linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: axboe@kernel.dk, newella@fb.com, clm@fb.com,
	josef@toxicpanda.com, dennisz@fb.com, lizefan@huawei.com,
	hannes@cmpxchg.org
Cc: linux-kernel@vger.kernel.org, linux-block@vger.kernel.org,
	kernel-team@fb.com, cgroups@vger.kernel.org, ast@kernel.org,
	daniel@iogearbox.net, kafai@fb.com, songliubraving@fb.com,
	yhs@fb.com, bpf@vger.kernel.org, Tejun Heo <tj@kernel.org>
Subject: [PATCH 07/10] blk-mq: add optional request->pre_start_time_ns
Date: Thu, 13 Jun 2019 18:56:17 -0700	[thread overview]
Message-ID: <20190614015620.1587672-8-tj@kernel.org> (raw)
In-Reply-To: <20190614015620.1587672-1-tj@kernel.org>

There are currently two start time timestamps - start_time_ns and
io_start_time_ns.  The former marks the request allocation and and the
second issue-to-device time.  The planned io.weight controller needs
to measure the total time bios take to execute after it leaves rq_qos
including the time spent waiting for request to become available,
which can easily dominate on saturated devices.

This patch adds request->pre_start_time_ns which records when the
request allocation attempt started.  As it isn't used for the usual
stats, make it optional behind QUEUE_FLAG_REC_PRESTART.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 block/blk-mq.c         | 11 +++++++++--
 include/linux/blkdev.h |  7 ++++++-
 2 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index ce0f5f4ede70..25ce27434c63 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -291,7 +291,7 @@ static inline bool blk_mq_need_time_stamp(struct request *rq)
 }
 
 static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
-		unsigned int tag, unsigned int op)
+		unsigned int tag, unsigned int op, u64 pre_start_time_ns)
 {
 	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
 	struct request *rq = tags->static_rqs[tag];
@@ -325,6 +325,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	RB_CLEAR_NODE(&rq->rb_node);
 	rq->rq_disk = NULL;
 	rq->part = NULL;
+	rq->pre_start_time_ns = pre_start_time_ns;
 	if (blk_mq_need_time_stamp(rq))
 		rq->start_time_ns = ktime_get_ns();
 	else
@@ -356,8 +357,14 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 	struct request *rq;
 	unsigned int tag;
 	bool put_ctx_on_error = false;
+	u64 pre_start_time_ns = 0;
 
 	blk_queue_enter_live(q);
+
+	/* pre_start_time includes depth and tag waits */
+	if (blk_queue_rec_prestart(q))
+		pre_start_time_ns = ktime_get_ns();
+
 	data->q = q;
 	if (likely(!data->ctx)) {
 		data->ctx = blk_mq_get_ctx(q);
@@ -395,7 +402,7 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 		return NULL;
 	}
 
-	rq = blk_mq_rq_ctx_init(data, tag, data->cmd_flags);
+	rq = blk_mq_rq_ctx_init(data, tag, data->cmd_flags, pre_start_time_ns);
 	if (!op_is_flush(data->cmd_flags)) {
 		rq->elv.icq = NULL;
 		if (e && e->type->ops.prepare_request) {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 592669bcc536..ff72eb940d4c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -194,7 +194,9 @@ struct request {
 
 	struct gendisk *rq_disk;
 	struct hd_struct *part;
-	/* Time that I/O was submitted to the kernel. */
+	/* Time that the first bio started allocating this request. */
+	u64 pre_start_time_ns;
+	/* Time that this request was allocated for this IO. */
 	u64 start_time_ns;
 	/* Time that I/O was submitted to the device. */
 	u64 io_start_time_ns;
@@ -606,6 +608,7 @@ struct request_queue {
 #define QUEUE_FLAG_SCSI_PASSTHROUGH 23	/* queue supports SCSI commands */
 #define QUEUE_FLAG_QUIESCED	24	/* queue has been quiesced */
 #define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
+#define QUEUE_FLAG_REC_PRESTART	26	/* record pre_start_time_ns */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP))
@@ -632,6 +635,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 	test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags)
 #define blk_queue_pci_p2pdma(q)	\
 	test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags)
+#define blk_queue_rec_prestart(q)	\
+	test_bit(QUEUE_FLAG_REC_PRESTART, &(q)->queue_flags)
 
