diff options
author | Christian Pointner <equinox@spreadspace.org> | 2021-09-26 04:29:02 +0200 |
---|---|---|
committer | Christian Pointner <equinox@spreadspace.org> | 2021-09-26 04:29:02 +0200 |
commit | 223297c29d78e4fe95e2ed2338455708e4e0a9c3 (patch) | |
tree | 02534f529becf59835dd1ed5dee0f2321966a09b /roles/monitoring/prometheus/server/defaults/main/rules_node.yml | |
parent | switch to pascal for pressure (diff) | |
parent | fix alert wording (diff) |
Merge branch 'topic/prometheus-refactoring'
Diffstat (limited to 'roles/monitoring/prometheus/server/defaults/main/rules_node.yml')
-rw-r--r-- | roles/monitoring/prometheus/server/defaults/main/rules_node.yml | 38 |
1 files changed, 37 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 ab7317ac..55641534 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 @@ -217,3 +226,30 @@ 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 {{ '}}' }} packages 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 {{ '}}' }}" |