public inbox for linux-block@vger.kernel.org
 help / color / mirror / Atom feed
From: Bart Van Assche <bvanassche@acm.org>
To: "Martin K . Petersen" <martin.petersen@oracle.com>
Cc: linux-scsi@vger.kernel.org, linux-block@vger.kernel.org,
	Bart Van Assche <bvanassche@acm.org>,
	Jens Axboe <axboe@kernel.dk>,
	Christoph Hellwig <hch@infradead.org>,
	Ming Lei <ming.lei@redhat.com>,
	John Garry <john.g.garry@oracle.com>,
	"James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Subject: [PATCH 3/3] scsi: core: Improve IOPS in case of host-wide tags
Date: Wed, 10 Sep 2025 14:32:51 -0700	[thread overview]
Message-ID: <20250910213254.1215318-4-bvanassche@acm.org> (raw)
In-Reply-To: <20250910213254.1215318-1-bvanassche@acm.org>

The SCSI core uses the budget map to enforce the cmd_per_lun limit.
That limit cannot be exceeded if host->cmd_per_lun >= host->can_queue
and if the host tag set is shared across all hardware queues.
Since scsi_mq_get_budget() shows up in all CPU profiles for fast SCSI
devices, do not allocate a budget map if cmd_per_lun >= can_queue and
if the host tag set is shared across all hardware queues.

On my UFS 4 test setup this patch improves IOPS by 1% and reduces the
time spent in scsi_mq_get_budget() from 0.22% to 0.01%.

Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: John Garry <john.g.garry@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
---
 drivers/scsi/scsi.c        |  7 ++++-
 drivers/scsi/scsi_lib.c    | 60 +++++++++++++++++++++++++++++++++-----
 drivers/scsi/scsi_scan.c   | 11 ++++++-
 include/scsi/scsi_device.h |  5 +---
 4 files changed, 70 insertions(+), 13 deletions(-)

diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 9a0f467264b3..06066b694d8a 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -216,6 +216,8 @@ int scsi_device_max_queue_depth(struct scsi_device *sdev)
  */
 int scsi_change_queue_depth(struct scsi_device *sdev, int depth)
 {
+	struct Scsi_Host *shost = sdev->host;
+
 	depth = min_t(int, depth, scsi_device_max_queue_depth(sdev));
 
 	if (depth > 0) {
@@ -226,7 +228,10 @@ int scsi_change_queue_depth(struct scsi_device *sdev, int depth)
 	if (sdev->request_queue)
 		blk_set_queue_depth(sdev->request_queue, depth);
 
-	sbitmap_resize(&sdev->budget_map, sdev->queue_depth);
+	if (shost->host_tagset && depth >= shost->can_queue)
+		sbitmap_free(&sdev->budget_map);
+	else
+		sbitmap_resize(&sdev->budget_map, sdev->queue_depth);
 
 	return sdev->queue_depth;
 }
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 0c65ecfedfbd..c546514d1049 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -396,7 +396,8 @@ void scsi_device_unbusy(struct scsi_device *sdev, struct scsi_cmnd *cmd)
 	if (starget->can_queue > 0)
 		atomic_dec(&starget->target_busy);
 
-	sbitmap_put(&sdev->budget_map, cmd->budget_token);
+	if (sdev->budget_map.map)
+		sbitmap_put(&sdev->budget_map, cmd->budget_token);
 	cmd->budget_token = -1;
 }
 
@@ -445,6 +446,47 @@ static void scsi_single_lun_run(struct scsi_device *current_sdev)
 	spin_unlock_irqrestore(shost->host_lock, flags);
 }
 
+struct sdev_in_flight_data {
+	const struct scsi_device *sdev;
+	int count;
+};
+
+static bool scsi_device_check_in_flight(struct request *rq, void *data)
+{
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+	struct sdev_in_flight_data *sifd = data;
+
+	if (cmd->device == sifd->sdev)
+		sifd->count++;
+
+	return true;
+}
+
+/**
+ * scsi_device_busy() - Number of commands allocated for a SCSI device
+ * @sdev: SCSI device.
+ *
+ * Note: There is a subtle difference between this function and
+ * scsi_host_busy(). scsi_host_busy() counts the number of commands that have
+ * been started. This function counts the number of commands that have been
+ * allocated. At least the UFS driver depends on this function counting commands
+ * that have already been allocated but that have not yet been started.
+ */
+int scsi_device_busy(const struct scsi_device *sdev)
+{
+	struct sdev_in_flight_data sifd = { .sdev = sdev };
+	struct blk_mq_tag_set *set = &sdev->host->tag_set;
+
+	if (sdev->budget_map.map)
+		return sbitmap_weight(&sdev->budget_map);
+	if (WARN_ON_ONCE(!set->shared_tags))
+		return 0;
+	blk_mq_all_tag_iter(set->shared_tags, scsi_device_check_in_flight,
+			    &sifd);
+	return sifd.count;
+}
+EXPORT_SYMBOL(scsi_device_busy);
+
 static inline bool scsi_device_is_busy(struct scsi_device *sdev)
 {
 	if (scsi_device_busy(sdev) >= sdev->queue_depth)
@@ -1358,11 +1400,13 @@ scsi_device_state_check(struct scsi_device *sdev, struct request *req)
 static inline int scsi_dev_queue_ready(struct request_queue *q,
 				  struct scsi_device *sdev)
 {
-	int token;
+	int token = INT_MAX;
 
