Add 'zpool status -e' flag to see unhealthy vdevs

When very large pools are present, it can be laborious to find
reasons for why a pool is degraded and/or where an unhealthy vdev
is. This option filters out vdevs that are ONLINE and with no errors
to make it easier to see where the issues are. Root and parents of
unhealthy vdevs will always be printed.

Testing:
ZFS errors and drive failures for multiple vdevs were simulated with
zinject.

Sample vdev listings with '-e' option
- All vdevs healthy
    NAME        STATE     READ WRITE CKSUM
    iron5       ONLINE       0     0     0

- ZFS errors
    NAME        STATE     READ WRITE CKSUM
    iron5       ONLINE       0     0     0
      raidz2-5  ONLINE       1     0     0
        L23     ONLINE       1     0     0
        L24     ONLINE       1     0     0
        L37     ONLINE       1     0     0

- Vdev faulted
    NAME        STATE     READ WRITE CKSUM
    iron5       DEGRADED     0     0     0
      raidz2-6  DEGRADED     0     0     0
        L67     FAULTED      0     0     0  too many errors

- Vdev faults and data errors
    NAME        STATE     READ WRITE CKSUM
    iron5       DEGRADED     0     0     0
      raidz2-1  DEGRADED     0     0     0
        L2      FAULTED      0     0     0  too many errors
      raidz2-5  ONLINE       1     0     0
        L23     ONLINE       1     0     0
        L24     ONLINE       1     0     0
        L37     ONLINE       1     0     0
      raidz2-6  DEGRADED     0     0     0
        L67     FAULTED      0     0     0  too many errors

- Vdev missing
    NAME        STATE     READ WRITE CKSUM
    iron5       DEGRADED     0     0     0
      raidz2-6  DEGRADED     0     0     0
        L67     UNAVAIL      3     1     0

- Slow devices when -s provided with -e
    NAME        STATE     READ WRITE CKSUM  SLOW
    iron5       DEGRADED     0     0     0     -
      raidz2-5  DEGRADED     0     0     0     -
        L10     FAULTED      0     0     0     0  external device fault
        L51     ONLINE       0     0     0    14

Reviewed-by: Tony Hutter <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Cameron Harr <[email protected]>
Closes #15769 

5 files changed, 112 insertions, 2 deletions

diff --git a/tests/runfiles/common.run b/tests/runfiles/common.run
index dd936ce59..733124451 100644
--- a/tests/runfiles/common.run
+++ b/tests/runfiles/common.run
@@ -535,7 +535,8 @@ tags = ['functional', 'cli_root', 'zpool_split']
 tests = ['zpool_status_001_pos', 'zpool_status_002_pos',
     'zpool_status_003_pos', 'zpool_status_004_pos',
     'zpool_status_005_pos', 'zpool_status_006_pos',
-    'zpool_status_007_pos', 'zpool_status_features_001_pos']
+    'zpool_status_007_pos', 'zpool_status_008_pos',
+    'zpool_status_features_001_pos']
 tags = ['functional', 'cli_root', 'zpool_status']
 
 [tests/functional/cli_root/zpool_sync]
diff --git a/tests/zfs-tests/tests/Makefile.am b/tests/zfs-tests/tests/Makefile.am
index 7442c7985..e2824ee06 100644
--- a/tests/zfs-tests/tests/Makefile.am
+++ b/tests/zfs-tests/tests/Makefile.am
@@ -1238,6 +1238,7 @@ nobase_dist_datadir_zfs_tests_tests_SCRIPTS += \
 	functional/cli_root/zpool_status/zpool_status_005_pos.ksh \
 	functional/cli_root/zpool_status/zpool_status_006_pos.ksh \
 	functional/cli_root/zpool_status/zpool_status_007_pos.ksh \
+	functional/cli_root/zpool_status/zpool_status_008_pos.ksh \
 	functional/cli_root/zpool_status/zpool_status_features_001_pos.ksh \
 	functional/cli_root/zpool_sync/cleanup.ksh \
 	functional/cli_root/zpool_sync/setup.ksh \
diff --git a/tests/zfs-tests/tests/functional/cli_root/zpool_status/zpool_status_002_pos.ksh b/tests/zfs-tests/tests/functional/cli_root/zpool_status/zpool_status_002_pos.ksh
index 3bdd7db64..d6f32cdc7 100755
--- a/tests/zfs-tests/tests/functional/cli_root/zpool_status/zpool_status_002_pos.ksh
+++ b/tests/zfs-tests/tests/functional/cli_root/zpool_status/zpool_status_002_pos.ksh
@@ -51,7 +51,7 @@ else
 fi
 
