linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Damien Le Moal <damien.lemoal@opensource.wdc.com>
To: Paolo Valente <paolo.valente@linaro.org>, Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
	arie.vanderhoeven@seagate.com, rory.c.chen@seagate.com
Subject: Re: [PATCH V6 2/8] block, bfq: forbid stable merging of queues associated with different actuators
Date: Mon, 21 Nov 2022 09:20:03 +0900	[thread overview]
Message-ID: <f23d1a4a-cdf9-3ab3-d2ec-fe55f5d06915@opensource.wdc.com> (raw)
In-Reply-To: <20221103162623.10286-3-paolo.valente@linaro.org>

On 11/4/22 01:26, Paolo Valente wrote:
> If queues associated with different actuators are merged, then control
> is lost on each actuator. Therefore some actuator may be
> underutilized, and throughput may decrease. This problem cannot occur
> with basic queue merging, because the latter is triggered by spatial
> locality, and sectors for different actuators are not close to each
> other. Yet it may happen with stable merging. To address this issue,
> this commit prevents stable merging from occurring among queues
> associated with different actuators.
> 
> Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
> ---
>  block/bfq-iosched.c | 13 +++++++++----
>  1 file changed, 9 insertions(+), 4 deletions(-)
> 
> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
> index 5c69394bbb65..ec4b0e70265f 100644
> --- a/block/bfq-iosched.c
> +++ b/block/bfq-iosched.c
> @@ -5705,9 +5705,13 @@ static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd,
>  	 * it has been set already, but too long ago, then move it
>  	 * forward to bfqq. Finally, move also if bfqq belongs to a
>  	 * different group than last_bfqq_created, or if bfqq has a
> -	 * different ioprio or ioprio_class. If none of these
> -	 * conditions holds true, then try an early stable merge or
> -	 * schedule a delayed stable merge.
> +	 * different ioprio, ioprio_class or actuator_idx. If none of
> +	 * these conditions holds true, then try an early stable merge
> +	 * or schedule a delayed stable merge. As for the condition on
> +	 * actuator_idx, the reason is that, if queues associated with
> +	 * different actuators are merged, then control is lost on
> +	 * each actuator. Therefore some actuator may be
> +	 * underutilized, and throughput may decrease.
>  	 *
>  	 * A delayed merge is scheduled (instead of performing an
>  	 * early merge), in case bfqq might soon prove to be more
> @@ -5725,7 +5729,8 @@ static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd,
>  			bfqq->creation_time) ||
>  		bfqq->entity.parent != last_bfqq_created->entity.parent ||
>  		bfqq->ioprio != last_bfqq_created->ioprio ||
> -		bfqq->ioprio_class != last_bfqq_created->ioprio_class)
> +		bfqq->ioprio_class != last_bfqq_created->ioprio_class ||
> +		bfqq->actuator_idx != last_bfqq_created->actuator_idx)
>  		*source_bfqq = bfqq;
>  	else if (time_after_eq(last_bfqq_created->creation_time +
>  				 bfqd->bfq_burst_interval,

Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>

-- 
Damien Le Moal
Western Digital Research


  reply	other threads:[~2022-11-21  0:20 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-03 16:26 [PATCH V6 0/8] block, bfq: extend bfq to support multi-actuator drives Paolo Valente
2022-11-03 16:26 ` [PATCH V6 1/8] block, bfq: split sync bfq_queues on a per-actuator basis Paolo Valente
2022-11-21  0:18   ` Damien Le Moal
2022-11-26 16:28     ` Paolo Valente
2022-11-28 14:32       ` Jens Axboe
2022-12-06  8:04     ` Paolo Valente
2022-11-03 16:26 ` [PATCH V6 2/8] block, bfq: forbid stable merging of queues associated with different actuators Paolo Valente
2022-11-21  0:20   ` Damien Le Moal [this message]
2022-11-03 16:26 ` [PATCH V6 3/8] block, bfq: move io_cq-persistent bfqq data into a dedicated struct Paolo Valente
2022-11-21  0:24   ` Damien Le Moal
2022-11-03 16:26 ` [PATCH V6 4/8] block, bfq: turn bfqq_data into an array in bfq_io_cq Paolo Valente
2022-11-21  0:39   ` Damien Le Moal
2022-12-06  8:00     ` Paolo Valente
2022-11-03 16:26 ` [PATCH V6 5/8] block, bfq: split also async bfq_queues on a per-actuator basis Paolo Valente
2022-11-21  0:52   ` Damien Le Moal
2022-11-03 16:26 ` [PATCH V6 6/8] block, bfq: retrieve independent access ranges from request queue Paolo Valente
2022-11-21  1:01   ` Damien Le Moal
2022-12-06  8:06     ` Paolo Valente
2022-12-06  8:29       ` Damien Le Moal
2022-12-06  8:41         ` Paolo Valente
2022-12-06  9:02           ` Damien Le Moal
2022-12-06 15:43             ` Paolo Valente
2022-12-06 23:34               ` Damien Le Moal
2022-12-08 10:43                 ` Paolo Valente
2022-11-03 16:26 ` [PATCH V6 7/8] block, bfq: inject I/O to underutilized actuators Paolo Valente
2022-11-21  1:17   ` Damien Le Moal
2022-11-03 16:26 ` [PATCH V6 8/8] block, bfq: balance I/O injection among " Paolo Valente
2022-11-10 15:25   ` Arie van der Hoeven
2022-11-20  7:29     ` Paolo Valente
2022-11-20 22:06       ` Jens Axboe
2022-11-20 23:41         ` Damien Le Moal

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=f23d1a4a-cdf9-3ab3-d2ec-fe55f5d06915@opensource.wdc.com \
    --to=damien.lemoal@opensource.wdc.com \
    --cc=arie.vanderhoeven@seagate.com \
    --cc=axboe@kernel.dk \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=paolo.valente@linaro.org \
    --cc=rory.c.chen@seagate.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).