From: Ming Lei <ming.lei@redhat.com>
To: Jens Axboe <axboe@kernel.dk>, linux-block@vger.kernel.org
Cc: Ming Lei <ming.lei@redhat.com>, Tejun Heo <tj@kernel.org>,
	Josef Bacik <josef@toxicpanda.com>, Yu Kuai <yukuai3@huawei.com>
Subject: [PATCH 3/3] blk-throttle: carry over directly
Date: Wed,  5 Mar 2025 12:31:21 +0800	[thread overview]
Message-ID: <20250305043123.3938491-4-ming.lei@redhat.com> (raw)
In-Reply-To: <20250305043123.3938491-1-ming.lei@redhat.com>

Now ->carryover_bytes[] and ->carryover_ios[] only covers limit/config
update.

Actually the carryover bytes/ios can be carried to ->bytes_disp[] and
->io_disp[] directly, since the carryover is one-shot thing and only valid
in current slice.

Then we can remove the two fields and simplify code much.

Type of ->bytes_disp[] and ->io_disp[] has to change as signed because the
two fields may become negative when updating limits or config, but both are
big enough for holding bytes/ios dispatched in single slice

Cc: Tejun Heo <tj@kernel.org>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-throttle.c | 49 +++++++++++++++++++-------------------------
 block/blk-throttle.h |  4 ++--
 2 files changed, 23 insertions(+), 30 deletions(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 7271aee94faf..91dab43c65ab 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -478,8 +478,6 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg,
 {
 	tg->bytes_disp[rw] = 0;
 	tg->io_disp[rw] = 0;
-	tg->carryover_bytes[rw] = 0;
-	tg->carryover_ios[rw] = 0;
 
 	/*
 	 * Previous slice has expired. We must have trimmed it after last
@@ -498,16 +496,14 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg,
 }
 
 static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw,
-					  bool clear_carryover)
+					  bool clear)
 {
-	tg->bytes_disp[rw] = 0;
-	tg->io_disp[rw] = 0;
+	if (clear) {
+		tg->bytes_disp[rw] = 0;
+		tg->io_disp[rw] = 0;
+	}
 	tg->slice_start[rw] = jiffies;
 	tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
-	if (clear_carryover) {
-		tg->carryover_bytes[rw] = 0;
-		tg->carryover_ios[rw] = 0;
-	}
 
 	throtl_log(&tg->service_queue,
 		   "[%c] new slice start=%lu end=%lu jiffies=%lu",
@@ -617,20 +613,16 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 	 */
 	time_elapsed -= tg->td->throtl_slice;
 	bytes_trim = calculate_bytes_allowed(tg_bps_limit(tg, rw),
-					     time_elapsed) +
-		     tg->carryover_bytes[rw];
-	io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed) +
-		  tg->carryover_ios[rw];
+					     time_elapsed);
+	io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed);
 	if (bytes_trim <= 0 && io_trim <= 0)
 		return;
 
-	tg->carryover_bytes[rw] = 0;
 	if ((long long)tg->bytes_disp[rw] >= bytes_trim)
 		tg->bytes_disp[rw] -= bytes_trim;
 	else
 		tg->bytes_disp[rw] = 0;
 
-	tg->carryover_ios[rw] = 0;
 	if ((int)tg->io_disp[rw] >= io_trim)
 		tg->io_disp[rw] -= io_trim;
 	else
@@ -645,7 +637,8 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 		   jiffies);
 }
 
-static void __tg_update_carryover(struct throtl_grp *tg, bool rw)
+static void __tg_update_carryover(struct throtl_grp *tg, bool rw,
+				  long long *bytes, int *ios)
 {
 	unsigned long jiffy_elapsed = jiffies - tg->slice_start[rw];
 	u64 bps_limit = tg_bps_limit(tg, rw);
@@ -658,26 +651,28 @@ static void __tg_update_carryover(struct throtl_grp *tg, bool rw)
 	 * configuration.
 	 */
 	if (bps_limit != U64_MAX)
-		tg->carryover_bytes[rw] +=
-			calculate_bytes_allowed(bps_limit, jiffy_elapsed) -
+		*bytes = calculate_bytes_allowed(bps_limit, jiffy_elapsed) -
 			tg->bytes_disp[rw];
 	if (iops_limit != UINT_MAX)
-		tg->carryover_ios[rw] +=
-			calculate_io_allowed(iops_limit, jiffy_elapsed) -
+		*ios = calculate_io_allowed(iops_limit, jiffy_elapsed) -
 			tg->io_disp[rw];
+	tg->bytes_disp[rw] -= *bytes;
+	tg->io_disp[rw] -= *ios;
 }
 
