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,
Jens Axboe <axboe@kernel.dk>,
Christoph Hellwig <hch@infradead.org>,
"Darrick J. Wong" <darrick.wong@oracle.com>,
Naohiro Aota <naohiro.aota@wdc.com>
Subject: [PATCH v11 27/40] btrfs: introduce dedicated data write path for ZONED mode
Date: Tue, 22 Dec 2020 12:49:20 +0900 [thread overview]
Message-ID: <2b4271752514c9f376b1fc6a988336ed9238aa0d.1608608848.git.naohiro.aota@wdc.com> (raw)
In-Reply-To: <06add214bc16ef08214de1594ecdfcc4cdcdbd78.1608608848.git.naohiro.aota@wdc.com>
If more than one IO is issued for one file extent, these IO can be written
to separate regions on a device. Since we cannot map one file extent to
such a separate area, we need to follow the "one IO == one ordered extent"
rule.
The Normal buffered, uncompressed, not pre-allocated write path (used by
cow_file_range()) sometimes does not follow this rule. It can write a part
of an ordered extent when specified a region to write e.g., when its
called from fdatasync().
Introduces a dedicated (uncompressed buffered) data write path for ZONED
mode. This write path will CoW the region and write it at once.
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
fs/btrfs/inode.c | 34 ++++++++++++++++++++++++++++++++--
1 file changed, 32 insertions(+), 2 deletions(-)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5e96d9631038..5f4de6ebebbd 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1400,6 +1400,29 @@ static int cow_file_range_async(struct btrfs_inode *inode,
return 0;
}
+static noinline int run_delalloc_zoned(struct btrfs_inode *inode,
+ struct page *locked_page, u64 start,
+ u64 end, int *page_started,
+ unsigned long *nr_written)
+{
+ int ret;
+
+ ret = cow_file_range(inode, locked_page, start, end,
+ page_started, nr_written, 0);
+ if (ret)
+ return ret;
+
+ if (*page_started)
+ return 0;
+
+ __set_page_dirty_nobuffers(locked_page);
+ account_page_redirty(locked_page);
+ extent_write_locked_range(&inode->vfs_inode, start, end, WB_SYNC_ALL);
+ *page_started = 1;
+
+ return 0;
+}
+
static noinline int csum_exist_in_range(struct btrfs_fs_info *fs_info,
u64 bytenr, u64 num_bytes)
{
@@ -1879,17 +1902,24 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page
{
int ret;
int force_cow = need_force_cow(inode, start, end);
+ const bool do_compress = inode_can_compress(inode) &&
+ inode_need_compress(inode, start, end);
+ const bool zoned = btrfs_is_zoned(inode->root->fs_info);
if (inode->flags & BTRFS_INODE_NODATACOW && !force_cow) {
+ ASSERT(!zoned);
ret = run_delalloc_nocow(inode, locked_page, start, end,
page_started, 1, nr_written);
} else if (inode->flags & BTRFS_INODE_PREALLOC && !force_cow) {
+ ASSERT(!zoned);
ret = run_delalloc_nocow(inode, locked_page, start, end,
page_started, 0, nr_written);
- } else if (!inode_can_compress(inode) ||
- !inode_need_compress(inode, start, end)) {
+ } else if (!do_compress && !zoned) {
ret = cow_file_range(inode, locked_page, start, end,
page_started, nr_written, 1);
+ } else if (!do_compress && zoned) {
+ ret = run_delalloc_zoned(inode, locked_page, start, end,
+ page_started, nr_written);
} else {
set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &inode->runtime_flags);
ret = cow_file_range_async(inode, wbc, locked_page, start, end,
--
2.27.0
next prev parent reply other threads:[~2020-12-22 3:54 UTC|newest]
Thread overview: 86+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-22 3:48 [PATCH v11 00/40] btrfs: zoned block device support Naohiro Aota
2020-12-22 3:48 ` [PATCH v11 01/40] block: add bio_add_zone_append_page Naohiro Aota
2020-12-22 3:48 ` [PATCH v11 02/40] iomap: support REQ_OP_ZONE_APPEND Naohiro Aota
2021-01-04 22:30 ` Darrick J. Wong
2021-01-13 9:34 ` Johannes Thumshirn
2020-12-22 3:48 ` [PATCH v11 03/40] btrfs: defer loading zone info after opening trees Naohiro Aota
2021-01-11 19:16 ` Josef Bacik
2020-12-22 3:48 ` [PATCH v11 04/40] btrfs: change superblock location on conventional zone Naohiro Aota
2021-01-11 19:47 ` Josef Bacik
2021-01-14 15:10 ` Naohiro Aota
2020-12-22 3:48 ` [PATCH v11 05/40] btrfs: release path before calling into btrfs_load_block_group_zone_info Naohiro Aota
2021-01-11 20:01 ` Josef Bacik
2021-01-12 8:05 ` Johannes Thumshirn
2020-12-22 3:48 ` [PATCH v11 06/40] btrfs: do not load fs_info->zoned from incompat flag Naohiro Aota
2021-01-11 20:08 ` Josef Bacik
2021-01-12 8:00 ` Johannes Thumshirn
2020-12-22 3:49 ` [PATCH v11 07/40] btrfs: disallow fitrim in ZONED mode Naohiro Aota
2021-01-11 20:12 ` Josef Bacik
2021-01-12 10:19 ` Johannes Thumshirn
2020-12-22 3:49 ` [PATCH v11 08/40] btrfs: emulated zoned mode on non-zoned devices Naohiro Aota
2021-01-11 20:54 ` Josef Bacik
2021-01-13 17:58 ` David Sterba