 set -A args "" "-x" "-v" "-x $testpool" "-v $testpool" "-xv $testpool" \
-	"-vx $testpool"
+	"-vx $testpool" "-e $testpool" "-es $testpool"
 
 log_assert "Executing 'zpool status' with correct options succeeds"
 
@@ -64,4 +64,6 @@ while [[ $i -lt ${#args[*]} ]]; do
 	(( i = i + 1 ))
 done
 
+cleanup 
+
 log_pass "'zpool status' with correct options succeeded"
diff --git a/tests/zfs-tests/tests/functional/cli_root/zpool_status/zpool_status_003_pos.ksh b/tests/zfs-tests/tests/functional/cli_root/zpool_status/zpool_status_003_pos.ksh
index b501aac5a..52b22dd83 100755
--- a/tests/zfs-tests/tests/functional/cli_root/zpool_status/zpool_status_003_pos.ksh
+++ b/tests/zfs-tests/tests/functional/cli_root/zpool_status/zpool_status_003_pos.ksh
@@ -37,6 +37,7 @@
 # 3. Read the file
 # 4. Take a snapshot and make a clone
 # 5. Verify we see "snapshot, clone and filesystem" output in 'zpool status -v'
+#      and 'zpool status -ev'
 
 function cleanup
 {
@@ -68,6 +69,7 @@ log_must zpool status -v $TESTPOOL2
 log_must eval "zpool status -v | grep '$TESTPOOL2@snap:/10m_file'"
 log_must eval "zpool status -v | grep '$TESTPOOL2/clone/10m_file'"
 log_must eval "zpool status -v | grep '$TESTPOOL2/10m_file'"
+log_must eval "zpool status -ev | grep '$TESTPOOL2/10m_file'"
 log_mustnot eval "zpool status -v | grep '$TESTFS1'"
 
