summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--roles/monitoring/prometheus/server/defaults/main/rules_node.yml9
1 files changed, 9 insertions, 0 deletions
diff --git a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml
index 6a77b105..0a28871d 100644
--- a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml
+++ b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml
@@ -281,6 +281,15 @@ prometheus_server_rules_node:
summary: Some processes still use a deleted library (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "The deleted library {{ '{{' }} $labels.library_name {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }} is still in use by {{ '{{' }} $value {{ '}}' }} processes.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
+ - alert: SmartmonMetricsMissing
+ expr: absent(smartmon_smartctl_run)
+ for: 30m
+ labels:
+ severity: warning
+ annotations:
+ summary: Metrics from smartctl are missing (instance {{ '{{' }} $labels.instance {{ '}}' }})
+ description: "smartctl on host {{ '{{' }} $labels.instance {{ '}}' }} stopped reporting metrics for device {{ '{{' }} $labels.device {{ '}}' }}.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
+
- alert: SmartmonMetricsOutdated
expr: time() - smartmon_smartctl_run > 3600
for: 0m