All of lore.kernel.org
 help / color / mirror / Atom feed
From: Qu Wenruo <wqu@suse.com>
To: linux-btrfs@vger.kernel.org
Cc: linux-block@vger.kernel.org, dm-devel@redhat.com
Subject: [PATCH 13/17] btrfs: allow btrfs_map_bio() to split bio according to chunk stripe boundaries
Date: Wed,  1 Dec 2021 13:17:52 +0800	[thread overview]
Message-ID: <20211201051756.53742-14-wqu@suse.com> (raw)
In-Reply-To: <20211201051756.53742-1-wqu@suse.com>

With the new btrfs_bio_split() helper, we are able to split bio
according to chunk stripe boundaries at btrfs_map_bio() time.

Although currently due bio split at buffered/compressed/direct IO time,
this ability is not yet utilized.

Signed-off-by: Qu Wenruo <wqu@suse.com>
---
 fs/btrfs/volumes.c | 48 ++++++++++++++++++++++++++++++----------------
 1 file changed, 31 insertions(+), 17 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 365e43bbfd14..35ba1ea95295 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6893,29 +6893,43 @@ static int submit_one_mapped_range(struct btrfs_fs_info *fs_info, struct bio *bi
 blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 			   int mirror_num)
 {
-	u64 logical = bio->bi_iter.bi_sector << 9;
-	u64 length = 0;
-	u64 map_length;
+	const u64 orig_logical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
+	const unsigned int orig_length = bio->bi_iter.bi_size;
+	const enum btrfs_map_op op = btrfs_op(bio);
+	u64 cur_logical = orig_logical;
 	int ret;
-	struct btrfs_io_context *bioc = NULL;
 
-	length = bio->bi_iter.bi_size;
-	map_length = length;
+	while (cur_logical < orig_logical + orig_length) {
+		u64 map_length = orig_logical + orig_length - cur_logical;
+		struct btrfs_io_context *bioc = NULL;
+		struct bio *cur_bio;
 
-	btrfs_bio_counter_inc_blocked(fs_info);
-	ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical,
-				&map_length, &bioc, mirror_num, 1);
-	if (ret) {
-		btrfs_bio_counter_dec(fs_info);
-		return errno_to_blk_status(ret);
-	}
+		ret = __btrfs_map_block(fs_info, op, cur_logical, &map_length,
+					&bioc, mirror_num, 1);
+		if (ret)
+			return errno_to_blk_status(ret);
 
-	ret = submit_one_mapped_range(fs_info, bio, bioc, map_length, mirror_num);
-	if (ret < 0) {
+		if (cur_logical + map_length < orig_logical + orig_length) {
+			/*
+			 * For now zoned write should never cross stripe
+			 * boundary
+			 */
+			ASSERT(bio_op(bio) != REQ_OP_ZONE_APPEND);
+
+			/* Split the bio */
+			cur_bio = btrfs_bio_split(fs_info, bio, map_length);
+		} else {
+			/* Use the existing bio directly */
+			cur_bio = bio;
+		}
+		btrfs_bio_counter_inc_blocked(fs_info);
+		ret = submit_one_mapped_range(fs_info, cur_bio, bioc,
+					      map_length, mirror_num);
 		btrfs_bio_counter_dec(fs_info);
-		return errno_to_blk_status(ret);
+		if (ret < 0)
+			return errno_to_blk_status(ret);
+		cur_logical += map_length;
 	}
-	btrfs_bio_counter_dec(fs_info);
 	return BLK_STS_OK;
 }
 
-- 
2.34.1


WARNING: multiple messages have this Message-ID (diff)
From: Qu Wenruo <wqu@suse.com>
To: linux-btrfs@vger.kernel.org
Cc: linux-block@vger.kernel.org, dm-devel@redhat.com
Subject: [dm-devel] [PATCH 13/17] btrfs: allow btrfs_map_bio() to split bio according to chunk stripe boundaries
Date: Wed,  1 Dec 2021 13:17:52 +0800	[thread overview]
Message-ID: <20211201051756.53742-14-wqu@suse.com> (raw)
In-Reply-To: <20211201051756.53742-1-wqu@suse.com>

With the new btrfs_bio_split() helper, we are able to split bio
according to chunk stripe boundaries at btrfs_map_bio() time.

Although currently due bio split at buffered/compressed/direct IO time,
this ability is not yet utilized.

