From: Jan Kara <jack@suse.cz>
To: Kemeng Shi <shikemeng@huaweicloud.com>
Cc: paolo.valente@linaro.org, axboe@kernel.dk,
linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
jack@suse.cz, hch@lst.de, damien.lemoal@wdc.com
Subject: Re: [PATCH RESEND v2 01/10] block, bfq: correctly raise inject limit in bfq_choose_bfqq_for_injection
Date: Mon, 2 Jan 2023 16:13:29 +0100 [thread overview]
Message-ID: <20230102151329.xzjalwcphmupf4jm@quack3> (raw)
In-Reply-To: <20221222191641.1643117-2-shikemeng@huaweicloud.com>
On Fri 23-12-22 03:16:32, Kemeng Shi wrote:
> Function bfq_choose_bfqq_for_injection may temporarily raise inject limit
> to one request if current inject_limit is 0 before search of the source
> queue for injection. However the search below will reset inject limit to
> bfqd->in_service_queue which is zero for raised inject limit. Then the
> temporarily raised inject limit never works as expected.
> Assigment limit to bfqd->in_service_queue in search is needed as limit
> maybe overwriten to min_t(unsigned int, 1, limit) for condition that
> a large in-flight request is on non-rotational devices in found queue.
> So we need to reset limit to bfqd->in_service_queue for normal case.
>
> Actually, we have already make sure bfqd->rq_in_driver is < limit before
> search, then
> -Limit is >= 1 as bfqd->rq_in_driver is >= 0. Then min_t(unsigned int,
> 1, limit) is always 1. So we can simply check bfqd->rq_in_driver with
> 1 instead of result of min_t(unsigned int, 1, limit) for larget request in
> non-rotational device case to avoid overwritting limit and the bug is gone.
> -For normal case, we have already check bfqd->rq_in_driver is < limit,
> so we can return found bfqq unconditionally to remove unncessary check.
>
> Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
The fix looks good to me. Feel free to add:
Reviewed-by: Jan Kara <jack@suse.cz>
Honza
> ---
> block/bfq-iosched.c | 10 ++++------
> 1 file changed, 4 insertions(+), 6 deletions(-)
>
> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
> index a72304c728fc..1220c41fc767 100644
> --- a/block/bfq-iosched.c
> +++ b/block/bfq-iosched.c
> @@ -4641,12 +4641,10 @@ bfq_choose_bfqq_for_injection(struct bfq_data *bfqd)
> */
> if (blk_queue_nonrot(bfqd->queue) &&
> blk_rq_sectors(bfqq->next_rq) >=
> - BFQQ_SECT_THR_NONROT)
> - limit = min_t(unsigned int, 1, limit);
> - else
> - limit = in_serv_bfqq->inject_limit;
> -
> - if (bfqd->rq_in_driver < limit) {
> + BFQQ_SECT_THR_NONROT &&
> + bfqd->rq_in_driver >= 1)
> + continue;
> + else {
> bfqd->rqs_injected = true;
> return bfqq;
> }
> --
> 2.30.0
>
--
Jan Kara <jack@suse.com>
SUSE Labs, CR
next prev parent reply other threads:[~2023-01-02 15:14 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-12-22 19:16 [PATCH RESEND v2 00/10] A few bugfix and cleancode patch for bfq Kemeng Shi
2022-12-22 19:16 ` [PATCH RESEND v2 01/10] block, bfq: correctly raise inject limit in bfq_choose_bfqq_for_injection Kemeng Shi
2023-01-02 15:13 ` Jan Kara [this message]
2022-12-22 19:16 ` [PATCH RESEND v2 02/10] block, bfq: remove unsed parameter reason in bfq_bfqq_is_slow Kemeng Shi
2023-01-02 15:14 ` Jan Kara
2022-12-22 19:16 ` [PATCH RESEND v2 03/10] block, bfq: initialize bfqq->decrease_time_jif correctly Kemeng Shi
2023-01-02 15:30 ` Jan Kara
2022-12-22 19:16 ` [PATCH RESEND v2 04/10] block, bfq: use helper macro RQ_BFQQ to get bfqq of request Kemeng Shi
2023-01-02 15:31 ` Jan Kara
2022-12-22 19:16 ` [PATCH RESEND v2 05/10] block, bfq: remove unnecessary dereference to get async_bfqq Kemeng Shi
2023-01-02 15:34 ` Jan Kara
2022-12-22 19:16 ` [PATCH RESEND v2 06/10] block, bfq: remove redundant bfqd->rq_in_driver > 0 check in bfq_add_request Kemeng Shi
2023-01-02 15:54 ` Jan Kara
2022-12-22 19:16 ` [PATCH RESEND v2 07/10] block, bfq: remove redundant check in bfq_put_cooperator Kemeng Shi
2023-01-02 15:57 ` Jan Kara
2022-12-22 19:16 ` [PATCH RESEND v2 08/10] block, bfq: remove unnecessary goto tag in bfq_dispatch_rq_from_bfqq Kemeng Shi
2023-01-02 15:59 ` Jan Kara
2022-12-22 19:16 ` [PATCH RESEND v2 09/10] block, bfq: remove unused bfq_wr_max_time in struct bfq_data Kemeng Shi
2023-01-02 16:00 ` Jan Kara
2022-12-22 19:16 ` [PATCH RESEND v2 10/10] block, bfq: remove check of bfq_wr_max_softrt_rate which is always greater than 0 Kemeng Shi
2023-01-02 16:05 ` Jan Kara
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=20230102151329.xzjalwcphmupf4jm@quack3 \
--to=jack@suse.cz \
--cc=axboe@kernel.dk \
--cc=damien.lemoal@wdc.com \
--cc=hch@lst.de \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=paolo.valente@linaro.org \
--cc=shikemeng@huaweicloud.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