From 0a6c4da661c3cb957c7c18a87af1da12b7374f19 Mon Sep 17 00:00:00 2001 From: Quentin Duchemin <quentinduchemin@tuta.io> Date: Wed, 1 Sep 2021 15:10:19 +0200 Subject: [PATCH] Fix network rules interpretation --- pica-metrologie/vmalert-rules.yml | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/pica-metrologie/vmalert-rules.yml b/pica-metrologie/vmalert-rules.yml index 5bf8331a..4654f5c7 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 -- GitLab