bfq_has_work() is using busy_queues currently, which is not accurate
because bfq_queue is busy doesn't represent that it has requests. Since
bfqd aready has a counter 'queued' to record how many requests are in
bfq, use it instead of busy_queues.
Noted that bfq_has_work() can be called with 'bfqd->lock' held, thus the
lock can't be held in bfq_has_work() to protect 'bfqd->queued'.
Signed-off-by: Yu Kuai <[email protected]>
---
block/bfq-iosched.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 61750696e87f..740dd83853a6 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -2210,7 +2210,11 @@ static void bfq_add_request(struct request *rq)
bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
bfqq->queued[rq_is_sync(rq)]++;
- bfqd->queued++;
+ /*
+ * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
+ * may be read without holding the lock in bfq_has_work().
+ */
+ WRITE_ONCE(bfqd->queued, bfqd->queued + 1);
if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) {
bfq_check_waker(bfqd, bfqq, now_ns);
@@ -2402,7 +2406,11 @@ static void bfq_remove_request(struct request_queue *q,
if (rq->queuelist.prev != &rq->queuelist)
list_del_init(&rq->queuelist);
bfqq->queued[sync]--;
- bfqd->queued--;
+ /*
+ * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
+ * may be read without holding the lock in bfq_has_work().
+ */
+ WRITE_ONCE(bfqd->queued, bfqd->queued - 1);
elv_rb_del(&bfqq->sort_list, rq);
elv_rqhash_del(q, rq);
@@ -5063,11 +5071,11 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
/*
- * Avoiding lock: a race on bfqd->busy_queues should cause at
+ * Avoiding lock: a race on bfqd->queued should cause at
* most a call to dispatch for nothing
*/
return !list_empty_careful(&bfqd->dispatch) ||
- bfq_tot_busy_queues(bfqd) > 0;
+ READ_ONCE(bfqd->queued);
}
static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
--
2.31.1
On Fri 13-05-22 10:35:07, Yu Kuai wrote:
> bfq_has_work() is using busy_queues currently, which is not accurate
> because bfq_queue is busy doesn't represent that it has requests. Since
> bfqd aready has a counter 'queued' to record how many requests are in
> bfq, use it instead of busy_queues.
>
> Noted that bfq_has_work() can be called with 'bfqd->lock' held, thus the
> lock can't be held in bfq_has_work() to protect 'bfqd->queued'.
>
> Signed-off-by: Yu Kuai <[email protected]>
Looks good. Feel free to add:
Reviewed-by: Jan Kara <[email protected]>
Honza
> ---
> block/bfq-iosched.c | 16 ++++++++++++----
> 1 file changed, 12 insertions(+), 4 deletions(-)
>
> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
> index 61750696e87f..740dd83853a6 100644
> --- a/block/bfq-iosched.c
> +++ b/block/bfq-iosched.c
> @@ -2210,7 +2210,11 @@ static void bfq_add_request(struct request *rq)
>
> bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
> bfqq->queued[rq_is_sync(rq)]++;
> - bfqd->queued++;
> + /*
> + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
> + * may be read without holding the lock in bfq_has_work().
> + */
> + WRITE_ONCE(bfqd->queued, bfqd->queued + 1);
>
> if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) {
> bfq_check_waker(bfqd, bfqq, now_ns);
> @@ -2402,7 +2406,11 @@ static void bfq_remove_request(struct request_queue *q,
> if (rq->queuelist.prev != &rq->queuelist)
> list_del_init(&rq->queuelist);
> bfqq->queued[sync]--;
> - bfqd->queued--;
> + /*
> + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
> + * may be read without holding the lock in bfq_has_work().
