From: Naohiro Aota <naohiro.aota@wdc.com>
To: linux-btrfs@vger.kernel.org, dsterba@suse.com
Cc: hare@suse.com, linux-fsdevel@vger.kernel.org,
Naohiro Aota <naohiro.aota@wdc.com>
Subject: [PATCH v8 23/41] btrfs: split ordered extent when bio is sent
Date: Fri, 2 Oct 2020 03:36:30 +0900 [thread overview]
Message-ID: <d193aa0f9ddaa4c008158851b16d7bfe220904cd.1601574234.git.naohiro.aota@wdc.com> (raw)
In-Reply-To: <dece91bca322ce44bed19f2b0f460fa5ded2e512.1601574234.git.naohiro.aota@wdc.com>
The device decides the written location of ZONE_APPEND write IO. Thus, we
cannot ensure two bios to be written continuously on the device. So, we
need to follow "one bio == one ordered extent" rule to ensure the region of
ordered extent maps to contiguous region on the disk.
This commit implements splitting of an ordered extent and an extent map on
submitting bio to follow the rule.
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
fs/btrfs/inode.c | 87 +++++++++++++++++++++++++++++++++++++++++
fs/btrfs/ordered-data.c | 73 ++++++++++++++++++++++++++++++++++
fs/btrfs/ordered-data.h | 2 +
3 files changed, 162 insertions(+)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 36efed0a24de..4bc975eafbd8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2158,6 +2158,87 @@ static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio,
return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
}
+int extract_ordered_extent(struct inode *inode, struct bio *bio)
+{
+ struct btrfs_ordered_extent *ordered;
+ struct extent_map *em = NULL, *em_new = NULL;
+ struct page *page = bio_first_bvec_all(bio)->bv_page;
+ struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+ u64 start = (u64)bio->bi_iter.bi_sector << SECTOR_SHIFT;
+ u64 len = bio->bi_iter.bi_size;
+ u64 end = start + len;
+ u64 ordered_end;
+ u64 pre, post;
+ int ret = 0;
+
+ ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode),
+ page_offset(page));
+ if (WARN_ON_ONCE(!ordered))
+ return -EIO;
+
+ /* no need to split */
+ if (ordered->disk_num_bytes == len)
+ goto out;
+
+ /* cannot split once end_bio'd ordered extent */
+ if (WARN_ON_ONCE(ordered->bytes_left != ordered->disk_num_bytes)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* we cannot split compressed ordered extent */
+ if (WARN_ON_ONCE(ordered->disk_num_bytes != ordered->num_bytes)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* cannot split waietd ordered extent */
+ if (WARN_ON_ONCE(wq_has_sleeper(&ordered->wait))) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ordered_end = ordered->disk_bytenr + ordered->disk_num_bytes;
+ /* bio must be in one ordered extent */
+ if (WARN_ON_ONCE(start < ordered->disk_bytenr || end > ordered_end)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* checksum list should be empty */
+ if (WARN_ON_ONCE(!list_empty(&ordered->list))) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ pre = start - ordered->disk_bytenr;
+ post = ordered_end - end;
+
+ btrfs_split_ordered_extent(ordered, pre, post);
+
+ read_lock(&em_tree->lock);
+ em = lookup_extent_mapping(em_tree, ordered->file_offset, len);
+ if (!em) {
+ read_unlock(&em_tree->lock);
+ ret = -EIO;
+ goto out;
+ }
+ read_unlock(&em_tree->lock);
+
+ ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags));
+ em_new = create_io_em(BTRFS_I(inode), em->start + pre, len,
+ em->start + pre, em->block_start + pre, len,
+ len, len, BTRFS_COMPRESS_NONE,
+ BTRFS_ORDERED_REGULAR);
+ free_extent_map(em_new);
+
+out:
+ free_extent_map(em);
+ btrfs_put_ordered_extent(ordered);
+
+ return ret;
+}
+
/*
* extent_io.c submission hook. This does the right thing for csum calculation
* on write, or reading the csums from the tree before a read.
