From: Yu Kuai <yukuai1@huaweicloud.com>
To: Bart Van Assche <bvanassche@acm.org>, Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, linux-scsi@vger.kernel.org,
"Martin K . Petersen" <martin.petersen@oracle.com>,
Christoph Hellwig <hch@lst.de>, Ming Lei <ming.lei@redhat.com>,
Keith Busch <kbusch@kernel.org>,
Damien Le Moal <damien.lemoal@opensource.wdc.com>,
Yu Kuai <yukuai1@huaweicloud.com>, Ed Tsai <ed.tsai@mediatek.com>,
Matthias Brugger <matthias.bgg@gmail.com>,
AngeloGioacchino Del Regno
<angelogioacchino.delregno@collabora.com>,
"yukuai (C)" <yukuai3@huawei.com>
Subject: Re: [PATCH v6 1/4] block: Make fair tag sharing configurable
Date: Sat, 2 Dec 2023 15:21:01 +0800 [thread overview]
Message-ID: <58f50403-fcc9-ec11-f52b-f11ced3d2652@huaweicloud.com> (raw)
In-Reply-To: <20231130193139.880955-2-bvanassche@acm.org>
Hi,
在 2023/12/01 3:31, Bart Van Assche 写道:
> The fair sharing algorithm has a negative performance impact for storage
> devices for which the full queue depth is required to reach peak
> performance, e.g. UFS devices. This is because it takes long after a
> request queue became inactive until tags are reassigned to the active
> request queue(s). Since making tag sharing fair is not needed if the
> request processing latency is similar for all request queues, introduce
> a function for configuring fair tag sharing. Increase
> BLK_MQ_F_ALLOC_POLICY_START_BIT to prevent that the fair tag sharing
> flag overlaps with the tag allocation policy.
>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Martin K. Petersen <martin.petersen@oracle.com>
> Cc: Ming Lei <ming.lei@redhat.com>
> Cc: Keith Busch <kbusch@kernel.org>
> Cc: Damien Le Moal <damien.lemoal@opensource.wdc.com>
> Cc: Yu Kuai <yukuai1@huaweicloud.com>
> Cc: Ed Tsai <ed.tsai@mediatek.com>
> Signed-off-by: Bart Van Assche <bvanassche@acm.org>
> ---
> block/blk-mq-debugfs.c | 1 +
> block/blk-mq.c | 28 ++++++++++++++++++++++++++++
> block/blk-mq.h | 3 ++-
> include/linux/blk-mq.h | 6 ++++--
> 4 files changed, 35 insertions(+), 3 deletions(-)
>
> diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
> index 5cbeb9344f2f..f41408103106 100644
> --- a/block/blk-mq-debugfs.c
> +++ b/block/blk-mq-debugfs.c
> @@ -198,6 +198,7 @@ static const char *const hctx_flag_name[] = {
> HCTX_FLAG_NAME(NO_SCHED),
> HCTX_FLAG_NAME(STACKING),
> HCTX_FLAG_NAME(TAG_HCTX_SHARED),
> + HCTX_FLAG_NAME(DISABLE_FAIR_TAG_SHARING),
> };
> #undef HCTX_FLAG_NAME
>
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index b8093155df8d..206295606cec 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -4569,6 +4569,34 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
> }
> EXPORT_SYMBOL(blk_mq_free_tag_set);
>
> +/*
> + * Enable or disable fair tag sharing for all request queues associated with
> + * a tag set.
> + */
> +void blk_mq_update_fair_sharing(struct blk_mq_tag_set *set, bool enable)
> +{
> + const unsigned int DFTS_BIT = ilog2(BLK_MQ_F_DISABLE_FAIR_TAG_SHARING);
> + struct blk_mq_hw_ctx *hctx;
> + struct request_queue *q;
> + unsigned long i;
> +
> + /*
> + * Serialize against blk_mq_update_nr_hw_queues() and
> + * blk_mq_realloc_hw_ctxs().
> + */
> + mutex_lock(&set->tag_list_lock);
I'm a litter confused about this comment, because
blk_mq_realloc_hw_ctxs() can be called from
blk_mq_update_nr_hw_queues().
If you are talking about blk_mq_init_allocated_queue(), it looks like
just holding this lock is not enough?