> + */
> + WRITE_ONCE(bfqd->queued, bfqd->queued - 1);
> elv_rb_del(&bfqq->sort_list, rq);
>
> elv_rqhash_del(q, rq);
> @@ -5063,11 +5071,11 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
> struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
>
> /*
> - * Avoiding lock: a race on bfqd->busy_queues should cause at
> + * Avoiding lock: a race on bfqd->queued should cause at
> * most a call to dispatch for nothing
> */
> return !list_empty_careful(&bfqd->dispatch) ||
> - bfq_tot_busy_queues(bfqd) > 0;
> + READ_ONCE(bfqd->queued);
> }
>
> static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
> --
> 2.31.1
>
--
Jan Kara <[email protected]>
SUSE Labs, CR
> Il giorno 16 mag 2022, alle ore 11:56, Jan Kara <[email protected]> ha scritto:
>
> On Fri 13-05-22 10:35:07, Yu Kuai wrote:
>> bfq_has_work() is using busy_queues currently, which is not accurate
>> because bfq_queue is busy doesn't represent that it has requests. Since
>> bfqd aready has a counter 'queued' to record how many requests are in
>> bfq, use it instead of busy_queues.
>>
The number of requests queued is not equal to the number of busy
queues (it is >=). If this patch is based on this assumption then
unfortunately it is wrong :(
Paolo
>> Noted that bfq_has_work() can be called with 'bfqd->lock' held, thus the
>> lock can't be held in bfq_has_work() to protect 'bfqd->queued'.
>>
>> Signed-off-by: Yu Kuai <[email protected]>
>
> Looks good. Feel free to add:
>
> Reviewed-by: Jan Kara <[email protected]>
>
> Honza
>
>> ---
>> block/bfq-iosched.c | 16 ++++++++++++----
>> 1 file changed, 12 insertions(+), 4 deletions(-)
>>
>> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
>> index 61750696e87f..740dd83853a6 100644
>> --- a/block/bfq-iosched.c
>> +++ b/block/bfq-iosched.c
>> @@ -2210,7 +2210,11 @@ static void bfq_add_request(struct request *rq)
>>
>> bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
>> bfqq->queued[rq_is_sync(rq)]++;
>> - bfqd->queued++;
>> + /*
>> + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
>> + * may be read without holding the lock in bfq_has_work().
>> + */
>> + WRITE_ONCE(bfqd->queued, bfqd->queued + 1);
>>
>> if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) {
>> bfq_check_waker(bfqd, bfqq, now_ns);
>> @@ -2402,7 +2406,11 @@ static void bfq_remove_request(struct request_queue *q,
>> if (rq->queuelist.prev != &rq->queuelist)
>> list_del_init(&rq->queuelist);
>> bfqq->queued[sync]--;
>> - bfqd->queued--;
>> + /*
>> + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
>> + * may be read without holding the lock in bfq_has_work().
>> + */
>> + WRITE_ONCE(bfqd->queued, bfqd->queued - 1);
>> elv_rb_del(&bfqq->sort_list, rq);
>>
>> elv_rqhash_del(q, rq);
>> @@ -5063,11 +5071,11 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
>> struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
>>
>> /*
>> - * Avoiding lock: a race on bfqd->busy_queues should cause at
>> + * Avoiding lock: a race on bfqd->queued should cause at
>> * most a call to dispatch for nothing
>> */
>> return !list_empty_careful(&bfqd->dispatch) ||
>> - bfq_tot_busy_queues(bfqd) > 0;
>> + READ_ONCE(bfqd->queued);
>> }
>>
>> static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
>> --
>> 2.31.1
>>
> --
> Jan Kara <[email protected]>
> SUSE Labs, CR
?? 2022/05/17 23:06, Paolo Valente д??:
>
>
>> Il giorno 17 mag 2022, alle ore 16:21, Paolo Valente <[email protected]> ha scritto:
>>
>>
>>
>>> Il giorno 16 mag 2022, alle ore 11:56, Jan Kara <[email protected]> ha scritto:
>>>
>>> On Fri 13-05-22 10:35:07, Yu Kuai wrote:
>>>> bfq_has_work() is using busy_queues currently, which is not accurate
>>>> because bfq_queue is busy doesn't represent that it has requests. Since
>>>> bfqd aready has a counter 'queued' to record how many requests are in
>>>> bfq, use it instead of busy_queues.
