[PATCH -next v6 0/3] support concurrent sync io for bfq on a specail occasion

[PATCH -next v6 0/3] support concurrent sync io for bfq on a specail occasion

[Yu Kuai]

Resend these patches just in case v5 end up in spam (for Paolo).
Changes in v6:
 - add reviewed-by tag for patch 1

Changes in v5:
 - rename bfq_add_busy_queues() to bfq_inc_busy_queues() in patch 1
 - fix wrong definition in patch 1
 - fix spelling mistake in patch 2: leaset -> least
 - update comments in patch 3
 - add reviewed-by tag in patch 2,3

Changes in v4:
 - split bfq_update_busy_queues() to bfq_add/dec_busy_queues(),
   suggested by Jan Kara.
 - remove unused 'in_groups_with_pending_reqs',

Changes in v3:
 - remove the cleanup patch that is irrelevant now(I'll post it
   separately).
 - instead of hacking wr queues and using weights tree insertion/removal,
   using bfq_add/del_bfqq_busy() to count the number of groups
   (suggested by Jan Kara).

Changes in v2:
 - Use a different approch to count root group, which is much simple.

Currently, bfq can't handle sync io concurrently as long as they
are not issued from root group. This is because
'bfqd->num_groups_with_pending_reqs > 0' is always true in
bfq_asymmetric_scenario().

The way that bfqg is counted into 'num_groups_with_pending_reqs':

Before this patchset:
 1) root group will never be counted.
 2) Count if bfqg or it's child bfqgs have pending requests.
 3) Don't count if bfqg and it's child bfqgs complete all the requests.

After this patchset:
 1) root group is counted.
 2) Count if bfqg have at least one bfqq that is marked busy.
 3) Don't count if bfqg doesn't have any busy bfqqs.

The main reason to use busy state of bfqq instead of 'pending requests'
is that bfqq can stay busy after dispatching the last request if idling
is needed for service guarantees.

With the above changes, concurrent sync io can be supported if only
one group is activated.

fio test script(startdelay is used to avoid queue merging):
[global]
filename=/dev/nvme0n1
allow_mounted_write=0
ioengine=psync
direct=1
ioscheduler=bfq
offset_increment=10g
group_reporting
rw=randwrite
bs=4k

[test1]
numjobs=1

[test2]
startdelay=1
numjobs=1

[test3]
startdelay=2
numjobs=1

[test4]
startdelay=3
numjobs=1

[test5]
startdelay=4
numjobs=1

[test6]
startdelay=5
numjobs=1

[test7]
startdelay=6
numjobs=1

[test8]
startdelay=7
numjobs=1

test result:
running fio on root cgroup
v5.18-rc1:	   550 Mib/s
v5.18-rc1-patched: 550 Mib/s

running fio on non-root cgroup
v5.18-rc1:	   349 Mib/s
v5.18-rc1-patched: 550 Mib/s

Note that I also test null_blk with "irqmode=2
completion_nsec=100000000(100ms) hw_queue_depth=1", and tests show
that service guarantees are still preserved.

Follow-up cleanup:
https://lore.kernel.org/all/20220521073523.3118246-1-yukuai3@huawei.com/

Previous versions:
RFC: https://lore.kernel.org/all/20211127101132.486806-1-yukuai3@huawei.com/
v1: https://lore.kernel.org/all/20220305091205.4188398-1-yukuai3@huawei.com/
v2: https://lore.kernel.org/all/20220416093753.3054696-1-yukuai3@huawei.com/
v3: https://lore.kernel.org/all/20220427124722.48465-1-yukuai3@huawei.com/
v4: https://lore.kernel.org/all/20220428111907.3635820-1-yukuai3@huawei.com/
v5: https://lore.kernel.org/all/20220428120837.3737765-1-yukuai3@huawei.com/

Yu Kuai (3):
  block, bfq: record how many queues are busy in bfq_group
  block, bfq: refactor the counting of 'num_groups_with_pending_reqs'
  block, bfq: do not idle if only one group is activated

 block/bfq-cgroup.c  |  1 +
 block/bfq-iosched.c | 48 +++-----------------------------------
 block/bfq-iosched.h | 57 +++++++--------------------------------------
 block/bfq-wf2q.c    | 35 +++++++++++++++++-----------
 4 files changed, 35 insertions(+), 106 deletions(-)

-- 
2.31.1

[PATCH -next v6 1/3] block, bfq: record how many queues are busy in bfq_group

[Yu Kuai]

Prepare to refactor the counting of 'num_groups_with_pending_reqs'.

Add a counter 'busy_queues' in bfq_group, and update it in
bfq_add/del_bfqq_busy().

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 block/bfq-cgroup.c  |  1 +
 block/bfq-iosched.h |  2 ++
 block/bfq-wf2q.c    | 20 ++++++++++++++++++++
 3 files changed, 23 insertions(+)

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 09574af83566..4d516879d9fa 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -557,6 +557,7 @@ static void bfq_pd_init(struct blkg_policy_data *pd)
 				   */
 	bfqg->bfqd = bfqd;
 	bfqg->active_entities = 0;
+	bfqg->busy_queues = 0;
 	bfqg->online = true;
 	bfqg->rq_pos_tree = RB_ROOT;
 }
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 978ef5d6fe6a..3847f4ab77ac 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -906,6 +906,7 @@ struct bfq_group_data {
  *                   are groups with more than one active @bfq_entity
  *                   (see the comments to the function
  *                   bfq_bfqq_may_idle()).
+ * @busy_queues: number of busy bfqqs.
  * @rq_pos_tree: rbtree sorted by next_request position, used when
  *               determining if two or more queues have interleaving
  *               requests (see bfq_find_close_cooperator()).
@@ -942,6 +943,7 @@ struct bfq_group {
 	struct bfq_entity *my_entity;
 
 	int active_entities;
+	int busy_queues;
 
 	struct rb_root rq_pos_tree;
 
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index f8eb340381cf..d9ff33e0be38 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -218,6 +218,16 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
 	return false;
 }
 
+static void bfq_inc_busy_queues(struct bfq_queue *bfqq)
+{
+	bfqq_group(bfqq)->busy_queues++;
+}
+
+static void bfq_dec_busy_queues(struct bfq_queue *bfqq)
+{
+	bfqq_group(bfqq)->busy_queues--;
+}
+
 #else /* CONFIG_BFQ_GROUP_IOSCHED */
 
 static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
@@ -230,6 +240,14 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
 	return true;
 }
 
+static void bfq_inc_busy_queues(struct bfq_queue *bfqq)
+{
+}
+
+static void bfq_dec_busy_queues(struct bfq_queue *bfqq)
+{
+}
+
 #endif /* CONFIG_BFQ_GROUP_IOSCHED */
 
 /*
@@ -1660,6 +1678,7 @@ void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	bfq_clear_bfqq_busy(bfqq);
 
 	bfqd->busy_queues[bfqq->ioprio_class - 1]--;
+	bfq_inc_busy_queues(bfqq);
 
 	if (bfqq->wr_coeff > 1)
 		bfqd->wr_busy_queues--;
@@ -1683,6 +1702,7 @@ void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 
 	bfq_mark_bfqq_busy(bfqq);
 	bfqd->busy_queues[bfqq->ioprio_class - 1]++;
+	bfq_dec_busy_queues(bfqq);
 
 	if (!bfqq->dispatched)
 		if (bfqq->wr_coeff == 1)
-- 
2.31.1

[PATCH -next v6 2/3] block, bfq: refactor the counting of 'num_groups_with_pending_reqs'

[Yu Kuai]

Currently, bfq can't handle sync io concurrently as long as they
are not issued from root group. This is because
'bfqd->num_groups_with_pending_reqs > 0' is always true in
bfq_asymmetric_scenario().

The way that bfqg is counted into 'num_groups_with_pending_reqs':

Before this patch:
 1) root group will never be counted.
 2) Count if bfqg or it's child bfqgs have pending requests.
 3) Don't count if bfqg and it's child bfqgs complete all the requests.

