diff --git a/check_smartstatus b/check_smartstatus
index ecd5584d740ecf57646a6ce3ebc89dbd03f1c550..2e691f0e5b4e66e3305003e5909911b81c641c98 100755
--- a/check_smartstatus
+++ b/check_smartstatus
@@ -38,11 +38,14 @@
# 2021-10-28 v1.3 <axel.hahn@iml.unibe.ch> detect -d param for smartctl
# 2022-07-08 v1.4 <axel.hahn@iml.unibe.ch> remove pipe in status line
# 2023-10-20 v1.5 <axel.hahn@unibe.ch> harden sudo command execution
+# 2024-06-07 v1.6 <axel.hahn@unibe.ch> add help page; use smartctl --scan to detect devices
# ======================================================================
. $(dirname $0)/inc_pluginfunctions
+self_APPVERSION=1.6
+
typeset -i iFound=0
typeset -i iErrors=0
sOut=
@@ -56,6 +59,35 @@ export PATH
# functions
# ----------------------------------------------------------------------
+# show help
+function showHelp(){
+ local self=$( basename $0 )
+ cat <<EOH
+$( ph.showImlHelpHeader )
+
+Show status of local S.M.A.R.T. devices.
+
+SYNTAX:
+ $self [-h] [-l] [devices]
+
+OPTIONS:
+
+ -h|--help show this help.
+ -l|--list list devices only.
+
+PARAMETERS:
+
+EXAMPLES
+
+ $self
+ Scan all local disks
+
+ $self -l
+ List all local disks without scanning them.
+
+EOH
+}
+
function detectParam(){
local _mydevice=$1
local _moreparam
@@ -74,7 +106,8 @@ function checkDrive(){
sLabel="^SMART.*Health"
sOK="(ok|passed)"
- sOut="$sOut ; ${device}:"
+ test -n "$sOut" && sOut="$sOut ; "
+ sOut="${device}:"
ls -ld $device >/dev/null 2>&1
@@ -91,7 +124,7 @@ function checkDrive(){
# --- check health
moreparam=$( detectParam $device )
echo sudo smartctl -Ha $device $moreparam >>$tmpfile 2>&1
- sudo smartctl -Ha $device $moreparam >>$tmpfile 2>&1
+ sudo -n smartctl -Ha $device $moreparam >>$tmpfile 2>&1
rcs=$?
echo $device - rc=$rcs >>$tmpfile
echo >>$tmpfile
@@ -103,7 +136,7 @@ function checkDrive(){
else
grep -i "$sLabel" $tmpfile >/dev/null
if [ $? -eq 0 ]; then
- status=`grep -i "$sLabel" $tmpfile | cut -f 2 -d ":"`
+ status=$( grep -i "$sLabel" $tmpfile | cut -f 2 -d ":")
sOut="$sOut ${status}"
echo $status | grep -Ei "$sOK" >>$tmpfile
if [ $? -ne 0 ]; then
@@ -124,10 +157,26 @@ function checkDrive(){
fi
}
+function listDevices(){
+ sudo -n smartctl --scan | grep -v "/dev/bus/"
+}
+
# ----------------------------------------------------------------------
# main
# ----------------------------------------------------------------------
+# parse params
+customaction=
+while [[ "$#" -gt 0 ]]; do case $1 in
+ -h|--help) showHelp; exit 0;;
+ -l|--list) customaction="list"; shift 1 ;;
+ *) if grep "^-" <<< "$1" >/dev/null ; then
+ echo; echo "ERROR: Unknown parameter: $1"; echo; exit 2
+ fi
+ break;
+ ;;
+esac; done
+
ph.require smartctl
rm -f $tmpDetailsfile 2>/dev/null
@@ -137,8 +186,15 @@ if ! sudo -n smartctl -h >/dev/null 2>&1; then
ph.abort "UNKNOWN: No sudo permissions to execute smartctl."
fi
+if [ "$customaction" == "list" ]; then
+ echo "Devices to scan:"
+ listDevices | sed "s#^#- #"
+ exit 0
+fi
+
# --- loop over sd devices
-for mydevice in $(ls -1 /dev/sd* | grep -v "[0-9]")
+# for mydevice in $(ls -1 /dev/sd* | grep -v "[0-9]")
+for mydevice in $( listDevices | cut -f 1 -d " " )
do
iFound=$iFound+1
@@ -154,12 +210,9 @@ do
checkDrive $mydevice
done
-ph.status "SMART check on $iFound HDs - $iErrors errors - $sOut"
-cat $tmpDetailsfile
-rm -f $tmpDetailsfile
-
+ph.status "SMART check on $iFound Disks - $iErrors errors - $sOut"
+cat $tmpDetailsfile 2>&1 && rm -f $tmpDetailsfile
ph.exit
-
# ----------------------------------------------------------------------
diff --git a/docs/20_Checks/_index.md b/docs/20_Checks/_index.md
index 0a06f3aae7377591d60b81c882f2fdc706cfade9..f8a7774e60f4e6ae2b0cc7ded88cdc4ac68d65c6 100644
--- a/docs/20_Checks/_index.md
+++ b/docs/20_Checks/_index.md
@@ -47,7 +47,7 @@ There is one include script used by all checks:
* [check_rearbackup](check_rearbackup.md)
* [check_reboot_required](check_reboot_required.md)
* [check_requirements](check_requirements.md)
-* check_smartstatus
+* [check_smartstatus](check_smartstatus.md)
* [check_snmp_data](check_snmp_data.md)
* check_snmp_printer
* check_snmp_switch
diff --git a/docs/20_Checks/check_smartstatus.md b/docs/20_Checks/check_smartstatus.md
new file mode 100644
index 0000000000000000000000000000000000000000..7131c8372b147759f8edba4b103d8d21a9ec0d74
--- /dev/null
+++ b/docs/20_Checks/check_smartstatus.md
@@ -0,0 +1,151 @@
+# Check_smartstatus
+
+## Introduction
+
+**check_smartstatus** is a plugin run a smartctl check to verify the disk status of all local harddisks/ ssds.
