groups: - name: NodeExporterGroup rules: - alert: HostOutOfMemory expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10 for: 2m labels: severity: warning annotations: summary: Host out of memory (instance {{ $labels.instance }}) description: "Node memory is filling up (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostUnusualNetworkThroughputIn expr: sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100 for: 5m labels: severity: warning annotations: summary: Host unusual network throughput in (instance {{ $labels.instance }}) description: "Host network interfaces are probably receiving too much data (> 100 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostUnusualNetworkThroughputOut expr: sum by (instance) (rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100 for: 5m labels: severity: warning annotations: summary: Host unusual network throughput out (instance {{ $labels.instance }}) description: "Host network interfaces are probably sending too much data (> 100 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostUnusualDiskReadRate expr: sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50 for: 5m labels: severity: warning annotations: summary: Host unusual disk read rate (instance {{ $labels.instance }}) description: "Disk is probably reading too much data (> 50 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostUnusualDiskWriteRate expr: sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50 for: 2m labels: severity: warning annotations: summary: Host unusual disk write rate (instance {{ $labels.instance }}) description: "Disk is probably writing too much data (> 50 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostOutOfDiskSpace expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0 for: 2m labels: severity: warning annotations: summary: Host out of disk space (instance {{ $labels.instance }}) description: "Disk is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostHighCpuLoad expr: sum by (instance) (avg by (mode, instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) > 0.8 for: 0m labels: severity: warning annotations: summary: Host high CPU load (instance {{ $labels.instance }}) description: "CPU load is > 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"