Linux EXT4 FS development
 help / color / mirror / Atom feed
From: "Darrick J. Wong" <djwong@kernel.org>
To: tytso@mit.edu
Cc: John@groves.net, linux-ext4@vger.kernel.org, miklos@szeredi.hu,
	joannelkoong@gmail.com, bernd@bsbernd.com,
	linux-fsdevel@vger.kernel.org
Subject: [PATCH 03/10] libext2fs: only fsync the unix fd if we wrote to the device
Date: Wed, 21 May 2025 17:09:01 -0700	[thread overview]
Message-ID: <174787198121.1484572.1065142120815903413.stgit@frogsfrogsfrogs> (raw)
In-Reply-To: <174787198025.1484572.10345977324531146086.stgit@frogsfrogsfrogs>

From: Darrick J. Wong <djwong@kernel.org>

As an optimization, only fsync the block device fd if we tried to  write
to the io channel.

Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
---
 lib/ext2fs/unix_io.c |   48 ++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 42 insertions(+), 6 deletions(-)


diff --git a/lib/ext2fs/unix_io.c b/lib/ext2fs/unix_io.c
index 7c5cb075d6b6b6..0fc83e471ca0fe 100644
--- a/lib/ext2fs/unix_io.c
+++ b/lib/ext2fs/unix_io.c
@@ -129,10 +129,13 @@ struct unix_cache {
 #define WRITE_DIRECT_SIZE 4	/* Must be smaller than CACHE_SIZE */
 #define READ_DIRECT_SIZE 4	/* Should be smaller than CACHE_SIZE */
 
+#define UNIX_STATE_DIRTY	(1U << 0) /* device needs fsyncing */
+
 struct unix_private_data {
 	int	magic;
 	int	dev;
 	int	flags;
+	unsigned int	state; /* UNIX_STATE_* */
 	int	align;
 	int	access_time;
 	ext2_loff_t offset;
@@ -1121,10 +1124,37 @@ static errcode_t unix_open(const char *name, int flags,
 	return unix_open_channel(name, fd, flags, channel, unix_io_manager);
 }
 
+static void mark_dirty(io_channel channel)
+{
+	struct unix_private_data *data =
+		(struct unix_private_data *) channel->private_data;
+
+	mutex_lock(data, CACHE_MTX);
+	data->state |= UNIX_STATE_DIRTY;
+	mutex_unlock(data, CACHE_MTX);
+}
+
+static errcode_t maybe_fsync(io_channel channel)
+{
+	struct unix_private_data *data =
+		(struct unix_private_data *) channel->private_data;
+	int was_dirty;
+
+	mutex_lock(data, CACHE_MTX);
+	was_dirty = data->state & UNIX_STATE_DIRTY;
+	data->state &= ~UNIX_STATE_DIRTY;
+	mutex_unlock(data, CACHE_MTX);
+
+	if (was_dirty && fsync(data->dev) != 0)
+		return errno;
+
+	return 0;
+}
+
 static errcode_t unix_close(io_channel channel)
 {
 	struct unix_private_data *data;
-	errcode_t	retval = 0;
+	errcode_t	retval = 0, retval2;
 
 	EXT2_CHECK_MAGIC(channel, EXT2_ET_MAGIC_IO_CHANNEL);
 	data = (struct unix_private_data *) channel->private_data;
@@ -1137,8 +1167,9 @@ static errcode_t unix_close(io_channel channel)
 	retval = flush_cached_blocks(channel, data, 0);
 #endif
 	/* always fsync the device, even if flushing our own cache failed */
-	if (fsync(data->dev) != 0 && !retval)
-		retval = errno;
+	retval2 = maybe_fsync(channel);
+	if (retval2 && !retval)
+		retval = retval2;
 
 	if (close(data->dev) < 0 && !retval)
 		retval = errno;
@@ -1306,6 +1337,8 @@ static errcode_t unix_write_blk64(io_channel channel, unsigned long long block,
 	data = (struct unix_private_data *) channel->private_data;
 	EXT2_CHECK_MAGIC(data, EXT2_ET_MAGIC_UNIX_IO_CHANNEL);
 