>>>>
>>
>> The number of requests queued is not equal to the number of busy
>> queues (it is >=).
>
> No, sorry. It is actually != in general.
Hi, Paolo
I'm aware that number of requests queued is not equal to the number of
busy queues, and that is the motivation of this patch.
>
> In particular, if queued == 0 but there are busy queues (although
> still waiting for I/O to arrive), then responding that there is no
> work caused blk-mq to stop asking, and hence an I/O freeze. IOW I/O
> eventually arrives for a busy queue, but blk-mq does not ask for a new
> request any longer. But maybe things have changed around bfq since
> then.
The problem is that if queued == 0 while there are busy queues, is there
any point to return true in bfq_has_work() ? IMO, it will only cause
unecessary run queue. And if new request arrives,
blk_mq_sched_insert_request() will trigger a run queue.
Thanks,
Kuai
>
> Paolo
>
>> If this patch is based on this assumption then
>> unfortunately it is wrong :(
>>
>> Paolo
>>
>>>> Noted that bfq_has_work() can be called with 'bfqd->lock' held, thus the
>>>> lock can't be held in bfq_has_work() to protect 'bfqd->queued'.
>>>>
>>>> Signed-off-by: Yu Kuai <[email protected]>
>>>
>>> Looks good. Feel free to add:
>>>
>>> Reviewed-by: Jan Kara <[email protected]>
>>>
>>> Honza
>>>
>>>> ---
>>>> block/bfq-iosched.c | 16 ++++++++++++----
>>>> 1 file changed, 12 insertions(+), 4 deletions(-)
>>>>
>>>> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
>>>> index 61750696e87f..740dd83853a6 100644
>>>> --- a/block/bfq-iosched.c
>>>> +++ b/block/bfq-iosched.c
>>>> @@ -2210,7 +2210,11 @@ static void bfq_add_request(struct request *rq)
>>>>
>>>> bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
>>>> bfqq->queued[rq_is_sync(rq)]++;
>>>> - bfqd->queued++;
>>>> + /*
>>>> + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
>>>> + * may be read without holding the lock in bfq_has_work().
>>>> + */
>>>> + WRITE_ONCE(bfqd->queued, bfqd->queued + 1);
>>>>
>>>> if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) {
>>>> bfq_check_waker(bfqd, bfqq, now_ns);
>>>> @@ -2402,7 +2406,11 @@ static void bfq_remove_request(struct request_queue *q,
>>>> if (rq->queuelist.prev != &rq->queuelist)
>>>> list_del_init(&rq->queuelist);
>>>> bfqq->queued[sync]--;
>>>> - bfqd->queued--;
>>>> + /*
>>>> + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
>>>> + * may be read without holding the lock in bfq_has_work().
>>>> + */
>>>> + WRITE_ONCE(bfqd->queued, bfqd->queued - 1);
>>>> elv_rb_del(&bfqq->sort_list, rq);
>>>>
>>>> elv_rqhash_del(q, rq);
>>>> @@ -5063,11 +5071,11 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
>>>> struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
>>>>
>>>> /*
>>>> - * Avoiding lock: a race on bfqd->busy_queues should cause at
>>>> + * Avoiding lock: a race on bfqd->queued should cause at
>>>> * most a call to dispatch for nothing
>>>> */
>>>> return !list_empty_careful(&bfqd->dispatch) ||
>>>> - bfq_tot_busy_queues(bfqd) > 0;
>>>> + READ_ONCE(bfqd->queued);
>>>> }
>>>>
>>>> static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
>>>> --
>>>> 2.31.1
>>>>
>>> --
>>> Jan Kara <[email protected]>
>>> SUSE Labs, CR
>>
>
> .
>
> Il giorno 17 mag 2022, alle ore 16:21, Paolo Valente <[email protected]> ha scritto:
>
>
>
>> Il giorno 16 mag 2022, alle ore 11:56, Jan Kara <[email protected]> ha scritto:
>>
>> On Fri 13-05-22 10:35:07, Yu Kuai wrote:
>>> bfq_has_work() is using busy_queues currently, which is not accurate
>>> because bfq_queue is busy doesn't represent that it has requests. Since
>>> bfqd aready has a counter 'queued' to record how many requests are in
>>> bfq, use it instead of busy_queues.
