Consider physical blocksize for SmartHealthStatusFail alert

canonical · Dec 14, 2024 · 10f2583 · 10f2583
1 parent af58ad1
commit 10f2583
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 1 deletion.
diff --git a/src/prometheus_alert_rules/smart.yaml b/src/prometheus_alert_rules/smart.yaml
@@ -33,7 +33,7 @@ groups:
           LABELS = {{ $labels }}
 
   - alert: SmartHealthStatusFail
-    expr: smartctl_device_smart_status == 0
+    expr: (smartctl_device_smart_status == 0) and on(device, juju_unit) (smartctl_device_block_size{blocks_type="physical"} != 0)
     for: 2m
     labels:
       severity: critical

diff --git a/tests/unit/test_alert_rules/test_smart.yaml b/tests/unit/test_alert_rules/test_smart.yaml
@@ -68,6 +68,8 @@ tests:
     input_series:
       - series: 'smartctl_device_smart_status{device="sda", instance="ubuntu-1"}'
         values: '0x15'
+      - series: 'smartctl_device_block_size{device="sda", instance="ubuntu-1", blocks_type="physical"}'
+        values: '1x15'
 
     alert_rule_test:
       - eval_time: 10m
@@ -84,6 +86,18 @@ tests:
                   VALUE = 0
                   LABELS = map[__name__:smartctl_device_smart_status device:sda instance:ubuntu-1]
 
+  - interval: 1m
+    input_series:
+      - series: 'smartctl_device_smart_status{device="sda", instance="ubuntu-1"}'
+        values: '0x15'
+      - series: 'smartctl_device_block_size{device="sda", instance="ubuntu-1", blocks_type="physical"}'
+        values: '0x15'
+
+    alert_rule_test:
+      - eval_time: 10m
+        alertname: SmartHealthStatusFail
+        exp_alerts: # alerts shouldn't fire since block size is 0
+
   - interval: 1m
     input_series:
       - series: 'smartctl_device_smartctl_exit_status{device="sda", instance="ubuntu-2"}'