> + list_for_each_entry(q, &set->tag_list, tag_set_list)
> + blk_mq_freeze_queue(q);
> + assign_bit(DFTS_BIT, &set->flags, !enable);
> + list_for_each_entry(q, &set->tag_list, tag_set_list)
> + queue_for_each_hw_ctx(q, hctx, i)
> + assign_bit(DFTS_BIT, &hctx->flags, !enable);
> + list_for_each_entry(q, &set->tag_list, tag_set_list)
> + blk_mq_unfreeze_queue(q);
> + mutex_unlock(&set->tag_list_lock);
> +}
> +EXPORT_SYMBOL(blk_mq_update_fair_sharing);
> +
> int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
> {
> struct blk_mq_tag_set *set = q->tag_set;
> diff --git a/block/blk-mq.h b/block/blk-mq.h
> index f75a9ecfebde..eda6bd0611ea 100644
> --- a/block/blk-mq.h
> +++ b/block/blk-mq.h
> @@ -416,7 +416,8 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
> {
> unsigned int depth, users;
>
> - if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
> + if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) ||
> + (hctx->flags & BLK_MQ_F_DISABLE_FAIR_TAG_SHARING))
> return true;
>
> /*
> diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
> index 1ab3081c82ed..ddda190b5c24 100644
> --- a/include/linux/blk-mq.h
> +++ b/include/linux/blk-mq.h
> @@ -503,7 +503,7 @@ struct blk_mq_tag_set {
> unsigned int cmd_size;
> int numa_node;
> unsigned int timeout;
> - unsigned int flags;
> + unsigned long flags;
> void *driver_data;
>
> struct blk_mq_tags **tags;
> @@ -662,7 +662,8 @@ enum {
> * or shared hwqs instead of 'mq-deadline'.
> */
> BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 7,
> - BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
> + BLK_MQ_F_DISABLE_FAIR_TAG_SHARING = 1 << 8,
> + BLK_MQ_F_ALLOC_POLICY_START_BIT = 16,
> BLK_MQ_F_ALLOC_POLICY_BITS = 1,
>
> BLK_MQ_S_STOPPED = 0,
> @@ -705,6 +706,7 @@ int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set,
> const struct blk_mq_ops *ops, unsigned int queue_depth,
> unsigned int set_flags);
> void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
> +void blk_mq_update_fair_sharing(struct blk_mq_tag_set *set, bool enable);
>
> void blk_mq_free_request(struct request *rq);
> int blk_rq_poll(struct request *rq, struct io_comp_batch *iob,
>
> .
>
next prev parent reply other threads:[~2023-12-02 7:21 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-30 19:31 [PATCH v6 0/6] Disable fair tag sharing for UFS devices Bart Van Assche
2023-11-30 19:31 ` [PATCH v6 1/4] block: Make fair tag sharing configurable Bart Van Assche
2023-12-01 12:52 ` Johannes Thumshirn
2023-12-01 22:14 ` Bart Van Assche
2023-12-02 7:21 ` Yu Kuai [this message]
2023-12-04 4:13 ` Bart Van Assche
2023-12-25 12:51 ` Yu Kuai
2023-12-26 2:22 ` Bart Van Assche
2024-01-11 19:22 ` Bart Van Assche
2024-01-12 1:08 ` Yu Kuai
2024-01-12 4:39 ` Christoph Hellwig
2024-01-14 3:22 ` Yu Kuai
2024-01-15 5:59 ` Christoph Hellwig
2024-01-15 6:18 ` Yu Kuai
2024-01-16 2:59 ` Bart Van Assche
2024-01-16 10:24 ` Yu Kuai
2024-01-16 17:36 ` Bart Van Assche
2024-01-18 7:31 ` Christoph Hellwig
2024-01-18 18:40 ` Bart Van Assche
2024-01-23 9:13 ` Christoph Hellwig
2024-01-23 15:16 ` Bart Van Assche
2024-01-24 9:08 ` Christoph Hellwig
2024-01-30 0:03 ` Bart Van Assche
2024-01-31 6:22 ` Christoph Hellwig
2024-01-31 21:32 ` Bart Van Assche
2024-01-31 21:37 ` Keith Busch
2024-01-31 21:42 ` Bart Van Assche
2024-01-31 23:04 ` Keith Busch
2024-01-31 23:41 ` Bart Van Assche
2024-01-31 23:52 ` Damien Le Moal
2024-01-16 2:52 ` Bart Van Assche
2023-11-30 19:31 ` [PATCH v6 2/4] scsi: core: Make fair tag sharing configurable in the host template Bart Van Assche
2023-11-30 19:31 ` [PATCH v6 3/4] scsi: core: Make fair tag sharing configurable via sysfs Bart Van Assche
2023-11-30 19:31 ` [PATCH v6 4/4] scsi: ufs: Disable fair tag sharing Bart Van Assche
2023-12-04 7:52 ` [PATCH v6 0/6] Disable fair tag sharing for UFS devices Christoph Hellwig
2023-12-05 3:15 ` Bart Van Assche
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=58f50403-fcc9-ec11-f52b-f11ced3d2652@huaweicloud.com \
--to=yukuai1@huaweicloud.com \
--cc=angelogioacchino.delregno@collabora.com \
--cc=axboe@kernel.dk \
--cc=bvanassche@acm.org \
--cc=damien.lemoal@opensource.wdc.com \
--cc=ed.tsai@mediatek.com \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=matthias.bgg@gmail.com \
--cc=ming.lei@redhat.com \
--cc=yukuai3@huawei.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).