After this patch:
 1) root group is counted.
 2) Count if bfqg have at least one bfqq that is marked busy.
 3) Don't count if bfqg doesn't have any busy bfqqs.

The main reason to use busy state of bfqq instead of 'pending requests'
is that bfqq can stay busy after dispatching the last request if idling
is needed for service guarantees.

With this change, the occasion that only one group is activated can be
detected, and next patch will support concurrent sync io in the
occasion.

This patch also rename 'num_groups_with_pending_reqs' to
'num_groups_with_busy_queues'.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 block/bfq-iosched.c | 46 ++-----------------------------------
 block/bfq-iosched.h | 55 ++++++---------------------------------------
 block/bfq-wf2q.c    | 19 ++++------------
 3 files changed, 13 insertions(+), 107 deletions(-)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index e47c75f1fa0f..609b4e894684 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -844,7 +844,7 @@ static bool bfq_asymmetric_scenario(struct bfq_data *bfqd,
 
 	return varied_queue_weights || multiple_classes_busy
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
-	       || bfqd->num_groups_with_pending_reqs > 0
+	       || bfqd->num_groups_with_busy_queues > 0
 #endif
 		;
 }
@@ -962,48 +962,6 @@ void __bfq_weights_tree_remove(struct bfq_data *bfqd,
 void bfq_weights_tree_remove(struct bfq_data *bfqd,
 			     struct bfq_queue *bfqq)
 {
-	struct bfq_entity *entity = bfqq->entity.parent;
-
-	for_each_entity(entity) {
-		struct bfq_sched_data *sd = entity->my_sched_data;
-
-		if (sd->next_in_service || sd->in_service_entity) {
-			/*
-			 * entity is still active, because either
-			 * next_in_service or in_service_entity is not
-			 * NULL (see the comments on the definition of
-			 * next_in_service for details on why
-			 * in_service_entity must be checked too).
-			 *
-			 * As a consequence, its parent entities are
-			 * active as well, and thus this loop must
-			 * stop here.
-			 */
-			break;
-		}
-
-		/*
-		 * The decrement of num_groups_with_pending_reqs is
-		 * not performed immediately upon the deactivation of
-		 * entity, but it is delayed to when it also happens
-		 * that the first leaf descendant bfqq of entity gets
-		 * all its pending requests completed. The following
-		 * instructions perform this delayed decrement, if
-		 * needed. See the comments on
-		 * num_groups_with_pending_reqs for details.
-		 */
-		if (entity->in_groups_with_pending_reqs) {
-			entity->in_groups_with_pending_reqs = false;
-			bfqd->num_groups_with_pending_reqs--;
-		}
-	}
-
-	/*
-	 * Next function is invoked last, because it causes bfqq to be
-	 * freed if the following holds: bfqq is not in service and
-	 * has no dispatched request. DO NOT use bfqq after the next
-	 * function invocation.
-	 */
 	__bfq_weights_tree_remove(bfqd, bfqq,
 				  &bfqd->queue_weights_tree);
 }
@@ -7107,7 +7065,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
 
 	bfqd->queue_weights_tree = RB_ROOT_CACHED;
-	bfqd->num_groups_with_pending_reqs = 0;
+	bfqd->num_groups_with_busy_queues = 0;
 
 	INIT_LIST_HEAD(&bfqd->active_list);
 	INIT_LIST_HEAD(&bfqd->idle_list);
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 3847f4ab77ac..b71a088a7f1d 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -197,9 +197,6 @@ struct bfq_entity {
 	/* flag, set to request a weight, ioprio or ioprio_class change  */
 	int prio_changed;
 
-	/* flag, set if the entity is counted in groups_with_pending_reqs */
-	bool in_groups_with_pending_reqs;
-
 	/* last child queue of entity created (for non-leaf entities) */
 	struct bfq_queue *last_bfqq_created;
 };
@@ -495,52 +492,14 @@ struct bfq_data {
 	struct rb_root_cached queue_weights_tree;
 
 	/*
-	 * Number of groups with at least one descendant process that
-	 * has at least one request waiting for completion. Note that
-	 * this accounts for also requests already dispatched, but not
-	 * yet completed. Therefore this number of groups may differ
-	 * (be larger) than the number of active groups, as a group is
-	 * considered active only if its corresponding entity has
-	 * descendant queues with at least one request queued. This
-	 * number is used to decide whether a scenario is symmetric.
-	 * For a detailed explanation see comments on the computation
-	 * of the variable asymmetric_scenario in the function
-	 * bfq_better_to_idle().
-	 *
-	 * However, it is hard to compute this number exactly, for
-	 * groups with multiple descendant processes. Consider a group
-	 * that is inactive, i.e., that has no descendant process with
-	 * pending I/O inside BFQ queues. Then suppose that
-	 * num_groups_with_pending_reqs is still accounting for this
-	 * group, because the group has descendant processes with some
-	 * I/O request still in flight. num_groups_with_pending_reqs
-	 * should be decremented when the in-flight request of the
-	 * last descendant process is finally completed (assuming that
-	 * nothing else has changed for the group in the meantime, in
-	 * terms of composition of the group and active/inactive state of child
-	 * groups and processes). To accomplish this, an additional
-	 * pending-request counter must be added to entities, and must
-	 * be updated correctly. To avoid this additional field and operations,
-	 * we resort to the following tradeoff between simplicity and
-	 * accuracy: for an inactive group that is still counted in
-	 * num_groups_with_pending_reqs, we decrement
-	 * num_groups_with_pending_reqs when the first descendant
-	 * process of the group remains with no request waiting for
-	 * completion.
-	 *
-	 * Even this simpler decrement strategy requires a little
-	 * carefulness: to avoid multiple decrements, we flag a group,
-	 * more precisely an entity representing a group, as still
-	 * counted in num_groups_with_pending_reqs when it becomes
-	 * inactive. Then, when the first descendant queue of the
-	 * entity remains with no request waiting for completion,
-	 * num_groups_with_pending_reqs is decremented, and this flag
-	 * is reset. After this flag is reset for the entity,
-	 * num_groups_with_pending_reqs won't be decremented any
-	 * longer in case a new descendant queue of the entity remains
-	 * with no request waiting for completion.
+	 * Number of groups with at least one bfqq that is marked busy,
+	 * and this number is used to decide whether a scenario is symmetric.
+	 * Note that bfqq is busy doesn't mean that the bfqq contains requests.
+	 * If idling is needed for service guarantees, bfqq will stay busy
+	 * after dispatching the last request, see details in
+	 * __bfq_bfqq_expire().
 	 */
-	unsigned int num_groups_with_pending_reqs;
+	unsigned int num_groups_with_busy_queues;
 
 	/*
 	 * Per-class (RT, BE, IDLE) number of bfq_queues containing
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index d9ff33e0be38..42464e6ff40c 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -220,12 +220,14 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
 
 static void bfq_inc_busy_queues(struct bfq_queue *bfqq)
 {
-	bfqq_group(bfqq)->busy_queues++;
+	if (!(bfqq_group(bfqq)->busy_queues++))
+		bfqq->bfqd->num_groups_with_busy_queues++;
 }
 
 static void bfq_dec_busy_queues(struct bfq_queue *bfqq)
 {
-	bfqq_group(bfqq)->busy_queues--;
+	if (!(--bfqq_group(bfqq)->busy_queues))
+		bfqq->bfqd->num_groups_with_busy_queues--;
 }
 
 #else /* CONFIG_BFQ_GROUP_IOSCHED */
@@ -1002,19 +1004,6 @@ static void __bfq_activate_entity(struct bfq_entity *entity,
 		entity->on_st_or_in_serv = true;
 	}
 
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-	if (!bfq_entity_to_bfqq(entity)) { /* bfq_group */
-		struct bfq_group *bfqg =
-			container_of(entity, struct bfq_group, entity);
-		struct bfq_data *bfqd = bfqg->bfqd;
-
-		if (!entity->in_groups_with_pending_reqs) {
-			entity->in_groups_with_pending_reqs = true;
-			bfqd->num_groups_with_pending_reqs++;
-		}
-	}
-#endif
-
 	bfq_update_fin_time_enqueue(entity, st, backshifted);
 }
 
-- 
2.31.1

[PATCH -next v6 3/3] block, bfq: do not idle if only one group is activated

[Yu Kuai]

Now that root group is counted into 'num_groups_with_busy_queues',
'num_groups_with_busy_queues > 0' is always true in
bfq_asymmetric_scenario(). Thus change the condition to '> 1'.

