diff --git a/dist/rules/host-and-hardware/node-exporter.yml b/dist/rules/host-and-hardware/node-exporter.yml index 5902305..de157bb 100644 --- a/dist/rules/host-and-hardware/node-exporter.yml +++ b/dist/rules/host-and-hardware/node-exporter.yml @@ -250,8 +250,9 @@ groups: summary: Host kernel version deviations (instance {{ $labels.instance }}) description: "Kernel version for {{ $labels.instance }} has changed.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + # When a machine runs out of memory, the node exporter can become unresponsive for several minutes. Even if the system takes 15–20 minutes to recover, the alert should still trigger. - alert: HostOomKillDetected - expr: '(increase(node_vmstat_oom_kill[1m]) > 0)' + expr: '(increase(node_vmstat_oom_kill[30m]) > 0)' for: 0m labels: severity: warning