From: Omar Sandoval <osandov@osandov.com>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, linux-nvme@lists.infradead.org
Subject: Re: [PATCH 2/8] block: improve logic around when to sort a plug list
Date: Tue, 27 Nov 2018 16:05:01 -0800 [thread overview]
Message-ID: <20181128000501.GH846@vader> (raw)
In-Reply-To: <62f96268-f596-78b8-d227-6be1f5ae1cea@kernel.dk>
On Tue, Nov 27, 2018 at 04:59:14PM -0700, Jens Axboe wrote:
> On 11/27/18 4:49 PM, Jens Axboe wrote:
> > On 11/27/18 4:31 PM, Omar Sandoval wrote:
> >> On Mon, Nov 26, 2018 at 09:35:50AM -0700, Jens Axboe wrote:
> >>> Do it for the nr_hw_queues == 1 case, but only do it for the multi queue
> >>> case if we have requests for multiple devices in the plug.
> >>>
> >>> Signed-off-by: Jens Axboe <axboe@kernel.dk>
> >>> ---
> >>> block/blk-core.c | 1 +
> >>> block/blk-mq.c | 7 +++++--
> >>> include/linux/blkdev.h | 1 +
> >>> 3 files changed, 7 insertions(+), 2 deletions(-)
> >>>
> >>> diff --git a/block/blk-core.c b/block/blk-core.c
> >>> index be9233400314..c9758d185357 100644
> >>> --- a/block/blk-core.c
> >>> +++ b/block/blk-core.c
> >>> @@ -1780,6 +1780,7 @@ void blk_start_plug(struct blk_plug *plug)
> >>> INIT_LIST_HEAD(&plug->mq_list);
> >>> INIT_LIST_HEAD(&plug->cb_list);
> >>> plug->rq_count = 0;
> >>> + plug->do_sort = false;
> >>>
> >>> /*
> >>> * Store ordering should not be needed here, since a potential
> >>> diff --git a/block/blk-mq.c b/block/blk-mq.c
> >>> index 99c66823d52f..6a249bf6ed00 100644
> >>> --- a/block/blk-mq.c
> >>> +++ b/block/blk-mq.c
> >>> @@ -1678,7 +1678,8 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
> >>> list_splice_init(&plug->mq_list, &list);
> >>> plug->rq_count = 0;
> >>>
> >>> - list_sort(NULL, &list, plug_rq_cmp);
> >>> + if (plug->do_sort)
> >>> + list_sort(NULL, &list, plug_rq_cmp);
> >>>
> >>> this_q = NULL;
> >>> this_hctx = NULL;
> >>> @@ -1935,6 +1936,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
> >>>
> >>> list_add_tail(&rq->queuelist, &plug->mq_list);
> >>> plug->rq_count++;
> >>> + plug->do_sort = true;
> >>> } else if (plug && !blk_queue_nomerges(q)) {
> >>> blk_mq_bio_to_request(rq, bio);
> >>>
> >>> @@ -1958,7 +1960,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
> >>> data.hctx = same_queue_rq->mq_hctx;
> >>> blk_mq_try_issue_directly(data.hctx, same_queue_rq,
> >>> &cookie);
> >>> - }
> >>> + } else if (plug->rq_count > 1)
> >>> + plug->do_sort = true;
> >>
> >> If plug->rq_count == 2, there's no benefit to sorting, either. The
> >> nr_hw_queues == 1 case could also avoid sorting in that case. So maybe
> >> this whole patch could just be replaced with:
> >
> > Heh yes, good point, it should be 3 at least. But if you look at the
> > later mq plug patch, we only sort for that one if we have multiple
> > queues. So the logic should be something ala:
> >
> > if (plug->rq_count > 2 && plug->has_multiple_queues)
> >
> > since that's the only case we want to sort for.
>
> How about something like this?
>
>
> diff --git a/block/blk-core.c b/block/blk-core.c
> index be9233400314..d107d016b92b 100644
> --- a/block/blk-core.c
> +++ b/block/blk-core.c
> @@ -1780,6 +1780,7 @@ void blk_start_plug(struct blk_plug *plug)
> INIT_LIST_HEAD(&plug->mq_list);
> INIT_LIST_HEAD(&plug->cb_list);
> plug->rq_count = 0;
> + plug->multiple_queues = false;
>
> /*
> * Store ordering should not be needed here, since a potential
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index 7b7dff85cf6c..02daa32c5d77 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -1677,7 +1677,8 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
> list_splice_init(&plug->mq_list, &list);
> plug->rq_count = 0;
>
> - list_sort(NULL, &list, plug_rq_cmp);
> + if (plug->rq_count > 2 && plug->multiple_queues)
> + list_sort(NULL, &list, plug_rq_cmp);
>
> this_q = NULL;
> this_hctx = NULL;
> @@ -1866,6 +1867,20 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
> }
> }
>
> +static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
> +{
> + list_add_tail(&rq->queuelist, &plug->mq_list);
> + plug->rq_count++;
> + if (!plug->multiple_queues && !list_is_singular(&plug->mq_list)) {
> + struct request *tmp;
> +
> + tmp = list_first_entry(&plug->mq_list, struct request,
> + queuelist);
> + if (tmp->q != rq->q)
> + plug->multiple_queues = true;
Actually, I thought we want to sort whenever there are different
software/hardware queues on the plug list, even if they're on the same
queue?