On the other hand, this change can enable concurrent sync io if only
one group is activated.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 block/bfq-iosched.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 609b4e894684..142e1ca4600f 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -812,7 +812,7 @@ bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
  * much easier to maintain the needed state:
  * 1) all active queues have the same weight,
  * 2) all active queues belong to the same I/O-priority class,
- * 3) there are no active groups.
+ * 3) there are one active group at most.
  * In particular, the last condition is always true if hierarchical
  * support or the cgroups interface are not enabled, thus no state
  * needs to be maintained in this case.
@@ -844,7 +844,7 @@ static bool bfq_asymmetric_scenario(struct bfq_data *bfqd,
 
 	return varied_queue_weights || multiple_classes_busy
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
-	       || bfqd->num_groups_with_busy_queues > 0
+	       || bfqd->num_groups_with_busy_queues > 1
 #endif
 		;
 }
-- 
2.31.1

Re: [PATCH -next v6 0/3] support concurrent sync io for bfq on a specail occasion

[Paolo Valente]

> Il giorno 23 mag 2022, alle ore 15:18, Yu Kuai <yukuai3@huawei.com> ha scritto:
> 
> Resend these patches just in case v5 end up in spam (for Paolo).

Thank you for resending, I do think I lost some email before.

Paolo

> Changes in v6:
> - add reviewed-by tag for patch 1
> 
> Changes in v5:
> - rename bfq_add_busy_queues() to bfq_inc_busy_queues() in patch 1
> - fix wrong definition in patch 1
> - fix spelling mistake in patch 2: leaset -> least
> - update comments in patch 3
> - add reviewed-by tag in patch 2,3
> 
> Changes in v4:
> - split bfq_update_busy_queues() to bfq_add/dec_busy_queues(),
>   suggested by Jan Kara.
> - remove unused 'in_groups_with_pending_reqs',
> 
> Changes in v3:
> - remove the cleanup patch that is irrelevant now(I'll post it
>   separately).
> - instead of hacking wr queues and using weights tree insertion/removal,
>   using bfq_add/del_bfqq_busy() to count the number of groups
>   (suggested by Jan Kara).
> 
> Changes in v2:
> - Use a different approch to count root group, which is much simple.
> 
> Currently, bfq can't handle sync io concurrently as long as they
> are not issued from root group. This is because
> 'bfqd->num_groups_with_pending_reqs > 0' is always true in
> bfq_asymmetric_scenario().
> 
> The way that bfqg is counted into 'num_groups_with_pending_reqs':
> 
> Before this patchset:
> 1) root group will never be counted.
> 2) Count if bfqg or it's child bfqgs have pending requests.
> 3) Don't count if bfqg and it's child bfqgs complete all the requests.
> 
> After this patchset:
> 1) root group is counted.
> 2) Count if bfqg have at least one bfqq that is marked busy.
> 3) Don't count if bfqg doesn't have any busy bfqqs.
> 
> The main reason to use busy state of bfqq instead of 'pending requests'
> is that bfqq can stay busy after dispatching the last request if idling
> is needed for service guarantees.
> 
> With the above changes, concurrent sync io can be supported if only
> one group is activated.
> 
> fio test script(startdelay is used to avoid queue merging):
> [global]
> filename=/dev/nvme0n1
> allow_mounted_write=0
> ioengine=psync
> direct=1
> ioscheduler=bfq
> offset_increment=10g
> group_reporting
> rw=randwrite
> bs=4k
> 
> [test1]
> numjobs=1
> 
> [test2]
> startdelay=1
> numjobs=1
> 
> [test3]
> startdelay=2
> numjobs=1
> 
> [test4]
> startdelay=3
> numjobs=1
> 
> [test5]
> startdelay=4
> numjobs=1
> 
> [test6]
> startdelay=5
> numjobs=1
> 
> [test7]
> startdelay=6
> numjobs=1
> 
> [test8]
> startdelay=7
> numjobs=1
> 
> test result:
> running fio on root cgroup
> v5.18-rc1:	   550 Mib/s
> v5.18-rc1-patched: 550 Mib/s
> 
> running fio on non-root cgroup
> v5.18-rc1:	   349 Mib/s
> v5.18-rc1-patched: 550 Mib/s
> 
> Note that I also test null_blk with "irqmode=2
> completion_nsec=100000000(100ms) hw_queue_depth=1", and tests show
> that service guarantees are still preserved.
> 
> Follow-up cleanup:
> https://lore.kernel.org/all/20220521073523.3118246-1-yukuai3@huawei.com/
> 
> Previous versions:
> RFC: https://lore.kernel.org/all/20211127101132.486806-1-yukuai3@huawei.com/
> v1: https://lore.kernel.org/all/20220305091205.4188398-1-yukuai3@huawei.com/
> v2: https://lore.kernel.org/all/20220416093753.3054696-1-yukuai3@huawei.com/
> v3: https://lore.kernel.org/all/20220427124722.48465-1-yukuai3@huawei.com/
> v4: https://lore.kernel.org/all/20220428111907.3635820-1-yukuai3@huawei.com/
> v5: https://lore.kernel.org/all/20220428120837.3737765-1-yukuai3@huawei.com/
> 
> Yu Kuai (3):
>  block, bfq: record how many queues are busy in bfq_group
>  block, bfq: refactor the counting of 'num_groups_with_pending_reqs'
>  block, bfq: do not idle if only one group is activated
> 
> block/bfq-cgroup.c  |  1 +
> block/bfq-iosched.c | 48 +++-----------------------------------
> block/bfq-iosched.h | 57 +++++++--------------------------------------
> block/bfq-wf2q.c    | 35 +++++++++++++++++-----------
> 4 files changed, 35 insertions(+), 106 deletions(-)
> 
> -- 
> 2.31.1
> 

Re: [PATCH -next v6 1/3] block, bfq: record how many queues are busy in bfq_group

[Paolo Valente]

