Force fault a vdev with 'zpool offline -f'

This patch adds a '-f' option to 'zpool offline' to fault a vdev
instead of bringing it offline.  Unlike the OFFLINE state, the
FAULTED state will trigger the FMA code, allowing for things like
autoreplace and triggering the slot fault LED.  The -f faults
persist across imports, unless they were set with the temporary
(-t) flag.  Both persistent and temporary faults can be cleared
with zpool clear.

Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Tony Hutter <[email protected]>
Closes #6094 

3 files changed, 114 insertions, 3 deletions

diff --git a/tests/zfs-tests/tests/functional/cli_root/zpool_offline/Makefile.am b/tests/zfs-tests/tests/functional/cli_root/zpool_offline/Makefile.am
index 6bb5fbf6a..33fbb18d6 100644
--- a/tests/zfs-tests/tests/functional/cli_root/zpool_offline/Makefile.am
+++ b/tests/zfs-tests/tests/functional/cli_root/zpool_offline/Makefile.am
@@ -3,4 +3,5 @@ dist_pkgdata_SCRIPTS = \
 	setup.ksh \
 	cleanup.ksh \
 	zpool_offline_001_pos.ksh \
-	zpool_offline_002_neg.ksh
+	zpool_offline_002_neg.ksh \
+	zpool_offline_003_pos.ksh
diff --git a/tests/zfs-tests/tests/functional/cli_root/zpool_offline/zpool_offline_001_pos.ksh b/tests/zfs-tests/tests/functional/cli_root/zpool_offline/zpool_offline_001_pos.ksh
index c0ccf0bb8..6f4c2e318 100755
--- a/tests/zfs-tests/tests/functional/cli_root/zpool_offline/zpool_offline_001_pos.ksh
+++ b/tests/zfs-tests/tests/functional/cli_root/zpool_offline/zpool_offline_001_pos.ksh
@@ -39,7 +39,6 @@
 # 1. Create an array of correctly formed 'zpool offline' options
 # 2. Execute each element of the array.
 # 3. Verify use of each option is successful.
-#
 
 verify_runnable "global"
 
@@ -122,4 +121,4 @@ for disk in $DISKLIST; do
 	fi
 done
 
-log_pass "'zpool offline' with correct options succeeded"
+log_pass "'zpool offline -f' succeeded"
diff --git a/tests/zfs-tests/tests/functional/cli_root/zpool_offline/zpool_offline_003_pos.ksh b/tests/zfs-tests/tests/functional/cli_root/zpool_offline/zpool_offline_003_pos.ksh
new file mode 100755
index 000000000..7b5d21cba
--- /dev/null
+++ b/tests/zfs-tests/tests/functional/cli_root/zpool_offline/zpool_offline_003_pos.ksh
@@ -0,0 +1,111 @@
+#!/bin/ksh -p
+#
+# CDDL HEADER START
+#
+# The contents of this file are subject to the terms of the
+# Common Development and Distribution License (the "License").
+# You may not use this file except in compliance with the License.
+#
+# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
+# or http://www.opensolaris.org/os/licensing.
+# See the License for the specific language governing permissions
+# and limitations under the License.
+#
+# When distributing Covered Code, include this CDDL HEADER in each
+# file and include the License file at usr/src/OPENSOLARIS.LICENSE.
+# If applicable, add the following below this CDDL HEADER, with the
+# fields enclosed by brackets "[]" replaced with your own identifying
+# information: Portions Copyright [yyyy] [name of copyright owner]
+#
+# CDDL HEADER END
+#
+
+#
+# Copyright 2009 Sun Microsystems, Inc.  All rights reserved.
+# Use is subject to license terms.
+#
+
+#
+# Copyright (c) 2016 by Delphix. All rights reserved.
+#
+
+. $STF_SUITE/include/libtest.shlib
+
+#
+# DESCRIPTION:
+# Test force faulting a VDEV with 'zpool offline -f'
+#
+# STRATEGY:
+# For both temporary and persistent faults, do the following:
+# 1. Force fault a vdev, and clear the fault.
+# 2. Offline a vdev, force fault it, clear the fault, and online it.
+# 3. Force fault a vdev, export it, then import it.
+
+verify_runnable "global"
+
+DISKLIST=$(get_disklist $TESTPOOL)
+set -A disks $DISKLIST
+typeset -i num=${#disks[*]}
+
+set -A args "" "-t"
+
+function cleanup
+{
+	# Ensure we don't leave disks in the offline state
+	for disk in $DISKLIST; do
+		log_must zpool online $TESTPOOL $disk
+		check_state $TESTPOOL $disk "online"
+		if [[ $? != 0 ]]; then
+			log_fail "Unable to online $disk"
+		fi
+	done
+}
+
+log_assert "Executing 'zpool offline -f' with correct options succeeds"
+
+log_onexit cleanup
+
+if [[ -z $DISKLIST ]]; then
+	log_fail "DISKLIST is empty."
+fi
+
+typeset -i i=0
+typeset -i j=1
+
+# Get name of the first disk in the pool
+disk=${DISKLIST%% *}
+
+# Test temporary and persistent faults
+for arg in f tf ; do
+	# Force fault disk, and clear the fault
+	log_must zpool offline -$arg $TESTPOOL $disk
+	check_state $TESTPOOL $disk "faulted"
+	log_must zpool clear $TESTPOOL $disk
+	check_state $TESTPOOL $disk "online"
+
+	# Offline a disk, force fault it, clear the fault, and online it
+	log_must zpool offline $TESTPOOL $disk
+	check_state $TESTPOOL $disk "offline"
+	log_must zpool offline -$arg $TESTPOOL $disk
+	check_state $TESTPOOL $disk "faulted"
+	log_must zpool clear $TESTPOOL $disk
+	check_state $TESTPOOL $disk "offline"
+	log_must zpool online $TESTPOOL $disk
+	check_state $TESTPOOL $disk "online"
+
+	# Test faults across imports
+	log_must zpool offline -tf $TESTPOOL $disk
+	check_state $TESTPOOL $disk "faulted"
+	log_must zpool export $TESTPOOL
+	log_must zpool import $TESTPOOL
+	log_note "-$arg now imported"
+	if [[ "$arg" = "f" ]] ; then
+		# Persistent fault
+		check_state $TESTPOOL $disk "faulted"
+		log_must zpool clear $TESTPOOL $disk
+	else
+		# Temporary faults get cleared by imports
+		check_state $TESTPOOL $disk "online"
+	fi
+done
+log_pass "'zpool offline -f' with correct options succeeded"