feat(systemd-units-failed): show failed unit names in first output line (#967)

Author: markuslf

CHANGELOG.md

@@ -85,6 +85,7 @@ Monitoring Plugins:
 * redis-status, valkey-status: modernize code and unify both plugins again after [PR #954](https://github.com/Linuxfabrik/monitoring-plugins/pull/954)
 * rocketchat-stats: improve output
 * statuspal: replace `flatdict` dependency with a recursive approach ([#1044](https://github.com/Linuxfabrik/monitoring-plugins/issues/1044))
+* systemd-units-failed: show failed unit names in the first output line for better dashboard and SMS alert readability ([#967](https://github.com/Linuxfabrik/monitoring-plugins/issues/967))
 * updates: adapt to updated powershell.py library
 
 

check-plugins/systemd-units-failed/README.md

@@ -45,11 +45,11 @@ options:
 Output:
 
 ```text
-There is 1 failed unit.
+1 failed unit: ipmievd.service
 
-unit            load   active sub    description
-----            ----   ------ ---    -----------
-ipmievd.service loaded failed failed Ipmievd Daemon
+unit            ! load   ! active ! sub    ! description
+----------------+--------+--------+--------+----------------
+ipmievd.service ! loaded ! failed ! failed ! Ipmievd Daemon
 ```
 
 

check-plugins/systemd-units-failed/systemd-units-failed

@@ -11,20 +11,20 @@
 """See the check's README for more details.
 """
 
-import argparse  # pylint: disable=C0413
-import fnmatch  # pylint: disable=C0413
-import sys  # pylint: disable=C0413
-
-import lib.args  # pylint: disable=C0413
-import lib.base  # pylint: disable=C0413
-import lib.shell  # pylint: disable=C0413
-import lib.lftest  # pylint: disable=C0413
-import lib.txt  # pylint: disable=C0413
-from lib.globals import (STATE_OK, STATE_UNKNOWN,  # pylint: disable=C0413
+import argparse
+import fnmatch
+import sys
+
+import lib.args
+import lib.base
+import lib.lftest
+import lib.shell
+import lib.txt
+from lib.globals import (STATE_OK, STATE_UNKNOWN,
                           STATE_WARN)
 
 __author__ = 'Linuxfabrik GmbH, Zurich/Switzerland'
-__version__ = '2025100601'
+__version__ = '2026040801'
 
 DESCRIPTION = """Warns on any failed systemd units."""
 
@@ -39,7 +39,7 @@ def parse_args():
     parser.add_argument(
         '-V', '--version',
         action='version',
-        version='%(prog)s: v{} by {}'.format(__version__, __author__)
+        version=f'%(prog)s: v{__version__} by {__author__}'
     )
 
     parser.add_argument(
@@ -52,7 +52,10 @@ def parse_args():
 
     parser.add_argument(
         '--ignore',
-        help='Ignore a unit, for example "dhcpd.service" (repeating). Supports glob according to https://docs.python.org/3/library/fnmatch.html. Default: %(default)s',
+        help='Ignore a unit, for example "dhcpd.service" (repeating). '
+             'Supports glob according to '
+             'https://docs.python.org/3/library/fnmatch.html. '
+             'Default: %(default)s',
         dest='IGNORE',
         default=DEFAULT_IGNORE,
         action='append',
@@ -103,7 +106,7 @@ def main():
             if line.startswith('*'):
                 offset = 1
             unit = line.split()
-            if any([fnmatch.fnmatchcase(unit[0 + offset], ignore) for ignore in args.IGNORE]):
+            if any(fnmatch.fnmatchcase(unit[0 + offset], ignore) for ignore in args.IGNORE):
                 continue
             count += 1
             table_data.append({
@@ -115,25 +118,27 @@ def main():
             })
         if count > 0:
             state = STATE_WARN
-            msg = 'There {} {} failed {}.\n'.format(
-                lib.txt.pluralize('', count, 'is,are'),
-                count,
-                lib.txt.pluralize('unit', count),
-            )
+            unit_names = ', '.join(row['unit'] for row in table_data)
+            msg = f'{count} failed {lib.txt.pluralize("unit", count)}: {unit_names}\n'
             table = lib.base.get_table(
                 table_data,
                 ['unit', 'load', 'active', 'sub', 'description'],
                 ['unit', 'load', 'active', 'sub', 'description'],
             )
 