> Il giorno 23 mag 2022, alle ore 15:18, Yu Kuai <yukuai3@huawei.com> ha scritto:
> 
> Prepare to refactor the counting of 'num_groups_with_pending_reqs'.
> 
> Add a counter 'busy_queues' in bfq_group, and update it in
> bfq_add/del_bfqq_busy().
> 
> Signed-off-by: Yu Kuai <yukuai3@huawei.com>
> Reviewed-by: Jan Kara <jack@suse.cz>
> ---
> block/bfq-cgroup.c  |  1 +
> block/bfq-iosched.h |  2 ++
> block/bfq-wf2q.c    | 20 ++++++++++++++++++++
> 3 files changed, 23 insertions(+)
> 
> diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
> index 09574af83566..4d516879d9fa 100644
> --- a/block/bfq-cgroup.c
> +++ b/block/bfq-cgroup.c
> @@ -557,6 +557,7 @@ static void bfq_pd_init(struct blkg_policy_data *pd)
> 				   */
> 	bfqg->bfqd = bfqd;
> 	bfqg->active_entities = 0;
> +	bfqg->busy_queues = 0;
> 	bfqg->online = true;
> 	bfqg->rq_pos_tree = RB_ROOT;
> }
> diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
> index 978ef5d6fe6a..3847f4ab77ac 100644
> --- a/block/bfq-iosched.h
> +++ b/block/bfq-iosched.h
> @@ -906,6 +906,7 @@ struct bfq_group_data {
>  *                   are groups with more than one active @bfq_entity
>  *                   (see the comments to the function
>  *                   bfq_bfqq_may_idle()).
> + * @busy_queues: number of busy bfqqs.
>  * @rq_pos_tree: rbtree sorted by next_request position, used when
>  *               determining if two or more queues have interleaving
>  *               requests (see bfq_find_close_cooperator()).
> @@ -942,6 +943,7 @@ struct bfq_group {
> 	struct bfq_entity *my_entity;
> 
> 	int active_entities;
> +	int busy_queues;
> 
> 	struct rb_root rq_pos_tree;
> 
> diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
> index f8eb340381cf..d9ff33e0be38 100644
> --- a/block/bfq-wf2q.c
> +++ b/block/bfq-wf2q.c
> @@ -218,6 +218,16 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
> 	return false;
> }
> 
> +static void bfq_inc_busy_queues(struct bfq_queue *bfqq)
> +{
> +	bfqq_group(bfqq)->busy_queues++;
> +}
> +
> +static void bfq_dec_busy_queues(struct bfq_queue *bfqq)
> +{
> +	bfqq_group(bfqq)->busy_queues--;
> +}
> +
> #else /* CONFIG_BFQ_GROUP_IOSCHED */
> 
> static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
> @@ -230,6 +240,14 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
> 	return true;
> }
> 
> +static void bfq_inc_busy_queues(struct bfq_queue *bfqq)
> +{
> +}
> +
> +static void bfq_dec_busy_queues(struct bfq_queue *bfqq)
> +{
> +}
> +
> #endif /* CONFIG_BFQ_GROUP_IOSCHED */
> 
> /*
> @@ -1660,6 +1678,7 @@ void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
> 	bfq_clear_bfqq_busy(bfqq);
> 
> 	bfqd->busy_queues[bfqq->ioprio_class - 1]--;
> +	bfq_inc_busy_queues(bfqq);
> 

Why do you increment the number of busy queues for the group on a
del_bfqq_busy, instead of an add_bfqq_busy?

Besides, the name of the function bfq_inc_busy_queues does not mention
the target of the update, namely the group.  This creates a little
confusion at a first sight, as one sees this function invoked right
after the update of a field with the same name: bfqd->busy_queues.

> 	if (bfqq->wr_coeff > 1)
> 		bfqd->wr_busy_queues--;
> @@ -1683,6 +1702,7 @@ void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
> 
> 	bfq_mark_bfqq_busy(bfqq);
> 	bfqd->busy_queues[bfqq->ioprio_class - 1]++;
> +	bfq_dec_busy_queues(bfqq);

Same pair of comments as above.

Thanks,
Paolo

> 
> 	if (!bfqq->dispatched)
> 		if (bfqq->wr_coeff == 1)
> -- 
> 2.31.1
> 

Re: [PATCH -next v6 2/3] block, bfq: refactor the counting of 'num_groups_with_pending_reqs'

[Paolo Valente]

> Il giorno 23 mag 2022, alle ore 15:18, Yu Kuai <yukuai3@huawei.com> ha scritto:
> 
> Currently, bfq can't handle sync io concurrently as long as they
> are not issued from root group. This is because
> 'bfqd->num_groups_with_pending_reqs > 0' is always true in
> bfq_asymmetric_scenario().
> 
> The way that bfqg is counted into 'num_groups_with_pending_reqs':
> 
> Before this patch:
> 1) root group will never be counted.
> 2) Count if bfqg or it's child bfqgs have pending requests.
> 3) Don't count if bfqg and it's child bfqgs complete all the requests.
> 
> After this patch:
> 1) root group is counted.
> 2) Count if bfqg have at least one bfqq that is marked busy.
> 3) Don't count if bfqg doesn't have any busy bfqqs.
> 
> The main reason to use busy state of bfqq instead of 'pending requests'
> is that bfqq can stay busy after dispatching the last request if idling
> is needed for service guarantees.
> 
> With this change, the occasion that only one group is activated can be
> detected, and next patch will support concurrent sync io in the
> occasion.
> 
> This patch also rename 'num_groups_with_pending_reqs' to
> 'num_groups_with_busy_queues'.
> 
> Signed-off-by: Yu Kuai <yukuai3@huawei.com>
> Reviewed-by: Jan Kara <jack@suse.cz>
> ---
> block/bfq-iosched.c | 46 ++-----------------------------------
> block/bfq-iosched.h | 55 ++++++---------------------------------------
> block/bfq-wf2q.c    | 19 ++++------------
> 3 files changed, 13 insertions(+), 107 deletions(-)
> 
> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
> index e47c75f1fa0f..609b4e894684 100644
> --- a/block/bfq-iosched.c
> +++ b/block/bfq-iosched.c
> @@ -844,7 +844,7 @@ static bool bfq_asymmetric_scenario(struct bfq_data *bfqd,
> 
> 	return varied_queue_weights || multiple_classes_busy
> #ifdef CONFIG_BFQ_GROUP_IOSCHED
> -	       || bfqd->num_groups_with_pending_reqs > 0
> +	       || bfqd->num_groups_with_busy_queues > 0
> #endif
> 		;
> }
> @@ -962,48 +962,6 @@ void __bfq_weights_tree_remove(struct bfq_data *bfqd,
> void bfq_weights_tree_remove(struct bfq_data *bfqd,
> 			     struct bfq_queue *bfqq)
> {
> -	struct bfq_entity *entity = bfqq->entity.parent;
> -
> -	for_each_entity(entity) {
> -		struct bfq_sched_data *sd = entity->my_sched_data;
> -
> -		if (sd->next_in_service || sd->in_service_entity) {
> -			/*
> -			 * entity is still active, because either
> -			 * next_in_service or in_service_entity is not
> -			 * NULL (see the comments on the definition of
> -			 * next_in_service for details on why
> -			 * in_service_entity must be checked too).
> -			 *
> -			 * As a consequence, its parent entities are
> -			 * active as well, and thus this loop must
> -			 * stop here.
> -			 */
> -			break;
> -		}
> -
> -		/*
> -		 * The decrement of num_groups_with_pending_reqs is
> -		 * not performed immediately upon the deactivation of
> -		 * entity, but it is delayed to when it also happens
> -		 * that the first leaf descendant bfqq of entity gets
> -		 * all its pending requests completed. The following
> -		 * instructions perform this delayed decrement, if
> -		 * needed. See the comments on
> -		 * num_groups_with_pending_reqs for details.
> -		 */
> -		if (entity->in_groups_with_pending_reqs) {
> -			entity->in_groups_with_pending_reqs = false;
> -			bfqd->num_groups_with_pending_reqs--;
> -		}
> -	}
> -
> -	/*
> -	 * Next function is invoked last, because it causes bfqq to be
> -	 * freed if the following holds: bfqq is not in service and
> -	 * has no dispatched request. DO NOT use bfqq after the next
> -	 * function invocation.
> -	 */
> 	__bfq_weights_tree_remove(bfqd, bfqq,
> 				  &bfqd->queue_weights_tree);
> }
> @@ -7107,7 +7065,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
> 	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
> 
> 	bfqd->queue_weights_tree = RB_ROOT_CACHED;
> -	bfqd->num_groups_with_pending_reqs = 0;
> +	bfqd->num_groups_with_busy_queues = 0;
> 
> 	INIT_LIST_HEAD(&bfqd->active_list);
> 	INIT_LIST_HEAD(&bfqd->idle_list);
> diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
> index 3847f4ab77ac..b71a088a7f1d 100644
> --- a/block/bfq-iosched.h
> +++ b/block/bfq-iosched.h
> @@ -197,9 +197,6 @@ struct bfq_entity {
> 	/* flag, set to request a weight, ioprio or ioprio_class change  */
> 	int prio_changed;
> 
> -	/* flag, set if the entity is counted in groups_with_pending_reqs */
> -	bool in_groups_with_pending_reqs;
> -
> 	/* last child queue of entity created (for non-leaf entities) */
> 	struct bfq_queue *last_bfqq_created;
> };
> @@ -495,52 +492,14 @@ struct bfq_data {
> 	struct rb_root_cached queue_weights_tree;
> 
> 	/*
> -	 * Number of groups with at least one descendant process that
> -	 * has at least one request waiting for completion. Note that
> -	 * this accounts for also requests already dispatched, but not
> -	 * yet completed. Therefore this number of groups may differ
> -	 * (be larger) than the number of active groups, as a group is
> -	 * considered active only if its corresponding entity has
> -	 * descendant queues with at least one request queued. This
> -	 * number is used to decide whether a scenario is symmetric.
> -	 * For a detailed explanation see comments on the computation
> -	 * of the variable asymmetric_scenario in the function
> -	 * bfq_better_to_idle().
> -	 *
> -	 * However, it is hard to compute this number exactly, for
> -	 * groups with multiple descendant processes. Consider a group
> -	 * that is inactive, i.e., that has no descendant process with
> -	 * pending I/O inside BFQ queues. Then suppose that
> -	 * num_groups_with_pending_reqs is still accounting for this
> -	 * group, because the group has descendant processes with some
> -	 * I/O request still in flight. num_groups_with_pending_reqs
> -	 * should be decremented when the in-flight request of the
> -	 * last descendant process is finally completed (assuming that
> -	 * nothing else has changed for the group in the meantime, in
> -	 * terms of composition of the group and active/inactive state of child
> -	 * groups and processes). To accomplish this, an additional
> -	 * pending-request counter must be added to entities, and must
> -	 * be updated correctly. To avoid this additional field and operations,
> -	 * we resort to the following tradeoff between simplicity and
> -	 * accuracy: for an inactive group that is still counted in
> -	 * num_groups_with_pending_reqs, we decrement
> -	 * num_groups_with_pending_reqs when the first descendant
> -	 * process of the group remains with no request waiting for
> -	 * completion.
> -	 *
> -	 * Even this simpler decrement strategy requires a little
> -	 * carefulness: to avoid multiple decrements, we flag a group,
> -	 * more precisely an entity representing a group, as still
> -	 * counted in num_groups_with_pending_reqs when it becomes
> -	 * inactive. Then, when the first descendant queue of the
> -	 * entity remains with no request waiting for completion,
> -	 * num_groups_with_pending_reqs is decremented, and this flag
> -	 * is reset. After this flag is reset for the entity,
> -	 * num_groups_with_pending_reqs won't be decremented any
> -	 * longer in case a new descendant queue of the entity remains
> -	 * with no request waiting for completion.
> +	 * Number of groups with at least one bfqq that is marked busy,
> +	 * and this number is used to decide whether a scenario is symmetric.
> +	 * Note that bfqq is busy doesn't mean that the bfqq contains requests.
> +	 * If idling is needed for service guarantees, bfqq will stay busy
> +	 * after dispatching the last request, see details in
> +	 * __bfq_bfqq_expire().
> 	 */
> -	unsigned int num_groups_with_pending_reqs;
> +	unsigned int num_groups_with_busy_queues;
> 
> 	/*
> 	 * Per-class (RT, BE, IDLE) number of bfq_queues containing
> diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
> index d9ff33e0be38..42464e6ff40c 100644
> --- a/block/bfq-wf2q.c
> +++ b/block/bfq-wf2q.c
> @@ -220,12 +220,14 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
> 
> static void bfq_inc_busy_queues(struct bfq_queue *bfqq)
> {
> -	bfqq_group(bfqq)->busy_queues++;
> +	if (!(bfqq_group(bfqq)->busy_queues++))
> +		bfqq->bfqd->num_groups_with_busy_queues++;
> }
> 
> static void bfq_dec_busy_queues(struct bfq_queue *bfqq)
> {
> -	bfqq_group(bfqq)->busy_queues--;
> +	if (!(--bfqq_group(bfqq)->busy_queues))

