avoid taking the iolock in fsync unless actually needed

avoid taking the iolock in fsync unless actually needed

[Christoph Hellwig]

Hi all,

this series avoids taking the iolock in fsync if there is no dirty
metadata.

[PATCH 1/2] xfs: refactor xfs_file_fsync

[Christoph Hellwig]

Factor out the log syncing logic into two helpers to make the code easier
to read and more maintainable.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_file.c | 81 +++++++++++++++++++++++++++++------------------
 1 file changed, 50 insertions(+), 31 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 5b0f93f738372d..414d856e2e755a 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -118,6 +118,54 @@ xfs_dir_fsync(
 	return xfs_log_force_inode(ip);
 }
 
+static xfs_lsn_t
+xfs_fsync_lsn(
+	struct xfs_inode	*ip,
+	bool			datasync)
+{
+	if (!xfs_ipincount(ip))
+		return 0;
+	if (datasync && !(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
+		return 0;
+	return ip->i_itemp->ili_last_lsn;
+}
+
+/*
+ * All metadata updates are logged, which means that we just have to flush the
+ * log up to the latest LSN that touched the inode.
+ *
+ * If we have concurrent fsync/fdatasync() calls, we need them to all block on
+ * the log force before we clear the ili_fsync_fields field. This ensures that
+ * we don't get a racing sync operation that does not wait for the metadata to
+ * hit the journal before returning.  If we race with clearing ili_fsync_fields,
+ * then all that will happen is the log force will do nothing as the lsn will
+ * already be on disk.  We can't race with setting ili_fsync_fields because that
+ * is done under XFS_ILOCK_EXCL, and that can't happen because we hold the lock
+ * shared until after the ili_fsync_fields is cleared.
+ */
+static  int
+xfs_fsync_flush_log(
+	struct xfs_inode	*ip,
+	bool			datasync,
+	int			*log_flushed)
+{
+	int			error = 0;
+	xfs_lsn_t		lsn;
+
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
+	lsn = xfs_fsync_lsn(ip, datasync);
+	if (lsn) {
+		error = xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC,
+					  log_flushed);
+
+		spin_lock(&ip->i_itemp->ili_lock);
+		ip->i_itemp->ili_fsync_fields = 0;
+		spin_unlock(&ip->i_itemp->ili_lock);
+	}
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	return error;
+}
+
 STATIC int
 xfs_file_fsync(
 	struct file		*file,
@@ -125,13 +173,10 @@ xfs_file_fsync(
 	loff_t			end,
 	int			datasync)
 {
-	struct inode		*inode = file->f_mapping->host;
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_inode_log_item *iip = ip->i_itemp;
+	struct xfs_inode	*ip = XFS_I(file->f_mapping->host);
 	struct xfs_mount	*mp = ip->i_mount;
 	int			error = 0;
 	int			log_flushed = 0;
-	xfs_lsn_t		lsn = 0;
 
 	trace_xfs_file_fsync(ip);
 
@@ -155,33 +200,7 @@ xfs_file_fsync(
 	else if (mp->m_logdev_targp != mp->m_ddev_targp)
 		xfs_blkdev_issue_flush(mp->m_ddev_targp);
 
-	/*
-	 * All metadata updates are logged, which means that we just have to
-	 * flush the log up to the latest LSN that touched the inode. If we have
-	 * concurrent fsync/fdatasync() calls, we need them to all block on the
-	 * log force before we clear the ili_fsync_fields field. This ensures
-	 * that we don't get a racing sync operation that does not wait for the
-	 * metadata to hit the journal before returning. If we race with
-	 * clearing the ili_fsync_fields, then all that will happen is the log
-	 * force will do nothing as the lsn will already be on disk. We can't
-	 * race with setting ili_fsync_fields because that is done under
-	 * XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared
-	 * until after the ili_fsync_fields is cleared.
-	 */
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	if (xfs_ipincount(ip)) {
-		if (!datasync ||
-		    (iip->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
-			lsn = iip->ili_last_lsn;
-	}
-
-	if (lsn) {
-		error = xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
-		spin_lock(&iip->ili_lock);
-		iip->ili_fsync_fields = 0;
-		spin_unlock(&iip->ili_lock);
-	}
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	error = xfs_fsync_flush_log(ip, datasync, &log_flushed);
 