@@ -2192,6 +2273,12 @@ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio,
if (btrfs_is_free_space_inode(BTRFS_I(inode)))
metadata = BTRFS_WQ_ENDIO_FREE_SPACE;
+ if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+ ret = extract_ordered_extent(inode, bio);
+ if (ret)
+ goto out;
+ }
+
if (bio_op(bio) != REQ_OP_WRITE) {
ret = btrfs_bio_wq_end_io(fs_info, bio, metadata);
if (ret)
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 87bac9ecdf4c..7cd22cb07f26 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -943,6 +943,79 @@ void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start,
}
}
+static void clone_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pos,
+ u64 len)
+{
+ struct inode *inode = ordered->inode;
+ u64 file_offset = ordered->file_offset + pos;
+ u64 disk_bytenr = ordered->disk_bytenr + pos;
+ u64 num_bytes = len;
+ u64 disk_num_bytes = len;
+ int type;
+ unsigned long flags_masked =
+ ordered->flags & ~(1 << BTRFS_ORDERED_DIRECT);
+ int compress_type = ordered->compress_type;
+ unsigned long weight;
+
+ weight = hweight_long(flags_masked);
+ WARN_ON_ONCE(weight > 1);
+ if (!weight)
+ type = 0;
+ else
+ type = __ffs(flags_masked);
+
+ ASSERT(!test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags));
+ if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered->flags)) {
+ WARN_ON_ONCE(1);
+ btrfs_add_ordered_extent_compress(BTRFS_I(inode), file_offset,
+ disk_bytenr, num_bytes,
+ disk_num_bytes, type,
+ compress_type);
+ } else {
+ btrfs_add_ordered_extent(BTRFS_I(inode), file_offset,
+ disk_bytenr, num_bytes, disk_num_bytes,
+ type);
+ }
+}
+
+void btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre,
+ u64 post)
+{
+ struct inode *inode = ordered->inode;
+ struct btrfs_ordered_inode_tree *tree = &BTRFS_I(inode)->ordered_tree;
+ struct rb_node *node;
+ struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+
+ spin_lock_irq(&tree->lock);
+ /* remove from tree once */
+ node = &ordered->rb_node;
+ rb_erase(node, &tree->tree);
+ RB_CLEAR_NODE(node);
+ if (tree->last == node)
+ tree->last = NULL;
+
+ ordered->file_offset += pre;
+ ordered->disk_bytenr += pre;
+ ordered->num_bytes -= (pre + post);
+ ordered->disk_num_bytes -= (pre + post);
+ ordered->bytes_left -= (pre + post);
+
+ /* re-insert the node */
+ node = tree_insert(&tree->tree, ordered->file_offset,
+ &ordered->rb_node);
+ if (node)
+ btrfs_panic(fs_info, -EEXIST,
+ "inconsistency in ordered tree at offset %llu",
+ ordered->file_offset);
+
+ spin_unlock_irq(&tree->lock);
+
+ if (pre)
+ clone_ordered_extent(ordered, 0, pre);
+ if (post)
+ clone_ordered_extent(ordered, pre + ordered->disk_num_bytes, post);
+}
+
int __init ordered_data_init(void)
{
btrfs_ordered_extent_cache = kmem_cache_create("btrfs_ordered_extent",
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index c3a2325e64a4..e346b03bd66a 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -193,6 +193,8 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start,
u64 end,
struct extent_state **cached_state);
+void btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre,
+ u64 post);
int __init ordered_data_init(void);
void __cold ordered_data_exit(void);
--
2.27.0
next prev parent reply other threads:[~2020-10-01 18:39 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-01 18:36 [PATCH v8 00/41] btrfs: zoned block device support Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 01/41] block: add bio_add_zone_append_page Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 02/41] btrfs: introduce ZONED feature flag Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 03/41] btrfs: Get zone information of zoned block devices Naohiro Aota
2020-10-13 15:53 ` David Sterba
2020-10-15 7:45 ` Johannes Thumshirn
2020-10-01 18:36 ` [PATCH v8 04/41] btrfs: Check and enable ZONED mode Naohiro Aota
2020-10-13 15:56 ` David Sterba
2020-10-28 14:49 ` Johannes Thumshirn
2020-10-13 16:13 ` David Sterba
2020-10-01 18:36 ` [PATCH v8 05/41] btrfs: introduce max_zone_append_size Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 06/41] btrfs: disallow space_cache in ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 07/41] btrfs: disallow NODATACOW " Naohiro Aota
2020-10-13 15:39 ` David Sterba