Are you sure this is correct?  You want to decrement
num_groups_with_busy_queues if busy_queues switches from 1 to 0.  But
if busy_queues == 1, then !(busy_queues) is false.

Paolo

> +		bfqq->bfqd->num_groups_with_busy_queues--;
> }
> 
> #else /* CONFIG_BFQ_GROUP_IOSCHED */
> @@ -1002,19 +1004,6 @@ static void __bfq_activate_entity(struct bfq_entity *entity,
> 		entity->on_st_or_in_serv = true;
> 	}
> 
> -#ifdef CONFIG_BFQ_GROUP_IOSCHED
> -	if (!bfq_entity_to_bfqq(entity)) { /* bfq_group */
> -		struct bfq_group *bfqg =
> -			container_of(entity, struct bfq_group, entity);
> -		struct bfq_data *bfqd = bfqg->bfqd;
> -
> -		if (!entity->in_groups_with_pending_reqs) {
> -			entity->in_groups_with_pending_reqs = true;
> -			bfqd->num_groups_with_pending_reqs++;
> -		}
> -	}
> -#endif
> -
> 	bfq_update_fin_time_enqueue(entity, st, backshifted);
> }
> 
> -- 
> 2.31.1
> 

Re: [PATCH -next v6 3/3] block, bfq: do not idle if only one group is activated

[Paolo Valente]

> Il giorno 23 mag 2022, alle ore 15:18, Yu Kuai <yukuai3@huawei.com> ha scritto:
> 
> Now that root group is counted into 'num_groups_with_busy_queues',
> 'num_groups_with_busy_queues > 0' is always true in
> bfq_asymmetric_scenario(). Thus change the condition to '> 1'.
> 
> On the other hand, this change can enable concurrent sync io if only
> one group is activated.

This is ok.  Yet, if the mistakes I found in the other two patches are
actual errors, I wonder how these changes made it to pass your tests.

Thanks,
Paolo

> 
> Signed-off-by: Yu Kuai <yukuai3@huawei.com>
> Reviewed-by: Jan Kara <jack@suse.cz>
> ---
> block/bfq-iosched.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
> index 609b4e894684..142e1ca4600f 100644
> --- a/block/bfq-iosched.c
> +++ b/block/bfq-iosched.c
> @@ -812,7 +812,7 @@ bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
>  * much easier to maintain the needed state:
>  * 1) all active queues have the same weight,
>  * 2) all active queues belong to the same I/O-priority class,
> - * 3) there are no active groups.
> + * 3) there are one active group at most.
>  * In particular, the last condition is always true if hierarchical
>  * support or the cgroups interface are not enabled, thus no state
>  * needs to be maintained in this case.
> @@ -844,7 +844,7 @@ static bool bfq_asymmetric_scenario(struct bfq_data *bfqd,
> 
> 	return varied_queue_weights || multiple_classes_busy
> #ifdef CONFIG_BFQ_GROUP_IOSCHED
> -	       || bfqd->num_groups_with_busy_queues > 0
> +	       || bfqd->num_groups_with_busy_queues > 1
> #endif
> 		;
> }
> -- 
> 2.31.1
> 

Re: [PATCH -next v6 1/3] block, bfq: record how many queues are busy in bfq_group

[Yu Kuai]

在 2022/05/28 16:18, Paolo Valente 写道:
> 

>> /*
>> @@ -1660,6 +1678,7 @@ void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
>> 	bfq_clear_bfqq_busy(bfqq);
>>
>> 	bfqd->busy_queues[bfqq->ioprio_class - 1]--;
>> +	bfq_inc_busy_queues(bfqq);
>>
> 
> Why do you increment the number of busy queues for the group on a
> del_bfqq_busy, instead of an add_bfqq_busy?
Hi, Paolo

You'are right, here should be bfq_dec_busy_queues()...
> 
> Besides, the name of the function bfq_inc_busy_queues does not mention
> the target of the update, namely the group.  This creates a little
> confusion at a first sight, as one sees this function invoked right
> after the update of a field with the same name: bfqd->busy_queues.
Ok, that make sense, I'll move the update of 'bfqd->busy_queues' into
the new api as well.