 	/*
 	 * If we only have a single device, and the log force about was
-- 
2.29.2

[PATCH 2/2] xfs: reduce ilock acquisitions in xfs_file_fsync

[Christoph Hellwig]

If the inode is not pinned by the time fsync is called we don't need the
ilock to protect against concurrent clearing of ili_fsync_fields as the
inode won't need a log flush or clearing of these fields.  Not taking
the iolock allows for full concurrency of fsync and thus O_DSYNC
completions with io_uring/aio write submissions.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_file.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 414d856e2e755a..ba02780dee6439 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -200,7 +200,8 @@ xfs_file_fsync(
 	else if (mp->m_logdev_targp != mp->m_ddev_targp)
 		xfs_blkdev_issue_flush(mp->m_ddev_targp);
 
-	error = xfs_fsync_flush_log(ip, datasync, &log_flushed);
+	if (xfs_ipincount(ip))
+		error = xfs_fsync_flush_log(ip, datasync, &log_flushed);
 
 	/*
 	 * If we only have a single device, and the log force about was
-- 
2.29.2

Re: [PATCH 1/2] xfs: refactor xfs_file_fsync

[Brian Foster]

On Mon, Jan 11, 2021 at 05:15:43PM +0100, Christoph Hellwig wrote:
> Factor out the log syncing logic into two helpers to make the code easier
> to read and more maintainable.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---

Looks fine, though it might be nice to find some commonality with
xfs_log_force_inode():

Reviewed-by: Brian Foster <bfoster@redhat.com>

>  fs/xfs/xfs_file.c | 81 +++++++++++++++++++++++++++++------------------
>  1 file changed, 50 insertions(+), 31 deletions(-)
> 
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index 5b0f93f738372d..414d856e2e755a 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -118,6 +118,54 @@ xfs_dir_fsync(
>  	return xfs_log_force_inode(ip);
>  }
>  
> +static xfs_lsn_t
> +xfs_fsync_lsn(
> +	struct xfs_inode	*ip,
> +	bool			datasync)
> +{
> +	if (!xfs_ipincount(ip))
> +		return 0;
> +	if (datasync && !(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
> +		return 0;
> +	return ip->i_itemp->ili_last_lsn;
> +}
> +
> +/*
> + * All metadata updates are logged, which means that we just have to flush the
> + * log up to the latest LSN that touched the inode.
> + *
> + * If we have concurrent fsync/fdatasync() calls, we need them to all block on
> + * the log force before we clear the ili_fsync_fields field. This ensures that
> + * we don't get a racing sync operation that does not wait for the metadata to
> + * hit the journal before returning.  If we race with clearing ili_fsync_fields,
> + * then all that will happen is the log force will do nothing as the lsn will
> + * already be on disk.  We can't race with setting ili_fsync_fields because that
> + * is done under XFS_ILOCK_EXCL, and that can't happen because we hold the lock
> + * shared until after the ili_fsync_fields is cleared.
> + */
> +static  int
> +xfs_fsync_flush_log(
> +	struct xfs_inode	*ip,
> +	bool			datasync,
> +	int			*log_flushed)
> +{
> +	int			error = 0;
> +	xfs_lsn_t		lsn;
> +
> +	xfs_ilock(ip, XFS_ILOCK_SHARED);
> +	lsn = xfs_fsync_lsn(ip, datasync);
> +	if (lsn) {
> +		error = xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC,
> +					  log_flushed);
> +
> +		spin_lock(&ip->i_itemp->ili_lock);
> +		ip->i_itemp->ili_fsync_fields = 0;
> +		spin_unlock(&ip->i_itemp->ili_lock);
> +	}
> +	xfs_iunlock(ip, XFS_ILOCK_SHARED);
> +	return error;
> +}
> +
>  STATIC int
>  xfs_file_fsync(
>  	struct file		*file,
> @@ -125,13 +173,10 @@ xfs_file_fsync(
>  	loff_t			end,
>  	int			datasync)
>  {
> -	struct inode		*inode = file->f_mapping->host;
> -	struct xfs_inode	*ip = XFS_I(inode);
> -	struct xfs_inode_log_item *iip = ip->i_itemp;
> +	struct xfs_inode	*ip = XFS_I(file->f_mapping->host);
>  	struct xfs_mount	*mp = ip->i_mount;
>  	int			error = 0;
>  	int			log_flushed = 0;
> -	xfs_lsn_t		lsn = 0;
>  
>  	trace_xfs_file_fsync(ip);
>  
> @@ -155,33 +200,7 @@ xfs_file_fsync(
>  	else if (mp->m_logdev_targp != mp->m_ddev_targp)
>  		xfs_blkdev_issue_flush(mp->m_ddev_targp);
>  
> -	/*
> -	 * All metadata updates are logged, which means that we just have to
> -	 * flush the log up to the latest LSN that touched the inode. If we have
> -	 * concurrent fsync/fdatasync() calls, we need them to all block on the
> -	 * log force before we clear the ili_fsync_fields field. This ensures
> -	 * that we don't get a racing sync operation that does not wait for the
> -	 * metadata to hit the journal before returning. If we race with
> -	 * clearing the ili_fsync_fields, then all that will happen is the log
> -	 * force will do nothing as the lsn will already be on disk. We can't
> -	 * race with setting ili_fsync_fields because that is done under
> -	 * XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared
> -	 * until after the ili_fsync_fields is cleared.
> -	 */
> -	xfs_ilock(ip, XFS_ILOCK_SHARED);
> -	if (xfs_ipincount(ip)) {
> -		if (!datasync ||
> -		    (iip->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
> -			lsn = iip->ili_last_lsn;
> -	}
> -
> -	if (lsn) {
> -		error = xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
> -		spin_lock(&iip->ili_lock);
> -		iip->ili_fsync_fields = 0;
> -		spin_unlock(&iip->ili_lock);
> -	}
> -	xfs_iunlock(ip, XFS_ILOCK_SHARED);
> +	error = xfs_fsync_flush_log(ip, datasync, &log_flushed);
>  
>  	/*
>  	 * If we only have a single device, and the log force about was
> -- 
> 2.29.2
> 

