A performance problem was reported in PR kern/181226:

    I have 25TB Dell PERC 6 RAID5 array. When it becomes almost
    full (10-20GB free), processes which write data to it start
    eating 100% CPU and write speed drops below 1MB/sec (normally
    to gives 400MB/sec). The revision at which it first became
    apparent was http://svnweb.freebsd.org/changeset/base/249782.

The offending change reserved an area in each cylinder group to
store metadata. The new algorithm attempts to save this area for
metadata and allows its use for non-metadata only after all the
data areas have been exhausted. The size of the reserved area
defaults to half of minfree, so the filesystem reports full before
the data area can completely fill. However, in this report, the
filesystem has had minfree reduced to 1% thus forcing the metadata
area to be used for data. As the filesystem approached full, it
had only metadata areas left to allocate. The result was that
every block allocation had to scan summary data for 30,000 cylinder
groups before falling back to searching up to 30,000 metadata areas.

The fix is to give up on saving the metadata areas once the free
space reserve drops below 2%. The effect of this change is to use
the old algorithm of just accepting the first available block that
we find. Since most filesystems use the default 5% minfree, this
will have no effect on their operation. For those that want to push
to the limit, they will get their crappy block placements quickly.

Submitted by:  Dmitry Sivachenko
Fix Tested by: Dmitry Sivachenko
PR:            kern/181226
MFC after:     2 weeks

1 files changed, 14 insertions, 2 deletions

diff --git a/sys/ufs/ffs/ffs_alloc.c b/sys/ufs/ffs/ffs_alloc.c
index cf1d953..cb5d45c 100644
--- a/sys/ufs/ffs/ffs_alloc.c
+++ b/sys/ufs/ffs/ffs_alloc.c
@@ -516,7 +516,13 @@ ffs_reallocblks_ufs1(ap)
 	ip = VTOI(vp);
 	fs = ip->i_fs;
 	ump = ip->i_ump;
-	if (fs->fs_contigsumsize <= 0)
+	/*
+	 * If we are not tracking block clusters or if we have less than 2%
+	 * free blocks left, then do not attempt to cluster. Running with
+	 * less than 5% free block reserve is not recommended and those that
+	 * choose to do so do not expect to have good file layout.
+	 */
+	if (fs->fs_contigsumsize <= 0 || freespace(fs, 2) < 0)
 		return (ENOSPC);
 	buflist = ap->a_buflist;
 	len = buflist->bs_nchildren;
@@ -737,7 +743,13 @@ ffs_reallocblks_ufs2(ap)
 	ip = VTOI(vp);
 	fs = ip->i_fs;
 	ump = ip->i_ump;
-	if (fs->fs_contigsumsize <= 0)
+	/*
+	 * If we are not tracking block clusters or if we have less than 2%
+	 * free blocks left, then do not attempt to cluster. Running with
+	 * less than 5% free block reserve is not recommended and those that
+	 * choose to do so do not expect to have good file layout.
+	 */
+	if (fs->fs_contigsumsize <= 0 || freespace(fs, 2) < 0)
 		return (ENOSPC);
 	buflist = ap->a_buflist;
 	len = buflist->bs_nchildren;