CCCHH/ansible-infra
CCCHH/ansible-infra
3
2
Fork 0
Code Issues2 Pull requests Wiki Activity Actions

grafana: pull out prom. net. rec. err. alerts for OPNs. to ex. wg int.

Browse source 
Pull out prometheus network receive error alerts for OPNsense to exclude
its WireGuard interfaces, which like to throw errors, but which aren't
of importance.
This commit is contained in:
June 2025-02-06 01:34:45 +01:00
parent ee66631c2d
commit c4e35c1adf
Signed by: june
SSH key fingerprint: SHA256:o9EAq4Y9N9K0pBQeBTqhSDrND5E7oB+60ZNx0U1yPe0
1 changed files with 13 additions and 1 deletions

14
resources/chaosknoten/grafana/docker_compose/prometheus_alerts.rules.yaml
View file

@ -79,14 +79,26 @@ groups:
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 }}"
# General network receive error alerts.
# Excluding: OPNsense hosts
- alert: HostNetworkReceiveErrors
expr: (rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
expr: (rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01) * on(instance) group_left (nodename) node_uname_info{nodename=~".+", nodename!="OPNsense"}
for: 2m
labels:
severity: warning
annotations:
summary: Host Network Receive Errors (instance {{ $labels.instance }})
description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} receive errors in the last two minutes.\n VALUE = {{ $value }}"
# OPNsense network receive error alerts.
# This is the same as the regular network receive error alerts, but excluding the WireGuard interfaces as they like to throw errors, but which aren't of importance.
- alert: OPNsenseHostNetworkReceiveErrors
expr: (rate(node_network_receive_errs_total{device!~"wg.+"}[2m]) / rate(node_network_receive_packets_total{device!~"wg.+"}[2m]) > 0.01) * on(instance) group_left (nodename) node_uname_info{nodename="OPNsense"}
for: 2m
labels:
severity: warning
annotations:
summary: OPNsense host Network Receive Errors (instance {{ $labels.instance }})
description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} receive errors in the last two minutes.\n VALUE = {{ $value }}"
- alert: HostNetworkTransmitErrors
expr: (rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m