> + }
> +}
> +
> static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
> {
> const int is_sync = op_is_sync(bio->bi_opf);
> @@ -1932,8 +1947,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
> trace_block_plug(q);
> }
>
> - list_add_tail(&rq->queuelist, &plug->mq_list);
> - plug->rq_count++;
> + blk_add_rq_to_plug(plug, rq);
> } else if (plug && !blk_queue_nomerges(q)) {
> blk_mq_bio_to_request(rq, bio);
>
> @@ -1948,8 +1962,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
> same_queue_rq = NULL;
> if (same_queue_rq)
> list_del_init(&same_queue_rq->queuelist);
> - list_add_tail(&rq->queuelist, &plug->mq_list);
> - plug->rq_count++;
> + blk_add_rq_to_plug(plug, rq);
>
> blk_mq_put_ctx(data.ctx);
>
> diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
> index 02732cae6080..08d940f85fa0 100644
> --- a/include/linux/blkdev.h
> +++ b/include/linux/blkdev.h
> @@ -1131,6 +1131,7 @@ struct blk_plug {
> struct list_head mq_list; /* blk-mq requests */
> struct list_head cb_list; /* md requires an unplug callback */
> unsigned short rq_count;
> + bool multiple_queues;
> };
> #define BLK_MAX_REQUEST_COUNT 16
> #define BLK_PLUG_FLUSH_SIZE (128 * 1024)
next prev parent reply other threads:[~2018-11-28 0:05 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-26 16:35 [PATCHSET 0/8] block plugging improvements Jens Axboe
2018-11-26 16:35 ` [PATCH 1/8] block: sum requests in the plug structure Jens Axboe
2018-11-26 17:02 ` Christoph Hellwig
2018-11-26 16:35 ` [PATCH 2/8] block: improve logic around when to sort a plug list Jens Axboe
2018-11-27 23:31 ` Omar Sandoval
2018-11-27 23:49 ` Jens Axboe
2018-11-27 23:55 ` Omar Sandoval
2018-11-27 23:59 ` Jens Axboe
2018-11-28 0:05 ` Omar Sandoval [this message]
2018-11-28 0:16 ` Jens Axboe
2018-11-26 16:35 ` [PATCH 3/8] blk-mq: add mq_ops->commit_rqs() Jens Axboe
2018-11-27 23:43 ` Omar Sandoval
2018-11-28 1:38 ` Ming Lei
2018-11-28 7:16 ` Christoph Hellwig
2018-11-28 12:54 ` Jens Axboe
2018-11-26 16:35 ` [PATCH 4/8] nvme: implement mq_ops->commit_rqs() hook Jens Axboe
2018-11-28 7:20 ` Christoph Hellwig
2018-11-28 13:07 ` Jens Axboe
2018-11-26 16:35 ` [PATCH 5/8] virtio_blk: " Jens Axboe
2018-11-27 23:45 ` Omar Sandoval
2018-11-28 3:05 ` Michael S. Tsirkin
2018-11-28 2:10 ` Ming Lei
2018-11-28 2:34 ` Jens Axboe
2018-11-29 1:23 ` Ming Lei
2018-11-29 2:19 ` Jens Axboe
2018-11-29 2:51 ` Ming Lei
2018-11-29 3:13 ` Jens Axboe
2018-11-29 3:27 ` Ming Lei
2018-11-29 3:53 ` Jens Axboe
2018-11-28 7:21 ` Christoph Hellwig
2018-11-26 16:35 ` [PATCH 6/8] ataflop: " Jens Axboe
2018-11-27 23:46 ` Omar Sandoval
2018-11-28 7:22 ` Christoph Hellwig
2018-11-28 13:09 ` Jens Axboe
2018-11-26 16:35 ` [PATCH 7/8] blk-mq: use bd->last == true for list inserts Jens Axboe
2018-11-27 23:49 ` Omar Sandoval
2018-11-27 23:51 ` Jens Axboe
2018-11-28 1:49 ` Ming Lei
2018-11-28 2:37 ` Jens Axboe
2018-11-26 16:35 ` [PATCH 8/8] blk-mq: add plug case for devices that implement ->commits_rqs() Jens Axboe
2018-11-28 7:26 ` Christoph Hellwig
2018-11-28 13:11 ` Jens Axboe
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=20181128000501.GH846@vader \
--to=osandov@osandov.com \
--cc=axboe@kernel.dk \
--cc=linux-block@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
/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