 static void tg_update_carryover(struct throtl_grp *tg)
 {
+	long long bytes[2] = {0};
+	int ios[2] = {0};
+
 	if (tg->service_queue.nr_queued[READ])
-		__tg_update_carryover(tg, READ);
+		__tg_update_carryover(tg, READ, &bytes[READ], &ios[READ]);
 	if (tg->service_queue.nr_queued[WRITE])
-		__tg_update_carryover(tg, WRITE);
+		__tg_update_carryover(tg, WRITE, &bytes[WRITE], &ios[WRITE]);
 
 	/* see comments in struct throtl_grp for meaning of these fields. */
 	throtl_log(&tg->service_queue, "%s: %lld %lld %d %d\n", __func__,
-		   tg->carryover_bytes[READ], tg->carryover_bytes[WRITE],
-		   tg->carryover_ios[READ], tg->carryover_ios[WRITE]);
+		   bytes[READ], bytes[WRITE], ios[READ], ios[WRITE]);
 }
 
 static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio,
@@ -695,8 +690,7 @@ static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio
 
 	/* Round up to the next throttle slice, wait time must be nonzero */
 	jiffy_elapsed_rnd = roundup(jiffy_elapsed + 1, tg->td->throtl_slice);
-	io_allowed = calculate_io_allowed(iops_limit, jiffy_elapsed_rnd) +
-		     tg->carryover_ios[rw];
+	io_allowed = calculate_io_allowed(iops_limit, jiffy_elapsed_rnd);
 	if (io_allowed > 0 && tg->io_disp[rw] + 1 <= io_allowed)
 		return 0;
 
@@ -729,8 +723,7 @@ static unsigned long tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio,
 		jiffy_elapsed_rnd = tg->td->throtl_slice;
 
 	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
-	bytes_allowed = calculate_bytes_allowed(bps_limit, jiffy_elapsed_rnd) +
-			tg->carryover_bytes[rw];
+	bytes_allowed = calculate_bytes_allowed(bps_limit, jiffy_elapsed_rnd);
 	if (bytes_allowed > 0 && tg->bytes_disp[rw] + bio_size <= bytes_allowed)
 		return 0;
 
diff --git a/block/blk-throttle.h b/block/blk-throttle.h
index ba8f6e986994..7964cc041e06 100644
--- a/block/blk-throttle.h
+++ b/block/blk-throttle.h
@@ -102,9 +102,9 @@ struct throtl_grp {
 	unsigned int iops[2];
 
 	/* Number of bytes dispatched in current slice */
-	uint64_t bytes_disp[2];
+	int64_t bytes_disp[2];
 	/* Number of bio's dispatched in current slice */
-	unsigned int io_disp[2];
+	int io_disp[2];
 
 	/*
 	 * The following two fields are updated when new configuration is
-- 
2.47.0


  parent reply	other threads:[~2025-03-05  4:32 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-03-05  4:31 [PATCH 0/3] blk-throttle: remove last_bytes/ios and carryover byte/ios Ming Lei
2025-03-05  4:31 ` [PATCH 1/3] blk-throttle: remove last_bytes_disp and last_ios_disp Ming Lei
2025-03-05 19:07   ` Tejun Heo
2025-03-05  4:31 ` [PATCH 2/3] blk-throttle: don't take carryover for prioritized processing of metadata Ming Lei
2025-03-05 19:11   ` Tejun Heo
2025-03-05  4:31 ` Ming Lei [this message]
2025-03-05 19:16   ` [PATCH 3/3] blk-throttle: carry over directly Tejun Heo
2025-04-11  2:53   ` Yu Kuai
2025-04-11 15:01     ` Ming Lei
2025-04-12  0:37       ` Yu Kuai
2025-04-14  2:32         ` Ming Lei
2025-04-14 11:47           ` Yu Kuai
2025-03-05 23:25 ` [PATCH 0/3] blk-throttle: remove last_bytes/ios and carryover byte/ios 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=20250305043123.3938491-4-ming.lei@redhat.com \
    --to=ming.lei@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=josef@toxicpanda.com \
    --cc=linux-block@vger.kernel.org \
    --cc=tj@kernel.org \
    --cc=yukuai3@huawei.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.