xfs: don't set bmapi total block req where minleft is

xfs_bmapi_write() takes a total block requirement parameter that is
passed down to the block allocation code and is used to specify the
total block requirement of the associated transaction. This is used
to try and select an AG that can not only satisfy the requested
extent allocation, but can also accommodate subsequent allocations
that might be required to complete the transaction. For example,
additional bmbt block allocations may be required on insertion of
the resulting extent to an inode data fork.

While it's important for callers to calculate and reserve such extra
blocks in the transaction, it is not necessary to pass the total
value to xfs_bmapi_write() in all cases. The latter automatically
sets minleft to ensure that sufficient free blocks remain after the
allocation attempt to expand the format of the associated inode
(i.e., such as extent to btree conversion, btree splits, etc).
Therefore, any callers that pass a total block requirement of the
bmap mapping length plus worst case bmbt expansion essentially
specify the additional reservation requirement twice. These callers
can pass a total of zero to rely on the bmapi minleft policy.

Beyond being superfluous, the primary motivation for this change is
that the total reservation logic in the bmbt code is dubious in
scenarios where minlen < maxlen and a maxlen extent cannot be
allocated (which is more common for data extent allocations where
contiguity is not required). The total value is based on maxlen in
the xfs_bmapi_write() caller. If the bmbt code falls back to an
allocation between minlen and maxlen, that allocation will not
succeed until total is reset to minlen, which essentially throws
away any additional reservation included in total by the caller. In
addition, the total value is not reset until after alignment is
dropped, which means that such callers drop alignment far too
aggressively than necessary.

Update all callers of xfs_bmapi_write() that pass a total block
value of the mapping length plus bmbt reservation to instead pass
zero and rely on xfs_bmapi_minleft() to enforce the bmbt reservation
requirement. This trades off slightly less conservative AG selection
for the ability to preserve alignment in more scenarios.
xfs_bmapi_write() callers that incorporate unrelated or additional
reservations in total beyond what is already included in minleft
must continue to use the former.

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>

fs/xfs/libxfs/xfs_bmap.c

@@ -4511,7 +4511,6 @@ xfs_bmapi_convert_delalloc(
 	bma.wasdel = true;
 	bma.offset = bma.got.br_startoff;
 	bma.length = max_t(xfs_filblks_t, bma.got.br_blockcount, MAXEXTLEN);
-	bma.total = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
 	bma.minleft = xfs_bmapi_minleft(tp, ip, whichfork);
 	if (whichfork == XFS_COW_FORK)
 		bma.flags = XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC;

fs/xfs/xfs_bmap_util.c

@@ -964,8 +964,8 @@ xfs_alloc_file_space(
 		xfs_trans_ijoin(tp, ip, 0);
 
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
-					allocatesize_fsb, alloc_type, resblks,
-					imapp, &nimaps);
+					allocatesize_fsb, alloc_type, 0, imapp,
+					&nimaps);
 		if (error)
 			goto error0;
 

fs/xfs/xfs_dquot.c

@@ -305,8 +305,8 @@ xfs_dquot_disk_alloc(
 	/* Create the block mapping. */
 	xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL);
 	error = xfs_bmapi_write(tp, quotip, dqp->q_fileoffset,
-			XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
-			XFS_QM_DQALLOC_SPACE_RES(mp), &map, &nmaps);
+			XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA, 0, &map,
+			&nmaps);
 	if (error)
 		return error;
 	ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);

fs/xfs/xfs_iomap.c

@@ -285,8 +285,8 @@ xfs_iomap_write_direct(
 	 * caller gave to us.
 	 */
 	nimaps = 1;
-	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-				bmapi_flags, resblks, imap, &nimaps);
+	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, bmapi_flags, 0,
+				imap, &nimaps);
 	if (error)
 		goto out_res_cancel;
 

fs/xfs/xfs_reflink.c

@@ -410,8 +410,8 @@ xfs_reflink_allocate_cow(
 	/* Allocate the entire reservation as unwritten blocks. */
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
-			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC,
-			resblks, cmap, &nimaps);
+			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, 0, cmap,
+			&nimaps);
 	if (error)
 		goto out_unreserve;
 

fs/xfs/xfs_rtalloc.c

@@ -792,8 +792,7 @@ xfs_growfs_rt_alloc(
 		 */
 		nmap = 1;
 		error = xfs_bmapi_write(tp, ip, oblocks, nblocks - oblocks,
-					XFS_BMAPI_METADATA, resblks, &map,
-					&nmap);
+					XFS_BMAPI_METADATA, 0, &map, &nmap);
 		if (!error && nmap < 1)
 			error = -ENOSPC;
 		if (error)