The function bfq_setup_merge prepares the merging between two
bfq_queues, say bfqq and new_bfqq. To this goal, it assigns
bfqq->new_bfqq = new_bfqq. Then, each time some I/O for bfqq arrives,
the process that generated that I/O is disassociated from bfqq and
associated with new_bfqq (merging is actually a redirection). In this
respect, bfq_setup_merge increases new_bfqq->ref in advance, adding
the number of processes that are expected to be associated with
new_bfqq.
Unfortunately, the stable-merging mechanism interferes with this
setup. After bfqq->new_bfqq has been set by bfq_setup_merge, and
before all the expected processes have been associated with
bfqq->new_bfqq, bfqq may happen to be stably merged with a different
queue than the current bfqq->new_bfqq. In this case, bfqq->new_bfqq
gets changed. So, some of the processes that have been already
accounted for in the ref counter of the previous new_bfqq will not be
associated with that queue. This creates an unbalance, because those
references will never be decremented.
This commit fixes this issue by reestablishing the previous, natural
behaviour: once bfqq->new_bfqq has been set, it will not be changed
until all expected redirections have occurred.
Signed-off-by: Davide Zini <[email protected]>
Signed-off-by: Paolo Valente <[email protected]>
---
block/bfq-iosched.c | 16 +++++++++++++---
1 file changed, 13 insertions(+), 3 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 727955918563..08d9122dd4c0 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -2659,6 +2659,15 @@ bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
* are likely to increase the throughput.
*/
bfqq->new_bfqq = new_bfqq;
+ /*
+ * The above assignment schedules the following redirections:
+ * each time some I/O for bfqq arrives, the process that
+ * generated that I/O is disassociated from bfqq and
+ * associated with new_bfqq. Here we increases new_bfqq->ref
+ * in advance, adding the number of processes that are
+ * expected to be associated with new_bfqq as they happen to
+ * issue I/O.
+ */
new_bfqq->ref += process_refs;
return new_bfqq;
}
@@ -2721,6 +2730,10 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
{
struct bfq_queue *in_service_bfqq, *new_bfqq;
+ /* if a merge has already been setup, then proceed with that first */
+ if (bfqq->new_bfqq)
+ return bfqq->new_bfqq;
+
/*
* Check delayed stable merge for rotational or non-queueing
* devs. For this branch to be executed, bfqq must not be
@@ -2822,9 +2835,6 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
if (bfq_too_late_for_merging(bfqq))
return NULL;
- if (bfqq->new_bfqq)
- return bfqq->new_bfqq;
-
if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq))
return NULL;
--
2.20.1
> Il giorno 2 ago 2021, alle ore 16:13, Paolo Valente <[email protected]> ha scritto:
>
> The function bfq_setup_merge prepares the merging between two
> bfq_queues, say bfqq and new_bfqq. To this goal, it assigns
> bfqq->new_bfqq = new_bfqq. Then, each time some I/O for bfqq arrives,
> the process that generated that I/O is disassociated from bfqq and
> associated with new_bfqq (merging is actually a redirection). In this
> respect, bfq_setup_merge increases new_bfqq->ref in advance, adding
> the number of processes that are expected to be associated with
> new_bfqq.
>
> Unfortunately, the stable-merging mechanism interferes with this
> setup. After bfqq->new_bfqq has been set by bfq_setup_merge, and
> before all the expected processes have been associated with
> bfqq->new_bfqq, bfqq may happen to be stably merged with a different
> queue than the current bfqq->new_bfqq. In this case, bfqq->new_bfqq
> gets changed. So, some of the processes that have been already
> accounted for in the ref counter of the previous new_bfqq will not be
> associated with that queue. This creates an unbalance, because those
> references will never be decremented.
>
> This commit fixes this issue by reestablishing the previous, natural
> behaviour: once bfqq->new_bfqq has been set, it will not be changed
> until all expected redirections have occurred.
>
Hi Jens,
did you have time to look at this fix?
Thanks,
Paolo
> Signed-off-by: Davide Zini <[email protected]>
> Signed-off-by: Paolo Valente <[email protected]>
> ---
> block/bfq-iosched.c | 16 +++++++++++++---
> 1 file changed, 13 insertions(+), 3 deletions(-)
>
> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
> index 727955918563..08d9122dd4c0 100644
> --- a/block/bfq-iosched.c
> +++ b/block/bfq-iosched.c
> @@ -2659,6 +2659,15 @@ bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
> * are likely to increase the throughput.
> */
> bfqq->new_bfqq = new_bfqq;
> + /*
> + * The above assignment schedules the following redirections:
> + * each time some I/O for bfqq arrives, the process that
> + * generated that I/O is disassociated from bfqq and
> + * associated with new_bfqq. Here we increases new_bfqq->ref
> + * in advance, adding the number of processes that are
> + * expected to be associated with new_bfqq as they happen to
> + * issue I/O.
