Add ipmiseld alert rule (canonical#261)

zxhdaze · Jun 19, 2024 · 2dcafeb · 2dcafeb
1 parent 651dded
commit 2dcafeb
Show file tree

Hide file tree

Showing 2 changed files with 45 additions and 0 deletions.
diff --git a/src/prometheus_alert_rules/ipmi_sel.yaml b/src/prometheus_alert_rules/ipmi_sel.yaml
@@ -35,3 +35,15 @@ groups:
         description: |
           IPMI SEL entry in critical state.
             LABELS = {{ $labels }}
+
+    - alert: IPMISELDStateWarning
+      expr: node_systemd_unit_state{name="ipmiseld.service", state=~"failed|inactive"} == 1
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: IPMISELD service is not active. (instance {{ $labels.instance }})
+        description: |
+          The ipmiseld service is not active, indicating a potential problem.
+            VALUE = {{ $value }}
+            LABELS = {{ $labels }}
diff --git a/tests/unit/test_alert_rules/test_ipmi_sel.yaml b/tests/unit/test_alert_rules/test_ipmi_sel.yaml
@@ -19,6 +19,12 @@ tests:
       - series: ipmi_sel_state{instance="ubuntu-2"}
         values: '2x15'
 
+      - series: node_systemd_unit_state{name="ipmiseld.service", instance="ubuntu-3", state="failed"}
+        values: '1x15'
+
+      - series: node_systemd_unit_state{name="ipmiseld.service", instance="ubuntu-4", state="inactive"}
+        values: '1x15'
+
     alert_rule_test:
       - eval_time: 10m
         alertname: IPMISELCommandFailed
@@ -56,3 +62,30 @@ tests:
               description: |
                 IPMI SEL entry in critical state.
                   LABELS = map[__name__:ipmi_sel_state instance:ubuntu-2]
+
+      - eval_time: 10m
+        alertname: IPMISELDStateWarning
+        exp_alerts:
+          - exp_labels:
+              severity: warning
+              name: ipmiseld.service
+              instance: ubuntu-3
+              state: failed
+            exp_annotations:
+              summary: IPMISELD service is not active. (instance ubuntu-3)
+              description: |
+                The ipmiseld service is not active, indicating a potential problem.
+                  VALUE = 1
+                  LABELS = map[__name__:node_systemd_unit_state instance:ubuntu-3 name:ipmiseld.service state:failed]
+
+          - exp_labels:
+              severity: warning
+              name: ipmiseld.service
+              instance: ubuntu-4
+              state: inactive
+            exp_annotations:
+              summary: IPMISELD service is not active. (instance ubuntu-4)
+              description: |
+                The ipmiseld service is not active, indicating a potential problem.
+                  VALUE = 1
+                  LABELS = map[__name__:node_systemd_unit_state instance:ubuntu-4 name:ipmiseld.service state:inactive]