zed: Add zedlet to power off slot when drive is faulted

If ZED_POWER_OFF_ENCLOUSRE_SLOT_ON_FAULT is enabled in zed.rc, then
power off the drive's slot in the enclosure if it becomes FAULTED.
This can help silence misbehaving drives.  This assumes your drive
enclosure fully supports slot power control via sysfs.

Reviewed-by: @AllKind
Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Tony Hutter <[email protected]>
Closes #15200 

2 files changed, 66 insertions, 0 deletions

diff --git a/cmd/zed/zed.d/statechange-slot_off.sh b/cmd/zed/zed.d/statechange-slot_off.sh
new file mode 100755
index 000000000..d6f3c94a4
--- /dev/null
+++ b/cmd/zed/zed.d/statechange-slot_off.sh
@@ -0,0 +1,61 @@
+#!/bin/sh
+#
+# Turn off disk's enclosure slot if it becomes FAULTED.
+#
+# Bad SCSI disks can often "disappear and reappear" causing all sorts of chaos
+# as they flip between FAULTED and ONLINE.  If
+# ZED_POWER_OFF_ENCLOUSRE_SLOT_ON_FAULT is set in zed.rc, and the disk gets
+# FAULTED, then power down the slot via sysfs:
+#
+# /sys/class/enclosure/<enclosure>/<slot>/power_status
+#
+# We assume the user will be responsible for turning the slot back on again.
+#
+# Note that this script requires that your enclosure be supported by the
+# Linux SCSI Enclosure services (SES) driver.  The script will do nothing
+# if you have no enclosure, or if your enclosure isn't supported.
+#
+# Exit codes:
+#   0: slot successfully powered off
+#   1: enclosure not available
+#   2: ZED_POWER_OFF_ENCLOUSRE_SLOT_ON_FAULT disabled
+#   3: vdev was not FAULTED
+#   4: The enclosure sysfs path passed from ZFS does not exist
+#   5: Enclosure slot didn't actually turn off after we told it to
+
+[ -f "${ZED_ZEDLET_DIR}/zed.rc" ] && . "${ZED_ZEDLET_DIR}/zed.rc"
+. "${ZED_ZEDLET_DIR}/zed-functions.sh"
+
+if [ ! -d /sys/class/enclosure ] ; then
+	# No JBOD enclosure or NVMe slots
+	exit 1
+fi
+
+if [ "${ZED_POWER_OFF_ENCLOUSRE_SLOT_ON_FAULT}" != "1" ] ; then
+	exit 2
+fi
+
+if [ "$ZEVENT_VDEV_STATE_STR" != "FAULTED" ] ; then
+	exit 3
+fi
+
+if [ ! -f "$ZEVENT_VDEV_ENC_SYSFS_PATH/power_status" ] ; then
+	exit 4
+fi
+
+echo "off" | tee "$ZEVENT_VDEV_ENC_SYSFS_PATH/power_status"
+
+# Wait for sysfs for report that the slot is off.  It can take ~400ms on some
+# enclosures.
+for i in $(seq 1 20) ; do
+	if [ "$(cat $ZEVENT_VDEV_ENC_SYSFS_PATH/power_status)" == "off" ] ; then
+		break
+	fi
+	sleep 0.1
+done
+
+if [ "$(cat $ZEVENT_VDEV_ENC_SYSFS_PATH/power_status)" != "off" ] ; then
+	exit 5
+fi
+
+zed_log_msg "powered down slot $ZEVENT_VDEV_ENC_SYSFS_PATH for $ZEVENT_VDEV_PATH"
diff --git a/cmd/zed/zed.d/zed.rc b/cmd/zed/zed.d/zed.rc
index c55a70c79..78dc1afc7 100644
--- a/cmd/zed/zed.d/zed.rc
+++ b/cmd/zed/zed.d/zed.rc
@@ -142,3 +142,8 @@ ZED_SYSLOG_SUBCLASS_EXCLUDE="history_event"
 # Disabled by default, 1 to enable and 0 to disable.
 #ZED_SYSLOG_DISPLAY_GUIDS=1
 
+##
+# Power off the drive's slot in the enclosure if it becomes FAULTED.  This can
+# help silence misbehaving drives.  This assumes your drive enclosure fully
+# supports slot power control via sysfs.
+#ZED_POWER_OFF_ENCLOUSRE_SLOT_ON_FAULT=1