Skip to content
Snippets Groups Projects
Verified Commit 72db3f67 authored by Quentin Duchemin's avatar Quentin Duchemin
Browse files

[Alerting] Send network alert if errors/drop last at least 30m

parent 406bca8f
No related branches found
No related tags found
No related merge requests found
......@@ -134,39 +134,39 @@ groups:
rules:
- alert: ReceiveHighErrors
expr: 100 * (rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m])) > 1
for: "5m"
for: "30m"
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 for 5 minutes.'
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }}% receive errors for 30 minutes.'
dashboard: https://grafana.picasoft.net/d/QPF5l5uZa/network?var-node={{ $labels.instance }}
- alert: SendHighErrors
expr: 100 * (rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m])) > 1
for: "5m"
for: "30m"
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 for 5 minutes.'
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }}% transmit errors for 30 minutes.'
dashboard: https://grafana.picasoft.net/d/QPF5l5uZa/network?var-node={{ $labels.instance }}
- alert: ReceiveHighDrop
expr: 100 * (rate(node_network_receive_drop_total[2m]) / rate(node_network_receive_packets_total[2m])) > 1
for: "5m"
for: "30m"
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 for 5 minutes.'
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }}% receive drops for 30 minutes.'
dashboard: https://grafana.picasoft.net/d/QPF5l5uZa/network?var-node={{ $labels.instance }}
- alert: SendHighDrop
expr: 100 * (rate(node_network_transmit_drop_total[2m]) / rate(node_network_transmit_packets_total[2m])) > 1
for: "5m"
for: "30m"
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 for 5 minutes.'
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }}% transmit drops for 30 minutes.'
dashboard: https://grafana.picasoft.net/d/QPF5l5uZa/network?var-node={{ $labels.instance }}
- name: services
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment