CLEAR_NODE(&cfqg->cfqe.rb_node);
 
 	/* Give preference to root group over other groups */
-	cfqg->weight = 2*BLKIO_WEIGHT_DEFAULT;
+	cfqg->cfqe.weight = 2*BLKIO_WEIGHT_DEFAULT;
+	cfqg->cfqe.is_group_entity = true;
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 	/*

-- 1.7.1

Gui Jianfeng

author

2011-02-21 06:13 UTC #22 lore raw

PATCH v5 3/6 cfq-iosched: Introduce vdisktime and io weight for CFQ queue

---
 block/cfq-iosched.c |  210 ++++++++++++++++++++++++++++++++++++++-------------
 1 files changed, 158 insertions(+), 52 deletions(-)

block/cfq-iosched.c +158 ~~-52~~

index f3a126e..81f8eb9 100644
@@ -40,6 +40,13 @@ static const int cfq_hist_divisor = 4;
 #define CFQ_IDLE_DELAY		(HZ / 5)
 
 /*
+ * The base boosting value.
+ */
+#define CFQ_BOOST_SYNC_BASE          ((HZ / 10) / 4)
+#define CFQ_BOOST_ASYNC_BASE          ((HZ / 25) / 4)
+
+
+/*
  * below this threshold, we consider thinktime immediate
  */
 #define CFQ_MIN_TT		(2)

@@ -99,10 +106,7 @@ struct cfq_entity {
 	struct cfq_rb_root *service_tree;
 	/* service_tree member */
 	struct rb_node rb_node;
-	/* service_tree key, represent the position on the tree */
-	unsigned long rb_key;
-
-	/* group service_tree key */
+	/* service_tree key */
 	u64 vdisktime;
 	bool is_group_entity;
 	unsigned int weight;

@@ -114,6 +118,8 @@ struct cfq_entity {
 struct cfq_queue {
 	/* The schedule entity */
 	struct cfq_entity cfqe;
+	/* Position time */
+	unsigned long position_time;
 	/* reference count */
 	int ref;
 	/* various state flags, see below */

@@ -312,6 +318,24 @@ struct cfq_data {
 	struct rcu_head rcu;
 };
 
+/*
+ * Map io priority(7 ~ 0) to io weight(100 ~ 1000) as follows
+ *     prio       0    1     2    3    4    5    6     7
+ *     weight  1000  868   740  612  484  356  228   100
+ */
+static inline unsigned int cfq_prio_to_weight(unsigned short ioprio)
+{
+	unsigned int step;
+
+	BUG_ON(ioprio >= IOPRIO_BE_NR);
+
+	step = (BLKIO_WEIGHT_MAX - BLKIO_WEIGHT_MIN) / (IOPRIO_BE_NR - 1);
+	if (ioprio == 0)
+		return BLKIO_WEIGHT_MAX;
+
+	return BLKIO_WEIGHT_MIN + (IOPRIO_BE_NR - ioprio - 1) * step;
+}
+
 static inline struct cfq_queue *
 cfqq_of_entity(struct cfq_entity *cfqe)
 {

@@ -840,16 +864,6 @@ cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	return cfq_choose_req(cfqd, next, prev, blk_rq_pos(last));
 }
 
-static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
-				      struct cfq_queue *cfqq)
-{
-	/*
-	 * just an approximation, should be ok.
-	 */
-	return (cfqq->cfqg->nr_cfqq - 1) * (cfq_prio_slice(cfqd, 1, 0) -
-		       cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio));
-}
-
 static inline s64
 entity_key(struct cfq_rb_root *st, struct cfq_entity *entity)
 {

@@ -1199,6 +1213,15 @@ static inline void cfq_put_cfqg(struct cfq_group *cfqg) {}
 
 #endif /* GROUP_IOSCHED */
 
+static inline u64 cfq_get_boost(struct cfq_data *cfqd,
+				 struct cfq_queue *cfqq)
+{
+	if (cfq_cfqq_sync(cfqq))
+		return cfq_scale_slice(CFQ_BOOST_SYNC_BASE, &cfqq->cfqe);
+	else
+		return cfq_scale_slice(CFQ_BOOST_ASYNC_BASE, &cfqq->cfqe);
+}
+
 /*
  * The cfqd->service_trees holds all pending cfq_queue's that have
  * requests waiting to be processed. It is sorted in the order that

@@ -1210,13 +1233,14 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	struct cfq_entity *cfqe;
 	struct rb_node **p, *parent;
 	struct cfq_entity *__cfqe;
-	unsigned long rb_key;
-	struct cfq_rb_root *service_tree;
+	struct cfq_rb_root *service_tree, *orig_st;
 	int left;
 	int new_cfqq = 1;
 	int group_changed = 0;
+	s64 key;
 
 	cfqe = &cfqq->cfqe;
+	orig_st = cfqe->service_tree;
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 	if (!cfqd->cfq_group_isolation

@@ -1224,8 +1248,15 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	    && cfqq->cfqg && cfqq->cfqg != &cfqd->root_group) {
 		/* Move this cfq to root group */
 		cfq_log_cfqq(cfqd, cfqq, "moving to root group");
-		if (!RB_EMPTY_NODE(&cfqe->rb_node))
+		if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
 			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
+			/*
+			 * Group changed, dequeue this CFQ queue from the
+			 * original service tree.
+			 */
+			cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
+			orig_st->total_weight -= cfqe->weight;
+		}
 		cfqq->orig_cfqg = cfqq->cfqg;
 		cfqq->cfqg = &cfqd->root_group;
 		cfqd->root_group.ref++;

@@ -1234,8 +1265,15 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		   && cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) {
 		/* cfqq is sequential now needs to go to its original group */
 		BUG_ON(cfqq->cfqg != &cfqd->root_group);
-		if (!RB_EMPTY_NODE(&cfqe->rb_node))
+		if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
 			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
+			/*
+			 * Group changed, dequeue this CFQ queue from the
+			 * original service tree.
+			 */
+			cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
+			orig_st->total_weight -= cfqe->weight;
+		}
 		cfq_put_cfqg(cfqq->cfqg);
 		cfqq->cfqg = cfqq->orig_cfqg;
 		cfqq->orig_cfqg = NULL;

@@ -1246,47 +1284,65 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 
 	service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq),
 						cfqq_type(cfqq));
+	if (RB_EMPTY_NODE(&cfqe->rb_node)) {
+		/*
+		 * If this CFQ queue moves to another group, the original
+		 * vdisktime makes no sense any more, reset the vdisktime
+		 * here.
+		 */
+		parent = rb_last(&service_tree->rb);
+		if (parent) {
+			u64 pos_offset;
+
+			/*
+			 * Estimate the position according to its weight and
+			 * ioprio.
+			 */
+			pos_offset = cfq_get_boost(cfqd, cfqq);
+			cfqe->vdisktime = service_tree->min_vdisktime +
+						pos_offset;
+		} else
+			cfqe->vdisktime = service_tree->min_vdisktime;
+
+		goto insert;
+	}
+
+	/*
+	 * Ok, we get here, this CFQ queue is on the service tree, dequeue it
+	 * firstly.
+	 */
+	cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
+	orig_st->total_weight -= cfqe->weight;
+
+	new_cfqq = 0;
+
 	if (cfq_class_idle(cfqq)) {
-		rb_key = CFQ_IDLE_DELAY;
 		parent = rb_last(&service_tree->rb);
 		if (parent && parent != &cfqe->rb_node) {
 			__cfqe = rb_entry(parent, struct cfq_entity, rb_node);
-			rb_key += __cfqe->rb_key;
+			cfqe->vdisktime = __cfqe->vdisktime + CFQ_IDLE_DELAY;
 		} else
-			rb_key += jiffies;
+			cfqe->vdisktime = service_tree->min_vdisktime;
 	} else if (!add_front) {
 		/*
-		 * Get our rb key offset. Subtract any residual slice
-		 * value carried from last service. A negative resid
-		 * count indicates slice overrun, and this should position
-		 * the next service time further away in the tree.
+		 * We charge the CFQ queue by the time this queue runs, and
+		 * repsition it on the service tree.
 		 */
-		rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
-		rb_key -= cfqq->slice_resid;
+		unsigned int used_sl;
+
+		used_sl = cfq_cfqq_slice_usage(cfqq);
+		cfqe->vdisktime += cfq_scale_slice(used_sl, cfqe);
 		cfqq->slice_resid = 0;
 	} else {
-		rb_key = -HZ;
-		__cfqe = cfq_rb_first(service_tree);
-		rb_key += __cfqe ? __cfqe->rb_key : jiffies;
-	}
-
-	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
-		new_cfqq = 0;
-		/*
-		 * same position, nothing more to do
-		 */
-		if (rb_key == cfqe->rb_key &&
-		    cfqe->service_tree == service_tree)
-			return;
-
-		cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
-		cfqe->service_tree = NULL;
+		cfqe->vdisktime = service_tree->min_vdisktime;
 	}
 
