Fix concurrent resilvers initiated at same time

For draid vdevs it was possible to initiate both the
sequential and healing resilver at same time.

This fixes the following two scenarios.
     1) There's a window where a sequential rebuild can
be started via ZED even if a healing resilver has been
scheduled.
	- This is fixed by adding additional check in
spa_vdev_attach() for any scheduled resilver and return
appropriate error code when a resilver is already in
progress.

     2) It was possible for zpool clear to start a healing
resilver when it wasn't needed at all. This occurs because
during a vdev_open() the device is presumed to be healthy not
until the device is validated by vdev_validate() and it's set
unavailable. However, by this point an async resilver will
have already been requested if the DTL isn't empty.
	- This is fixed by cancelling the SPA_ASYNC_RESILVER
request immediately at the end of vdev_reopen() when a resilver
is unneeded.

Finally, added a testcase in ZTS for verification.

Reviewed-by: Brian Behlendorf <[email protected]>
Reviewed-by: Dipak Ghosh <[email protected]>
Signed-off-by: Akash B <[email protected]>
Closes #14881
Closes #14892 

3 files changed, 104 insertions, 1 deletions

diff --git a/tests/runfiles/common.run b/tests/runfiles/common.run
index 9ed1a6d37..10525289a 100644
--- a/tests/runfiles/common.run
+++ b/tests/runfiles/common.run
@@ -472,7 +472,8 @@ tests = ['zpool_replace_001_neg', 'replace-o_ashift', 'replace_prop_ashift']
 tags = ['functional', 'cli_root', 'zpool_replace']
 
 [tests/functional/cli_root/zpool_resilver]
-tests = ['zpool_resilver_bad_args', 'zpool_resilver_restart']
+tests = ['zpool_resilver_bad_args', 'zpool_resilver_restart',
+    'zpool_resilver_concurrent']
 tags = ['functional', 'cli_root', 'zpool_resilver']
 
 [tests/functional/cli_root/zpool_scrub]
diff --git a/tests/zfs-tests/tests/Makefile.am b/tests/zfs-tests/tests/Makefile.am
index ad4aec543..129893cd6 100644
--- a/tests/zfs-tests/tests/Makefile.am
+++ b/tests/zfs-tests/tests/Makefile.am
@@ -1142,6 +1142,7 @@ nobase_dist_datadir_zfs_tests_tests_SCRIPTS += \
 	functional/cli_root/zpool_resilver/setup.ksh \
 	functional/cli_root/zpool_resilver/zpool_resilver_bad_args.ksh \
 	functional/cli_root/zpool_resilver/zpool_resilver_restart.ksh \
+	functional/cli_root/zpool_resilver/zpool_resilver_concurrent.ksh \
 	functional/cli_root/zpool_scrub/cleanup.ksh \
 	functional/cli_root/zpool_scrub/setup.ksh \
 	functional/cli_root/zpool_scrub/zpool_scrub_001_neg.ksh \
diff --git a/tests/zfs-tests/tests/functional/cli_root/zpool_resilver/zpool_resilver_concurrent.ksh b/tests/zfs-tests/tests/functional/cli_root/zpool_resilver/zpool_resilver_concurrent.ksh
new file mode 100755
index 000000000..4c3b09796
--- /dev/null
+++ b/tests/zfs-tests/tests/functional/cli_root/zpool_resilver/zpool_resilver_concurrent.ksh
@@ -0,0 +1,101 @@
+#!/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 (c) 2023 Hewlett Packard Enterprise Development LP.
+#
+
+. $STF_SUITE/include/libtest.shlib
+. $STF_SUITE/tests/functional/redundancy/redundancy.kshlib
+
+#
+# DESCRIPTION:
+#	Verify 'zpool clear' doesn't cause concurrent resilvers
+#
+# STRATEGY:
+#	1. Create N(10) virtual disk files.
+#	2. Create draid pool based on the virtual disk files.
+#	3. Fill the filesystem with directories and files.
+#	4. Force-fault 2 vdevs and verify distributed spare is kicked in.
+#	5. Free the distributed spare by replacing the faulty drive.
+#	6. Run zpool clear and verify that it does not initiate 2 resilvers
+#	   concurrently while distributed spare gets kicked in.
+#
+
+verify_runnable "global"
+
+typeset -ir devs=10
+typeset -ir nparity=1
+typeset -ir ndata=8
+typeset -ir dspare=1
+
+function cleanup
+{
+	poolexists "$TESTPOOL" && destroy_pool "$TESTPOOL"
+
+	for i in {0..$devs}; do
+		log_must rm -f "$BASEDIR/vdev$i"
+	done
+
+	for dir in $BASEDIR; do
+		if [[ -d $dir ]]; then
+			log_must rm -rf $dir
+		fi
+	done
+
+	zed_stop
+	zed_cleanup
+}
+
+log_assert "Verify zpool clear on draid pool doesn't cause concurrent resilvers"
+log_onexit cleanup
+
+setup_test_env $TESTPOOL draid${nparity}:${ndata}d:${dspare}s $devs
+
+# ZED needed for sequential resilver
+zed_setup
+log_must zed_start
+
+log_must zpool offline -f $TESTPOOL $BASEDIR/vdev5
+log_must wait_vdev_state  $TESTPOOL draid1-0-0 "ONLINE" 60
+log_must zpool wait -t resilver $TESTPOOL
+log_must zpool offline -f $TESTPOOL $BASEDIR/vdev6
+
+log_must zpool labelclear -f $BASEDIR/vdev5
+log_must zpool labelclear -f $BASEDIR/vdev6
+
+log_must zpool replace -w $TESTPOOL $BASEDIR/vdev5
+sync_pool $TESTPOOL
+
+log_must zpool events -c
+log_must zpool clear $TESTPOOL
+log_must wait_vdev_state  $TESTPOOL draid1-0-0 "ONLINE" 60
+log_must zpool wait -t resilver $TESTPOOL
+log_must zpool wait -t scrub $TESTPOOL
+
+nof_resilver=$(zpool events | grep -c resilver_start)
+if [ $nof_resilver = 1 ] ; then
+	log_must verify_pool $TESTPOOL
+	log_pass "zpool clear on draid pool doesn't cause concurrent resilvers"
+else
+	log_fail "FAIL: sequential and healing resilver initiated concurrently"
+fi