From c36e7b7a8f2dfe1c54e537b737340e025fa81467 Mon Sep 17 00:00:00 2001 From: Christian Pointner Date: Fri, 24 Sep 2021 02:04:31 +0200 Subject: add some alert rule for newly added node exporter metrics --- .../prometheus/server/defaults/main/rules_node.yml | 27 ++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'roles/monitoring') diff --git a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml index ab7317ac..2c7f9319 100644 --- a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml +++ b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml @@ -217,3 +217,30 @@ prometheus_server_rules_node: annotations: summary: Host clock not synchronising (instance {{ '{{' }} $labels.instance {{ '}}' }}) description: "Clock not synchronising.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" + + - alert: AptUpgradesPending + expr: sum by (instance) (apt_upgrades_pending) > 0 + for: 0m + labels: + severity: warning + annotations: + summary: Host has upgradeable packages (instance {{ '{{' }} $labels.instance {{ '}}' }}) + description: "Host {{ '{{' }} $labels.instance {{ '}}' }} has {{ '{{' }} $value {{ '}}' }} upgradable packages.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" + + - alert: AptAutoremovePending + expr: sum by (instance) (apt_autoremove_pending) > 0 + for: 0m + labels: + severity: warning + annotations: + summary: Host has packages that can be autoremoved (instance {{ '{{' }} $labels.instance {{ '}}' }}) + description: "Host {{ '{{' }} $labels.instance {{ '}}' }} has {{ '{{' }} $value {{ '}}' }} that can be autoremoved.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" + + - alert: HostNeedsRebooting + expr: node_reboot_required > 0 + for: 0m + labels: + severity: warning + annotations: + summary: Host must be rebootet (instance {{ '{{' }} $labels.instance {{ '}}' }}) + description: "Host {{ '{{' }} $labels.instance {{ '}}' }} must be rebootet for security uppdates to take effect.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" -- cgit v1.2.3