Re: [PATCH 2/2] xfs: reduce ilock acquisitions in xfs_file_fsync

[Brian Foster]

On Mon, Jan 11, 2021 at 05:15:44PM +0100, Christoph Hellwig wrote:
> If the inode is not pinned by the time fsync is called we don't need the
> ilock to protect against concurrent clearing of ili_fsync_fields as the
> inode won't need a log flush or clearing of these fields.  Not taking
> the iolock allows for full concurrency of fsync and thus O_DSYNC
> completions with io_uring/aio write submissions.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---

So this changes fsync semantics for when a concurrent modification might
already be in progress (but not yet complete) to essentially skip the
log force rather than serialize/wait and force. This seems.. reasonable
I suppose since nothign has committed at that point, but I feel like
could use more documentation and justification around that and why this
might be acceptable behavior.

Brian

>  fs/xfs/xfs_file.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index 414d856e2e755a..ba02780dee6439 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -200,7 +200,8 @@ xfs_file_fsync(
>  	else if (mp->m_logdev_targp != mp->m_ddev_targp)
>  		xfs_blkdev_issue_flush(mp->m_ddev_targp);
>  
> -	error = xfs_fsync_flush_log(ip, datasync, &log_flushed);
> +	if (xfs_ipincount(ip))
> +		error = xfs_fsync_flush_log(ip, datasync, &log_flushed);
>  
>  	/*
>  	 * If we only have a single device, and the log force about was
> -- 
> 2.29.2
> 

Re: [PATCH 1/2] xfs: refactor xfs_file_fsync

[Christoph Hellwig]

On Tue, Jan 12, 2021 at 10:33:47AM -0500, Brian Foster wrote:
> Looks fine, though it might be nice to find some commonality with
> xfs_log_force_inode():

The common logic is called xfs_log_force_lsn :)

The fact that fsync checks and modifies ili_fsync_fields makes it rather
impractival to share more code unfortunately.

Re: [PATCH 1/2] xfs: refactor xfs_file_fsync

[Dave Chinner]

On Fri, Jan 22, 2021 at 05:46:42PM +0100, Christoph Hellwig wrote:
> Factor out the log syncing logic into two helpers to make the code easier
> to read and more maintainable.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Brian Foster <bfoster@redhat.com>

LGTM.

