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>,
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 11/14] block/mq-deadline: Reserve 25% of scheduler tags for synchronous requests
Date: Tue, 8 Jun 2021 16:07:00 -0700 [thread overview]
Message-ID: <20210608230703.19510-12-bvanassche@acm.org> (raw)
In-Reply-To: <20210608230703.19510-1-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 | 52 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 52 insertions(+)
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 1d1bb7a41d2a..a7d0584437d1 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;
@@ -733,6 +772,15 @@ 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 +823,7 @@ 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 +832,8 @@ 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 +847,7 @@ 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
next prev parent reply other threads:[~2021-06-08 23:07 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-08 23:06 [PATCH 00/14] Improve I/O priority support Bart Van Assche
2021-06-08 23:06 ` [PATCH 01/14] block/Kconfig: Make the BLK_WBT and BLK_WBT_MQ entries consecutive Bart Van Assche
2021-06-09 4:14 ` Damien Le Moal
2021-06-09 7:03 ` Johannes Thumshirn
2021-06-10 6:02 ` Hannes Reinecke
2021-06-08 23:06 ` [PATCH 02/14] block/blk-cgroup: Swap the blk_throtl_init() and blk_iolatency_init() calls Bart Van Assche
2021-06-09 4:19 ` Damien Le Moal
2021-06-09 7:05 ` Johannes Thumshirn
2021-06-10 6:02 ` Hannes Reinecke
2021-06-08 23:06 ` [PATCH 03/14] block/blk-rq-qos: Move a function from a header file into a C file Bart Van Assche
2021-06-09 4:22 ` Damien Le Moal
2021-06-10 6:03 ` Hannes Reinecke
2021-06-08 23:06 ` [PATCH 04/14] block: Introduce the ioprio rq-qos policy Bart Van Assche
2021-06-09 4:40 ` Damien Le Moal
2021-06-09 16:48 ` Bart Van Assche
2021-06-10 0:29 ` Damien Le Moal
2021-06-10 6:20 ` Hannes Reinecke
2021-06-10 17:14 ` Bart Van Assche
2021-06-08 23:06 ` [PATCH 05/14] block/mq-deadline: Add several comments Bart Van Assche
2021-06-10 6:21 ` Hannes Reinecke
2021-06-08 23:06 ` [PATCH 06/14] block/mq-deadline: Add two lockdep_assert_held() statements Bart Van Assche
2021-06-10 6:21 ` Hannes Reinecke
2021-06-08 23:06 ` [PATCH 07/14] block/mq-deadline: Remove two local variables Bart Van Assche
2021-06-10 6:22 ` Hannes Reinecke
2021-06-08 23:06 ` [PATCH 08/14] block/mq-deadline: Rename dd_init_queue() and dd_exit_queue() Bart Van Assche
2021-06-08 23:06 ` [PATCH 09/14] block/mq-deadline: Improve compile-time argument checking Bart Van Assche
2021-06-08 23:06 ` [PATCH 10/14] block/mq-deadline: Improve the sysfs show and store macros Bart Van Assche
2021-06-09 4:46 ` Damien Le Moal
2021-06-09 16:54 ` Bart Van Assche
2021-06-10 0:31 ` Damien Le Moal
2021-06-09 7:11 ` Johannes Thumshirn
2021-06-09 16:59 ` Bart Van Assche
2021-06-10 6:23 ` Hannes Reinecke
2021-06-08 23:07 ` Bart Van Assche [this message]
2021-06-10 6:26 ` [PATCH 11/14] block/mq-deadline: Reserve 25% of scheduler tags for synchronous requests Hannes Reinecke
2021-06-08 23:07 ` [PATCH 12/14] block/mq-deadline: Add I/O priority support Bart Van Assche
2021-06-09 5:03 ` Damien Le Moal
2021-06-09 17:25 ` Bart Van Assche
2021-06-10 0:39 ` Damien Le Moal
2021-06-10 6:35 ` Hannes Reinecke
2021-06-08 23:07 ` [PATCH 13/14] block/mq-deadline: Add cgroup support Bart Van Assche
2021-06-10 6:37 ` Hannes Reinecke
2021-06-08 23:07 ` [PATCH 14/14] block/mq-deadline: Prioritize high-priority requests Bart Van Assche
2021-06-09 5:10 ` Damien Le Moal
2021-06-10 6:43 ` Hannes Reinecke
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=20210608230703.19510-12-bvanassche@acm.org \
--to=bvanassche@acm.org \
--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).