Linux-BTRFS Archive on lore.kernel.org
 help / color / Atom feed
From: Ming Lei <ming.lei@redhat.com>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, Theodore Ts'o <tytso@mit.edu>,
	Omar Sandoval <osandov@fb.com>, Sagi Grimberg <sagi@grimberg.me>,
	Dave Chinner <dchinner@redhat.com>,
	Kent Overstreet <kent.overstreet@gmail.com>,
	Mike Snitzer <snitzer@redhat.com>,
	dm-devel@redhat.com, Alexander Viro <viro@zeniv.linux.org.uk>,
	linux-fsdevel@vger.kernel.org, linux-raid@vger.kernel.org,
	David Sterba <dsterba@suse.com>,
	linux-btrfs@vger.kernel.org,
	"Darrick J . Wong" <darrick.wong@oracle.com>,
	linux-xfs@vger.kernel.org, Gao Xiang <gaoxiang25@huawei.com>,
	Christoph Hellwig <hch@lst.de>,
	linux-ext4@vger.kernel.org, Coly Li <colyli@suse.de>,
	linux-bcache@vger.kernel.org, Boaz Harrosh <ooo@electrozaur.com>,
	Bob Peterson <rpeterso@redhat.com>,
	cluster-devel@redhat.com, Ming Lei <ming.lei@redhat.com>
Subject: [PATCH V14 06/18] block: use bio_for_each_mp_bvec() to compute multi-page bvec count
Date: Mon, 21 Jan 2019 16:17:53 +0800
Message-ID: <20190121081805.32727-7-ming.lei@redhat.com> (raw)
In-Reply-To: <20190121081805.32727-1-ming.lei@redhat.com>

First it is more efficient to use bio_for_each_mp_bvec() in both
blk_bio_segment_split() and __blk_recalc_rq_segments() to compute how
many multi-page bvecs there are in the bio.

Secondly once bio_for_each_mp_bvec() is used, the bvec may need to be
splitted because its length can be very longer than max segment size,
so we have to split the big bvec into several segments.

Thirdly when splitting multi-page bvec into segments, the max segment
limit may be reached, so the bio split need to be considered under
this situation too.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-merge.c | 103 +++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 83 insertions(+), 20 deletions(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index f85d878f313d..2dfc30d8bc77 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -161,6 +161,73 @@ static inline unsigned get_max_io_size(struct request_queue *q,
 	return sectors;
 }
 
+static unsigned get_max_segment_size(struct request_queue *q,
+				     unsigned offset)
+{
+	unsigned long mask = queue_segment_boundary(q);
+
+	/* default segment boundary mask means no boundary limit */
+	if (mask == BLK_SEG_BOUNDARY_MASK)
+		return queue_max_segment_size(q);
+
+	return min_t(unsigned long, mask - (mask & offset) + 1,
+		     queue_max_segment_size(q));
+}
+
+/*
+ * Split the bvec @bv into segments, and update all kinds of
+ * variables.
+ */
+static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
+		unsigned *nsegs, unsigned *last_seg_size,
+		unsigned *front_seg_size, unsigned *sectors)
+{
+	unsigned len = bv->bv_len;
+	unsigned total_len = 0;
+	unsigned new_nsegs = 0, seg_size = 0;
+
+	/*
+	 * Multi-page bvec may be too big to hold in one segment, so the
+	 * current bvec has to be splitted as multiple segments.
+	 */
+	while (len && new_nsegs + *nsegs < queue_max_segments(q)) {
+		seg_size = get_max_segment_size(q, bv->bv_offset + total_len);
+		seg_size = min(seg_size, len);
+
+		new_nsegs++;
+		total_len += seg_size;
+		len -= seg_size;
+
+		if ((bv->bv_offset + total_len) & queue_virt_boundary(q))
+			break;
+	}
+
+	if (!new_nsegs)
+		return !!len;
+
+	/* update front segment size */
+	if (!*nsegs) {
+		unsigned first_seg_size;
+
+		if (new_nsegs == 1)
+			first_seg_size = get_max_segment_size(q, bv->bv_offset);
+		else
+			first_seg_size = queue_max_segment_size(q);
+
+		if (*front_seg_size < first_seg_size)
+			*front_seg_size = first_seg_size;
+	}
+
+	/* update other varibles */
+	*last_seg_size = seg_size;
+	*nsegs += new_nsegs;
+	if (sectors)
+		*sectors += total_len >> 9;
+
+	/* split in the middle of the bvec if len != 0 */
+	return !!len;
+}
+
 static struct bio *blk_bio_segment_split(struct request_queue *q,
 					 struct bio *bio,
 					 struct bio_set *bs,
@@ -174,7 +241,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	struct bio *new = NULL;
 	const unsigned max_sectors = get_max_io_size(q, bio);
 
