From: John Garry <john.g.garry@oracle.com>
To: david@fromorbit.com, djwong@kernel.org, hch@lst.de,
viro@zeniv.linux.org.uk, brauner@kernel.org, jack@suse.cz,
chandan.babu@oracle.com, willy@infradead.org
Cc: axboe@kernel.dk, martin.petersen@oracle.com,
linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
tytso@mit.edu, jbongio@google.com, ojaswin@linux.ibm.com,
ritesh.list@gmail.com, mcgrof@kernel.org, p.raghav@samsung.com,
linux-xfs@vger.kernel.org, catherine.hoang@oracle.com,
John Garry <john.g.garry@oracle.com>
Subject: [PATCH v3 15/21] fs: xfs: iomap: Sub-extent zeroing
Date: Mon, 29 Apr 2024 17:47:40 +0000 [thread overview]
Message-ID: <20240429174746.2132161-16-john.g.garry@oracle.com> (raw)
In-Reply-To: <20240429174746.2132161-1-john.g.garry@oracle.com>
Set iomap->extent_size when sub-extent zeroing is required.
We treat a sub-extent write same as an unaligned write, so we can leverage
the existing sub-FSblock unaligned write support, i.e. try a shared lock
with IOMAP_DIO_OVERWRITE_ONLY flag, if this fails then try the exclusive
lock.
In xfs_iomap_write_unwritten(), FSB calcs are now based on the extsize.
Signed-off-by: John Garry <john.g.garry@oracle.com>
---
fs/xfs/xfs_file.c | 35 ++++++++++++++++++++++-------------
fs/xfs/xfs_iomap.c | 13 +++++++++++--
2 files changed, 33 insertions(+), 15 deletions(-)
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index e81e01e6b22b..ee4f94cf6f4e 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -620,18 +620,19 @@ xfs_file_dio_write_aligned(
* Handle block unaligned direct I/O writes
*
* In most cases direct I/O writes will be done holding IOLOCK_SHARED, allowing
- * them to be done in parallel with reads and other direct I/O writes. However,
- * if the I/O is not aligned to filesystem blocks, the direct I/O layer may need
- * to do sub-block zeroing and that requires serialisation against other direct
- * I/O to the same block. In this case we need to serialise the submission of
- * the unaligned I/O so that we don't get racing block zeroing in the dio layer.
- * In the case where sub-block zeroing is not required, we can do concurrent
- * sub-block dios to the same block successfully.
+ * them to be done in parallel with reads and other direct I/O writes.
+ * However if the I/O is not aligned to filesystem blocks/extent, the direct
+ * I/O layer may need to do sub-block/extent zeroing and that requires
+ * serialisation against other direct I/O to the same block/extent. In this
+ * case we need to serialise the submission of the unaligned I/O so that we
+ * don't get racing block/extent zeroing in the dio layer.
+ * In the case where sub-block/extent zeroing is not required, we can do
+ * concurrent sub-block/extent dios to the same block/extent successfully.
*
* Optimistically submit the I/O using the shared lock first, but use the
* IOMAP_DIO_OVERWRITE_ONLY flag to tell the lower layers to return -EAGAIN
- * if block allocation or partial block zeroing would be required. In that case
- * we try again with the exclusive lock.
+ * if block/extent allocation or partial block/extent zeroing would be
+ * required. In that case we try again with the exclusive lock.
*/
static noinline ssize_t
xfs_file_dio_write_unaligned(
@@ -646,9 +647,9 @@ xfs_file_dio_write_unaligned(
ssize_t ret;
/*
- * Extending writes need exclusivity because of the sub-block zeroing
- * that the DIO code always does for partial tail blocks beyond EOF, so
- * don't even bother trying the fast path in this case.
+ * Extending writes need exclusivity because of the sub-block/extent
+ * zeroing that the DIO code always does for partial tail blocks
+ * beyond EOF, so don't even bother trying the fast path in this case.
*/
if (iocb->ki_pos > isize || iocb->ki_pos + count >= isize) {
if (iocb->ki_flags & IOCB_NOWAIT)
@@ -714,11 +715,19 @@ xfs_file_dio_write(
struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp));
struct xfs_buftarg *target = xfs_inode_buftarg(ip);
size_t count = iov_iter_count(from);
+ struct xfs_mount *mp = ip->i_mount;
+ unsigned int blockmask;
/* direct I/O must be aligned to device logical sector size */
if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
return -EINVAL;
- if ((iocb->ki_pos | count) & ip->i_mount->m_blockmask)
+
+ if (xfs_inode_has_forcealign(ip) && ip->i_extsize > 1)
+ blockmask = XFS_FSB_TO_B(mp, ip->i_extsize) - 1;
+ else
+ blockmask = mp->m_blockmask;
+
+ if ((iocb->ki_pos | count) & blockmask)
return xfs_file_dio_write_unaligned(ip, iocb, from);
return xfs_file_dio_write_aligned(ip, iocb, from);
}
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 4087af7f3c9f..1a3692bbc84d 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -138,6 +138,8 @@ xfs_bmbt_to_iomap(