+insert:
 	left = 1;
 	parent = NULL;
 	cfqe->service_tree = service_tree;
 	p = &service_tree->rb.rb_node;
+	key = entity_key(service_tree, cfqe);
 	while (*p) {
 		struct rb_node **n;

@@ -1296,7 +1352,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		/*
 		 * sort by key, that represents service time.
 		 */
-		if (time_before(rb_key, __cfqe->rb_key))
+		if (key < entity_key(service_tree, __cfqe))
 			n = &(*p)->rb_left;
 		else {
 			n = &(*p)->rb_right;

@@ -1309,10 +1365,12 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	if (left)
 		service_tree->left = &cfqe->rb_node;
 
-	cfqe->rb_key = rb_key;
 	rb_link_node(&cfqe->rb_node, parent, p);
 	rb_insert_color(&cfqe->rb_node, &service_tree->rb);
+	update_min_vdisktime(service_tree);
 	service_tree->count++;
+	service_tree->total_weight += cfqe->weight;
+	cfqq->position_time = jiffies;
 	if ((add_front || !new_cfqq) && !group_changed)
 		return;
 	cfq_group_service_tree_add(cfqd, cfqq->cfqg);

@@ -1414,14 +1472,18 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	struct cfq_entity *cfqe;
+	struct cfq_rb_root *service_tree;
+
 	cfq_log_cfqq(cfqd, cfqq, "del_from_rr");
 	BUG_ON(!cfq_cfqq_on_rr(cfqq));
 	cfq_clear_cfqq_on_rr(cfqq);
 
 	cfqe = &cfqq->cfqe;
+	service_tree = cfqe->service_tree;
 
 	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
 		cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
+		service_tree->total_weight -= cfqe->weight;
 		cfqe->service_tree = NULL;
 	}
 	if (cfqq->p_root) {

@@ -2120,23 +2182,36 @@ static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
 	}
 }
 
+/*
+ * The time when a CFQ queue is put onto a service tree is recoreded in
+ * cfqq->position_time. Currently, we check the first priority CFQ queues
+ * on each service tree, and select the workload type that contains the lowest
+ * position_time CFQ queue among them.
+ */
 static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
 				struct cfq_group *cfqg, enum wl_prio_t prio)
 {
 	struct cfq_entity *cfqe;
+	struct cfq_queue *cfqq;
+	unsigned long lowest_start_time;
 	int i;
-	bool key_valid = false;
-	unsigned long lowest_key = 0;
+	bool time_valid = false;
 	enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD;
 
+	/*
+	 * TODO: We may take io priority and io class into account when
+	 * choosing a workload type. But for the time being just make use of
+	 * position_time only.
+	 */
 	for (i = 0; i <= SYNC_WORKLOAD; ++i) {
-		/* select the one with lowest rb_key */
 		cfqe = cfq_rb_first(service_tree_for(cfqg, prio, i));
-		if (cfqe &&
-		    (!key_valid || time_before(cfqe->rb_key, lowest_key))) {
-			lowest_key = cfqe->rb_key;
+		cfqq = cfqq_of_entity(cfqe);
+		if (cfqe && (!time_valid ||
+			     time_before(cfqq->position_time,
+					 lowest_start_time))) {
+			lowest_start_time = cfqq->position_time;
 			cur_best = i;
-			key_valid = true;
+			time_valid = true;
 		}
 	}