>>>
>
> The number of requests queued is not equal to the number of busy
> queues (it is >=).
No, sorry. It is actually != in general.
In particular, if queued == 0 but there are busy queues (although
still waiting for I/O to arrive), then responding that there is no
work caused blk-mq to stop asking, and hence an I/O freeze. IOW I/O
eventually arrives for a busy queue, but blk-mq does not ask for a new
request any longer. But maybe things have changed around bfq since
then.
Paolo
> If this patch is based on this assumption then
> unfortunately it is wrong :(
>
> Paolo
>
>>> Noted that bfq_has_work() can be called with 'bfqd->lock' held, thus the
>>> lock can't be held in bfq_has_work() to protect 'bfqd->queued'.
>>>
>>> Signed-off-by: Yu Kuai <[email protected]>
>>
>> Looks good. Feel free to add:
>>
>> Reviewed-by: Jan Kara <[email protected]>
>>
>> Honza
>>
>>> ---
>>> block/bfq-iosched.c | 16 ++++++++++++----
>>> 1 file changed, 12 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
>>> index 61750696e87f..740dd83853a6 100644
>>> --- a/block/bfq-iosched.c
>>> +++ b/block/bfq-iosched.c
>>> @@ -2210,7 +2210,11 @@ static void bfq_add_request(struct request *rq)
>>>
>>> bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
>>> bfqq->queued[rq_is_sync(rq)]++;
>>> - bfqd->queued++;
>>> + /*
>>> + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
>>> + * may be read without holding the lock in bfq_has_work().
>>> + */
>>> + WRITE_ONCE(bfqd->queued, bfqd->queued + 1);
>>>
>>> if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) {
>>> bfq_check_waker(bfqd, bfqq, now_ns);
>>> @@ -2402,7 +2406,11 @@ static void bfq_remove_request(struct request_queue *q,
>>> if (rq->queuelist.prev != &rq->queuelist)
>>> list_del_init(&rq->queuelist);
>>> bfqq->queued[sync]--;
>>> - bfqd->queued--;
>>> + /*
>>> + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
>>> + * may be read without holding the lock in bfq_has_work().
>>> + */
>>> + WRITE_ONCE(bfqd->queued, bfqd->queued - 1);
>>> elv_rb_del(&bfqq->sort_list, rq);
>>>
>>> elv_rqhash_del(q, rq);
>>> @@ -5063,11 +5071,11 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
>>> struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
>>>
>>> /*
>>> - * Avoiding lock: a race on bfqd->busy_queues should cause at
>>> + * Avoiding lock: a race on bfqd->queued should cause at
>>> * most a call to dispatch for nothing
>>> */
>>> return !list_empty_careful(&bfqd->dispatch) ||
>>> - bfq_tot_busy_queues(bfqd) > 0;
>>> + READ_ONCE(bfqd->queued);
>>> }
>>>
>>> static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
>>> --
>>> 2.31.1
>>>
>> --
>> Jan Kara <[email protected]>
>> SUSE Labs, CR
>
> Il giorno 18 mag 2022, alle ore 03:17, yukuai (C) <[email protected]> ha scritto:
>
> 在 2022/05/17 23:06, Paolo Valente 写道:
>>> Il giorno 17 mag 2022, alle ore 16:21, Paolo Valente <[email protected]> ha scritto:
>>>
>>>
>>>
>>>> Il giorno 16 mag 2022, alle ore 11:56, Jan Kara <[email protected]> ha scritto:
>>>>
>>>> On Fri 13-05-22 10:35:07, Yu Kuai wrote:
>>>>> bfq_has_work() is using busy_queues currently, which is not accurate
>>>>> because bfq_queue is busy doesn't represent that it has requests. Since
>>>>> bfqd aready has a counter 'queued' to record how many requests are in
>>>>> bfq, use it instead of busy_queues.
