diff options
| author | Christian Pointner <equinox@spreadspace.org> | 2024-05-29 15:08:49 +0200 |
|---|---|---|
| committer | Christian Pointner <equinox@spreadspace.org> | 2024-05-29 15:08:49 +0200 |
| commit | 9156c07b0246b44556019efe3546c79e01a303b9 (patch) | |
| tree | 0d54a55099a230292cd240badbfa4fbee9601893 | |
| parent | ch-cm4-sensor: make install in iot possible (diff) | |
add prometheus alert for host reboots
| -rw-r--r-- | roles/monitoring/prometheus/server/defaults/main/rules_node.yml | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml index fe6e781b..262f1af7 100644 --- a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml +++ b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml @@ -2,6 +2,14 @@ ## https://awesome-prometheus-alerts.grep.to/rules#host-and-hardware prometheus_server_rules_node_extra: [] prometheus_server_rules_node: + - alert: HostRebooted + expr: ((node_time_seconds - node_boot_time_seconds) / 60) < 15 + labels: + severity: warning + annotations: + summary: Host has rebooted less then 15 minutes ago (instance {{ '{{' }} $labels.instance {{ '}}' }}) + description: "The node has been rebootet {{ '{{' }} $value {{ '}}' }} minutes ago. If this was not done intentionally please check if everything is alright.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" + - alert: HostOutOfMemory expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10 for: 2m |