> + */
> new_bfqq->ref += process_refs;
> return new_bfqq;
> }
> @@ -2721,6 +2730,10 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
> {
> struct bfq_queue *in_service_bfqq, *new_bfqq;
>
> + /* if a merge has already been setup, then proceed with that first */
> + if (bfqq->new_bfqq)
> + return bfqq->new_bfqq;
> +
> /*
> * Check delayed stable merge for rotational or non-queueing
> * devs. For this branch to be executed, bfqq must not be
> @@ -2822,9 +2835,6 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
> if (bfq_too_late_for_merging(bfqq))
> return NULL;
>
> - if (bfqq->new_bfqq)
> - return bfqq->new_bfqq;
> -
> if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq))
> return NULL;
>
> --
> 2.20.1
>
> Il giorno 26 ago 2021, alle ore 11:16, Paolo Valente <[email protected]> ha scritto:
>
>
>
>> Il giorno 2 ago 2021, alle ore 16:13, Paolo Valente <[email protected]> ha scritto:
>>
>> The function bfq_setup_merge prepares the merging between two
>> bfq_queues, say bfqq and new_bfqq. To this goal, it assigns
>> bfqq->new_bfqq = new_bfqq. Then, each time some I/O for bfqq arrives,
>> the process that generated that I/O is disassociated from bfqq and
>> associated with new_bfqq (merging is actually a redirection). In this
>> respect, bfq_setup_merge increases new_bfqq->ref in advance, adding
>> the number of processes that are expected to be associated with
>> new_bfqq.
>>
>> Unfortunately, the stable-merging mechanism interferes with this
>> setup. After bfqq->new_bfqq has been set by bfq_setup_merge, and
>> before all the expected processes have been associated with
>> bfqq->new_bfqq, bfqq may happen to be stably merged with a different
>> queue than the current bfqq->new_bfqq. In this case, bfqq->new_bfqq
>> gets changed. So, some of the processes that have been already
>> accounted for in the ref counter of the previous new_bfqq will not be
>> associated with that queue. This creates an unbalance, because those
>> references will never be decremented.
>>
>> This commit fixes this issue by reestablishing the previous, natural
>> behaviour: once bfqq->new_bfqq has been set, it will not be changed
>> until all expected redirections have occurred.
>>
>
> Hi Jens,
> did you have time to look at this fix?
>
ping ...
> Thanks,
> Paolo
>
>
>> Signed-off-by: Davide Zini <[email protected]>
>> Signed-off-by: Paolo Valente <[email protected]>
>> ---
>> block/bfq-iosched.c | 16 +++++++++++++---
>> 1 file changed, 13 insertions(+), 3 deletions(-)
>>
>> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
>> index 727955918563..08d9122dd4c0 100644
>> --- a/block/bfq-iosched.c
>> +++ b/block/bfq-iosched.c
>> @@ -2659,6 +2659,15 @@ bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
>> * are likely to increase the throughput.
>> */
>> bfqq->new_bfqq = new_bfqq;
>> + /*
>> + * The above assignment schedules the following redirections:
>> + * each time some I/O for bfqq arrives, the process that
>> + * generated that I/O is disassociated from bfqq and
>> + * associated with new_bfqq. Here we increases new_bfqq->ref
>> + * in advance, adding the number of processes that are
>> + * expected to be associated with new_bfqq as they happen to
>> + * issue I/O.
>> + */
>> new_bfqq->ref += process_refs;
>> return new_bfqq;
>> }
>> @@ -2721,6 +2730,10 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
>> {
>> struct bfq_queue *in_service_bfqq, *new_bfqq;
>>
>> + /* if a merge has already been setup, then proceed with that first */
>> + if (bfqq->new_bfqq)
>> + return bfqq->new_bfqq;
>> +
>> /*
>> * Check delayed stable merge for rotational or non-queueing
>> * devs. For this branch to be executed, bfqq must not be
>> @@ -2822,9 +2835,6 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
>> if (bfq_too_late_for_merging(bfqq))
>> return NULL;
>>
>> - if (bfqq->new_bfqq)
>> - return bfqq->new_bfqq;
>> -
>> if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq))
>> return NULL;
>>
>> --
>> 2.20.1
On 8/2/21 8:13 AM, Paolo Valente wrote:
> The function bfq_setup_merge prepares the merging between two
> bfq_queues, say bfqq and new_bfqq. To this goal, it assigns
> bfqq->new_bfqq = new_bfqq. Then, each time some I/O for bfqq arrives,
> the process that generated that I/O is disassociated from bfqq and
> associated with new_bfqq (merging is actually a redirection). In this
> respect, bfq_setup_merge increases new_bfqq->ref in advance, adding
> the number of processes that are expected to be associated with
> new_bfqq.
>
> Unfortunately, the stable-merging mechanism interferes with this
> setup. After bfqq->new_bfqq has been set by bfq_setup_merge, and
> before all the expected processes have been associated with
> bfqq->new_bfqq, bfqq may happen to be stably merged with a different
> queue than the current bfqq->new_bfqq. In this case, bfqq->new_bfqq
> gets changed. So, some of the processes that have been already
> accounted for in the ref counter of the previous new_bfqq will not be
> associated with that queue. This creates an unbalance, because those
> references will never be decremented.
>
> This commit fixes this issue by reestablishing the previous, natural
> behaviour: once bfqq->new_bfqq has been set, it will not be changed
> until all expected redirections have occurred.
Applied, thanks.
--
Jens Axboe