xfs: garbage collect old cowextsz reservations

Trim CoW reservations made on behalf of a cowextsz hint if they get too
old or we run low on quota, so long as we don't have dirty data awaiting
writeback or directio operations in progress.

Garbage collection of the cowextsize extents are kept separate from
prealloc extent reaping because setting the CoW prealloc lifetime to a
(much) higher value than the regular prealloc extent lifetime has been
useful for combatting CoW fragmentation on VM hosts where the VMs
experience bursty write behaviors and we can keep the utilization ratios
low enough that we don't start to run out of space.  IOWs, it benefits
us to keep the CoW fork reservations around for as long as we can unless
we run out of blocks or hit inode reclaim.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>

1 files changed, 38 insertions, 0 deletions

diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index e92ccd316391..685c419ae011 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -304,6 +304,9 @@ retry:
 		goto out_unlock;
 	}
 
+	if (end_fsb != orig_end_fsb)
+		xfs_inode_set_cowblocks_tag(ip);
+
 	trace_xfs_reflink_cow_alloc(ip, &got);
 done:
 	*offset_fsb = end_fsb;
@@ -1562,6 +1565,7 @@ next:
 	/* Clear the inode flag. */
 	trace_xfs_reflink_unset_inode_flag(ip);
 	ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+	xfs_inode_clear_cowblocks_tag(ip);
 	xfs_trans_ijoin(*tpp, ip, 0);
 	xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);
 
@@ -1662,3 +1666,37 @@ out:
 	trace_xfs_reflink_unshare_error(ip, error, _RET_IP_);
 	return error;
 }
+
+/*
+ * Does this inode have any real CoW reservations?
+ */
+bool
+xfs_reflink_has_real_cow_blocks(
+	struct xfs_inode		*ip)
+{
+	struct xfs_bmbt_irec		irec;
+	struct xfs_ifork		*ifp;
+	struct xfs_bmbt_rec_host	*gotp;
+	xfs_extnum_t			idx;
+
+	if (!xfs_is_reflink_inode(ip))
+		return false;
+
+	/* Go find the old extent in the CoW fork. */
+	ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	gotp = xfs_iext_bno_to_ext(ifp, 0, &idx);
+	while (gotp) {
+		xfs_bmbt_get_all(gotp, &irec);
+
+		if (!isnullstartblock(irec.br_startblock))
+			return true;
+
+		/* Roll on... */
+		idx++;
+		if (idx >= ifp->if_bytes / sizeof(xfs_bmbt_rec_t))
+			break;
+		gotp = xfs_iext_get_ext(ifp, idx);
+	}
+
+	return false;
+}