Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1250842 > unrolled thread

Re: [PATCH v1 4/6] block: check bio_mergeable() early before merging

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  Re: [PATCH v1 4/6] block: check bio_mergeable() early before merging Jeff Moyer <jmoyer@redhat.com> - 2015-10-19 17:30 +0200
    Re: [PATCH v1 4/6] block: check bio_mergeable() early before merging Ming Lei <ming.lei@canonical.com> - 2015-10-19 17:40 +0200
      Re: [PATCH v1 4/6] block: check bio_mergeable() early before merging Jeff Moyer <jmoyer@redhat.com> - 2015-10-19 17:50 +0200

#1250842 — Re: [PATCH v1 4/6] block: check bio_mergeable() early before merging

Ming Lei <ming.lei@canonical.com> writes:

> After bio splitting is introduced, one bio can be splitted
> and it is marked as NOMERGE because it is too fat to be merged,
> so check bio_mergeable() earlier to avoid to try to merge it
> unnecessarily.
>
> Signed-off-by: Ming Lei <ming.lei@canonical.com>

Reviewed-by: Jeff Moyer <jmoyer@redhat.com>

Ming, do you think we should also add a check in blk_attempt_plug_merge?

-Jeff

> ---
>  block/elevator.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/block/elevator.c b/block/elevator.c
> index 84d6394..c3555c9 100644
> --- a/block/elevator.c
> +++ b/block/elevator.c
> @@ -420,7 +420,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
>  	 * 	noxmerges: Only simple one-hit cache try
>  	 * 	merges:	   All merge tries attempted
>  	 */
> -	if (blk_queue_nomerges(q))
> +	if (blk_queue_nomerges(q) || !bio_mergeable(bio))
>  		return ELEVATOR_NO_MERGE;
>  
>  	/*
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [next] | [standalone]

#1250855

On Mon, Oct 19, 2015 at 11:27 PM, Jeff Moyer <jmoyer@redhat.com> wrote:
> Ming Lei <ming.lei@canonical.com> writes:
>
>> After bio splitting is introduced, one bio can be splitted
>> and it is marked as NOMERGE because it is too fat to be merged,
>> so check bio_mergeable() earlier to avoid to try to merge it
>> unnecessarily.
>>
>> Signed-off-by: Ming Lei <ming.lei@canonical.com>
>
> Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
>
> Ming, do you think we should also add a check in blk_attempt_plug_merge?

No, because 'request_count' need to be figured out for automatic flush plug.

Thanks,

>
> -Jeff
>
>> ---
>>  block/elevator.c | 2 +-
>>  1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/block/elevator.c b/block/elevator.c
>> index 84d6394..c3555c9 100644
>> --- a/block/elevator.c
>> +++ b/block/elevator.c
>> @@ -420,7 +420,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
>>        *      noxmerges: Only simple one-hit cache try
>>        *      merges:    All merge tries attempted
>>        */
>> -     if (blk_queue_nomerges(q))
>> +     if (blk_queue_nomerges(q) || !bio_mergeable(bio))
>>               return ELEVATOR_NO_MERGE;
>>
>>       /*
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1250859

Ming Lei <ming.lei@canonical.com> writes:

> On Mon, Oct 19, 2015 at 11:27 PM, Jeff Moyer <jmoyer@redhat.com> wrote:
>> Ming Lei <ming.lei@canonical.com> writes:
>>
>>> After bio splitting is introduced, one bio can be splitted
>>> and it is marked as NOMERGE because it is too fat to be merged,
>>> so check bio_mergeable() earlier to avoid to try to merge it
>>> unnecessarily.
>>>
>>> Signed-off-by: Ming Lei <ming.lei@canonical.com>
>>
>> Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
>>
>> Ming, do you think we should also add a check in blk_attempt_plug_merge?
>
> No, because 'request_count' need to be figured out for automatic flush plug.

Interesting.  See my follow-up to patch 5.  :)

-Jeff

>
> Thanks,
>
>>
>> -Jeff
>>
>>> ---
>>>  block/elevator.c | 2 +-
>>>  1 file changed, 1 insertion(+), 1 deletion(-)
>>>
>>> diff --git a/block/elevator.c b/block/elevator.c
>>> index 84d6394..c3555c9 100644
>>> --- a/block/elevator.c
>>> +++ b/block/elevator.c
>>> @@ -420,7 +420,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
>>>        *      noxmerges: Only simple one-hit cache try
>>>        *      merges:    All merge tries attempted
>>>        */
>>> -     if (blk_queue_nomerges(q))
>>> +     if (blk_queue_nomerges(q) || !bio_mergeable(bio))
>>>               return ELEVATOR_NO_MERGE;
>>>
>>>       /*
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
>> the body of a message to majordomo@vger.kernel.org
>> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>> Please read the FAQ at  http://www.tux.org/lkml/
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web