@@ -2808,10 +2883,13 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc)
 {
 	struct task_struct *tsk = current;
 	int ioprio_class;
+	struct cfq_entity *cfqe;
 
 	if (!cfq_cfqq_prio_changed(cfqq))
 		return;
 
+	cfqe = &cfqq->cfqe;
+
 	ioprio_class = IOPRIO_PRIO_CLASS(ioc->ioprio);
 	switch (ioprio_class) {
 	default:

@@ -2838,6 +2916,17 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc)
 		break;
 	}
 
+	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
+		/*
+		 * If this CFQ entity is already on service tree, we need to
+		 * adjust service tree's total weight accordingly.
+		 */
+		cfqe->service_tree->total_weight -= cfqe->weight;
+		cfqe->weight = cfq_prio_to_weight(cfqq->ioprio);
+		cfqe->service_tree->total_weight += cfqe->weight;
+	} else
+		cfqe->weight = cfq_prio_to_weight(cfqq->ioprio);
+
 	/*
 	 * keep track of original prio settings in case we have to temporarily
 	 * elevate the priority of this queue

@@ -3572,6 +3661,9 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
  */
 static void cfq_prio_boost(struct cfq_queue *cfqq)
 {
+	struct cfq_entity *cfqe;
+
+	cfqe = &cfqq->cfqe;
 	if (has_fs_excl()) {
 		/*
 		 * boost idle prio on transactions that would lock out other

@@ -3588,6 +3680,20 @@ static void cfq_prio_boost(struct cfq_queue *cfqq)
 		cfqq->ioprio_class = cfqq->org_ioprio_class;
 		cfqq->ioprio = cfqq->org_ioprio;
 	}
+
+	/*
+	 * update the io weight if io priority gets changed.
+	 */
+	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
+		/*
+		 * If this CFQ entity is already on service tree, we need to
+		 * adjust service tree's total weight accordingly.
+		 */
+		cfqe->service_tree->total_weight -= cfqe->weight;
+		cfqe->weight = cfq_prio_to_weight(cfqq->ioprio);
+		cfqe->service_tree->total_weight += cfqe->weight;
+	} else
+		cfqe->weight = cfq_prio_to_weight(cfqq->ioprio);
 }
 
 static inline int __cfq_may_queue(struct cfq_queue *cfqq)

-- 1.7.1

Gui Jianfeng

author

2011-02-21 06:16 UTC #23 lore raw

PATCH v5 4/6 cfq-iosched: Extract some common code of service tree handling for CFQ queue and CFQ group.

Extract some common code of service tree handling for CFQ queue and CFQ group. This helps when CFQ queue and CFQ group are scheduling together.

---
 block/cfq-iosched.c |   86 +++++++++++++++++++++-----------------------------
 1 files changed, 36 insertions(+), 50 deletions(-)

block/cfq-iosched.c +36 ~~-50~~

index 81f8eb9..23aa8c5 100644
@@ -871,12 +871,11 @@ entity_key(struct cfq_rb_root *st, struct cfq_entity *entity)
 }
 
 static void
-__cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
+__cfq_entity_service_tree_add(struct cfq_rb_root *st, struct cfq_entity *cfqe)
 {
 	struct rb_node **node = &st->rb.rb_node;
 	struct rb_node *parent = NULL;
 	struct cfq_entity *__cfqe;
-	struct cfq_entity *cfqe = &cfqg->cfqe;
 	s64 key = entity_key(st, cfqe);
 	int left = 1;

@@ -900,6 +899,14 @@ __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 }
 
 static void
+cfq_entity_service_tree_add(struct cfq_rb_root *st, struct cfq_entity *cfqe)
+{
+	__cfq_entity_service_tree_add(st, cfqe);
+	st->count++;
+	st->total_weight += cfqe->weight;
+}
+
+static void
 cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;

@@ -923,8 +930,23 @@ cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	} else
 		cfqe->vdisktime = st->min_vdisktime;
 