+
+It works on physical machines only.
+
+## Requirements
+
+* `smartctl`
+
+The icinga user needs sudo permissions on the smartctl binary.
+
+```txt
+icingaclient ALL=(ALL) NOPASSWD: /sbin/smartctl
+```
+
+## Syntax
+
+```txt
+______________________________________________________________________
+
+CHECK_SMARTSTATUS
+v1.6
+
+(c) Institute for Medical Education - University of Bern
+Licence: GNU GPL 3
+
+https://os-docs.iml.unibe.ch/icinga-checks/Checks/check_smartstatus.html
+______________________________________________________________________
+
+Show status of local S.M.A.R.T. devices.
+
+SYNTAX:
+ check_smartstatus [-h] [-l] [devices]
+
+OPTIONS:
+
+ -h|--help show this help.
+ -l|--list list devices only.
+
+PARAMETERS:
+
+EXAMPLES
+
+ check_smartstatus
+ Scan all local disks
+
+ check_smartstatus -l
+ List all local disks without scanning them.
+
+```
+
+### Parameters
+
+(none)
+
+## Examples
+
+Fort testing purposes: Show devices only without scanning them:
+
+```txt
+./check_smartstatus -l
+Devices to scan:
+- /dev/nvme0 -d nvme # /dev/nvme0, NVMe device
+```
+
+Without parameter `check_smartstatus` will loop over all found devices and perform a SMART scan on each. You get a status line with a summary followed by the output sections for each disk.
+
+This is the output of a single SSD:
+
+```txt
+OK: SMART check on 1 Disks - 0 errors - /dev/nvme0: PASSED
+SMART/Health Information (NVMe Log 0x02)
+----------------------------------------------------------------------
+
+/dev/nvme0
+
+sudo smartctl -Ha /dev/nvme0
+smartctl 7.4 2023-08-01 r5530 [x86_64-linux-6.9.2-1-MANJARO] (local build)
+Copyright (C) 2002-23, Bruce Allen, Christian Franke, www.smartmontools.org
+
+=== START OF INFORMATION SECTION ===
+Model Number: SKHynix_HFS001TEJ9X162N
+Serial Number: AJC9N469110209D22
+Firmware Version: 51730A10
+PCI Vendor/Subsystem ID: 0x1c5c
+IEEE OUI Identifier: 0xace42e
+Controller ID: 0
+NVMe Version: 1.4
+Number of Namespaces: 1
+Namespace 1 Size/Capacity: 1,024,209,543,168 [1.02 TB]
+Namespace 1 Formatted LBA Size: 512
+Namespace 1 IEEE EUI-64: ace42e 0035db84db
+Local Time is: Fri Jun 7 12:59:02 2024 CEST
+Firmware Updates (0x16): 3 Slots, no Reset required
+Optional Admin Commands (0x0017): Security Format Frmw_DL Self_Test
+Optional NVM Commands (0x00df): Comp Wr_Unc DS_Mngmt Wr_Zero Sav/Sel_Feat Timestmp Verify
+Log Page Attributes (0x1e): Cmd_Eff_Lg Ext_Get_Lg Telmtry_Lg Pers_Ev_Lg
+Maximum Data Transfer Size: 64 Pages
+Warning Comp. Temp. Threshold: 86 Celsius
+Critical Comp. Temp. Threshold: 87 Celsius
+
+Supported Power States
+St Op Max Active Idle RL RT WL WT Ent_Lat Ex_Lat
+ 0 + 7.50W - - 0 0 0 0 5 305
+ 1 + 3.9000W - - 1 1 1 1 30 330
+ 2 + 1.5000W - - 2 2 2 2 100 400
+ 3 - 0.0500W - - 3 3 3 3 500 1500
+ 4 - 0.0050W - - 4 4 4 4 1000 9000
+
+Supported LBA Sizes (NSID 0x1)
+Id Fmt Data Metadt Rel_Perf
+ 0 + 512 0 0
+
+=== START OF SMART DATA SECTION ===
+SMART overall-health self-assessment test result: PASSED
+
+SMART/Health Information (NVMe Log 0x02)
+Critical Warning: 0x00
+Temperature: 43 Celsius
+Available Spare: 100%
+Available Spare Threshold: 10%
+Percentage Used: 0%
+Data Units Read: 6,589,009 [3.37 TB]
+Data Units Written: 3,879,914 [1.98 TB]
+Host Read Commands: 39,241,205
+Host Write Commands: 72,717,841
+Controller Busy Time: 2,112
+Power Cycles: 176
+Power On Hours: 642
+Unsafe Shutdowns: 21
+Media and Data Integrity Errors: 0
+Error Information Log Entries: 0
+Warning Comp. Temperature Time: 0
+Critical Comp. Temperature Time: 0
+Temperature Sensor 1: 40 Celsius
+Temperature Sensor 2: 37 Celsius
+
+Error Information (NVMe Log 0x01, 16 of 256 entries)
+No Errors Logged
+
+Self-test Log (NVMe Log 0x06)
+Self-test status: No self-test in progress
+No Self-tests Logged
+
+/dev/nvme0 - rc=0
+
+PASSED SMART/Health Information (NVMe Log 0x02)
+```