linux-block.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Bart Van Assche <bvanassche@acm.org>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, Christoph Hellwig <hch@lst.de>,
	Jaegeuk Kim <jaegeuk@kernel.org>,
	Adam Manzanares <a.manzanares@samsung.com>,
	Bart Van Assche <bvanassche@acm.org>,
	Damien Le Moal <damien.lemoal@wdc.com>,
	Hannes Reinecke <hare@suse.de>, Ming Lei <ming.lei@redhat.com>,
	Johannes Thumshirn <johannes.thumshirn@wdc.com>,
	Himanshu Madhani <himanshu.madhani@oracle.com>
Subject: [PATCH v3 11/16] block/mq-deadline: Reserve 25% of scheduler tags for synchronous requests
Date: Thu, 17 Jun 2021 17:44:51 -0700	[thread overview]
Message-ID: <20210618004456.7280-12-bvanassche@acm.org> (raw)
In-Reply-To: <20210618004456.7280-1-bvanassche@acm.org>

For interactive workloads it is important that synchronous requests are
not delayed. Hence reserve 25% of scheduler tags for synchronous requests.
This patch still allows asynchronous requests to fill the hardware queues
since blk_mq_init_sched() makes sure that the number of scheduler requests
is the double of the hardware queue depth. From blk_mq_init_sched():

	q->nr_requests = 2 * min_t(unsigned int, q->tag_set->queue_depth,
				   BLKDEV_MAX_RQ);

Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
---
 block/mq-deadline.c | 55 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index f92224ff0256..44da481c3fea 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -67,6 +67,7 @@ struct deadline_data {
 	int fifo_batch;
 	int writes_starved;
 	int front_merges;
+	u32 async_depth;
 
 	spinlock_t lock;
 	spinlock_t zone_lock;
@@ -397,6 +398,44 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	return rq;
 }
 
+/*
+ * Called by __blk_mq_alloc_request(). The shallow_depth value set by this
+ * function is used by __blk_mq_get_tag().
+ */
+static void dd_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
+{
+	struct deadline_data *dd = data->q->elevator->elevator_data;
+
+	/* Do not throttle synchronous reads. */
+	if (op_is_sync(op) && !op_is_write(op))
+		return;
+
+	/*
+	 * Throttle asynchronous requests and writes such that these requests
+	 * do not block the allocation of synchronous requests.
+	 */
+	data->shallow_depth = dd->async_depth;
+}
+
+/* Called by blk_mq_update_nr_requests(). */
+static void dd_depth_updated(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+	struct deadline_data *dd = q->elevator->elevator_data;
+	struct blk_mq_tags *tags = hctx->sched_tags;
+
+	dd->async_depth = max(1UL, 3 * q->nr_requests / 4);
+
+	sbitmap_queue_min_shallow_depth(tags->bitmap_tags, dd->async_depth);
+}
+
+/* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */
+static int dd_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
+{
+	dd_depth_updated(hctx);
+	return 0;
+}
+
 static void dd_exit_sched(struct elevator_queue *e)
 {
 	struct deadline_data *dd = e->elevator_data;
@@ -617,6 +656,7 @@ SHOW_JIFFIES(deadline_read_expire_show, dd->fifo_expire[DD_READ]);
 SHOW_JIFFIES(deadline_write_expire_show, dd->fifo_expire[DD_WRITE]);
 SHOW_INT(deadline_writes_starved_show, dd->writes_starved);
 SHOW_INT(deadline_front_merges_show, dd->front_merges);
+SHOW_INT(deadline_async_depth_show, dd->front_merges);
 SHOW_INT(deadline_fifo_batch_show, dd->fifo_batch);
 #undef SHOW_INT
 #undef SHOW_JIFFIES
@@ -645,6 +685,7 @@ STORE_JIFFIES(deadline_read_expire_store, &dd->fifo_expire[DD_READ], 0, INT_MAX)
 STORE_JIFFIES(deadline_write_expire_store, &dd->fifo_expire[DD_WRITE], 0, INT_MAX);
 STORE_INT(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX);
 STORE_INT(deadline_front_merges_store, &dd->front_merges, 0, 1);
+STORE_INT(deadline_async_depth_store, &dd->front_merges, 1, INT_MAX);
 STORE_INT(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX);
 #undef STORE_FUNCTION
 #undef STORE_INT
@@ -658,6 +699,7 @@ static struct elv_fs_entry deadline_attrs[] = {
 	DD_ATTR(write_expire),
 	DD_ATTR(writes_starved),
 	DD_ATTR(front_merges),
+	DD_ATTR(async_depth),
 	DD_ATTR(fifo_batch),
 	__ATTR_NULL
 };
@@ -733,6 +775,15 @@ static int deadline_starved_show(void *data, struct seq_file *m)
 	return 0;
 }
 
