xfs: defer agfl block frees when dfops is available

The AGFL fixup code executes before every block allocation/free and
rectifies the AGFL based on the current, dynamic allocation
requirements of the fs. The AGFL must hold a minimum number of
blocks to satisfy a worst case split of the free space btrees caused
by the impending allocation operation. The AGFL is also updated to
maintain the implicit requirement for a minimum number of free slots
to satisfy a worst case join of the free space btrees.

Since the AGFL caches individual blocks, AGFL reduction typically
involves multiple, single block frees. We've had reports of
transaction overrun problems during certain workloads that boil down
to AGFL reduction freeing multiple blocks and consuming more space
in the log than was reserved for the transaction.

Since the objective of freeing AGFL blocks is to ensure free AGFL
free slots are available for the upcoming allocation, one way to
address this problem is to release surplus blocks from the AGFL
immediately but defer the free of those blocks (similar to how
file-mapped blocks are unmapped from the file in one transaction and
freed via a deferred operation) until the transaction is rolled.
This turns AGFL reduction into an operation with predictable log
reservation consumption.

Add the capability to defer AGFL block frees when a deferred ops
list is available to the AGFL fixup code. Add a dfops pointer to the
transaction to carry dfops through various contexts to the allocator
context. Deferring AGFL frees is  conditional behavior based on
whether the transaction pointer is populated. The long term
objective is to reuse the transaction pointer to clean up all
unrelated callchains that pass dfops on the stack along with a
transaction and in doing so, consistently defer AGFL blocks from the
allocator.

A bit of customization is required to handle deferred completion
processing because AGFL blocks are accounted against a per-ag
reservation pool and AGFL blocks are not inserted into the extent
busy list when freed (they are inserted when used and released back
to the AGFL). Reuse the majority of the existing deferred extent
free infrastructure and customize it appropriately to handle AGFL
blocks.

Note that this patch only adds infrastructure. It does not change
behavior because no callers have been updated to pass ->t_agfl_dfops
into the allocation code.

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>

1 files changed, 70 insertions, 0 deletions

diff --git a/fs/xfs/xfs_trans_extfree.c b/fs/xfs/xfs_trans_extfree.c
index ab438647592a..f5620796ae25 100644
--- a/fs/xfs/xfs_trans_extfree.c
+++ b/fs/xfs/xfs_trans_extfree.c
@@ -231,9 +231,79 @@ static const struct xfs_defer_op_type xfs_extent_free_defer_type = {
 	.cancel_item	= xfs_extent_free_cancel_item,
 };
 
+/*
+ * AGFL blocks are accounted differently in the reserve pools and are not
+ * inserted into the busy extent list.
+ */
+STATIC int
+xfs_agfl_free_finish_item(
+	struct xfs_trans		*tp,
+	struct xfs_defer_ops		*dop,
+	struct list_head		*item,
+	void				*done_item,
+	void				**state)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_efd_log_item		*efdp = done_item;
+	struct xfs_extent_free_item	*free;
+	struct xfs_extent		*extp;
+	struct xfs_buf			*agbp;
+	int				error;
+	xfs_agnumber_t			agno;
+	xfs_agblock_t			agbno;
+	uint				next_extent;
+
+	free = container_of(item, struct xfs_extent_free_item, xefi_list);
+	ASSERT(free->xefi_blockcount == 1);
+	agno = XFS_FSB_TO_AGNO(mp, free->xefi_startblock);
+	agbno = XFS_FSB_TO_AGBNO(mp, free->xefi_startblock);
+
+	trace_xfs_agfl_free_deferred(mp, agno, 0, agbno, free->xefi_blockcount);
+
+	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
+	if (!error)
+		error = xfs_free_agfl_block(tp, agno, agbno, agbp,
+					    &free->xefi_oinfo);
+
+	/*
+	 * Mark the transaction dirty, even on error. This ensures the
+	 * transaction is aborted, which:
+	 *
+	 * 1.) releases the EFI and frees the EFD
+	 * 2.) shuts down the filesystem
+	 */
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	efdp->efd_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+
+	next_extent = efdp->efd_next_extent;
+	ASSERT(next_extent < efdp->efd_format.efd_nextents);
+	extp = &(efdp->efd_format.efd_extents[next_extent]);
+	extp->ext_start = free->xefi_startblock;
+	extp->ext_len = free->xefi_blockcount;
+	efdp->efd_next_extent++;
+
+	kmem_free(free);
+	return error;
+}
+
+
+/* sub-type with special handling for AGFL deferred frees */
+static const struct xfs_defer_op_type xfs_agfl_free_defer_type = {
+	.type		= XFS_DEFER_OPS_TYPE_AGFL_FREE,
+	.max_items	= XFS_EFI_MAX_FAST_EXTENTS,
+	.diff_items	= xfs_extent_free_diff_items,
+	.create_intent	= xfs_extent_free_create_intent,
+	.abort_intent	= xfs_extent_free_abort_intent,
+	.log_item	= xfs_extent_free_log_item,
+	.create_done	= xfs_extent_free_create_done,
+	.finish_item	= xfs_agfl_free_finish_item,
+	.cancel_item	= xfs_extent_free_cancel_item,
+};
+
 /* Register the deferred op type. */
 void
 xfs_extent_free_init_defer_op(void)
 {
 	xfs_defer_init_op_type(&xfs_extent_free_defer_type);
+	xfs_defer_init_op_type(&xfs_agfl_free_defer_type);
 }