Fix template variable usage (#199)

* Update host_health.rules Signed-off-by: Leon <[email protected]> * Move individual alerts under group * Rename ext to match contents --------- Signed-off-by: Leon <[email protected]>
canonical · Nov 20, 2024 · 2eecc8f · 2eecc8f
1 parent a5e2f57
commit 2eecc8f
Show file tree

Hide file tree

Showing 5 changed files with 24 additions and 18 deletions.
diff --git a/src/prometheus_alert_rules/high_cpu_iowait.rule b/src/prometheus_alert_rules/high_cpu_iowait.rule
diff --git a/src/prometheus_alert_rules/high_cpu_iowait.rules b/src/prometheus_alert_rules/high_cpu_iowait.rules
@@ -0,0 +1,11 @@
+groups:
+- name: HostCpu
+  rules:
+  - alert: HostCpuHighIowait
+    expr: avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 10
+    for: 0m
+    labels:
+      severity: warning
+    annotations:
+      summary: Host CPU high iowait (instance {{ $labels.instance }})
+      description: "CPU iowait > 10%. A high iowait means that you are disk or network bound.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
diff --git a/src/prometheus_alert_rules/host_health.rules b/src/prometheus_alert_rules/host_health.rules
@@ -7,7 +7,7 @@ groups:
     labels:
       severity: critical
     annotations:
-      summary: Host '{{labels.instance}}' is down.
+      summary: Host '{{ $labels.instance }}' is down.
       description: >-
         Host '{{ $labels.instance }}' is down.
           VALUE = {{ $value }}
@@ -18,7 +18,7 @@ groups:
     labels:
       severity: critical
     annotations:
-      summary: Metrics not received from host '{{labels.instance}}'.
+      summary: Metrics not received from host '{{ $labels.instance }}'.
       description: >-
         The metrics endpoint for host '{{ $labels.instance }}' is unreachable.
           VALUE = {{ $value }}

diff --git a/src/prometheus_alert_rules/oomkill.rule b/src/prometheus_alert_rules/oomkill.rule
diff --git a/src/prometheus_alert_rules/oomkill.rules b/src/prometheus_alert_rules/oomkill.rules
@@ -0,0 +1,11 @@
+groups:
+- name: HostMemory
+  rules:
+  - alert: HostOomKillDetected
+    expr: increase(node_vmstat_oom_kill[1h]) > 0
+    for: 0m
+    labels:
+      severity: warning
+    annotations:
+      summary: Host OOM kill detected (instance {{ $labels.instance }})
+      description: "OOM kill detected\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"