-	__cfq_group_service_tree_add(st, cfqg);
-	st->total_weight += cfqe->weight;
+	cfq_entity_service_tree_add(st, cfqe);
+}
+
+static void
+__cfq_entity_service_tree_del(struct cfq_rb_root *st, struct cfq_entity *cfqe)
+{
+	cfq_rb_erase(&cfqe->rb_node, st);
+}
+
+static void
+cfq_entity_service_tree_del(struct cfq_rb_root *st, struct cfq_entity *cfqe)
+{
+	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
+		__cfq_entity_service_tree_del(st, cfqe);
+		st->total_weight -= cfqe->weight;
+		cfqe->service_tree = NULL;
+	}
 }
 
 static void

@@ -941,9 +963,7 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		return;
 
 	cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
-	st->total_weight -= cfqe->weight;
-	if (!RB_EMPTY_NODE(&cfqe->rb_node))
-		cfq_rb_erase(&cfqe->rb_node, st);
+	cfq_entity_service_tree_del(st, cfqe);
 	cfqg->saved_workload_slice = 0;
 	cfq_blkiocg_update_dequeue_stats(&cfqg->blkg, 1);
 }

@@ -992,9 +1012,9 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 		charge = cfqq->allocated_slice;
 
 	/* Can't update vdisktime while group is on service tree */
-	cfq_rb_erase(&cfqe->rb_node, st);
+	__cfq_entity_service_tree_del(st, cfqe);
 	cfqe->vdisktime += cfq_scale_slice(charge, cfqe);
-	__cfq_group_service_tree_add(st, cfqg);
+	__cfq_entity_service_tree_add(st, cfqe);
 
 	/* This group is being expired. Save the context */
 	if (time_after(cfqd->workload_expires, jiffies)) {

@@ -1231,13 +1251,11 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 				 bool add_front)
 {
 	struct cfq_entity *cfqe;
-	struct rb_node **p, *parent;
+	struct rb_node *parent;
 	struct cfq_entity *__cfqe;
 	struct cfq_rb_root *service_tree, *orig_st;
-	int left;
 	int new_cfqq = 1;
 	int group_changed = 0;
-	s64 key;
 
 	cfqe = &cfqq->cfqe;
 	orig_st = cfqe->service_tree;

@@ -1254,8 +1272,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			 * Group changed, dequeue this CFQ queue from the
 			 * original service tree.
 			 */
-			cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
-			orig_st->total_weight -= cfqe->weight;
+			cfq_entity_service_tree_del(orig_st, cfqe);
 		}
 		cfqq->orig_cfqg = cfqq->cfqg;
 		cfqq->cfqg = &cfqd->root_group;

@@ -1271,8 +1288,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			 * Group changed, dequeue this CFQ queue from the
 			 * original service tree.
 			 */
-			cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
-			orig_st->total_weight -= cfqe->weight;
+			cfq_entity_service_tree_del(orig_st, cfqe);
 		}
 		cfq_put_cfqg(cfqq->cfqg);
 		cfqq->cfqg = cfqq->orig_cfqg;

@@ -1311,8 +1327,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	 * Ok, we get here, this CFQ queue is on the service tree, dequeue it
 	 * firstly.
 	 */
-	cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
-	orig_st->total_weight -= cfqe->weight;
+	cfq_entity_service_tree_del(orig_st, cfqe);
 
 	new_cfqq = 0;

@@ -1338,38 +1353,11 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	}
 
 insert:
-	left = 1;
-	parent = NULL;
 	cfqe->service_tree = service_tree;
-	p = &service_tree->rb.rb_node;
-	key = entity_key(service_tree, cfqe);
-	while (*p) {
-		struct rb_node **n;
-
-		parent = *p;
-		__cfqe = rb_entry(parent, struct cfq_entity, rb_node);
-
-		/*
-		 * sort by key, that represents service time.
-		 */
-		if (key < entity_key(service_tree, __cfqe))
-			n = &(*p)->rb_left;
-		else {
-			n = &(*p)->rb_right;
-			left = 0;
-		}
-
-		p = n;
-	}
 
