From 4ec26b272ab6090498a9eefa4a0efb06248b1ef4 Mon Sep 17 00:00:00 2001 From: Christian Pointner Date: Fri, 24 Sep 2021 14:11:35 +0200 Subject: prometheus: add monitoring for systemd units --- .../monitoring/prometheus/server/defaults/main/rules_node.yml | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'roles/monitoring/prometheus/server/defaults') 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 -- cgit v1.2.3