>>>>>
>>>
>>> The number of requests queued is not equal to the number of busy
>>> queues (it is >=).
>> No, sorry. It is actually != in general.
> Hi, Paolo
>
> I'm aware that number of requests queued is not equal to the number of
> busy queues, and that is the motivation of this patch.
>
>> In particular, if queued == 0 but there are busy queues (although
>> still waiting for I/O to arrive), then responding that there is no
>> work caused blk-mq to stop asking, and hence an I/O freeze. IOW I/O
>> eventually arrives for a busy queue, but blk-mq does not ask for a new
>> request any longer. But maybe things have changed around bfq since
>> then.
>
> The problem is that if queued == 0 while there are busy queues, is there
> any point to return true in bfq_has_work() ? IMO, it will only cause
> unecessary run queue. And if new request arrives,
> blk_mq_sched_insert_request() will trigger a run queue.
Great, if this is the scheme now, then the patch is correct and optimizing.
Thanks,
Paolo
>
> Thanks,
> Kuai
>> Paolo
>>> If this patch is based on this assumption then
>>> unfortunately it is wrong :(
>>>
>>> Paolo
>>>
>>>>> Noted that bfq_has_work() can be called with 'bfqd->lock' held, thus the
>>>>> lock can't be held in bfq_has_work() to protect 'bfqd->queued'.
>>>>>
>>>>> Signed-off-by: Yu Kuai <[email protected]>
>>>>
>>>> Looks good. Feel free to add:
>>>>
>>>> Reviewed-by: Jan Kara <[email protected]>
>>>>
>>>> Honza
>>>>
>>>>> ---
>>>>> block/bfq-iosched.c | 16 ++++++++++++----
>>>>> 1 file changed, 12 insertions(+), 4 deletions(-)
>>>>>
>>>>> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
>>>>> index 61750696e87f..740dd83853a6 100644
>>>>> --- a/block/bfq-iosched.c
>>>>> +++ b/block/bfq-iosched.c
>>>>> @@ -2210,7 +2210,11 @@ static void bfq_add_request(struct request *rq)
>>>>>
>>>>> bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
>>>>> bfqq->queued[rq_is_sync(rq)]++;
>>>>> - bfqd->queued++;
>>>>> + /*
>>>>> + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
>>>>> + * may be read without holding the lock in bfq_has_work().
>>>>> + */
>>>>> + WRITE_ONCE(bfqd->queued, bfqd->queued + 1);
>>>>>
>>>>> if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) {
>>>>> bfq_check_waker(bfqd, bfqq, now_ns);
>>>>> @@ -2402,7 +2406,11 @@ static void bfq_remove_request(struct request_queue *q,
>>>>> if (rq->queuelist.prev != &rq->queuelist)
>>>>> list_del_init(&rq->queuelist);
>>>>> bfqq->queued[sync]--;
>>>>> - bfqd->queued--;
>>>>> + /*
>>>>> + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
>>>>> + * may be read without holding the lock in bfq_has_work().
>>>>> + */
>>>>> + WRITE_ONCE(bfqd->queued, bfqd->queued - 1);
>>>>> elv_rb_del(&bfqq->sort_list, rq);
>>>>>
>>>>> elv_rqhash_del(q, rq);
>>>>> @@ -5063,11 +5071,11 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
>>>>> struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
>>>>>
>>>>> /*
>>>>> - * Avoiding lock: a race on bfqd->busy_queues should cause at
>>>>> + * Avoiding lock: a race on bfqd->queued should cause at
>>>>> * most a call to dispatch for nothing
>>>>> */
>>>>> return !list_empty_careful(&bfqd->dispatch) ||
>>>>> - bfq_tot_busy_queues(bfqd) > 0;
>>>>> + READ_ONCE(bfqd->queued);
>>>>> }
>>>>>
>>>>> static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
>>>>> --
>>>>> 2.31.1
>>>>>
>>>> --
>>>> Jan Kara <[email protected]>
>>>> SUSE Labs, CR
>>>
>> .