-	if (left)
-		service_tree->left = &cfqe->rb_node;
-
-	rb_link_node(&cfqe->rb_node, parent, p);
-	rb_insert_color(&cfqe->rb_node, &service_tree->rb);
+	/* Add cfqq onto service tree. */
+	cfq_entity_service_tree_add(service_tree, cfqe);
 	update_min_vdisktime(service_tree);
-	service_tree->count++;
-	service_tree->total_weight += cfqe->weight;
 	cfqq->position_time = jiffies;
 	if ((add_front || !new_cfqq) && !group_changed)
 		return;

@@ -1482,9 +1470,7 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	service_tree = cfqe->service_tree;
 
 	if (!RB_EMPTY_NODE(&cfqe->rb_node)) {
-		cfq_rb_erase(&cfqe->rb_node, cfqe->service_tree);
-		service_tree->total_weight -= cfqe->weight;
-		cfqe->service_tree = NULL;
+		cfq_entity_service_tree_del(service_tree, cfqe);
 	}
 	if (cfqq->p_root) {
 		rb_erase(&cfqq->p_node, cfqq->p_root);

-- 1.7.1

Gui Jianfeng

author

2011-02-21 06:16 UTC #24 lore raw

PATCH v5 5/6 cfq-iosched: CFQ group hierarchical scheduling and use_hierarchy interface.

CFQ group hierarchical scheduling and use_hierarchy interface.

---
 block/blk-cgroup.c  |   61 +++++-
 block/blk-cgroup.h  |    3 +
 block/cfq-iosched.c |  600 +++++++++++++++++++++++++++++++++++++--------------
 3 files changed, 500 insertions(+), 164 deletions(-)

block/blk-cgroup.c +59 -2

index 455768a..c55fecd 100644
@@ -25,7 +25,10 @@
 static DEFINE_SPINLOCK(blkio_list_lock);
 static LIST_HEAD(blkio_list);
 
-struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
+struct blkio_cgroup blkio_root_cgroup = {
+	.weight = 2*BLKIO_WEIGHT_DEFAULT,
+	.use_hierarchy = 0
+};
 EXPORT_SYMBOL_GPL(blkio_root_cgroup);
 
 static struct cgroup_subsys_state *blkiocg_create(struct cgroup_subsys *,

@@ -454,6 +457,7 @@ static void __blkiocg_del_blkio_group(struct blkio_group *blkg)
 	blkg->blkcg_id = 0;
 }
 
+
 /*
  * returns 0 if blkio_group was still on cgroup list. Otherwise returns 1
  * indicating that blk_group was unhashed by the time we got to it.

@@ -765,6 +769,12 @@ unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
 }
 EXPORT_SYMBOL_GPL(blkcg_get_weight);
 
+unsigned int blkcg_get_use_hierarchy(struct blkio_cgroup *blkcg)
+{
+	return blkcg->use_hierarchy;
+}
+EXPORT_SYMBOL_GPL(blkcg_get_use_hierarchy);
+
 uint64_t blkcg_get_read_bps(struct blkio_cgroup *blkcg, dev_t dev)
 {
 	struct blkio_policy_node *pn;

@@ -1202,6 +1212,8 @@ static u64 blkiocg_file_read_u64 (struct cgroup *cgrp, struct cftype *cft) {
 		switch(name) {
 		case BLKIO_PROP_weight:
 			return (u64)blkcg->weight;
+		case BLKIO_PROP_use_hierarchy:
+			return (u64)blkcg->use_hierarchy;
 		}
 		break;
 	default:

@@ -1210,6 +1222,36 @@ static u64 blkiocg_file_read_u64 (struct cgroup *cgrp, struct cftype *cft) {
 	return 0;
 }
 