 log_pass "'zpool status -v' outputs affected filesystem, snapshot & clone"
diff --git a/tests/zfs-tests/tests/functional/cli_root/zpool_status/zpool_status_008_pos.ksh b/tests/zfs-tests/tests/functional/cli_root/zpool_status/zpool_status_008_pos.ksh
new file mode 100755
index 000000000..6be2ad5a7
--- /dev/null
+++ b/tests/zfs-tests/tests/functional/cli_root/zpool_status/zpool_status_008_pos.ksh
@@ -0,0 +1,104 @@
+#!/bin/ksh -p
+
+#
+# CDDL HEADER START
+#
+# This file and its contents are supplied under the terms of the
+# Common Development and Distribution License ("CDDL"), version 1.0.
+# You may only use this file in accordance with the terms of version
+# 1.0 of the CDDL.
+#
+# A full copy of the text of the CDDL should have accompanied this
+# source.  A copy of the CDDL is also available via the Internet at
+# http://www.illumos.org/license/CDDL.
+#
+# CDDL HEADER END
+#
+
+#
+# Copyright (c) 2024 by Lawrence Livermore National Security, LLC.
+#
+
+. $STF_SUITE/include/libtest.shlib
+
+#
+# DESCRIPTION:
+# Verify 'zpool status -e' only shows unhealthy devices.
+#
+# STRATEGY:
+# 1. Create zpool
+# 2. Force DEGRADE, FAULT, or inject slow IOs for vdevs
+# 3. Verify vdevs are reported correctly with -e and -s
+# 4. Verify parents are reported as DEGRADED
+# 5. Verify healthy children are not reported
+#
+
+function cleanup
+{
+	log_must set_tunable64 ZIO_SLOW_IO_MS $OLD_SLOW_IO
+	zinject -c all
+	poolexists $TESTPOOL2 && destroy_pool $TESTPOOL2
+	log_must rm -f $all_vdevs
+}
+
+log_assert "Verify 'zpool status -e'"
+
+log_onexit cleanup
+
+all_vdevs=$(echo $TESTDIR/vdev{1..6})
+log_must mkdir -p $TESTDIR
+log_must truncate -s $MINVDEVSIZE $all_vdevs
+
+OLD_SLOW_IO=$(get_tunable ZIO_SLOW_IO_MS)
+
+for raid_type in "draid2:3d:6c:1s" "raidz2"; do
+
+	log_must zpool create -f $TESTPOOL2 $raid_type $all_vdevs
+
+	# Check DEGRADED vdevs are shown.
+	log_must check_vdev_state $TESTPOOL2 $TESTDIR/vdev4 "ONLINE"
+	log_must zinject -d $TESTDIR/vdev4 -A degrade $TESTPOOL2
+	log_must eval "zpool status -e $TESTPOOL2 | grep $TESTDIR/vdev4 | grep DEGRADED"
+
+	# Check FAULTED vdevs are shown.
+	log_must check_vdev_state $TESTPOOL2 $TESTDIR/vdev5 "ONLINE"
+	log_must zinject -d $TESTDIR/vdev5 -A fault $TESTPOOL2
+	log_must eval "zpool status -e $TESTPOOL2 | grep $TESTDIR/vdev5 | grep FAULTED"
+
+	# Check no ONLINE vdevs are shown
+	log_mustnot eval "zpool status -e $TESTPOOL2 | grep ONLINE"
+
+	# Check no ONLINE slow vdevs are show.  Then mark IOs greater than
+	# 10ms slow, delay IOs 20ms to vdev6, check slow IOs.
+	log_must check_vdev_state $TESTPOOL2 $TESTDIR/vdev6 "ONLINE"
+	log_mustnot eval "zpool status -es $TESTPOOL2 | grep ONLINE"
+
+	log_must set_tunable64 ZIO_SLOW_IO_MS 10
+	log_must zinject -d $TESTDIR/vdev6 -D20:100 $TESTPOOL2
+	log_must mkfile 1048576 /$TESTPOOL2/testfile
+	sync_pool $TESTPOOL2
+	log_must set_tunable64 ZIO_SLOW_IO_MS $OLD_SLOW_IO
+
+	# Check vdev6 slow IOs are only shown when requested with -s.
+	log_mustnot eval "zpool status -e $TESTPOOL2 | grep $TESTDIR/vdev6 | grep ONLINE"
+	log_must eval "zpool status -es $TESTPOOL2 | grep $TESTDIR/vdev6 | grep ONLINE"
+
+	# Pool level and top-vdev level status must be DEGRADED.
+	log_must eval "zpool status -e $TESTPOOL2 | grep $TESTPOOL2 | grep DEGRADED"
+	log_must eval "zpool status -e $TESTPOOL2 | grep $raid_type | grep DEGRADED"
+
+	# Check that healthy vdevs[1-3] aren't shown with -e.
+	log_must check_vdev_state $TESTPOOL2 $TESTDIR/vdev1 "ONLINE"
+	log_must check_vdev_state $TESTPOOL2 $TESTDIR/vdev2 "ONLINE"
+	log_must check_vdev_state $TESTPOOL2 $TESTDIR/vdev3 "ONLINE"
+	log_mustnot eval "zpool status -es $TESTPOOL2 | grep $TESTDIR/vdev1 | grep ONLINE"
+	log_mustnot eval "zpool status -es $TESTPOOL2 | grep $TESTDIR/vdev2 | grep ONLINE"
+	log_mustnot eval "zpool status -es $TESTPOOL2 | grep $TESTDIR/vdev3 | grep ONLINE"
+
+	log_must zinject -c all
+	log_must zpool status -es $TESTPOOL2
+
+	zpool destroy $TESTPOOL2
+done
+
+log_pass "Verify zpool status -e shows only unhealthy vdevs"