Reviewed-by: Dave Chinner <dchinner@redhat.com>
-- 
Dave Chinner
david@fromorbit.com

[PATCH 1/2] xfs: refactor xfs_file_fsync

[Christoph Hellwig]

Factor out the log syncing logic into two helpers to make the code easier
to read and more maintainable.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/xfs_file.c | 81 +++++++++++++++++++++++++++++------------------
 1 file changed, 50 insertions(+), 31 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 39695b59dfcc92..588232c77f11e0 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -118,6 +118,54 @@ xfs_dir_fsync(
 	return xfs_log_force_inode(ip);
 }
 
+static xfs_lsn_t
+xfs_fsync_lsn(
+	struct xfs_inode	*ip,
+	bool			datasync)
+{
+	if (!xfs_ipincount(ip))
+		return 0;
+	if (datasync && !(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
+		return 0;
+	return ip->i_itemp->ili_last_lsn;
+}
+
+/*
+ * All metadata updates are logged, which means that we just have to flush the
+ * log up to the latest LSN that touched the inode.
+ *
+ * If we have concurrent fsync/fdatasync() calls, we need them to all block on
+ * the log force before we clear the ili_fsync_fields field. This ensures that
+ * we don't get a racing sync operation that does not wait for the metadata to
+ * hit the journal before returning.  If we race with clearing ili_fsync_fields,
+ * then all that will happen is the log force will do nothing as the lsn will
+ * already be on disk.  We can't race with setting ili_fsync_fields because that
+ * is done under XFS_ILOCK_EXCL, and that can't happen because we hold the lock
+ * shared until after the ili_fsync_fields is cleared.
+ */
+static  int
+xfs_fsync_flush_log(
+	struct xfs_inode	*ip,
+	bool			datasync,
+	int			*log_flushed)
+{
+	int			error = 0;
+	xfs_lsn_t		lsn;
+
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
+	lsn = xfs_fsync_lsn(ip, datasync);
+	if (lsn) {
+		error = xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC,
+					  log_flushed);
+
+		spin_lock(&ip->i_itemp->ili_lock);
+		ip->i_itemp->ili_fsync_fields = 0;
+		spin_unlock(&ip->i_itemp->ili_lock);
+	}
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	return error;
+}
+
 STATIC int
 xfs_file_fsync(
 	struct file		*file,
@@ -125,13 +173,10 @@ xfs_file_fsync(
 	loff_t			end,
 	int			datasync)
 {
-	struct inode		*inode = file->f_mapping->host;
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_inode_log_item *iip = ip->i_itemp;
+	struct xfs_inode	*ip = XFS_I(file->f_mapping->host);
 	struct xfs_mount	*mp = ip->i_mount;
 	int			error = 0;
 	int			log_flushed = 0;
-	xfs_lsn_t		lsn = 0;
 
 	trace_xfs_file_fsync(ip);
 
@@ -155,33 +200,7 @@ xfs_file_fsync(
 	else if (mp->m_logdev_targp != mp->m_ddev_targp)
 		xfs_blkdev_issue_flush(mp->m_ddev_targp);
 
-	/*
-	 * All metadata updates are logged, which means that we just have to
-	 * flush the log up to the latest LSN that touched the inode. If we have
-	 * concurrent fsync/fdatasync() calls, we need them to all block on the
-	 * log force before we clear the ili_fsync_fields field. This ensures
-	 * that we don't get a racing sync operation that does not wait for the
-	 * metadata to hit the journal before returning. If we race with
-	 * clearing the ili_fsync_fields, then all that will happen is the log
-	 * force will do nothing as the lsn will already be on disk. We can't
-	 * race with setting ili_fsync_fields because that is done under
-	 * XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared
-	 * until after the ili_fsync_fields is cleared.
-	 */
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	if (xfs_ipincount(ip)) {
-		if (!datasync ||
-		    (iip->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
-			lsn = iip->ili_last_lsn;
-	}
-
-	if (lsn) {
-		error = xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
-		spin_lock(&iip->ili_lock);
-		iip->ili_fsync_fields = 0;
-		spin_unlock(&iip->ili_lock);
-	}
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	error = xfs_fsync_flush_log(ip, datasync, &log_flushed);
 
 	/*
 	 * If we only have a single device, and the log force about was
-- 
2.29.2