From: John Garry <john.garry@huawei.com>
To: <axboe@kernel.dk>, <jejb@linux.ibm.com>,
<martin.petersen@oracle.com>, <don.brace@microsemi.com>,
<kashyap.desai@broadcom.com>, <sumit.saxena@broadcom.com>,
<ming.lei@redhat.com>, <bvanassche@acm.org>, <hare@suse.com>,
<hch@lst.de>, <shivasharan.srikanteshwara@broadcom.com>
Cc: <linux-block@vger.kernel.org>, <linux-scsi@vger.kernel.org>,
<esc.storagedev@microsemi.com>, <chenxiang66@hisilicon.com>,
<megaraidlinux.pdl@broadcom.com>,
John Garry <john.garry@huawei.com>
Subject: [PATCH RFC v7 05/12] blk-mq: Record nr_active_requests per queue for when using shared sbitmap
Date: Thu, 11 Jun 2020 01:29:12 +0800 [thread overview]
Message-ID: <1591810159-240929-6-git-send-email-john.garry@huawei.com> (raw)
In-Reply-To: <1591810159-240929-1-git-send-email-john.garry@huawei.com>
The per-hctx nr_active value can no longer be used to fairly assign a share
of tag depth per request queue for when using a shared sbitmap, as it does
not consider that the tags are shared tags over all hctx's.
For this case, record the nr_active_requests per request_queue, and make
the judgment based on that value.
Also introduce a debugfs version of per-hctx blk_mq_debugfs_attr, omitting
hctx_active_show() (as blk_mq_hw_ctx.nr_active is no longer maintained for
the case of shared sbitmap) and other entries which we can add which would
be revised specifically for when using a shared sbitmap.
Co-developed-with: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
block/blk-core.c | 2 ++
block/blk-mq-debugfs.c | 23 ++++++++++++++++++++++-
block/blk-mq-tag.c | 10 ++++++----
block/blk-mq.c | 6 +++---
block/blk-mq.h | 28 +++++++++++++++++++++++++++-
include/linux/blkdev.h | 2 ++
6 files changed, 62 insertions(+), 9 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 03252af8c82c..c622453c1363 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -529,6 +529,8 @@ struct request_queue *__blk_alloc_queue(int node_id)
q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
q->node = node_id;
+ atomic_set(&q->nr_active_requests_shared_sbitmap, 0);
+
timer_setup(&q->backing_dev_info->laptop_mode_wb_timer,
laptop_mode_timer_fn, 0);
timer_setup(&q->timeout, blk_rq_timed_out_timer, 0);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index a400b6698dff..0fa3af41ab65 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -796,6 +796,23 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
{},
};
+static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_shared_sbitmap_attrs[] = {
+ {"state", 0400, hctx_state_show},
+ {"flags", 0400, hctx_flags_show},
+ {"dispatch", 0400, .seq_ops = &hctx_dispatch_seq_ops},
+ {"busy", 0400, hctx_busy_show},
+ {"ctx_map", 0400, hctx_ctx_map_show},
+ {"sched_tags", 0400, hctx_sched_tags_show},
+ {"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show},
+ {"io_poll", 0600, hctx_io_poll_show, hctx_io_poll_write},
+ {"dispatched", 0600, hctx_dispatched_show, hctx_dispatched_write},
+ {"queued", 0600, hctx_queued_show, hctx_queued_write},
+ {"run", 0600, hctx_run_show, hctx_run_write},
+ {"active", 0400, hctx_active_show},
+ {"dispatch_busy", 0400, hctx_dispatch_busy_show},
+ {}
+};
+
static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = {
{"default_rq_list", 0400, .seq_ops = &ctx_default_rq_list_seq_ops},
{"read_rq_list", 0400, .seq_ops = &ctx_read_rq_list_seq_ops},
@@ -878,13 +895,17 @@ void blk_mq_debugfs_register_hctx(struct request_queue *q,
struct blk_mq_hw_ctx *hctx)
{
struct blk_mq_ctx *ctx;
+ struct blk_mq_tag_set *set = q->tag_set;
char name[20];
int i;
snprintf(name, sizeof(name), "hctx%u", hctx->queue_num);
hctx->debugfs_dir = debugfs_create_dir(name, q->debugfs_dir);
- debugfs_create_files(hctx->debugfs_dir, hctx, blk_mq_debugfs_hctx_attrs);
+ if (blk_mq_is_sbitmap_shared(set))
+ debugfs_create_files(hctx->debugfs_dir, hctx, blk_mq_debugfs_hctx_shared_sbitmap_attrs);
+ else
+ debugfs_create_files(hctx->debugfs_dir, hctx, blk_mq_debugfs_hctx_attrs);
hctx_for_each_ctx(hctx, ctx, i)
blk_mq_debugfs_register_ctx(hctx, ctx);
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 92843e3e1a2a..7db16e49f6f6 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -60,9 +60,11 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
* For shared tag users, we track the number of currently active users
* and attempt to provide a fair share of the tag depth for each of them.