Signed-off-by: Qu Wenruo <wqu@suse.com>
---
 fs/btrfs/volumes.c | 48 ++++++++++++++++++++++++++++++----------------
 1 file changed, 31 insertions(+), 17 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 365e43bbfd14..35ba1ea95295 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6893,29 +6893,43 @@ static int submit_one_mapped_range(struct btrfs_fs_info *fs_info, struct bio *bi
 blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 			   int mirror_num)
 {
-	u64 logical = bio->bi_iter.bi_sector << 9;
-	u64 length = 0;
-	u64 map_length;
+	const u64 orig_logical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
+	const unsigned int orig_length = bio->bi_iter.bi_size;
+	const enum btrfs_map_op op = btrfs_op(bio);
+	u64 cur_logical = orig_logical;
 	int ret;
-	struct btrfs_io_context *bioc = NULL;
 
-	length = bio->bi_iter.bi_size;
-	map_length = length;
+	while (cur_logical < orig_logical + orig_length) {
+		u64 map_length = orig_logical + orig_length - cur_logical;
+		struct btrfs_io_context *bioc = NULL;
+		struct bio *cur_bio;
 
-	btrfs_bio_counter_inc_blocked(fs_info);
-	ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical,
-				&map_length, &bioc, mirror_num, 1);
-	if (ret) {
-		btrfs_bio_counter_dec(fs_info);
-		return errno_to_blk_status(ret);
-	}
+		ret = __btrfs_map_block(fs_info, op, cur_logical, &map_length,
+					&bioc, mirror_num, 1);
+		if (ret)
+			return errno_to_blk_status(ret);
 
-	ret = submit_one_mapped_range(fs_info, bio, bioc, map_length, mirror_num);
-	if (ret < 0) {
+		if (cur_logical + map_length < orig_logical + orig_length) {
+			/*
+			 * For now zoned write should never cross stripe
+			 * boundary
+			 */
+			ASSERT(bio_op(bio) != REQ_OP_ZONE_APPEND);
+
+			/* Split the bio */
+			cur_bio = btrfs_bio_split(fs_info, bio, map_length);
+		} else {
+			/* Use the existing bio directly */
+			cur_bio = bio;
+		}
+		btrfs_bio_counter_inc_blocked(fs_info);
+		ret = submit_one_mapped_range(fs_info, cur_bio, bioc,
+					      map_length, mirror_num);
 		btrfs_bio_counter_dec(fs_info);
-		return errno_to_blk_status(ret);
+		if (ret < 0)
+			return errno_to_blk_status(ret);
+		cur_logical += map_length;
 	}
-	btrfs_bio_counter_dec(fs_info);
 	return BLK_STS_OK;
 }
 
-- 
2.34.1


--
dm-devel mailing list
dm-devel@redhat.com
https://listman.redhat.com/mailman/listinfo/dm-devel


  parent reply	other threads:[~2021-12-01  5:18 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-12-01  5:17 [PATCH 00/17] btrfs: split bio at btrfs_map_bio() time Qu Wenruo
2021-12-01  5:17 ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 01/17] btrfs: update an stale comment on btrfs_submit_bio_hook() Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 02/17] btrfs: save bio::bi_iter into btrfs_bio::iter before submitting Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01 11:52   ` Qu Wenruo
2021-12-01 11:52     ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 03/17] btrfs: use correct bio size for error message in btrfs_end_dio_bio() Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 04/17] btrfs: refactor btrfs_map_bio() Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 05/17] btrfs: move btrfs_bio_wq_end_io() calls into submit_stripe_bio() Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 06/17] btrfs: replace btrfs_dio_private::refs with btrfs_dio_private::pending_bytes Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 07/17] btrfs: introduce btrfs_bio_split() helper Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 08/17] btrfs: make data buffered read path to handle split bio properly Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 09/17] btrfs: make data buffered write endio function to be split bio compatible Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 10/17] btrfs: make metadata write endio functions " Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 11/17] btrfs: make dec_and_test_compressed_bio() " Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2022-03-16 19:46   ` Josef Bacik
2022-03-16 19:46     ` [dm-devel] " Josef Bacik
2022-03-16 23:30     ` Qu Wenruo
2022-03-16 23:30       ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 12/17] btrfs: return proper mapped length for RAID56 profiles in __btrfs_map_block() Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  6:52   ` Qu Wenruo
2021-12-01  6:52     ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` Qu Wenruo [this message]
2021-12-01  5:17   ` [dm-devel] [PATCH 13/17] btrfs: allow btrfs_map_bio() to split bio according to chunk stripe boundaries Qu Wenruo
2021-12-01  5:17 ` [PATCH 14/17] btrfs: remove buffered IO stripe boundary calculation Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 15/17] btrfs: remove stripe boundary calculation for compressed IO Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 16/17] btrfs: remove the stripe boundary calculation for direct IO Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  5:17 ` [PATCH 17/17] btrfs: unexport btrfs_get_io_geometry() Qu Wenruo
2021-12-01  5:17   ` [dm-devel] " Qu Wenruo
2021-12-01  8:57 ` [PATCH 00/17] btrfs: split bio at btrfs_map_bio() time Qu Wenruo
2021-12-01  8:57   ` [dm-devel] " Qu Wenruo

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=20211201051756.53742-14-wqu@suse.com \
    --to=wqu@suse.com \
    --cc=dm-devel@redhat.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-btrfs@vger.kernel.org \
    /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.