+static int dd_async_depth_show(void *data, struct seq_file *m)
+{
+	struct request_queue *q = data;
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	seq_printf(m, "%u\n", dd->async_depth);
+	return 0;
+}
+
 static void *deadline_dispatch_start(struct seq_file *m, loff_t *pos)
 	__acquires(&dd->lock)
 {
@@ -775,6 +826,7 @@ static const struct blk_mq_debugfs_attr deadline_queue_debugfs_attrs[] = {
 	DEADLINE_QUEUE_DDIR_ATTRS(write),
 	{"batching", 0400, deadline_batching_show},
 	{"starved", 0400, deadline_starved_show},
+	{"async_depth", 0400, dd_async_depth_show},
 	{"dispatch", 0400, .seq_ops = &deadline_dispatch_seq_ops},
 	{},
 };
@@ -783,6 +835,8 @@ static const struct blk_mq_debugfs_attr deadline_queue_debugfs_attrs[] = {
 
 static struct elevator_type mq_deadline = {
 	.ops = {
+		.depth_updated		= dd_depth_updated,
+		.limit_depth		= dd_limit_depth,
 		.insert_requests	= dd_insert_requests,
 		.dispatch_request	= dd_dispatch_request,
 		.prepare_request	= dd_prepare_request,
@@ -796,6 +850,7 @@ static struct elevator_type mq_deadline = {
 		.has_work		= dd_has_work,
 		.init_sched		= dd_init_sched,
 		.exit_sched		= dd_exit_sched,
+		.init_hctx		= dd_init_hctx,
 	},
 
 #ifdef CONFIG_BLK_DEBUG_FS

  parent reply	other threads:[~2021-06-18  0:45 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-18  0:44 [PATCH v3 00/16] Improve I/O priority support Bart Van Assche
2021-06-18  0:44 ` [PATCH v3 01/16] block/Kconfig: Make the BLK_WBT and BLK_WBT_MQ entries consecutive Bart Van Assche
2021-06-18 17:09   ` Adam Manzanares
2021-06-18 19:49   ` Himanshu Madhani
2021-06-18  0:44 ` [PATCH v3 02/16] block/blk-cgroup: Swap the blk_throtl_init() and blk_iolatency_init() calls Bart Van Assche
2021-06-18 17:15   ` Adam Manzanares
2021-06-18 19:49   ` Himanshu Madhani
2021-06-21 14:24   ` Tejun Heo
2021-06-18  0:44 ` [PATCH v3 03/16] block/blk-rq-qos: Move a function from a header file into a C file Bart Van Assche
2021-06-18 17:22   ` Adam Manzanares
2021-06-18 19:49   ` Himanshu Madhani
2021-06-18  0:44 ` [PATCH v3 04/16] block: Introduce the ioprio rq-qos policy Bart Van Assche
2021-06-18 22:02   ` Adam Manzanares
2021-06-18  0:44 ` [PATCH v3 05/16] block/mq-deadline: Add several comments Bart Van Assche
2021-06-18 22:06   ` Adam Manzanares
2021-06-18  0:44 ` [PATCH v3 06/16] block/mq-deadline: Add two lockdep_assert_held() statements Bart Van Assche
2021-06-18 22:09   ` Adam Manzanares
2021-06-18  0:44 ` [PATCH v3 07/16] block/mq-deadline: Remove two local variables Bart Van Assche
2021-06-18 22:16   ` Adam Manzanares
2021-06-18  0:44 ` [PATCH v3 08/16] block/mq-deadline: Rename dd_init_queue() and dd_exit_queue() Bart Van Assche
2021-06-18 22:18   ` Adam Manzanares
2021-06-18  0:44 ` [PATCH v3 09/16] block/mq-deadline: Improve compile-time argument checking Bart Van Assche
2021-06-18 22:30   ` Adam Manzanares
2021-06-18  0:44 ` [PATCH v3 10/16] block/mq-deadline: Improve the sysfs show and store macros Bart Van Assche
2021-06-18 23:07   ` Adam Manzanares
2021-06-18  0:44 ` Bart Van Assche [this message]
2021-06-18  0:44 ` [PATCH v3 12/16] block/mq-deadline: Micro-optimize the batching algorithm Bart Van Assche
2021-06-18  0:44 ` [PATCH v3 13/16] block/mq-deadline: Add I/O priority support Bart Van Assche
2021-06-18  0:44 ` [PATCH v3 14/16] block/mq-deadline: Track I/O statistics Bart Van Assche
2021-06-18  0:44 ` [PATCH v3 15/16] block/mq-deadline: Add cgroup support Bart Van Assche
2021-06-18  0:44 ` [PATCH v3 16/16] block/mq-deadline: Prioritize high-priority requests Bart Van Assche
2021-08-20  0:45   ` Niklas Cassel
2021-08-20 18:04     ` Bart Van Assche
2021-08-20 23:05       ` Niklas Cassel
2021-08-20 23:38         ` Bart Van Assche
2021-08-23  7:36           ` Niklas Cassel
2021-08-23 17:15             ` Bart Van Assche
2021-08-23 23:01               ` Damien Le Moal
2021-08-24 21:33               ` Niklas Cassel
2021-06-21 16:06 ` [PATCH v3 00/16] Improve I/O priority support 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=20210618004456.7280-12-bvanassche@acm.org \
    --to=bvanassche@acm.org \
    --cc=a.manzanares@samsung.com \
    --cc=axboe@kernel.dk \
    --cc=damien.lemoal@wdc.com \
    --cc=hare@suse.de \
    --cc=hch@lst.de \
    --cc=himanshu.madhani@oracle.com \
    --cc=jaegeuk@kernel.org \
    --cc=johannes.thumshirn@wdc.com \
    --cc=linux-block@vger.kernel.org \
    --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;
as well as URLs for NNTP newsgroup(s).