*/
-static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
+static inline bool hctx_may_queue(struct blk_mq_alloc_data *data,
struct sbitmap_queue *bt)
{
+ struct blk_mq_hw_ctx *hctx = data->hctx;
+ struct request_queue *q = data->q;
unsigned int depth, users;
if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
@@ -84,15 +86,15 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
* Allow at least some tags
*/
depth = max((bt->sb.depth + users - 1) / users, 4U);
- return atomic_read(&hctx->nr_active) < depth;
+ return __blk_mq_active_requests(hctx, q) < depth;
}
static int __blk_mq_get_tag(struct blk_mq_alloc_data *data,
struct sbitmap_queue *bt)
{
if (!(data->flags & BLK_MQ_REQ_INTERNAL) &&
- !hctx_may_queue(data->hctx, bt))
- return BLK_MQ_NO_TAG;
+ !hctx_may_queue(data, bt))
+ return -1;
if (data->shallow_depth)
return __sbitmap_queue_get_shallow(bt, data->shallow_depth);
else
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 77120dd4e4d5..0f7e062a1665 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -283,7 +283,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
} else {
if (data->hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) {
rq_flags = RQF_MQ_INFLIGHT;
- atomic_inc(&data->hctx->nr_active);
+ __blk_mq_inc_active_requests(data->hctx, data->q);
}
rq->tag = tag;
rq->internal_tag = BLK_MQ_NO_TAG;
@@ -527,7 +527,7 @@ void blk_mq_free_request(struct request *rq)
ctx->rq_completed[rq_is_sync(rq)]++;
if (rq->rq_flags & RQF_MQ_INFLIGHT)
- atomic_dec(&hctx->nr_active);
+ __blk_mq_dec_active_requests(hctx, q);
if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
laptop_io_completion(q->backing_dev_info);
@@ -1073,7 +1073,7 @@ bool blk_mq_get_driver_tag(struct request *rq)
if (rq->tag >= 0) {
if (shared) {
rq->rq_flags |= RQF_MQ_INFLIGHT;
- atomic_inc(&data.hctx->nr_active);
+ __blk_mq_inc_active_requests(rq->mq_hctx, rq->q);
}
data.hctx->tags->rqs[rq->tag] = rq;
}
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 1a283c707215..9c1e612c2298 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -202,6 +202,32 @@ static inline bool blk_mq_get_dispatch_budget(struct blk_mq_hw_ctx *hctx)
return true;
}
+static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx,
+ struct request_queue *q)
+{
+ if (blk_mq_is_sbitmap_shared(q->tag_set))
+ atomic_inc(&q->nr_active_requests_shared_sbitmap);
+ else
+ atomic_inc(&hctx->nr_active);
+}
+
+static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx,
+ struct request_queue *q)
+{
+ if (blk_mq_is_sbitmap_shared(q->tag_set))
+ atomic_dec(&q->nr_active_requests_shared_sbitmap);
+ else
+ atomic_dec(&hctx->nr_active);
+}
+
+static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx,
+ struct request_queue *q)
+{
+ if (blk_mq_is_sbitmap_shared(q->tag_set))
+ return atomic_read(&q->nr_active_requests_shared_sbitmap);
+ return atomic_read(&hctx->nr_active);
+}
+
static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
@@ -210,7 +236,7 @@ static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
if (rq->rq_flags & RQF_MQ_INFLIGHT) {
rq->rq_flags &= ~RQF_MQ_INFLIGHT;
