Rules

ansible managed alert rules

1.526s ago

1.397ms

Rule State Error Last Evaluation Evaluation Time
alert: InstanceDown expr: up == 0 for: 5m labels: severity: critical annotations: description: '{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes.' summary: Instance {{ $labels.instance }} down ok 1.528s ago 332us
alert: CriticalCPULoad expr: 100 - (avg by(instance) (irate(node_cpu_seconds_total{job="node",mode="idle"}[5m])) * 100) > 96 for: 2m labels: severity: critical annotations: description: '{{ $labels.instance }} of job {{ $labels.job }} has Critical CPU load for more than 2 minutes.' summary: Instance {{ $labels.instance }} - Critical CPU load ok 1.535s ago 260.3us
alert: CriticalRAMUsage expr: (1 - ((node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes) / node_memory_MemTotal_bytes)) * 100 > 98 for: 5m labels: severity: critical annotations: description: '{{ $labels.instance }} has Critical Memory Usage more than 5 minutes.' summary: Instance {{ $labels.instance }} has Critical Memory Usage ok 1.535s ago 295.5us
alert: CriticalDiskSpace expr: node_filesystem_free_bytes{fstype!~"(squashfs|fuse.*)",job="node",mountpoint!~"^/run(/.*|$)"} / node_filesystem_size_bytes{job="node"} < 0.1 for: 4m labels: severity: critical annotations: description: '{{ $labels.instance }} of job {{ $labels.job }} has less than 10% space remaining.' summary: Instance {{ $labels.instance }} - Critical disk space usage ok 1.535s ago 434.9us
alert: RebootRequired expr: node_reboot_required > 0 labels: severity: warning annotations: description: '{{ $labels.instance }} requires a reboot.' summary: Instance {{ $labels.instance }} - reboot required ok 1.535s ago 54.99us