xfs: test io error reporting via healthmon

Create a new test to make sure the kernel can report IO errors via
health monitoring.

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/656 b/tests/xfs/656
new file mode 100755 (executable)
index 0000000..3a86769
--- /dev/null
+++ b/tests/xfs/656
@@ -0,0 +1,98 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2024-2026 Oracle.  All Rights Reserved.
+#
+# FS QA Test No. 656
+#
+# Attempt to read and write a file in buffered and directio mode with the
+# health monitoring program running.  Check that healthmon observes all four
+# types of IO errors.
+#
+. ./common/preamble
+_begin_fstest auto quick eio selfhealing
+
+_cleanup()
+{
+       cd /
+       test -n "$healer_pid" && kill $healer_pid &>/dev/null
+       wait
+       rm -rf $tmp.* $testdir
+       _dmerror_cleanup
+}
+
+. ./common/filter
+. ./common/dmerror
+
+_require_scratch_nocheck
+_require_xfs_io_command healthmon
+_require_dm_target error
+
+filter_healer_errors() {
+       _filter_scratch | \
+               grep -E '(buffered|directio)' | \
+               sed \
+                   -e 's/ino [0-9]*/ino NUM/g' \
+                   -e 's/gen 0x[0-9a-f]*/gen NUM/g' \
+                   -e 's/pos [0-9]*/pos NUM/g' \
+                   -e 's/len [0-9]*/len NUM/g' \
+                   -e 's|SCRATCH_MNT/a|VICTIM|g' \
+                   -e 's|SCRATCH_MNT ino NUM gen NUM|VICTIM|g' | \
+               uniq
+}
+
+# Disable the scratch rt device to avoid test failures relating to the rt
+# bitmap consuming all the free space in our small data device.
+unset SCRATCH_RTDEV
+
+echo "Format and mount"
+_scratch_mkfs > $seqres.full 2>&1
+_dmerror_init no_log
+_dmerror_mount
+
+_require_fs_space $SCRATCH_MNT 65536
+
+# Create a file with written regions far enough apart that the pagecache can't
+# possibly be caching the regions with a single folio.
+testfile=$SCRATCH_MNT/fsync-err-test
+$XFS_IO_PROG -f \
+       -c 'pwrite -b 1m 0 1m' \
+       -c 'pwrite -b 1m 10g 1m' \
+       -c 'pwrite -b 1m 20g 1m' \
+       -c fsync $testfile >> $seqres.full
+
+# First we check if directio errors get reported
+$XFS_IO_PROG -c 'healthmon -c -v' $SCRATCH_MNT >> $tmp.healthmon &
+healer_pid=$!
+sleep 1        # wait for program to start up
+_dmerror_load_error_table
+$XFS_IO_PROG -d -c 'pwrite -b 256k 12k 16k' $testfile >> $seqres.full
+$XFS_IO_PROG -d -c 'pread -b 256k 10g 16k' $testfile >> $seqres.full
+_dmerror_load_working_table
+
+_dmerror_unmount
+wait   # for healthmon to finish
+unset healer_pid
+_dmerror_mount
+
+# Next we check if buffered io errors get reported.  We have to write something
+# before loading the error table to ensure the dquots get loaded.
+$XFS_IO_PROG -c 'pwrite -b 256k 20g 1k' -c fsync $testfile >> $seqres.full
+$XFS_IO_PROG -c 'healthmon -c -v' $SCRATCH_MNT >> $tmp.healthmon &
+healer_pid=$!
+sleep 1        # wait for program to start up
+_dmerror_load_error_table
+$XFS_IO_PROG -c 'pread -b 256k 12k 16k' $testfile >> $seqres.full
+$XFS_IO_PROG -c 'pwrite -b 256k 20g 16k' -c fsync $testfile >> $seqres.full
+_dmerror_load_working_table
+
+_dmerror_unmount
+wait   # for healthmon to finish
+unset healer_pid
+
+# Did we get errors?
+cat $tmp.healthmon >> $seqres.full
+filter_healer_errors < $tmp.healthmon
+
+_dmerror_cleanup
+
+_exit 0

diff --git a/tests/xfs/656.out b/tests/xfs/656.out
new file mode 100644 (file)
index 0000000..83b2f59
--- /dev/null
+++ b/tests/xfs/656.out
@@ -0,0 +1,10 @@
+QA output created by 656
+Format and mount
+pwrite: Input/output error
+pread: Input/output error
+pread: Input/output error
+fsync: Input/output error
+VICTIM pos NUM len NUM: directio_write: Input/output error
+VICTIM pos NUM len NUM: directio_read: Input/output error
+VICTIM pos NUM len NUM: buffered_read: Input/output error
+VICTIM pos NUM len NUM: buffered_write: Input/output error