- atomic_dec(&hctx->nr_active);
+ __blk_mq_dec_active_requests(hctx, rq->q);
}
}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8fd900998b4e..c536278bec9e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -488,6 +488,8 @@ struct request_queue {
struct timer_list timeout;
struct work_struct timeout_work;
+ atomic_t nr_active_requests_shared_sbitmap;
+
struct list_head icq_list;
#ifdef CONFIG_BLK_CGROUP
DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS);
--
2.26.2
next prev parent reply other threads:[~2020-06-10 17:33 UTC|newest]
Thread overview: 123+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-10 17:29 [PATCH RFC v7 00/12] blk-mq/scsi: Provide hostwide shared tags for SCSI HBAs John Garry
2020-06-10 17:29 ` [PATCH RFC v7 01/12] blk-mq: rename BLK_MQ_F_TAG_SHARED as BLK_MQ_F_TAG_QUEUE_SHARED John Garry
2020-06-10 17:29 ` [PATCH RFC v7 02/12] blk-mq: rename blk_mq_update_tag_set_depth() John Garry
2020-06-11 2:57 ` Ming Lei
2020-06-11 8:26 ` John Garry
2020-06-23 11:25 ` John Garry
2020-06-23 14:23 ` Hannes Reinecke
2020-06-24 8:13 ` Kashyap Desai
2020-06-29 16:18 ` John Garry
2020-08-10 16:51 ` Kashyap Desai
2020-08-11 8:01 ` John Garry
2020-08-11 16:34 ` Kashyap Desai
2020-06-10 17:29 ` [PATCH RFC v7 03/12] blk-mq: Use pointers for blk_mq_tags bitmap tags John Garry
2020-06-10 17:29 ` [PATCH RFC v7 04/12] blk-mq: Facilitate a shared sbitmap per tagset John Garry
2020-06-11 3:37 ` Ming Lei
2020-06-11 10:09 ` John Garry
2020-06-10 17:29 ` John Garry [this message]
2020-06-11 4:04 ` [PATCH RFC v7 05/12] blk-mq: Record nr_active_requests per queue for when using shared sbitmap Ming Lei
2020-06-11 10:22 ` John Garry
2020-06-10 17:29 ` [PATCH RFC v7 06/12] blk-mq: Record active_queues_shared_sbitmap per tag_set " John Garry
2020-06-11 13:16 ` Hannes Reinecke
2020-06-11 14:22 ` John Garry
2020-06-10 17:29 ` [PATCH RFC v7 07/12] blk-mq: Add support in hctx_tags_bitmap_show() for a " John Garry
2020-06-11 13:19 ` Hannes Reinecke
2020-06-11 14:33 ` John Garry
2020-06-12 6:06 ` Hannes Reinecke
2020-06-29 15:32 ` About sbitmap_bitmap_show() and cleared bits (was Re: [PATCH RFC v7 07/12] blk-mq: Add support in hctx_tags_bitmap_show() for a shared sbitmap) John Garry
2020-06-30 6:33 ` Hannes Reinecke
2020-06-30 7:30 ` John Garry
2020-06-30 11:36 ` John Garry
2020-06-30 14:55 ` Bart Van Assche
2020-07-13 9:41 ` [PATCH RFC v7 07/12] blk-mq: Add support in hctx_tags_bitmap_show() for a shared sbitmap John Garry
2020-07-13 12:20 ` Hannes Reinecke
2020-06-10 17:29 ` [PATCH RFC v7 08/12] scsi: Add template flag 'host_tagset' John Garry
2020-06-10 17:29 ` [PATCH RFC v7 09/12] scsi: hisi_sas: Switch v3 hw to MQ John Garry
2020-06-10 17:29 ` [PATCH RFC v7 10/12] megaraid_sas: switch fusion adapters " John Garry
2020-07-02 10:23 ` Kashyap Desai
2020-07-06 8:23 ` John Garry
2020-07-06 8:45 ` Hannes Reinecke
2020-07-06 9:26 ` John Garry
2020-07-06 9:40 ` Hannes Reinecke
2020-07-06 19:19 ` Kashyap Desai
2020-07-07 7:58 ` John Garry
2020-07-07 14:45 ` Kashyap Desai
2020-07-07 16:17 ` John Garry
2020-07-09 19:01 ` Kashyap Desai
2020-07-10 8:10 ` John Garry
