From: Darrick J. Wong <djwong@kernel.org>
Date: Tue, 10 Mar 2026 03:52:44 +0000 (-0700)
Subject: xfs: test xfs_healer can initiate full filesystem repairs
X-Git-Tag: v2026.03.20~6
X-Git-Url: http://git-server-git.apps.pok.os.sepia.ceph.com/?a=commitdiff_plain;h=20dffed104b65a84377dd5431a9ebaf31eedd7fe;p=xfstests-dev.git

xfs: test xfs_healer can initiate full filesystem repairs

Make sure that when xfs_healer can't perform a spot repair, it will actually
start up xfs_scrub to perform a full scan and repair.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Zorro Lang <zlang@redhat.com>
Signed-off-by: Zorro Lang <zlang@kernel.org>
---

diff --git a/tests/xfs/662 b/tests/xfs/662
new file mode 100755
index 00000000..6136a595
--- /dev/null
+++ b/tests/xfs/662
@@ -0,0 +1,107 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2024-2026 Oracle.  All Rights Reserved.
+#
+# FS QA Test No. 662
+#
+# Ensure that autonomous self healing works fixes the filesystem correctly
+# even if the spot repair doesn't work and it falls back to a full fsck.
+#
+. ./common/preamble
+_begin_fstest auto selfhealing
+
+. ./common/filter
+. ./common/fuzzy
+. ./common/systemd
+
+_require_scrub
+_require_xfs_io_command "repair"	# online repair support
+_require_xfs_db_command "blocktrash"
+_require_command "$XFS_HEALER_PROG" "xfs_healer"
+_require_command "$XFS_PROPERTY_PROG" "xfs_property"
+_require_scratch
+_require_systemd_unit_defined "xfs_scrub@.service"
+
+_scratch_mkfs >> $seqres.full
+_scratch_mount
+
+_xfs_has_feature $SCRATCH_MNT rmapbt || \
+	_notrun "reverse mapping required to test directory auto-repair"
+_xfs_has_feature $SCRATCH_MNT parent || \
+	_notrun "parent pointers required to test directory auto-repair"
+_require_xfs_healer $SCRATCH_MNT --repair
+
+filter_healer() {
+	_filter_scratch | \
+		grep 'Full repairs in progress' | \
+		uniq
+}
+
+# Configure the filesystem for automatic repair of the filesystem.
+$XFS_PROPERTY_PROG $SCRATCH_MNT set autofsck=repair >> $seqres.full
+
+# Create a largeish directory
+dblksz=$(_xfs_get_dir_blocksize "$SCRATCH_MNT")
+echo testdata > $SCRATCH_MNT/a
+mkdir -p "$SCRATCH_MNT/some/victimdir"
+for ((i = 0; i < (dblksz / 255); i++)); do
+	fname="$(printf "%0255d" "$i")"
+	ln $SCRATCH_MNT/a $SCRATCH_MNT/some/victimdir/$fname
+done
+
+# Did we get at least two dir blocks?
+dirsize=$(stat -c '%s' $SCRATCH_MNT/some/victimdir)
+test "$dirsize" -gt "$dblksz" || echo "failed to create two-block directory"
+
+# Break the directory, remount filesystem
+_scratch_unmount
+_scratch_xfs_db -x \
+	-c 'path /some/victimdir' \
+	-c 'bmap' \
+	-c 'dblock 1' \
+	-c 'blocktrash -z -0 -o 0 -x 2048 -y 2048 -n 2048' \
+	-c 'path /a' \
+	-c 'bmap -a' \
+	-c 'ablock 1' \
+	-c 'blocktrash -z -0 -o 0 -x 2048 -y 2048 -n 2048' \
+	>> $seqres.full
+_scratch_mount
+
+_scratch_invoke_xfs_healer "$tmp.healer" --repair
+
+# Access the broken directory to trigger a repair, then poll the directory
+# for 5 seconds to see if it gets fixed without us needing to intervene.
+ls $SCRATCH_MNT/some/victimdir > /dev/null 2> $tmp.err
+_filter_scratch < $tmp.err
+try=0
+while [ $try -lt 50 ] && grep -q 'Structure needs cleaning' $tmp.err; do
+	echo "try $try saw corruption" >> $seqres.full
+	sleep 0.1
+	ls $SCRATCH_MNT/some/victimdir > /dev/null 2> $tmp.err
+	try=$((try + 1))
+done
+echo "try $try no longer saw corruption or gave up" >> $seqres.full
+_filter_scratch < $tmp.err
+
+# Wait for the background fixer to finish
+svc="$(_xfs_scrub_svcname "$SCRATCH_MNT")"
+_systemd_unit_wait "$svc"
+
+# List the dirents of /victimdir and parent pointers of /a to see if they both
+# stop reporting corruption
+(ls $SCRATCH_MNT/some/victimdir ; $XFS_IO_PROG -c 'parent') > /dev/null 2> $tmp.err
+try=0
+while [ $try -lt 50 ] && grep -q 'Structure needs cleaning' $tmp.err; do
+	echo "retry $try still saw corruption" >> $seqres.full
+	sleep 0.1
+	(ls $SCRATCH_MNT/some/victimdir ; $XFS_IO_PROG -c 'parent') > /dev/null 2> $tmp.err
+	try=$((try + 1))
+done
+echo "retry $try no longer saw corruption or gave up" >> $seqres.full
+
+# Unmount to kill the healer
+_scratch_kill_xfs_healer
+cat $tmp.healer >> $seqres.full
+cat $tmp.healer | filter_healer
+
+_exit 0
diff --git a/tests/xfs/662.out b/tests/xfs/662.out
new file mode 100644
index 00000000..466920f7
--- /dev/null
+++ b/tests/xfs/662.out
@@ -0,0 +1,3 @@
+QA output created by 662
+ls: reading directory 'SCRATCH_MNT/some/victimdir': Structure needs cleaning
+SCRATCH_MNT: Full repairs in progress.