iomap->validity_cookie = sequence_cookie;
iomap->folio_ops = &xfs_iomap_folio_ops;
+ if (xfs_inode_has_forcealign(ip) && ip->i_extsize > 1)
+ iomap->extent_size = XFS_FSB_TO_B(mp, ip->i_extsize);
return 0;
}
@@ -570,8 +572,15 @@ xfs_iomap_write_unwritten(
trace_xfs_unwritten_convert(ip, offset, count);
- offset_fsb = XFS_B_TO_FSBT(mp, offset);
- count_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
+ if (xfs_inode_has_forcealign(ip) && ip->i_extsize > 1) {
+ xfs_extlen_t extsize_bytes = mp->m_sb.sb_blocksize * ip->i_extsize;
+
+ offset_fsb = XFS_B_TO_FSBT(mp, round_down(offset, extsize_bytes));
+ count_fsb = XFS_B_TO_FSB(mp, round_up(offset + count, extsize_bytes));
+ } else {
+ offset_fsb = XFS_B_TO_FSBT(mp, offset);
+ count_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
+ }
count_fsb = (xfs_filblks_t)(count_fsb - offset_fsb);
/*
--
2.31.1
next prev parent reply other threads:[~2024-04-29 17:49 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-29 17:47 [PATCH v3 00/21] block atomic writes for XFS John Garry
2024-04-29 17:47 ` [PATCH v3 01/21] fs: Add generic_atomic_write_valid_size() John Garry
2024-04-29 17:47 ` [PATCH v3 02/21] xfs: only allow minlen allocations when near ENOSPC John Garry
2024-04-29 17:47 ` [PATCH v3 03/21] xfs: always tail align maxlen allocations John Garry
2024-04-29 17:47 ` [PATCH v3 04/21] xfs: simplify extent allocation alignment John Garry
2024-04-29 17:47 ` [PATCH v3 05/21] xfs: make EOF allocation simpler John Garry
2024-04-29 17:47 ` [PATCH v3 06/21] xfs: introduce forced allocation alignment John Garry
2024-04-29 17:47 ` [PATCH v3 07/21] fs: xfs: align args->minlen for " John Garry
2024-06-05 14:26 ` John Garry
2024-06-06 8:47 ` Dave Chinner
2024-06-06 16:22 ` John Garry
2024-06-07 6:04 ` John Garry
2024-04-29 17:47 ` [PATCH v3 08/21] xfs: Introduce FORCEALIGN inode flag John Garry
2024-04-30 23:22 ` Dave Chinner
2024-05-01 10:03 ` John Garry
2024-05-02 0:50 ` Dave Chinner
2024-05-02 7:56 ` John Garry
2024-06-12 2:10 ` Long Li
2024-06-12 6:55 ` John Garry
2024-04-29 17:47 ` [PATCH v3 09/21] xfs: Do not free EOF blocks for forcealign John Garry
2024-04-30 22:54 ` Dave Chinner
2024-05-01 8:30 ` John Garry
2024-05-02 1:11 ` Dave Chinner
2024-05-02 8:55 ` John Garry
2024-04-29 17:47 ` [PATCH v3 10/21] xfs: Update xfs_is_falloc_aligned() mask " John Garry
2024-04-30 23:35 ` Dave Chinner
2024-05-01 10:48 ` John Garry
2024-05-01 23:45 ` Darrick J. Wong
2024-04-29 17:47 ` [PATCH RFC v3 11/21] xfs: Unmap blocks according to forcealign John Garry
2024-05-01 0:10 ` Dave Chinner
2024-05-01 10:54 ` John Garry
2024-06-06 9:50 ` John Garry
2024-04-29 17:47 ` [PATCH RFC v3 12/21] xfs: Only free full extents for forcealign John Garry
2024-05-01 0:53 ` Dave Chinner
2024-05-01 11:24 ` John Garry
2024-05-01 23:53 ` Darrick J. Wong
2024-05-02 3:12 ` Dave Chinner
2024-04-29 17:47 ` [PATCH v3 13/21] xfs: Enable file data forcealign feature John Garry
2024-04-29 17:47 ` [PATCH v3 14/21] iomap: Sub-extent zeroing John Garry
2024-05-01 1:07 ` Dave Chinner
2024-05-01 10:23 ` John Garry
2024-05-30 10:40 ` John Garry
2024-06-11 3:10 ` Long Li
2024-06-11 7:29 ` John Garry
2024-04-29 17:47 ` John Garry [this message]
2024-05-01 1:32 ` [PATCH v3 15/21] fs: xfs: " Dave Chinner
2024-05-01 11:36 ` John Garry
2024-05-02 1:26 ` Dave Chinner
2024-04-29 17:47 ` [PATCH v3 16/21] fs: Add FS_XFLAG_ATOMICWRITES flag John Garry
2024-04-29 17:47 ` [PATCH v3 17/21] iomap: Atomic write support John Garry
2024-05-01 1:47 ` Dave Chinner
2024-05-01 11:08 ` John Garry
2024-05-02 1:43 ` Dave Chinner
2024-05-02 9:12 ` John Garry
2024-04-29 17:47 ` [PATCH v3 18/21] xfs: Support FS_XFLAG_ATOMICWRITES for forcealign John Garry
2024-04-29 17:47 ` [PATCH v3 19/21] xfs: Support atomic write for statx John Garry
2024-04-29 17:47 ` [PATCH v3 20/21] xfs: Validate atomic writes John Garry
2024-04-29 17:47 ` [PATCH v3 21/21] xfs: Support setting FMODE_CAN_ATOMIC_WRITE John Garry
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=20240429174746.2132161-16-john.g.garry@oracle.com \
--to=john.g.garry@oracle.com \
--cc=axboe@kernel.dk \
--cc=brauner@kernel.org \
--cc=catherine.hoang@oracle.com \
--cc=chandan.babu@oracle.com \
--cc=david@fromorbit.com \
--cc=djwong@kernel.org \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=jbongio@google.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=mcgrof@kernel.org \
--cc=ojaswin@linux.ibm.com \
--cc=p.raghav@samsung.com \
--cc=ritesh.list@gmail.com \
--cc=tytso@mit.edu \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.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 read-only IMAP folder(s) and NNTP newsgroup(s).