Thanks,
Kuai
> 
>> 	if (bfqq->wr_coeff > 1)
>> 		bfqd->wr_busy_queues--;
>> @@ -1683,6 +1702,7 @@ void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
>>
>> 	bfq_mark_bfqq_busy(bfqq);
>> 	bfqd->busy_queues[bfqq->ioprio_class - 1]++;
>> +	bfq_dec_busy_queues(bfqq);
> 
> Same pair of comments as above.
> 
> Thanks,
> Paolo
> 
>>
>> 	if (!bfqq->dispatched)
>> 		if (bfqq->wr_coeff == 1)
>> -- 
>> 2.31.1
>>
> 
> .
> 

Re: [PATCH -next v6 2/3] block, bfq: refactor the counting of 'num_groups_with_pending_reqs'

[Yu Kuai]

在 2022/05/28 16:27, Paolo Valente 写道:
> 
> 
>> Il giorno 23 mag 2022, alle ore 15:18, Yu Kuai <yukuai3@huawei.com> ha scritto:
>>
>> Currently, bfq can't handle sync io concurrently as long as they
>> are not issued from root group. This is because
>> 'bfqd->num_groups_with_pending_reqs > 0' is always true in
>> bfq_asymmetric_scenario().
>>
>> The way that bfqg is counted into 'num_groups_with_pending_reqs':
>>
>> Before this patch:
>> 1) root group will never be counted.
>> 2) Count if bfqg or it's child bfqgs have pending requests.
>> 3) Don't count if bfqg and it's child bfqgs complete all the requests.
>>
>> After this patch:
>> 1) root group is counted.
>> 2) Count if bfqg have at least one bfqq that is marked busy.
>> 3) Don't count if bfqg doesn't have any busy bfqqs.
>>
>> The main reason to use busy state of bfqq instead of 'pending requests'
>> is that bfqq can stay busy after dispatching the last request if idling
>> is needed for service guarantees.
>>
>> With this change, the occasion that only one group is activated can be
>> detected, and next patch will support concurrent sync io in the
>> occasion.
>>
>> This patch also rename 'num_groups_with_pending_reqs' to
>> 'num_groups_with_busy_queues'.
>>
>> Signed-off-by: Yu Kuai <yukuai3@huawei.com>
>> Reviewed-by: Jan Kara <jack@suse.cz>
>> ---
>> block/bfq-iosched.c | 46 ++-----------------------------------
>> block/bfq-iosched.h | 55 ++++++---------------------------------------
>> block/bfq-wf2q.c    | 19 ++++------------
>> 3 files changed, 13 insertions(+), 107 deletions(-)
>>
>> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
>> index e47c75f1fa0f..609b4e894684 100644
>> --- a/block/bfq-iosched.c
>> +++ b/block/bfq-iosched.c
>> @@ -844,7 +844,7 @@ static bool bfq_asymmetric_scenario(struct bfq_data *bfqd,
>>
>> 	return varied_queue_weights || multiple_classes_busy
>> #ifdef CONFIG_BFQ_GROUP_IOSCHED
>> -	       || bfqd->num_groups_with_pending_reqs > 0
>> +	       || bfqd->num_groups_with_busy_queues > 0
>> #endif
>> 		;
>> }
>> @@ -962,48 +962,6 @@ void __bfq_weights_tree_remove(struct bfq_data *bfqd,
>> void bfq_weights_tree_remove(struct bfq_data *bfqd,
>> 			     struct bfq_queue *bfqq)
>> {
>> -	struct bfq_entity *entity = bfqq->entity.parent;
>> -
>> -	for_each_entity(entity) {
>> -		struct bfq_sched_data *sd = entity->my_sched_data;
>> -
>> -		if (sd->next_in_service || sd->in_service_entity) {
>> -			/*
>> -			 * entity is still active, because either
>> -			 * next_in_service or in_service_entity is not
>> -			 * NULL (see the comments on the definition of
>> -			 * next_in_service for details on why
>> -			 * in_service_entity must be checked too).
>> -			 *
>> -			 * As a consequence, its parent entities are
>> -			 * active as well, and thus this loop must
>> -			 * stop here.
>> -			 */
>> -			break;
>> -		}
>> -
>> -		/*
>> -		 * The decrement of num_groups_with_pending_reqs is
>> -		 * not performed immediately upon the deactivation of
>> -		 * entity, but it is delayed to when it also happens
>> -		 * that the first leaf descendant bfqq of entity gets
>> -		 * all its pending requests completed. The following
>> -		 * instructions perform this delayed decrement, if
>> -		 * needed. See the comments on
>> -		 * num_groups_with_pending_reqs for details.
>> -		 */
>> -		if (entity->in_groups_with_pending_reqs) {
>> -			entity->in_groups_with_pending_reqs = false;
>> -			bfqd->num_groups_with_pending_reqs--;
>> -		}
>> -	}
>> -
>> -	/*
>> -	 * Next function is invoked last, because it causes bfqq to be
>> -	 * freed if the following holds: bfqq is not in service and
>> -	 * has no dispatched request. DO NOT use bfqq after the next
>> -	 * function invocation.
>> -	 */
>> 	__bfq_weights_tree_remove(bfqd, bfqq,
>> 				  &bfqd->queue_weights_tree);
>> }
>> @@ -7107,7 +7065,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
>> 	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
>>
>> 	bfqd->queue_weights_tree = RB_ROOT_CACHED;
>> -	bfqd->num_groups_with_pending_reqs = 0;
>> +	bfqd->num_groups_with_busy_queues = 0;
>>
>> 	INIT_LIST_HEAD(&bfqd->active_list);
>> 	INIT_LIST_HEAD(&bfqd->idle_list);
>> diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
>> index 3847f4ab77ac..b71a088a7f1d 100644
>> --- a/block/bfq-iosched.h
>> +++ b/block/bfq-iosched.h
>> @@ -197,9 +197,6 @@ struct bfq_entity {
>> 	/* flag, set to request a weight, ioprio or ioprio_class change  */
>> 	int prio_changed;
>>
>> -	/* flag, set if the entity is counted in groups_with_pending_reqs */
>> -	bool in_groups_with_pending_reqs;
>> -
>> 	/* last child queue of entity created (for non-leaf entities) */
>> 	struct bfq_queue *last_bfqq_created;
>> };
>> @@ -495,52 +492,14 @@ struct bfq_data {
>> 	struct rb_root_cached queue_weights_tree;
>>
>> 	/*
>> -	 * Number of groups with at least one descendant process that
>> -	 * has at least one request waiting for completion. Note that
>> -	 * this accounts for also requests already dispatched, but not
>> -	 * yet completed. Therefore this number of groups may differ
>> -	 * (be larger) than the number of active groups, as a group is
>> -	 * considered active only if its corresponding entity has
>> -	 * descendant queues with at least one request queued. This
>> -	 * number is used to decide whether a scenario is symmetric.
>> -	 * For a detailed explanation see comments on the computation
>> -	 * of the variable asymmetric_scenario in the function
>> -	 * bfq_better_to_idle().
>> -	 *
>> -	 * However, it is hard to compute this number exactly, for
>> -	 * groups with multiple descendant processes. Consider a group
>> -	 * that is inactive, i.e., that has no descendant process with
>> -	 * pending I/O inside BFQ queues. Then suppose that
>> -	 * num_groups_with_pending_reqs is still accounting for this
>> -	 * group, because the group has descendant processes with some
>> -	 * I/O request still in flight. num_groups_with_pending_reqs
>> -	 * should be decremented when the in-flight request of the
>> -	 * last descendant process is finally completed (assuming that
>> -	 * nothing else has changed for the group in the meantime, in
>> -	 * terms of composition of the group and active/inactive state of child
>> -	 * groups and processes). To accomplish this, an additional
>> -	 * pending-request counter must be added to entities, and must
>> -	 * be updated correctly. To avoid this additional field and operations,
>> -	 * we resort to the following tradeoff between simplicity and
>> -	 * accuracy: for an inactive group that is still counted in
>> -	 * num_groups_with_pending_reqs, we decrement
>> -	 * num_groups_with_pending_reqs when the first descendant
>> -	 * process of the group remains with no request waiting for
>> -	 * completion.
>> -	 *
>> -	 * Even this simpler decrement strategy requires a little
>> -	 * carefulness: to avoid multiple decrements, we flag a group,
>> -	 * more precisely an entity representing a group, as still
>> -	 * counted in num_groups_with_pending_reqs when it becomes
>> -	 * inactive. Then, when the first descendant queue of the
>> -	 * entity remains with no request waiting for completion,
>> -	 * num_groups_with_pending_reqs is decremented, and this flag
>> -	 * is reset. After this flag is reset for the entity,
>> -	 * num_groups_with_pending_reqs won't be decremented any
>> -	 * longer in case a new descendant queue of the entity remains
>> -	 * with no request waiting for completion.
>> +	 * Number of groups with at least one bfqq that is marked busy,
>> +	 * and this number is used to decide whether a scenario is symmetric.
>> +	 * Note that bfqq is busy doesn't mean that the bfqq contains requests.
>> +	 * If idling is needed for service guarantees, bfqq will stay busy
>> +	 * after dispatching the last request, see details in
>> +	 * __bfq_bfqq_expire().
>> 	 */
>> -	unsigned int num_groups_with_pending_reqs;
>> +	unsigned int num_groups_with_busy_queues;
>>
>> 	/*
>> 	 * Per-class (RT, BE, IDLE) number of bfq_queues containing
>> diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
>> index d9ff33e0be38..42464e6ff40c 100644
>> --- a/block/bfq-wf2q.c
>> +++ b/block/bfq-wf2q.c
>> @@ -220,12 +220,14 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
>>
>> static void bfq_inc_busy_queues(struct bfq_queue *bfqq)
>> {
>> -	bfqq_group(bfqq)->busy_queues++;
>> +	if (!(bfqq_group(bfqq)->busy_queues++))
>> +		bfqq->bfqd->num_groups_with_busy_queues++;
>> }
>>
>> static void bfq_dec_busy_queues(struct bfq_queue *bfqq)
>> {
>> -	bfqq_group(bfqq)->busy_queues--;
>> +	if (!(--bfqq_group(bfqq)->busy_queues))
> 
> Are you sure this is correct?  You want to decrement
> num_groups_with_busy_queues if busy_queues switches from 1 to 0.  But
> if busy_queues == 1, then !(busy_queues) is false.