-	bio_for_each_segment(bv, bio, iter) {
+	bio_for_each_mp_bvec(bv, bio, iter) {
 		/*
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
@@ -189,8 +256,12 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 			 */
 			if (nsegs < queue_max_segments(q) &&
 			    sectors < max_sectors) {
-				nsegs++;
-				sectors = max_sectors;
+				/* split in the middle of bvec */
+				bv.bv_len = (max_sectors - sectors) << 9;
+				bvec_split_segs(q, &bv, &nsegs,
+						&seg_size,
+						&front_seg_size,
+						&sectors);
 			}
 			goto split;
 		}
@@ -212,14 +283,12 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 		if (nsegs == queue_max_segments(q))
 			goto split;
 
-		if (nsegs == 1 && seg_size > front_seg_size)
-			front_seg_size = seg_size;
-
-		nsegs++;
 		bvprv = bv;
 		bvprvp = &bvprv;
-		seg_size = bv.bv_len;
-		sectors += bv.bv_len >> 9;
+
+		if (bvec_split_segs(q, &bv, &nsegs, &seg_size,
+				    &front_seg_size, &sectors))
+			goto split;
 
 	}
 
@@ -233,8 +302,6 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 			bio = new;
 	}
 
-	if (nsegs == 1 && seg_size > front_seg_size)
-		front_seg_size = seg_size;
 	bio->bi_seg_front_size = front_seg_size;
 	if (seg_size > bio->bi_seg_back_size)
 		bio->bi_seg_back_size = seg_size;
@@ -297,6 +364,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	struct bio_vec bv, bvprv = { NULL };
 	int prev = 0;
 	unsigned int seg_size, nr_phys_segs;
+	unsigned front_seg_size = bio->bi_seg_front_size;
 	struct bio *fbio, *bbio;
 	struct bvec_iter iter;
 
@@ -316,7 +384,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	seg_size = 0;
 	nr_phys_segs = 0;
 	for_each_bio(bio) {
-		bio_for_each_segment(bv, bio, iter) {
+		bio_for_each_mp_bvec(bv, bio, iter) {
 			/*
 			 * If SG merging is disabled, each bio vector is
 			 * a segment
@@ -336,20 +404,15 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 				continue;
 			}
 new_segment:
-			if (nr_phys_segs == 1 && seg_size >
-			    fbio->bi_seg_front_size)
-				fbio->bi_seg_front_size = seg_size;
-
-			nr_phys_segs++;
 			bvprv = bv;
 			prev = 1;
-			seg_size = bv.bv_len;
+			bvec_split_segs(q, &bv, &nr_phys_segs, &seg_size,
+					&front_seg_size, NULL);
 		}
 		bbio = bio;
 	}
 
-	if (nr_phys_segs == 1 && seg_size > fbio->bi_seg_front_size)
-		fbio->bi_seg_front_size = seg_size;
+	fbio->bi_seg_front_size = front_seg_size;
 	if (seg_size > bbio->bi_seg_back_size)
 		bbio->bi_seg_back_size = seg_size;
 