2020-07-13 7:55 ` Kashyap Desai
2020-07-13 8:42 ` John Garry
2020-07-19 19:07 ` Kashyap Desai
2020-07-20 7:23 ` Kashyap Desai
2020-07-20 9:18 ` John Garry
2020-07-21 1:13 ` Ming Lei
2020-07-21 6:53 ` Kashyap Desai
2020-07-22 4:12 ` Ming Lei
2020-07-22 5:30 ` Kashyap Desai
2020-07-22 8:04 ` Ming Lei
2020-07-22 9:32 ` John Garry
2020-07-23 14:07 ` Ming Lei
2020-07-23 17:29 ` John Garry
2020-07-24 2:47 ` Ming Lei
2020-07-28 7:54 ` John Garry
2020-07-28 8:45 ` Ming Lei
2020-07-29 5:25 ` Kashyap Desai
2020-07-29 15:36 ` Ming Lei
2020-07-29 18:31 ` Kashyap Desai
2020-08-04 8:36 ` Ming Lei
2020-08-04 9:27 ` Kashyap Desai
2020-08-05 8:40 ` Ming Lei
2020-08-06 10:25 ` Kashyap Desai
2020-08-06 13:38 ` Ming Lei
2020-08-06 14:37 ` Kashyap Desai
2020-08-06 15:29 ` Ming Lei
2020-08-08 19:05 ` Kashyap Desai
2020-08-09 2:16 ` Ming Lei
2020-08-10 16:38 ` Kashyap Desai
2020-08-11 8:09 ` John Garry
2020-08-04 17:00 ` John Garry
2020-08-05 2:56 ` Ming Lei
2020-07-28 8:01 ` Kashyap Desai
2020-07-08 11:31 ` John Garry
2020-06-10 17:29 ` [PATCH RFC v7 11/12] smartpqi: enable host tagset John Garry
2020-07-14 13:16 ` John Garry
2020-07-14 13:31 ` John Garry
2020-07-14 18:16 ` Don.Brace
2020-07-15 7:28 ` John Garry
2020-07-14 14:02 ` Hannes Reinecke
2020-08-18 8:33 ` John Garry
2020-06-10 17:29 ` [PATCH RFC v7 12/12] hpsa: enable host_tagset and switch to MQ John Garry
2020-07-14 7:37 ` John Garry
2020-07-14 7:41 ` Hannes Reinecke
2020-07-14 7:52 ` John Garry
2020-07-14 8:06 ` Ming Lei
2020-07-14 9:53 ` John Garry
2020-07-14 10:14 ` Ming Lei
2020-07-14 10:43 ` Hannes Reinecke
2020-07-14 10:19 ` Hannes Reinecke
2020-07-14 10:35 ` John Garry
2020-07-14 10:44 ` Ming Lei
2020-07-14 10:52 ` John Garry
2020-07-14 12:04 ` Ming Lei
2020-08-03 20:39 ` Don.Brace
2020-08-04 9:27 ` John Garry
2020-08-04 15:18 ` Don.Brace
2020-08-05 11:21 ` John Garry
2020-08-14 21:04 ` Don.Brace
2020-08-17 8:00 ` John Garry
2020-08-17 18:39 ` Don.Brace
2020-08-18 7:14 ` Hannes Reinecke
2020-07-16 16:14 ` Don.Brace
2020-07-16 19:45 ` Don.Brace
2020-07-17 10:11 ` John Garry
2020-06-11 3:07 ` [PATCH RFC v7 00/12] blk-mq/scsi: Provide hostwide shared tags for SCSI HBAs Ming Lei
2020-06-11 9:35 ` John Garry
2020-06-12 18:47 ` Kashyap Desai
2020-06-15 2:13 ` Ming Lei
2020-06-15 6:57 ` Kashyap Desai
2020-06-16 1:00 ` Ming Lei
2020-06-17 11:26 ` Kashyap Desai
2020-06-22 6:24 ` Hannes Reinecke
2020-06-23 0:55 ` Ming Lei
2020-06-23 11:50 ` Kashyap Desai
2020-06-23 12:11 ` Kashyap Desai
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=1591810159-240929-6-git-send-email-john.garry@huawei.com \
--to=john.garry@huawei.com \
--cc=axboe@kernel.dk \
--cc=bvanassche@acm.org \
--cc=chenxiang66@hisilicon.com \
--cc=don.brace@microsemi.com \
--cc=esc.storagedev@microsemi.com \
--cc=hare@suse.com \
--cc=hch@lst.de \
--cc=jejb@linux.ibm.com \
--cc=kashyap.desai@broadcom.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=megaraidlinux.pdl@broadcom.com \
--cc=ming.lei@redhat.com \
--cc=shivasharan.srikanteshwara@broadcom.com \
--cc=sumit.saxena@broadcom.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).