mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Xue He <xue01.he@samsung.com>
To: axboe@kernel.dk, akpm@linux-foundation.org, yukuai1@huaweicloud.com
Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
	yukuai3@huawei.com, hexue <xue01.he@samsung.com>
Subject: [PATCH v4] block: plug attempts to batch allocate tags multiple times
Date: Fri, 10 Oct 2025 06:35:38 +0000	[thread overview]
Message-ID: <20251010063538.3597-1-xue01.he@samsung.com> (raw)
In-Reply-To: <CGME20251010064008epcas5p3c507d64678fadfb71574050b01357341@epcas5p3.samsung.com>

This patch aims to enable batch allocation of sufficient tags after
batch IO submission with plug mechanism, thereby avoiding the need for
frequent individual requests when the initial allocation is
insufficient.

------------------------------------------------------------
Perf:
base code: __blk_mq_alloc_requests() 1.31%
patch: __blk_mq_alloc_requests() 0.71%
------------------------------------------------------------

---
changes since v1:
- Modify multiple batch registrations into a single loop to achieve
  the batch quantity

changes since v2:
- Modify the call location of remainder handling
- Refactoring sbitmap cleanup time

changes since v3:
- Add handle operation in loop
- Add helper sbitmap_find_bits_in_word

Signed-off-by: hexue <xue01.he@samsung.com>
---
 block/blk-mq.c | 39 ++++++++++++++++++---------------
 lib/sbitmap.c  | 58 ++++++++++++++++++++++++++++++++++----------------
 2 files changed, 62 insertions(+), 35 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index ba3a4b77f578..695ccc72e69f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -458,26 +458,31 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data)
 	unsigned long tag_mask;
 	int i, nr = 0;
 
-	tag_mask = blk_mq_get_tags(data, data->nr_tags, &tag_offset);
-	if (unlikely(!tag_mask))
-		return NULL;
+	do {
+		tag_mask = blk_mq_get_tags(data, data->nr_tags, &tag_offset);
+		if (unlikely(!tag_mask)) {
+			if (nr == 0)
+				return NULL;
+			break;
+		}
+		tags = blk_mq_tags_from_data(data);
+		for (i = 0; tag_mask; i++) {
+			if (!(tag_mask & (1UL << i)))
+				continue;
+			tag = tag_offset + i;
+			prefetch(tags->static_rqs[tag]);
+			tag_mask &= ~(1UL << i);
+			rq = blk_mq_rq_ctx_init(data, tags, tag);
+			rq_list_add_head(data->cached_rqs, rq);
+			data->nr_tags--;
+			nr++;
+		}
+		if (!(data->rq_flags & RQF_SCHED_TAGS))
+			blk_mq_add_active_requests(data->hctx, nr);
+	} while (data->nr_tags);
 
-	tags = blk_mq_tags_from_data(data);
-	for (i = 0; tag_mask; i++) {
-		if (!(tag_mask & (1UL << i)))
-			continue;
-		tag = tag_offset + i;
-		prefetch(tags->static_rqs[tag]);
-		tag_mask &= ~(1UL << i);
-		rq = blk_mq_rq_ctx_init(data, tags, tag);
-		rq_list_add_head(data->cached_rqs, rq);
-		nr++;
-	}
-	if (!(data->rq_flags & RQF_SCHED_TAGS))
-		blk_mq_add_active_requests(data->hctx, nr);
 	/* caller already holds a reference, add for remainder */
 	percpu_ref_get_many(&data->q->q_usage_counter, nr - 1);
-	data->nr_tags -= nr;
 
 	return rq_list_pop(data->cached_rqs);
 }
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 4d188d05db15..c0a8da1beec9 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -208,6 +208,32 @@ static int sbitmap_find_bit_in_word(struct sbitmap_word *map,
 	return nr;
 }
 
+static unsigned long sbitmap_find_bits_in_word(struct sbitmap_word *map,
+				    unsigned int depth, unsigned int alloc_hint, bool wrap,
+				    unsigned long *val, int nr_tags, unsigned int map_depth)
+{
+	unsigned long local_val, nr;
+
+	while (1) {
+		local_val = READ_ONCE(map->word);
+		if (local_val == (1UL << (map_depth - 1)) - 1) {
+			if (!sbitmap_deferred_clear(map, depth, alloc_hint, wrap))
+				return -1UL;
+			continue;
+		}
+
+		nr = find_first_zero_bit(&local_val, map_depth);
+		if (nr + nr_tags <= map_depth)
+			break;
+
+		if (!sbitmap_deferred_clear(map, depth, alloc_hint, wrap))
+			return -1UL;
+	};
+
+	*val = local_val;
+	return nr;
+}
+
 static unsigned int __map_depth_with_shallow(const struct sbitmap *sb,
 					     int index,
 					     unsigned int shallow_depth)
@@ -534,26 +560,22 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
 		unsigned int map_depth = __map_depth(sb, index);
 		unsigned long val;
 
-		sbitmap_deferred_clear(map, 0, 0, 0);
-		val = READ_ONCE(map->word);
-		if (val == (1UL << (map_depth - 1)) - 1)
+		nr = sbitmap_find_bits_in_word(map, 0, 0, 0, &val, nr_tags, map_depth);
+		if (nr == -1UL)
 			goto next;
 
-		nr = find_first_zero_bit(&val, map_depth);
-		if (nr + nr_tags <= map_depth) {
-			atomic_long_t *ptr = (atomic_long_t *) &map->word;
-
-			get_mask = ((1UL << nr_tags) - 1) << nr;
-			while (!atomic_long_try_cmpxchg(ptr, &val,
-							  get_mask | val))
-				;
-			get_mask = (get_mask & ~val) >> nr;
-			if (get_mask) {
-				*offset = nr + (index << sb->shift);
-				update_alloc_hint_after_get(sb, depth, hint,
-							*offset + nr_tags - 1);
-				return get_mask;
-			}
+		atomic_long_t *ptr = (atomic_long_t *) &map->word;
+
+		get_mask = ((1UL << nr_tags) - 1) << nr;
+		while (!atomic_long_try_cmpxchg(ptr, &val,
+						  get_mask | val))
+			;
+		get_mask = (get_mask & ~val) >> nr;
+		if (get_mask) {
+			*offset = nr + (index << sb->shift);
+			update_alloc_hint_after_get(sb, depth, hint,
+						*offset + nr_tags - 1);
+			return get_mask;
 		}
 next:
 		/* Jump to next index. */
-- 
2.34.1


       reply	other threads:[~2025-10-10  6:40 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20251010064008epcas5p3c507d64678fadfb71574050b01357341@epcas5p3.samsung.com>
2025-10-10  6:35 ` Xue He [this message]
2025-10-14  6:28   ` Yu Kuai
     [not found]     ` <CGME20251014083611epcas5p1c198e2ad844eb0ac08f0a9cafdeedb46@epcas5p1.samsung.com>
2025-10-14  8:31       ` Xue He
2025-10-15  2:20         ` [PATCH " Yu Kuai

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=20251010063538.3597-1-xue01.he@samsung.com \
    --to=xue01.he@samsung.com \
    --cc=akpm@linux-foundation.org \
    --cc=axboe@kernel.dk \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=yukuai1@huaweicloud.com \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®