-- 
2.9.5


  parent reply index

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-21  8:17 [PATCH V14 00/18] block: support multi-page bvec Ming Lei
2019-01-21  8:17 ` [PATCH V14 01/18] btrfs: look at bi_size for repair decisions Ming Lei
2019-01-21  8:17 ` [PATCH V14 02/18] block: don't use bio->bi_vcnt to figure out segment number Ming Lei
2019-01-21  8:17 ` [PATCH V14 03/18] block: remove bvec_iter_rewind() Ming Lei
2019-01-21  8:17 ` [PATCH V14 04/18] block: introduce multi-page bvec helpers Ming Lei
2019-01-21  8:17 ` [PATCH V14 05/18] block: introduce bio_for_each_mp_bvec() and rq_for_each_mp_bvec() Ming Lei
2019-01-21  8:17 ` Ming Lei [this message]
2019-01-21  8:17 ` [PATCH V14 07/18] block: use bio_for_each_mp_bvec() to map sg Ming Lei
2019-01-21  8:17 ` [PATCH V14 08/18] block: introduce mp_bvec_last_segment() Ming Lei
2019-01-21  8:17 ` [PATCH V14 09/18] fs/buffer.c: use bvec iterator to truncate the bio Ming Lei
2019-01-21  8:17 ` [PATCH V14 10/18] btrfs: use mp_bvec_last_segment to get bio's last page Ming Lei
2019-01-21  8:17 ` [PATCH V14 11/18] block: loop: pass multi-page bvec to iov_iter Ming Lei
2019-01-21  8:17 ` [PATCH V14 12/18] bcache: avoid to use bio_for_each_segment_all() in bch_bio_alloc_pages() Ming Lei
2019-01-21  8:18 ` [PATCH V14 13/18] block: allow bio_for_each_segment_all() to iterate over multi-page bvec Ming Lei
2019-01-21  8:18 ` [PATCH V14 14/18] block: enable multipage bvecs Ming Lei
2019-01-21  8:18 ` [PATCH V14 15/18] block: always define BIO_MAX_PAGES as 256 Ming Lei
2019-01-21  8:18 ` [PATCH V14 16/18] block: document usage of bio iterator helpers Ming Lei
2019-01-21  8:18 ` [PATCH V14 17/18] block: kill QUEUE_FLAG_NO_SG_MERGE Ming Lei
2019-01-21  8:18 ` [PATCH V14 18/18] block: kill BLK_MQ_F_SG_MERGE Ming Lei
2019-01-21  8:22 ` [PATCH V14 00/18] block: support multi-page bvec Christoph Hellwig
2019-01-21  8:37   ` Ming Lei
2019-01-21  8:38     ` Christoph Hellwig
2019-01-21  8:40       ` Ming Lei
2019-01-21  9:43 ` Sagi Grimberg
2019-01-22  2:01   ` Ming Lei

Reply instructions:

You may reply publically 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=20190121081805.32727-7-ming.lei@redhat.com \
    --to=ming.lei@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=cluster-devel@redhat.com \
    --cc=colyli@suse.de \
    --cc=darrick.wong@oracle.com \
    --cc=dchinner@redhat.com \
    --cc=dm-devel@redhat.com \
    --cc=dsterba@suse.com \
    --cc=gaoxiang25@huawei.com \
    --cc=hch@lst.de \
    --cc=kent.overstreet@gmail.com \
    --cc=linux-bcache@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-raid@vger.kernel.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=ooo@electrozaur.com \
    --cc=osandov@fb.com \
    --cc=rpeterso@redhat.com \
    --cc=sagi@grimberg.me \
    --cc=snitzer@redhat.com \
    --cc=tytso@mit.edu \
    --cc=viro@zeniv.linux.org.uk \
    /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

Linux-BTRFS Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-btrfs/0 linux-btrfs/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-btrfs linux-btrfs/ https://lore.kernel.org/linux-btrfs \
		linux-btrfs@vger.kernel.org linux-btrfs@archiver.kernel.org
	public-inbox-index linux-btrfs

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-btrfs


AGPL code for this site: git clone https://public-inbox.org/ public-inbox