2021-01-13 18:23 ` Johannes Thumshirn
2020-12-22 3:49 ` [PATCH v11 09/40] btrfs: implement zoned chunk allocator Naohiro Aota
2021-01-11 21:24 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 10/40] btrfs: verify device extent is aligned to zone Naohiro Aota
2020-12-22 3:49 ` [PATCH v11 11/40] btrfs: load zone's allocation offset Naohiro Aota
2020-12-22 3:49 ` [PATCH v11 12/40] btrfs: calculate allocation offset for conventional zones Naohiro Aota
2021-01-12 15:12 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 13/40] btrfs: track unusable bytes for zones Naohiro Aota
2021-01-12 15:45 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 14/40] btrfs: do sequential extent allocation in ZONED mode Naohiro Aota
2020-12-22 3:49 ` [PATCH v11 15/40] btrfs: redirty released extent buffers " Naohiro Aota
2021-01-12 15:51 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 16/40] btrfs: advance allocation pointer after tree log node Naohiro Aota
2021-01-12 15:52 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 17/40] btrfs: enable to mount ZONED incompat flag Naohiro Aota
2020-12-22 3:49 ` [PATCH v11 18/40] btrfs: reset zones of unused block groups Naohiro Aota
2021-01-12 15:54 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 19/40] btrfs: extract page adding function Naohiro Aota
2021-01-11 16:22 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 20/40] btrfs: use bio_add_zone_append_page for zoned btrfs Naohiro Aota
2021-01-12 15:55 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 21/40] btrfs: handle REQ_OP_ZONE_APPEND as writing Naohiro Aota
2020-12-22 3:49 ` [PATCH v11 22/40] btrfs: split ordered extent when bio is sent Naohiro Aota
2021-01-12 15:59 ` Josef Bacik
2021-01-13 10:05 ` Johannes Thumshirn
2021-01-15 7:08 ` Su Yue
2020-12-22 3:49 ` [PATCH v11 23/40] btrfs: extend btrfs_rmap_block for specifying a device Naohiro Aota
2021-01-12 16:00 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 24/40] btrfs: cache if block-group is on a sequential zone Naohiro Aota
2021-01-12 16:01 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 25/40] btrfs: use ZONE_APPEND write for ZONED btrfs Naohiro Aota
2020-12-22 3:49 ` [PATCH v11 26/40] btrfs: enable zone append writing for direct IO Naohiro Aota
2020-12-22 3:49 ` Naohiro Aota [this message]
2021-01-12 19:24 ` [PATCH v11 27/40] btrfs: introduce dedicated data write path for ZONED mode Josef Bacik
2021-01-13 10:41 ` Naohiro Aota
2021-01-12 19:28 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 28/40] btrfs: serialize meta IOs on " Naohiro Aota
2020-12-22 3:49 ` [PATCH v11 29/40] btrfs: wait existing extents before truncating Naohiro Aota
2020-12-22 3:49 ` [PATCH v11 30/40] btrfs: avoid async metadata checksum on ZONED mode Naohiro Aota
2020-12-22 3:49 ` [PATCH v11 31/40] btrfs: mark block groups to copy for device-replace Naohiro Aota
2021-01-12 19:30 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 32/40] btrfs: implement cloning for ZONED device-replace Naohiro Aota
2021-01-12 19:36 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 33/40] btrfs: implement copying " Naohiro Aota
2021-01-12 19:37 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 34/40] btrfs: support dev-replace in ZONED mode Naohiro Aota
2021-01-12 19:37 ` Josef Bacik
2021-01-12 19:40 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 35/40] btrfs: enable relocation " Naohiro Aota
2021-01-12 19:43 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 36/40] btrfs: relocate block group to repair IO failure in ZONED Naohiro Aota
2020-12-22 3:49 ` [PATCH v11 37/40] btrfs: split alloc_log_tree() Naohiro Aota
2021-01-12 19:44 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 38/40] btrfs: extend zoned allocator to use dedicated tree-log block group Naohiro Aota
2021-01-12 19:48 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 39/40] btrfs: serialize log transaction on ZONED mode Naohiro Aota
2021-01-12 19:50 ` Josef Bacik
2020-12-22 3:49 ` [PATCH v11 40/40] btrfs: reorder log node allocation Naohiro Aota
2020-12-22 13:35 ` [PATCH v11 01/40] block: add bio_add_zone_append_page Christoph Hellwig
2021-01-12 13:48 ` Johannes Thumshirn
2020-12-22 13:38 ` [PATCH v11 00/40] btrfs: zoned block device support Christoph Hellwig
2021-01-11 10:17 ` Johannes Thumshirn
2021-01-12 10:23 ` hch
2021-01-12 10:26 ` Johannes Thumshirn
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=2b4271752514c9f376b1fc6a988336ed9238aa0d.1608608848.git.naohiro.aota@wdc.com \
--to=naohiro.aota@wdc.com \
--cc=axboe@kernel.dk \
--cc=darrick.wong@oracle.com \
--cc=dsterba@suse.com \
--cc=hare@suse.com \
--cc=hch@infradead.org \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).