+static int blkio_use_hierarchy_write(struct cgroup *cgrp, u64 val)
+{
+	struct cgroup *parent = cgrp->parent;
+	struct blkio_cgroup *blkcg, *parent_blkcg = NULL;
+	int ret = 0;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	blkcg = cgroup_to_blkio_cgroup(cgrp);
+	if (parent)
+		parent_blkcg = cgroup_to_blkio_cgroup(parent);
+
+	cgroup_lock();
+	/*
+	 * If parent's use_hierarchy is set, we can't make any modifications
+	 * in the child subtrees. If it is unset, then the change can occur,
+	 * provided the current cgroup has no children.
+	 */
+	if (!parent_blkcg || !parent_blkcg->use_hierarchy) {
+		if (list_empty(&cgrp->children))
+			blkcg->use_hierarchy = val;
+		else
+			ret = -EBUSY;
+	} else
+		ret = -EINVAL;
+	cgroup_unlock();
+	return ret;
+}
+
 static int
 blkiocg_file_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
 {

@@ -1224,6 +1266,8 @@ blkiocg_file_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
 		switch(name) {
 		case BLKIO_PROP_weight:
 			return blkio_weight_write(blkcg, val);
+		case BLKIO_PROP_use_hierarchy:
+			return blkio_use_hierarchy_write(cgrp, val);
 		}
 		break;
 	default:

@@ -1301,6 +1345,13 @@ struct cftype blkio_files[] = {
 		.name = "reset_stats",
 		.write_u64 = blkiocg_reset_stats,
 	},
+	{
+		.name = "use_hierarchy",
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+					     BLKIO_PROP_use_hierarchy),
+		.read_u64 = blkiocg_file_read_u64,
+		.write_u64 = blkiocg_file_write_u64,
+	},
 #ifdef CONFIG_BLK_DEV_THROTTLING
 	{
 		.name = "throttle.read_bps_device",

@@ -1444,7 +1495,7 @@ static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 static struct cgroup_subsys_state *
 blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 {
-	struct blkio_cgroup *blkcg;
+	struct blkio_cgroup *blkcg, *parent_blkcg = NULL;
 	struct cgroup *parent = cgroup->parent;
 
 	if (!parent) {

@@ -1452,6 +1503,7 @@ blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 		goto done;
 	}
 
+	parent_blkcg = cgroup_to_blkio_cgroup(parent);
 	blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
 	if (!blkcg)
 		return ERR_PTR(-ENOMEM);

@@ -1462,6 +1514,11 @@ done:
 	INIT_HLIST_HEAD(&blkcg->blkg_list);
 
 	INIT_LIST_HEAD(&blkcg->policy_list);
+	if (parent)
+		blkcg->use_hierarchy = parent_blkcg->use_hierarchy;
+	else
+		blkcg->use_hierarchy = 0;
+
 	return &blkcg->css;
 }

block/blk-cgroup.h +3 -0

index ea4861b..5b4b351 100644
@@ -90,6 +90,7 @@ enum blkcg_file_name_prop {
 	BLKIO_PROP_idle_time,
 	BLKIO_PROP_empty_time,
 	BLKIO_PROP_dequeue,
+	BLKIO_PROP_use_hierarchy,
 };
 
 /* cgroup files owned by throttle policy */

@@ -105,6 +106,7 @@ enum blkcg_file_name_throtl {
 struct blkio_cgroup {
 	struct cgroup_subsys_state css;
 	unsigned int weight;
+	bool use_hierarchy;
 	spinlock_t lock;
 	struct hlist_head blkg_list;
 	struct list_head policy_list; /* list of blkio_policy_node */

@@ -179,6 +181,7 @@ struct blkio_policy_node {
 
 extern unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
 				     dev_t dev);
+extern unsigned int blkcg_get_use_hierarchy(struct blkio_cgroup *blkcg);
 extern uint64_t blkcg_get_read_bps(struct blkio_cgroup *blkcg,
 				     dev_t dev);
 extern uint64_t blkcg_get_write_bps(struct blkio_cgroup *blkcg,

block/cfq-iosched.c +438 ~~-162~~

876 lines not on this page · raw message

-- 1.7.1

Gui Jianfeng

author

2011-02-21 06:17 UTC #25 lore raw

PATCH v5 6/6 blkio-cgroup: Document for blkio.use_hierarchy interface

Document for blkio.use_hierarchy interface.