Hi, Paolo

I'm sure this is correct.

if busy_queues == 1, then !(--busy_queues) is true; while
!(busy_queues--) is false.

Thanks,
Kuai
> 
> Paolo
> 
>> +		bfqq->bfqd->num_groups_with_busy_queues--;
>> }
>>
>> #else /* CONFIG_BFQ_GROUP_IOSCHED */
>> @@ -1002,19 +1004,6 @@ static void __bfq_activate_entity(struct bfq_entity *entity,
>> 		entity->on_st_or_in_serv = true;
>> 	}
>>
>> -#ifdef CONFIG_BFQ_GROUP_IOSCHED
>> -	if (!bfq_entity_to_bfqq(entity)) { /* bfq_group */
>> -		struct bfq_group *bfqg =
>> -			container_of(entity, struct bfq_group, entity);
>> -		struct bfq_data *bfqd = bfqg->bfqd;
>> -
>> -		if (!entity->in_groups_with_pending_reqs) {
>> -			entity->in_groups_with_pending_reqs = true;
>> -			bfqd->num_groups_with_pending_reqs++;
>> -		}
>> -	}
>> -#endif
>> -
>> 	bfq_update_fin_time_enqueue(entity, st, backshifted);
>> }
>>
>> -- 
>> 2.31.1
>>
> 
> .
> 

Re: [PATCH -next v6 2/3] block, bfq: refactor the counting of 'num_groups_with_pending_reqs'

[Paolo Valente]