+	mark_dirty(channel);
+
 #ifdef NO_IO_CACHE
 	return raw_write_blk(channel, data, block, count, buf, 0);
 #else
@@ -1430,6 +1463,8 @@ static errcode_t unix_write_byte(io_channel channel, unsigned long offset,
 	if (lseek(data->dev, offset + data->offset, SEEK_SET) < 0)
 		return errno;
 
+	mark_dirty(channel);
+
 	actual = write(data->dev, buf, size);
 	if (actual < 0)
 		return errno;
@@ -1445,7 +1480,7 @@ static errcode_t unix_write_byte(io_channel channel, unsigned long offset,
 static errcode_t unix_flush(io_channel channel)
 {
 	struct unix_private_data *data;
-	errcode_t retval = 0;
+	errcode_t retval = 0, retval2;
 
 	EXT2_CHECK_MAGIC(channel, EXT2_ET_MAGIC_IO_CHANNEL);
 	data = (struct unix_private_data *) channel->private_data;
@@ -1456,8 +1491,9 @@ static errcode_t unix_flush(io_channel channel)
 #endif
 #ifdef HAVE_FSYNC
 	/* always fsync the device, even if flushing our own cache failed */
-	if (fsync(data->dev) != 0 && !retval)
-		return errno;
+	retval2 = maybe_fsync(channel);
+	if (retval2 && !retval)
+		retval = retval2;
 #endif
 	return retval;
 }


