diff --git a/pica-metrologie/vmalert-rules.yml b/pica-metrologie/vmalert-rules.yml index 5bf8331a71a403df12abdb23fcd8998fa25f7b8b..4654f5c758f5aa602371b0460d9914340857d028 100644 --- a/pica-metrologie/vmalert-rules.yml +++ b/pica-metrologie/vmalert-rules.yml @@ -133,40 +133,40 @@ groups: - name: network rules: - alert: ReceiveHighErrors - expr: rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01 + expr: 100 * (rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m])) > 1 for: "5m" labels: severity: warning annotations: summary: Network interface is reporting many receive errors - description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last two minutes.' + description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }}% receive errors for 5 minutes.' dashboard: https://grafana.picasoft.net/d/QPF5l5uZa/network?var-node={{ $labels.instance }} - alert: SendHighErrors - expr: rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01 + expr: 100 * (rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m])) > 1 for: "5m" labels: severity: warning annotations: summary: Network interface is reporting many transmit errors - description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last two minutes.' + description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }}% transmit errors for 5 minutes.' dashboard: https://grafana.picasoft.net/d/QPF5l5uZa/network?var-node={{ $labels.instance }} - alert: ReceiveHighDrop - expr: rate(node_network_receive_drop_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01 + expr: 100 * (rate(node_network_receive_drop_total[2m]) / rate(node_network_receive_packets_total[2m])) > 1 for: "5m" labels: severity: warning annotations: summary: Network interface is reporting many receive drops - description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive drops in the last two minutes.' + description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }}% receive drops for 5 minutes.' dashboard: https://grafana.picasoft.net/d/QPF5l5uZa/network?var-node={{ $labels.instance }} - alert: SendHighDrop - expr: rate(node_network_transmit_drop_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01 + expr: 100 * (rate(node_network_transmit_drop_total[2m]) / rate(node_network_transmit_packets_total[2m])) > 1 for: "5m" labels: severity: warning annotations: summary: Network interface is reporting many transmit drops - description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit drops in the last two minutes.' + description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }}% transmit drops for 5 minutes.' dashboard: https://grafana.picasoft.net/d/QPF5l5uZa/network?var-node={{ $labels.instance }} - name: services