xfs: disable the agi rotor for metadata inodes

Ideally, we'd put all the metadata inodes in one place if we could, so
that the metadata all stay reasonably close together instead of
spreading out over the disk.  Furthermore, if the log is internal we'd
probably prefer to keep the metadata near the log.  Therefore, disable
AGI rotoring for metadata inode allocations.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

3 files changed, 37 insertions, 24 deletions

diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 6740771f0ff5..e349c2d7a860 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -943,20 +943,21 @@ xfs_ialloc_next_ag(
  */
 STATIC xfs_agnumber_t
 xfs_ialloc_ag_select(
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_ino_t	parent,		/* parent directory inode number */
-	umode_t		mode)		/* bits set to indicate file type */
+	struct xfs_trans	*tp,
+	struct xfs_inode	*pip,
+	umode_t			mode)
 {
-	xfs_agnumber_t	agcount;	/* number of ag's in the filesystem */
-	xfs_agnumber_t	agno;		/* current ag number */
-	int		flags;		/* alloc buffer locking flags */
-	xfs_extlen_t	ineed;		/* blocks needed for inode allocation */
-	xfs_extlen_t	longest = 0;	/* longest extent available */
-	xfs_mount_t	*mp;		/* mount point structure */
-	int		needspace;	/* file mode implies space allocated */
-	xfs_perag_t	*pag;		/* per allocation group data */
-	xfs_agnumber_t	pagno;		/* parent (starting) ag number */
-	int		error;
+	struct xfs_mount	*mp;
+	struct xfs_perag	*pag;
+	xfs_ino_t		parent = pip ? pip->i_ino : 0;
+	xfs_agnumber_t		agcount;
+	xfs_agnumber_t		agno;
+	xfs_agnumber_t		pagno;
+	xfs_extlen_t		ineed;
+	xfs_extlen_t		longest = 0;	/* longest extent available */
+	int			needspace;	/* file mode implies space allocated */
+	int			flags;
+	int			error;
 
 	/*
 	 * Files of these types need at least one block if length > 0
@@ -965,9 +966,21 @@ xfs_ialloc_ag_select(
 	needspace = S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode);
 	mp = tp->t_mountp;
 	agcount = mp->m_maxagi;
-	if (S_ISDIR(mode))
+	if (pip && xfs_is_metadata_inode(pip)) {
+		/*
+		 * Try to squash all the metadata inodes into the parent's
+		 * AG, or the one with the log if the log is internal, or
+		 * AG 0 if all else fails.
+		 */
+		if (xfs_verify_ino(mp, parent))
+			pagno = XFS_INO_TO_AGNO(mp, parent);
+		else if (mp->m_sb.sb_logstart != 0)
+			pagno = XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart);
+		else
+			pagno = 0;
+	} else if (S_ISDIR(mode)) {
 		pagno = xfs_ialloc_next_ag(mp);
-	else {
+	} else {
 		pagno = XFS_INO_TO_AGNO(mp, parent);
 		if (pagno >= agcount)
 			pagno = 0;
@@ -1755,13 +1768,14 @@ error_cur:
 int
 xfs_dialloc(
 	struct xfs_trans	*tp,
-	xfs_ino_t		parent,
+	struct xfs_inode	*pip,
 	umode_t			mode,
 	struct xfs_buf		**IO_agbp,
 	xfs_ino_t		*inop)
 {
 	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_buf		*agbp;
+	xfs_ino_t		parent = pip ? pip->i_ino : 0;
 	xfs_agnumber_t		agno;
 	int			error;
 	int			ialloced;
@@ -1785,7 +1799,7 @@ xfs_dialloc(
 	 * We do not have an agbp, so select an initial allocation
 	 * group for inode allocation.
 	 */
-	start_agno = xfs_ialloc_ag_select(tp, parent, mode);
+	start_agno = xfs_ialloc_ag_select(tp, pip, mode);
 	if (start_agno == NULLAGNUMBER) {
 		*inop = NULLFSINO;
 		return 0;
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index 632f8ed0a228..cc854fea047b 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -56,11 +56,11 @@ xfs_make_iptr(struct xfs_mount *mp, struct xfs_buf *b, int o)
  */
 int					/* error */
 xfs_dialloc(
-	struct xfs_trans *tp,		/* transaction pointer */
-	xfs_ino_t	parent,		/* parent inode (directory) */
-	umode_t		mode,		/* mode bits for new inode */
-	struct xfs_buf	**agbp,		/* buf for a.g. inode header */
-	xfs_ino_t	*inop);		/* inode number allocated */
+	struct xfs_trans	*tp,	/* transaction pointer */
+	struct xfs_inode	*pip,	/* parent inode (directory) */
+	umode_t			mode,	/* mode bits for new inode */
+	struct xfs_buf		**agbp,	/* buf for a.g. inode header */
+	xfs_ino_t		*inop);	/* inode number allocated */
 
 /*
  * Free disk inode.  Carefully avoids touching the incore inode, all
diff --git a/fs/xfs/libxfs/xfs_inode_util.c b/fs/xfs/libxfs/xfs_inode_util.c
index f7cf64c2dee8..a2af152fecec 100644
--- a/fs/xfs/libxfs/xfs_inode_util.c
+++ b/fs/xfs/libxfs/xfs_inode_util.c
@@ -350,8 +350,7 @@ xfs_ialloc(
 	 * Call the space management code to pick
 	 * the on-disk inode to be allocated.
 	 */
-	error = xfs_dialloc(tp, pip ? pip->i_ino : 0, args->mode,
-			    ialloc_context, &ino);
+	error = xfs_dialloc(tp, pip, args->mode, ialloc_context, &ino);
 	if (error)
 		return error;
 	if (*ialloc_context || ino == NULLFSINO) {