[v2,05/13] xfs: introduce forced allocation alignment

Commit Message

John Garry July 5, 2024, 4:24 p.m. UTC

From: Dave Chinner <[e-mail]>

When forced allocation alignment is specified, the extent will
be aligned to the extent size hint size rather than stripe
alignment. If aligned allocation cannot be done, then the allocation
is failed rather than attempting non-aligned fallbacks.

Note: none of the per-inode force align configuration is present
yet, so this just triggers off an "always false" wrapper function
for the moment.

Signed-off-by: Dave Chinner <[e-mail]>
Reviewed-by: "Darrick J. Wong" <[e-mail]>
Signed-off-by: John Garry <[e-mail]>
---
 fs/xfs/libxfs/xfs_alloc.h |  1 +
 fs/xfs/libxfs/xfs_bmap.c  | 29 +++++++++++++++++++++++------
 fs/xfs/xfs_inode.h        |  5 +++++
 3 files changed, 29 insertions(+), 6 deletions(-)

Patch

diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 1e9d0bde5640..71a85439e5fc 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -66,6 +66,7 @@  typedef struct xfs_alloc_arg {
 #define XFS_ALLOC_USERDATA		(1 << 0)/* allocation is for user data*/
 #define XFS_ALLOC_INITIAL_USER_DATA	(1 << 1)/* special case start of file */
 #define XFS_ALLOC_NOBUSY		(1 << 2)/* Busy extents not allowed */
+#define XFS_ALLOC_FORCEALIGN		(1 << 3)/* forced extent alignment */
 
 /* freespace limit calculations */
 unsigned int xfs_alloc_set_aside(struct xfs_mount *mp);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 4122a2da06ec..1cc2d812a6e9 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3400,9 +3400,10 @@  xfs_bmap_alloc_account(
  * Calculate the extent start alignment and the extent length adjustments that
  * constrain this allocation.
  *
- * Extent start alignment is currently determined by stripe configuration and is
- * carried in args->alignment, whilst extent length adjustment is determined by
- * extent size hints and is carried by args->prod and args->mod.
+ * Extent start alignment is currently determined by forced inode alignment or
+ * stripe configuration and is carried in args->alignment, whilst extent length
+ * adjustment is determined by extent size hints and is carried by args->prod
+ * and args->mod.
  *
  * Low level allocation code is free to either ignore or override these values
  * as required.
@@ -3415,11 +3416,18 @@  xfs_bmap_compute_alignments(
 	struct xfs_mount	*mp = args->mp;
 	xfs_extlen_t		align = 0; /* minimum allocation alignment */
 
-	/* stripe alignment for allocation is determined by mount parameters */
-	if (mp->m_swidth && xfs_has_swalloc(mp))
+	/*
+	 * Forced inode alignment takes preference over stripe alignment.
+	 * Stripe alignment for allocation is determined by mount parameters.
+	 */
+	if (xfs_inode_has_forcealign(ap->ip)) {
+		args->alignment = xfs_get_extsz_hint(ap->ip);
+		args->datatype |= XFS_ALLOC_FORCEALIGN;
+	} else if (mp->m_swidth && xfs_has_swalloc(mp)) {
 		args->alignment = mp->m_swidth;
-	else if (mp->m_dalign)
+	} else if (mp->m_dalign) {
 		args->alignment = mp->m_dalign;
+	}
 
 	if (ap->flags & XFS_BMAPI_COWFORK)
 		align = xfs_get_cowextsz_hint(ap->ip);
@@ -3606,6 +3614,11 @@  xfs_bmap_btalloc_low_space(
 {
 	int			error;
 
+	if (args->alignment > 1 && (args->datatype & XFS_ALLOC_FORCEALIGN)) {
+		args->fsbno = NULLFSBLOCK;
+		return 0;
+	}
+
 	args->alignment = 1;
 	if (args->minlen > ap->minlen) {
 		args->minlen = ap->minlen;
@@ -3657,6 +3670,8 @@  xfs_bmap_btalloc_filestreams(
 
 	/* Attempt non-aligned allocation if we haven't already. */
 	if (!error && args->fsbno == NULLFSBLOCK && args->alignment > 1)  {
+		if (args->datatype & XFS_ALLOC_FORCEALIGN)
+			return error;
 		args->alignment = 1;
 		error = xfs_alloc_vextent_near_bno(args, ap->blkno);
 	}
@@ -3715,6 +3730,8 @@  xfs_bmap_btalloc_best_length(
 
 	/* Attempt non-aligned allocation if we haven't already. */
 	if (!error && args->fsbno == NULLFSBLOCK && args->alignment > 1)  {
+		if (args->datatype & XFS_ALLOC_FORCEALIGN)
+			return error;
 		args->alignment = 1;
 		error = xfs_alloc_vextent_start_ag(args, ap->blkno);
 	}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 292b90b5f2ac..42f999c1106c 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -311,6 +311,11 @@  static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip)
 	return ip->i_diflags2 & XFS_DIFLAG2_NREXT64;
 }
 
+static inline bool xfs_inode_has_forcealign(struct xfs_inode *ip)
+{
+	return false;
+}
+
 /*
  * Decide if this file is a realtime file whose data allocation unit is larger
  * than a single filesystem block.