-    perfdata = lib.base.get_perfdata('systemd-units-failed', count, None, 1, None, 0, None)
+    perfdata = lib.base.get_perfdata(
+        'systemd-units-failed',
+        count,
+        warn=1,
+        _min=0,
+    )
 
     # over and out
-    lib.base.oao('{}\n\n{}'.format(msg, table), state, perfdata, always_ok=args.ALWAYS_OK)
+    lib.base.oao(f'{msg}\n\n{table}', state, perfdata, always_ok=args.ALWAYS_OK)
 
 
 if __name__ == '__main__':
     try:
         main()
-    except Exception:   # pylint: disable=W0703
+    except Exception:
         lib.base.cu()

check-plugins/systemd-units-failed/unit-test/run

@@ -32,19 +32,19 @@ class TestCheck(unittest.TestCase):
 
     def test_if_check_runs_EXAMPLE02(self):
         stdout, stderr, retc = lib.base.coe(lib.shell.shell_exec(self.check + ' --test=stdout/EXAMPLE02,,0'))
-        self.assertRegex(stdout, r'There is 1 failed unit.')
+        self.assertIn('1 failed unit: openipmi.service', stdout)
         self.assertEqual(stderr, '')
         self.assertEqual(retc, STATE_WARN)
 
     def test_if_check_runs_EXAMPLE03(self):
         stdout, stderr, retc = lib.base.coe(lib.shell.shell_exec(self.check + ' --test=stdout/EXAMPLE03,,0'))
-        self.assertRegex(stdout, r'There are 2 failed units.')
+        self.assertIn('2 failed units: openipmi.service, smartd.service', stdout)
         self.assertEqual(stderr, '')
         self.assertEqual(retc, STATE_WARN)
 
     def test_if_check_runs_EXAMPLE03_ignore1(self):
         stdout, stderr, retc = lib.base.coe(lib.shell.shell_exec(self.check + ' --ignore=openipmi.service --test=stdout/EXAMPLE03,,0'))
-        self.assertRegex(stdout, r'There is 1 failed unit.')
+        self.assertIn('1 failed unit: smartd.service', stdout)
         self.assertEqual(stderr, '')
         self.assertEqual(retc, STATE_WARN)
 
@@ -62,13 +62,13 @@ class TestCheck(unittest.TestCase):
 
     def test_if_check_runs_EXAMPLE04(self):
         stdout, stderr, retc = lib.base.coe(lib.shell.shell_exec(self.check + ' --test=stdout/EXAMPLE04,,0'))
-        self.assertRegex(stdout, r'There is 1 failed unit.')
+        self.assertIn('1 failed unit: chronyd.service', stdout)
         self.assertEqual(stderr, '')
         self.assertEqual(retc, STATE_WARN)
 
     def test_if_check_runs_EXAMPLE05(self):
         stdout, stderr, retc = lib.base.coe(lib.shell.shell_exec(self.check + ' --test=stdout/EXAMPLE05,,0'))
-        self.assertRegex(stdout, r'There are 3 failed units.')
+        self.assertIn('3 failed units: tomcat8.service, varnish.service, varnishlog.service', stdout)
         self.assertRegex(stdout, r'unit               ! load      ! active ! sub    ! description')
         self.assertRegex(stdout, r'tomcat8.service    ! not-found ! failed ! failed ! tomcat8.service')
         self.assertRegex(stdout, r'varnish.service    ! loaded    ! failed ! failed ! Varnish HTTP accelerator')