xfs: cap longest free extent to maximum allocatable

Cap longest extent to the largest we can allocate based on limits
calculated at mount time. Dynamic state (such as finobt blocks)
can result in the longest free extent exceeding the size we can
allocate, and that results in failure to align full AG allocations
when the AG is empty.

Result:

xfs_io-4413  [003]   426.412459: xfs_alloc_vextent_loopfailed: dev 8:96 agno 0 agbno 32 minlen 243968 maxlen 244000 mod 0 prod 1 minleft 1 total 262148 alignment 32 minalignslop 0 len 0 type NEAR_BNO otype START_BNO wasdel 0 wasfromfl 0 resv 0 datatype 0x5 firstblock 0xffffffffffffffff

minlen and maxlen are now separated by the alignment size, and
allocation fails because args.total > free space in the AG.

[bfoster: Added xfs_bmap_btalloc() changes.]

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 925eba9..84866c1 100644 (file)
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2116,7 +2116,8 @@ xfs_alloc_longest_free_extent(
         * reservations and AGFL rules in place, we can return this extent.
         */
        if (pag->pagf_longest > delta)
-               return pag->pagf_longest - delta;
+               return min_t(xfs_extlen_t, pag->pag_mount->m_ag_max_usable,
+                               pag->pagf_longest - delta);
 
        /* Otherwise, let the caller try for 1 block if there's space. */
        return pag->pagf_flcount > 0 || pag->pagf_longest > 0;

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index ef75e22..3b300b5 100644 (file)
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3501,13 +3501,11 @@ xfs_bmap_btalloc(
                        args.mod = args.prod - args.mod;
        }
        /*
-        * If we are not low on available data blocks, and the
-        * underlying logical volume manager is a stripe, and
-        * the file offset is zero then try to allocate data
-        * blocks on stripe unit boundary.
-        * NOTE: ap->aeof is only set if the allocation length
-        * is >= the stripe unit and the allocation offset is
-        * at the end of file.
+        * If we are not low on available data blocks, and the underlying
+        * logical volume manager is a stripe, and the file offset is zero then
+        * try to allocate data blocks on stripe unit boundary. NOTE: ap->aeof
+        * is only set if the allocation length is >= the stripe unit and the
+        * allocation offset is at the end of file.
         */
        if (!(ap->tp->t_flags & XFS_TRANS_LOWMODE) && ap->aeof) {
                if (!ap->offset) {
@@ -3515,9 +3513,11 @@ xfs_bmap_btalloc(
                        atype = args.type;
                        isaligned = 1;
                        /*
-                        * Adjust for alignment
+                        * Adjust minlen to try and preserve alignment if we
+                        * can't guarantee an aligned maxlen extent.
                         */
-                       if (blen > args.alignment && blen <= args.maxlen)
+                       if (blen > args.alignment &&
+                           blen <= args.maxlen + args.alignment)
                                args.minlen = blen - args.alignment;
                        args.minalignslop = 0;
                } else {