 #define blk_noretry_request(rq) \
 	((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
-- 
2.17.1


  parent reply	other threads:[~2019-06-14  1:57 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-14  1:56 [PATCHSET block/for-next] IO cost model based work-conserving porportional controller Tejun Heo
2019-06-14  1:56 ` [PATCH 01/10] blkcg: pass @q and @blkcg into blkcg_pol_alloc_pd_fn() Tejun Heo
2019-06-14  1:56 ` [PATCH 02/10] blkcg: make ->cpd_init_fn() optional Tejun Heo
2019-06-14  1:56 ` [PATCH 03/10] blkcg: separate blkcg_conf_get_disk() out of blkg_conf_prep() Tejun Heo
2019-06-14  1:56 ` [PATCH 04/10] block/rq_qos: add rq_qos_merge() Tejun Heo
2019-06-14  1:56 ` [PATCH 05/10] block/rq_qos: implement rq_qos_ops->queue_depth_changed() Tejun Heo
2019-06-14  1:56 ` [PATCH 06/10] blkcg: s/RQ_QOS_CGROUP/RQ_QOS_LATENCY/ Tejun Heo
2019-06-14  1:56 ` Tejun Heo [this message]
2019-06-14  1:56 ` [PATCH 08/10] blkcg: implement blk-ioweight Tejun Heo
2019-06-14 12:17   ` Toke Høiland-Jørgensen
2019-06-14 15:09     ` Tejun Heo
2019-06-14 20:50       ` Toke Høiland-Jørgensen
2019-06-15 15:57         ` Tejun Heo
2019-06-14  1:56 ` [PATCH 09/10] blkcg: add tools/cgroup/monitor_ioweight.py Tejun Heo
2019-06-14  1:56 ` [PATCH 10/10] blkcg: implement BPF_PROG_TYPE_IO_COST Tejun Heo
2019-06-14 11:32   ` Quentin Monnet
2019-06-14 14:52     ` Tejun Heo
2019-06-14 16:35       ` Alexei Starovoitov
2019-06-14 17:09         ` Tejun Heo
2019-06-14 17:56 ` [PATCHSET block/for-next] IO cost model based work-conserving porportional controller Tejun Heo
2019-08-20 10:48   ` Paolo Valente
2019-08-20 15:04     ` Paolo Valente
2019-08-20 15:19       ` Tejun Heo
2019-08-22  8:58         ` Paolo Valente
2019-08-31  6:53           ` Tejun Heo
2019-08-31  7:10             ` Paolo Valente
2019-08-31 11:20               ` Tejun Heo
2019-09-02 15:45             ` Paolo Valente
2019-09-02 15:56               ` Tejun Heo
2019-09-02 19:43                 ` Paolo Valente
2019-09-05 16:55                   ` Tejun Heo
2019-09-06  9:07                     ` Paolo Valente
2019-09-06 14:58                       ` Tejun Heo
2020-02-19 18:34                         ` Paolo Valente
2019-07-10 20:51 [PATCHSET v2 block/for-linus] " Tejun Heo
2019-07-10 20:51 ` [PATCH 07/10] blk-mq: add optional request->pre_start_time_ns Tejun Heo

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=20190614015620.1587672-8-tj@kernel.org \
    --to=tj@kernel.org \
    --cc=ast@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=bpf@vger.kernel.org \
    --cc=cgroups@vger.kernel.org \
    --cc=clm@fb.com \
    --cc=daniel@iogearbox.net \
    --cc=dennisz@fb.com \
    --cc=hannes@cmpxchg.org \
    --cc=josef@toxicpanda.com \
    --cc=kafai@fb.com \
    --cc=kernel-team@fb.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lizefan@huawei.com \
    --cc=newella@fb.com \
    --cc=songliubraving@fb.com \
    --cc=yhs@fb.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).