-	token = sbitmap_get(&sdev->budget_map);
-	if (token < 0)
-		return -1;
+	if (sdev->budget_map.map) {
+		token = sbitmap_get(&sdev->budget_map);
+		if (token < 0)
+			return -1;
+	}
 
 	if (!atomic_read(&sdev->device_blocked))
 		return token;
@@ -1373,7 +1417,8 @@ static inline int scsi_dev_queue_ready(struct request_queue *q,
 	 */
 	if (scsi_device_busy(sdev) > 1 ||
 	    atomic_dec_return(&sdev->device_blocked) > 0) {
-		sbitmap_put(&sdev->budget_map, token);
+		if (sdev->budget_map.map)
+			sbitmap_put(&sdev->budget_map, token);
 		return -1;
 	}
 
@@ -1749,7 +1794,8 @@ static void scsi_mq_put_budget(struct request_queue *q, int budget_token)
 {
 	struct scsi_device *sdev = q->queuedata;
 
-	sbitmap_put(&sdev->budget_map, budget_token);
+	if (sdev->budget_map.map)
+		sbitmap_put(&sdev->budget_map, budget_token);
 }
 
 /*
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 3c6e089e80c3..6f2d0bf0e3ec 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -218,6 +218,7 @@ static void scsi_unlock_floptical(struct scsi_device *sdev,
 static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev,
 					unsigned int depth)
 {
+	struct Scsi_Host *shost = sdev->host;
 	int new_shift = sbitmap_calculate_shift(depth);
 	bool need_alloc = !sdev->budget_map.map;
 	bool need_free = false;
@@ -225,6 +226,13 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev,
 	int ret;
 	struct sbitmap sb_backup;
 
+	if (shost->host_tagset && depth >= shost->can_queue) {
+		memflags = blk_mq_freeze_queue(sdev->request_queue);
+		sbitmap_free(&sb_backup);
+		blk_mq_unfreeze_queue(sdev->request_queue, memflags);
+		return 0;
+	}
+
 	depth = min_t(unsigned int, depth, scsi_device_max_queue_depth(sdev));
 
 	/*
@@ -1112,7 +1120,8 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,
 	scsi_cdl_check(sdev);
 
 	sdev->max_queue_depth = sdev->queue_depth;
-	WARN_ON_ONCE(sdev->max_queue_depth > sdev->budget_map.depth);
+	WARN_ON_ONCE(sdev->budget_map.map &&
+		     sdev->max_queue_depth > sdev->budget_map.depth);
 	sdev->sdev_bflags = *bflags;
 
 	/*
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 6d6500148c4b..3c7a95fa9b67 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -687,10 +687,7 @@ static inline int scsi_device_supports_vpd(struct scsi_device *sdev)
 	return 0;
 }
 
-static inline int scsi_device_busy(struct scsi_device *sdev)
-{
-	return sbitmap_weight(&sdev->budget_map);
-}
+int scsi_device_busy(const struct scsi_device *sdev);
 
 /* Macros to access the UNIT ATTENTION counters */
 #define scsi_get_ua_new_media_ctr(sdev) \

  parent reply	other threads:[~2025-09-10 21:33 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-10 21:32 [PATCH 0/3] Improve host-wide tag IOPS Bart Van Assche
2025-09-10 21:32 ` [PATCH 1/3] block: Export blk_mq_all_tag_iter() Bart Van Assche
2025-09-11  8:32   ` Ming Lei
2025-09-11 16:49     ` Bart Van Assche
2025-09-10 21:32 ` [PATCH 2/3] ufs: core: Use scsi_device_busy() Bart Van Assche
2025-09-11  9:18   ` Peter Wang (王信友)
2025-09-10 21:32 ` Bart Van Assche [this message]
2025-09-11  6:40   ` [PATCH 3/3] scsi: core: Improve IOPS in case of host-wide tags Hannes Reinecke
2025-09-11 15:45     ` Bart Van Assche
2025-09-11  8:15   ` John Garry
2025-09-11 15:59     ` Bart Van Assche
2025-09-11 17:37     ` Bart Van Assche
2025-09-12 14:37       ` John Garry

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=20250910213254.1215318-4-bvanassche@acm.org \
    --to=bvanassche@acm.org \
    --cc=James.Bottomley@HansenPartnership.com \
    --cc=axboe@kernel.dk \
    --cc=hch@infradead.org \
    --cc=john.g.garry@oracle.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    --cc=ming.lei@redhat.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