[27/52] xfs: don't merge ioends across RTGs

Commit Message

Darrick J. Wong Dec. 23, 2024, 10:05 p.m. UTC

From: Darrick J. Wong <[e-mail]>

Source kernel commit: b91afef724710e3dc7d65a28105ffd7a4e861d69

Unlike AGs, RTGs don't always have metadata in their first blocks, and
thus we don't get automatic protection from merging I/O completions
across RTG boundaries.  Add code to set the IOMAP_F_BOUNDARY flag for
ioends that start at the first block of a RTG so that they never get
merged into the previous ioend.

Signed-off-by: Christoph Hellwig <[e-mail]>
Reviewed-by: Darrick J. Wong <[e-mail]>
Signed-off-by: Darrick J. Wong <[e-mail]>
Reviewed-by: Christoph Hellwig <[e-mail]>
---
 libxfs/xfs_rtgroup.h |    9 +++++++++
 1 file changed, 9 insertions(+)

Patch

diff --git a/libxfs/xfs_rtgroup.h b/libxfs/xfs_rtgroup.h
index 026f34f984b32f..2ddfac9a0182f9 100644
--- a/libxfs/xfs_rtgroup.h
+++ b/libxfs/xfs_rtgroup.h
@@ -188,6 +188,15 @@  xfs_rtb_to_rgbno(
 	return __xfs_rtb_to_rgbno(mp, rtbno);
 }
 
+/* Is rtbno the start of a RT group? */
+static inline bool
+xfs_rtbno_is_group_start(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	return (rtbno & mp->m_rgblkmask) == 0;
+}
+
 static inline xfs_daddr_t
 xfs_rtb_to_daddr(
 	struct xfs_mount	*mp,