summaryrefslogtreecommitdiff
path: root/roles/monitoring/prometheus/server/defaults/main/rules_node.yml
diff options
context:
space:
mode:
Diffstat (limited to 'roles/monitoring/prometheus/server/defaults/main/rules_node.yml')
-rw-r--r--roles/monitoring/prometheus/server/defaults/main/rules_node.yml11
1 files changed, 10 insertions, 1 deletions
diff --git a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml
index 2c7f9319..64a7d562 100644
--- a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml
+++ b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml
@@ -92,6 +92,15 @@ prometheus_server_rules_node:
summary: Host CPU steal noisy neighbor (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
+ - alert: HostSystemdNotRunning
+ expr: node_systemd_system_running == 0
+ for: 0m
+ labels:
+ severity: warning
+ annotations:
+ summary: Host systemd is not in running state (instance {{ '{{' }} $labels.instance {{ '}}' }})
+ description: "systemd is not in running state.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
+
- alert: HostSystemdServiceCrashed
expr: node_systemd_unit_state{state="failed"} == 1
for: 0m
@@ -99,7 +108,7 @@ prometheus_server_rules_node:
severity: warning
annotations:
summary: Host systemd service crashed (instance {{ '{{' }} $labels.instance {{ '}}' }})
- description: "systemd service crashed\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
+ description: "The systemd service unit {{ '{{' }} $labels.name {{ '}}' }} is in failed state.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
- alert: HostPhysicalComponentTooHot
expr: node_hwmon_temp_celsius > 75