> Il giorno 28 mag 2022, alle ore 10:39, Yu Kuai <yukuai3@huawei.com> ha scritto:
> 
> 在 2022/05/28 16:27, Paolo Valente 写道:
>>> Il giorno 23 mag 2022, alle ore 15:18, Yu Kuai <yukuai3@huawei.com> ha scritto:
>>> 
>>> Currently, bfq can't handle sync io concurrently as long as they
>>> are not issued from root group. This is because
>>> 'bfqd->num_groups_with_pending_reqs > 0' is always true in
>>> bfq_asymmetric_scenario().
>>> 
>>> The way that bfqg is counted into 'num_groups_with_pending_reqs':
>>> 
>>> Before this patch:
>>> 1) root group will never be counted.
>>> 2) Count if bfqg or it's child bfqgs have pending requests.
>>> 3) Don't count if bfqg and it's child bfqgs complete all the requests.
>>> 
>>> After this patch:
>>> 1) root group is counted.
>>> 2) Count if bfqg have at least one bfqq that is marked busy.
>>> 3) Don't count if bfqg doesn't have any busy bfqqs.
>>> 
>>> The main reason to use busy state of bfqq instead of 'pending requests'
>>> is that bfqq can stay busy after dispatching the last request if idling
>>> is needed for service guarantees.
>>> 
>>> With this change, the occasion that only one group is activated can be
>>> detected, and next patch will support concurrent sync io in the
>>> occasion.
>>> 
>>> This patch also rename 'num_groups_with_pending_reqs' to
>>> 'num_groups_with_busy_queues'.
>>> 
>>> Signed-off-by: Yu Kuai <yukuai3@huawei.com>
>>> Reviewed-by: Jan Kara <jack@suse.cz>
>>> ---
>>> block/bfq-iosched.c | 46 ++-----------------------------------
>>> block/bfq-iosched.h | 55 ++++++---------------------------------------
>>> block/bfq-wf2q.c    | 19 ++++------------
>>> 3 files changed, 13 insertions(+), 107 deletions(-)
>>> 
>>> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
>>> index e47c75f1fa0f..609b4e894684 100644
>>> --- a/block/bfq-iosched.c
>>> +++ b/block/bfq-iosched.c
>>> @@ -844,7 +844,7 @@ static bool bfq_asymmetric_scenario(struct bfq_data *bfqd,
>>> 
>>> 	return varied_queue_weights || multiple_classes_busy
>>> #ifdef CONFIG_BFQ_GROUP_IOSCHED
>>> -	       || bfqd->num_groups_with_pending_reqs > 0
>>> +	       || bfqd->num_groups_with_busy_queues > 0
>>> #endif
>>> 		;
>>> }
>>> @@ -962,48 +962,6 @@ void __bfq_weights_tree_remove(struct bfq_data *bfqd,
>>> void bfq_weights_tree_remove(struct bfq_data *bfqd,
>>> 			     struct bfq_queue *bfqq)
>>> {
>>> -	struct bfq_entity *entity = bfqq->entity.parent;
>>> -
>>> -	for_each_entity(entity) {
>>> -		struct bfq_sched_data *sd = entity->my_sched_data;
>>> -
>>> -		if (sd->next_in_service || sd->in_service_entity) {
>>> -			/*
>>> -			 * entity is still active, because either
>>> -			 * next_in_service or in_service_entity is not
>>> -			 * NULL (see the comments on the definition of
>>> -			 * next_in_service for details on why
>>> -			 * in_service_entity must be checked too).
>>> -			 *
>>> -			 * As a consequence, its parent entities are
>>> -			 * active as well, and thus this loop must
>>> -			 * stop here.
>>> -			 */
>>> -			break;
>>> -		}
>>> -
>>> -		/*
>>> -		 * The decrement of num_groups_with_pending_reqs is
>>> -		 * not performed immediately upon the deactivation of
>>> -		 * entity, but it is delayed to when it also happens
>>> -		 * that the first leaf descendant bfqq of entity gets
>>> -		 * all its pending requests completed. The following
>>> -		 * instructions perform this delayed decrement, if
>>> -		 * needed. See the comments on
>>> -		 * num_groups_with_pending_reqs for details.
>>> -		 */
>>> -		if (entity->in_groups_with_pending_reqs) {
>>> -			entity->in_groups_with_pending_reqs = false;
>>> -			bfqd->num_groups_with_pending_reqs--;
>>> -		}
>>> -	}
>>> -
>>> -	/*
>>> -	 * Next function is invoked last, because it causes bfqq to be
>>> -	 * freed if the following holds: bfqq is not in service and
>>> -	 * has no dispatched request. DO NOT use bfqq after the next
>>> -	 * function invocation.
>>> -	 */
>>> 	__bfq_weights_tree_remove(bfqd, bfqq,
>>> 				  &bfqd->queue_weights_tree);
>>> }
>>> @@ -7107,7 +7065,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
>>> 	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
>>> 
>>> 	bfqd->queue_weights_tree = RB_ROOT_CACHED;
>>> -	bfqd->num_groups_with_pending_reqs = 0;
>>> +	bfqd->num_groups_with_busy_queues = 0;
>>> 
>>> 	INIT_LIST_HEAD(&bfqd->active_list);
>>> 	INIT_LIST_HEAD(&bfqd->idle_list);
>>> diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
>>> index 3847f4ab77ac..b71a088a7f1d 100644
>>> --- a/block/bfq-iosched.h
>>> +++ b/block/bfq-iosched.h
>>> @@ -197,9 +197,6 @@ struct bfq_entity {
>>> 	/* flag, set to request a weight, ioprio or ioprio_class change  */
>>> 	int prio_changed;
>>> 
>>> -	/* flag, set if the entity is counted in groups_with_pending_reqs */
>>> -	bool in_groups_with_pending_reqs;
>>> -
>>> 	/* last child queue of entity created (for non-leaf entities) */
>>> 	struct bfq_queue *last_bfqq_created;
>>> };
>>> @@ -495,52 +492,14 @@ struct bfq_data {
>>> 	struct rb_root_cached queue_weights_tree;
>>> 
>>> 	/*
>>> -	 * Number of groups with at least one descendant process that
>>> -	 * has at least one request waiting for completion. Note that
>>> -	 * this accounts for also requests already dispatched, but not
>>> -	 * yet completed. Therefore this number of groups may differ
>>> -	 * (be larger) than the number of active groups, as a group is
>>> -	 * considered active only if its corresponding entity has
>>> -	 * descendant queues with at least one request queued. This
>>> -	 * number is used to decide whether a scenario is symmetric.
>>> -	 * For a detailed explanation see comments on the computation
>>> -	 * of the variable asymmetric_scenario in the function
>>> -	 * bfq_better_to_idle().
>>> -	 *
>>> -	 * However, it is hard to compute this number exactly, for
>>> -	 * groups with multiple descendant processes. Consider a group
>>> -	 * that is inactive, i.e., that has no descendant process with
>>> -	 * pending I/O inside BFQ queues. Then suppose that
>>> -	 * num_groups_with_pending_reqs is still accounting for this
>>> -	 * group, because the group has descendant processes with some
>>> -	 * I/O request still in flight. num_groups_with_pending_reqs
>>> -	 * should be decremented when the in-flight request of the
>>> -	 * last descendant process is finally completed (assuming that
>>> -	 * nothing else has changed for the group in the meantime, in
>>> -	 * terms of composition of the group and active/inactive state of child
>>> -	 * groups and processes). To accomplish this, an additional
>>> -	 * pending-request counter must be added to entities, and must
>>> -	 * be updated correctly. To avoid this additional field and operations,
>>> -	 * we resort to the following tradeoff between simplicity and
>>> -	 * accuracy: for an inactive group that is still counted in
>>> -	 * num_groups_with_pending_reqs, we decrement
>>> -	 * num_groups_with_pending_reqs when the first descendant
>>> -	 * process of the group remains with no request waiting for
>>> -	 * completion.
>>> -	 *
>>> -	 * Even this simpler decrement strategy requires a little
>>> -	 * carefulness: to avoid multiple decrements, we flag a group,
>>> -	 * more precisely an entity representing a group, as still
>>> -	 * counted in num_groups_with_pending_reqs when it becomes
>>> -	 * inactive. Then, when the first descendant queue of the
>>> -	 * entity remains with no request waiting for completion,
>>> -	 * num_groups_with_pending_reqs is decremented, and this flag
>>> -	 * is reset. After this flag is reset for the entity,
>>> -	 * num_groups_with_pending_reqs won't be decremented any
>>> -	 * longer in case a new descendant queue of the entity remains
>>> -	 * with no request waiting for completion.
>>> +	 * Number of groups with at least one bfqq that is marked busy,
>>> +	 * and this number is used to decide whether a scenario is symmetric.
>>> +	 * Note that bfqq is busy doesn't mean that the bfqq contains requests.
>>> +	 * If idling is needed for service guarantees, bfqq will stay busy
>>> +	 * after dispatching the last request, see details in
>>> +	 * __bfq_bfqq_expire().
>>> 	 */
>>> -	unsigned int num_groups_with_pending_reqs;
>>> +	unsigned int num_groups_with_busy_queues;
>>> 
>>> 	/*
>>> 	 * Per-class (RT, BE, IDLE) number of bfq_queues containing
>>> diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
>>> index d9ff33e0be38..42464e6ff40c 100644
>>> --- a/block/bfq-wf2q.c
>>> +++ b/block/bfq-wf2q.c
>>> @@ -220,12 +220,14 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
>>> 
>>> static void bfq_inc_busy_queues(struct bfq_queue *bfqq)
>>> {
>>> -	bfqq_group(bfqq)->busy_queues++;
>>> +	if (!(bfqq_group(bfqq)->busy_queues++))
>>> +		bfqq->bfqd->num_groups_with_busy_queues++;
>>> }
>>> 
>>> static void bfq_dec_busy_queues(struct bfq_queue *bfqq)
>>> {
>>> -	bfqq_group(bfqq)->busy_queues--;
>>> +	if (!(--bfqq_group(bfqq)->busy_queues))
>> Are you sure this is correct?  You want to decrement
>> num_groups_with_busy_queues if busy_queues switches from 1 to 0.  But
>> if busy_queues == 1, then !(busy_queues) is false.
> 
> Hi, Paolo
> 
> I'm sure this is correct.
> 

Yeah, sorry, I didn't notice you switched to prefix increment here.

Paolo

> if busy_queues == 1, then !(--busy_queues) is true; while
> !(busy_queues--) is false.
> 
> Thanks,
> Kuai
>> Paolo
>>> +		bfqq->bfqd->num_groups_with_busy_queues--;
>>> }
>>> 
>>> #else /* CONFIG_BFQ_GROUP_IOSCHED */
>>> @@ -1002,19 +1004,6 @@ static void __bfq_activate_entity(struct bfq_entity *entity,
>>> 		entity->on_st_or_in_serv = true;
>>> 	}
>>> 
>>> -#ifdef CONFIG_BFQ_GROUP_IOSCHED
>>> -	if (!bfq_entity_to_bfqq(entity)) { /* bfq_group */
>>> -		struct bfq_group *bfqg =
>>> -			container_of(entity, struct bfq_group, entity);
>>> -		struct bfq_data *bfqd = bfqg->bfqd;
>>> -
>>> -		if (!entity->in_groups_with_pending_reqs) {
>>> -			entity->in_groups_with_pending_reqs = true;
>>> -			bfqd->num_groups_with_pending_reqs++;
>>> -		}
>>> -	}
>>> -#endif
>>> -
>>> 	bfq_update_fin_time_enqueue(entity, st, backshifted);
>>> }
>>> 
>>> -- 
>>> 2.31.1
>>> 
>> .