2020-10-21 8:53 ` Johannes Thumshirn
2020-10-01 18:36 ` [PATCH v8 08/41] btrfs: disable fallocate " Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 09/41] btrfs: disallow mixed-bg " Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 10/41] btrfs: disallow inode_cache " Naohiro Aota
2020-10-13 15:41 ` David Sterba
2020-10-22 6:48 ` Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 11/41] btrfs: implement log-structured superblock for " Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 12/41] btrfs: implement zoned chunk allocator Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 13/41] btrfs: verify device extent is aligned to zone Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 14/41] btrfs: load zone's alloction offset Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 15/41] btrfs: emulate write pointer for conventional zones Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 16/41] btrfs: track unusable bytes for zones Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 17/41] btrfs: do sequential extent allocation in ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 18/41] btrfs: reset zones of unused block groups Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 19/41] btrfs: redirty released extent buffers in ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 20/41] btrfs: extract page adding function Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 21/41] btrfs: use bio_add_zone_append_page for zoned btrfs Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 22/41] btrfs: handle REQ_OP_ZONE_APPEND as writing Naohiro Aota
2020-10-01 18:36 ` Naohiro Aota [this message]
2020-10-01 18:36 ` [PATCH v8 24/41] btrfs: extend btrfs_rmap_block for specifying a device Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 25/41] btrfs: use ZONE_APPEND write for ZONED btrfs Naohiro Aota
2020-10-13 16:45 ` David Sterba
2020-10-01 18:36 ` [PATCH v8 26/41] btrfs: enable zone append writing for direct IO Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 27/41] btrfs: introduce dedicated data write path for ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 28/41] btrfs: serialize meta IOs on " Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 29/41] btrfs: wait existing extents before truncating Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 30/41] btrfs: avoid async metadata checksum on ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 31/41] btrfs: mark block groups to copy for device-replace Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 32/41] btrfs: implement cloning for ZONED device-replace Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 33/41] btrfs: implement copying " Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 34/41] btrfs: support dev-replace in ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 35/41] btrfs: enable relocation " Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 36/41] btrfs: relocate block group to repair IO failure in ZONED Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 37/41] btrfs: split alloc_log_tree() Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 38/41] btrfs: extend zoned allocator to use dedicated tree-log block group Naohiro Aota
2020-10-13 16:26 ` David Sterba
2020-10-15 7:21 ` Johannes Thumshirn
2020-10-01 18:36 ` [PATCH v8 39/41] btrfs: serialize log transaction on ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 40/41] btrfs: reorder log node allocation Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 41/41] btrfs: enable to mount ZONED incompat flag Naohiro Aota
2020-10-02 13:39 ` [PATCH v8 01/41] block: add bio_add_zone_append_page Martin K. Petersen
2020-10-05 1:46 ` Damien Le Moal
2020-10-05 13:43 ` Christoph Hellwig
2020-10-06 1:26 ` Martin K. Petersen
2020-10-06 5:12 ` Damien Le Moal
2020-10-09 15:40 ` [PATCH v8 00/41] btrfs: zoned block device support Josef Bacik
2020-10-12 9:17 ` Naohiro Aota
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=d193aa0f9ddaa4c008158851b16d7bfe220904cd.1601574234.git.naohiro.aota@wdc.com \
--to=naohiro.aota@wdc.com \
--cc=dsterba@suse.com \
--cc=hare@suse.com \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@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.