  parent reply	other threads:[~2025-05-22  0:09 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-05-21 23:58 [RFC[RAP]] fuse: use fs-iomap for better performance so we can containerize ext4 Darrick J. Wong
2025-05-22  0:01 ` [PATCHSET 1/3] fuse2fs: upgrade to libfuse 3.17 Darrick J. Wong
2025-05-22  0:07   ` [PATCH 1/3] fuse2fs: bump library version Darrick J. Wong
2025-05-22  0:07   ` [PATCH 2/3] fuse2fs: wrap the fuse_set_feature_flag helper for older libfuse Darrick J. Wong
2025-05-22  0:08   ` [PATCH 3/3] fuse2fs: disable nfs exports Darrick J. Wong
2025-05-22  0:02 ` [PATCHSET RFC[RAP] 2/3] libext2fs: refactoring for fuse2fs iomap support Darrick J. Wong
2025-05-22  0:08   ` [PATCH 01/10] libext2fs: always fsync the device when flushing the cache Darrick J. Wong
2025-05-22  0:08   ` [PATCH 02/10] libext2fs: always fsync the device when closing the unix IO manager Darrick J. Wong
2025-05-22  0:09   ` Darrick J. Wong [this message]
2025-05-22  0:09   ` [PATCH 04/10] libext2fs: invalidate cached blocks when freeing them Darrick J. Wong
2025-05-22  0:09   ` [PATCH 05/10] libext2fs: add tagged block IO for better caching Darrick J. Wong
2025-05-22  0:09   ` [PATCH 06/10] libext2fs: add tagged block IO caching to the unix IO manager Darrick J. Wong
2025-05-22  0:10   ` [PATCH 07/10] libext2fs: only flush affected blocks in unix_write_byte Darrick J. Wong
2025-05-22  0:10   ` [PATCH 08/10] libext2fs: allow unix_write_byte when the write would be aligned Darrick J. Wong
2025-05-22  0:10   ` [PATCH 09/10] libext2fs: allow clients to ask to write full superblocks Darrick J. Wong
2025-05-22  0:10   ` [PATCH 10/10] libext2fs: allow callers to disallow I/O to file data blocks Darrick J. Wong
2025-05-22  0:02 ` [PATCHSET RFC[RAP] 3/3] fuse2fs: use fuse iomap data paths for better file I/O performance Darrick J. Wong
2025-05-22  0:11   ` [PATCH 01/16] fuse2fs: implement bare minimum iomap for file mapping reporting Darrick J. Wong
2025-05-22  0:11   ` [PATCH 02/16] fuse2fs: register block devices for use with iomap Darrick J. Wong
2025-05-22  0:11   ` [PATCH 03/16] fuse2fs: always use directio disk reads with fuse2fs Darrick J. Wong
2025-05-22  0:11   ` [PATCH 04/16] fuse2fs: implement directio file reads Darrick J. Wong
2025-05-22  0:12   ` [PATCH 05/16] fuse2fs: use tagged block IO for zeroing sub-block regions Darrick J. Wong
2025-05-22  0:12   ` [PATCH 06/16] fuse2fs: only flush the cache for the file under directio read Darrick J. Wong
2025-05-22  0:12   ` [PATCH 07/16] fuse2fs: add extent dump function for debugging Darrick J. Wong
2025-05-22  0:12   ` [PATCH 08/16] fuse2fs: implement direct write support Darrick J. Wong
2025-05-22  0:13   ` [PATCH 09/16] fuse2fs: turn on iomap for pagecache IO Darrick J. Wong
2025-05-22  0:13   ` [PATCH 10/16] fuse2fs: flush and invalidate the buffer cache on trim Darrick J. Wong
2025-05-22  0:13   ` [PATCH 11/16] fuse2fs: improve tracing for fallocate Darrick J. Wong
2025-05-22  0:13   ` [PATCH 12/16] fuse2fs: don't zero bytes in punch hole Darrick J. Wong
2025-05-22  0:14   ` [PATCH 13/16] fuse2fs: don't do file data block IO when iomap is enabled Darrick J. Wong
2025-05-22  0:14   ` [PATCH 14/16] fuse2fs: disable most io channel flush/invalidate in iomap pagecache mode Darrick J. Wong
2025-05-22  0:14   ` [PATCH 15/16] fuse2fs: re-enable the block device pagecache for metadata IO Darrick J. Wong
2025-05-22  0:15   ` [PATCH 16/16] fuse2fs: avoid fuseblk mode if fuse-iomap support is likely Darrick J. Wong
2025-05-22 16:24 ` [RFC[RAP]] fuse: use fs-iomap for better performance so we can containerize ext4 Amir Goldstein
2025-05-29 16:45   ` Darrick J. Wong
2025-05-29 19:41     ` Amir Goldstein
2025-06-09 22:31       ` Darrick J. Wong
2025-06-10 10:59         ` Amir Goldstein
2025-06-10 19:00           ` Darrick J. Wong
2025-06-10 19:51             ` Amir Goldstein
2025-06-11  6:00               ` Darrick J. Wong
2025-06-11  8:54                 ` Amir Goldstein
2025-06-12  5:54                   ` Miklos Szeredi
2025-06-13 17:44                     ` Darrick J. Wong
2025-06-11 11:56             ` Theodore Ts'o
2025-06-12  3:20               ` Darrick J. Wong
2025-06-12  6:10                 ` Amir Goldstein
2025-06-20  8:58               ` Allison Karlitskaya
2025-06-20 11:50                 ` Bernd Schubert
2025-07-01  6:02                   ` Darrick J. Wong
2025-07-01  5:58                 ` Darrick J. Wong
2025-07-12 10:57       ` Amir Goldstein
2025-06-13 17:37   ` [RFC[RAP] V2] " Darrick J. Wong
2025-06-23 13:16     ` Miklos Szeredi
2025-07-01  6:05       ` Darrick J. Wong

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=174787198121.1484572.1065142120815903413.stgit@frogsfrogsfrogs \
    --to=djwong@kernel.org \
    --cc=John@groves.net \
    --cc=bernd@bsbernd.com \
    --cc=joannelkoong@gmail.com \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=miklos@szeredi.hu \
    --cc=tytso@mit.edu \
    /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