monitoring: optimize alerts and mitigate fritzbox-exporter timeouts

This commit is contained in:
Moritz Graf
2026-07-11 07:40:06 +02:00
parent c5458821a7
commit bdabc56afe
10 changed files with 269 additions and 14 deletions
+29 -1
View File
@@ -15,6 +15,34 @@ spec:
labels:
app: fritzbox-exporter
spec:
initContainers:
# This initContainer implements the Egress Reject Workaround (Option B).
# The FRITZ!Box TR-064 API redirects login_sid.lua calls to its public WAN IP because
# we query it from a different subnet (192.168.11.1). When the WAN IP is dynamic or port
# 80/443 are closed, the HTTP client hangs for the default 2-minute Linux TCP timeout,
# failing the entire Prometheus scrape.
# This container injects iptables rules into the pod's network namespace to instantly
# reject (TCP RST) egress to any public WAN IPs on port 80/443. The exporter will immediately
# fail the login step (in ms) and continue scraping TR-064 metrics on port 49000 (which is allowed).
- name: init-iptables
image: alpine:latest
securityContext:
capabilities:
add:
- NET_ADMIN
command: ["/bin/sh", "-c"]
args:
- |
apk add --no-cache iptables
# Allow all local RFC1918 subnets and loopback
iptables -A OUTPUT -d 127.0.0.1/32 -j ACCEPT
iptables -A OUTPUT -d 10.0.0.0/8 -j ACCEPT
iptables -A OUTPUT -d 172.16.0.0/12 -j ACCEPT
iptables -A OUTPUT -d 192.168.0.0/16 -j ACCEPT
# Reject port 80 and 443 egress to any public IP (non-RFC1918)
iptables -A OUTPUT -p tcp --dport 80 -j REJECT --reject-with tcp-reset
iptables -A OUTPUT -p tcp --dport 443 -j REJECT --reject-with tcp-reset
echo "Egress iptables REJECT rules injected successfully"
containers:
- name: fritzbox-exporter
image: ghcr.io/sberk42/fritzbox_exporter/fritzbox_exporter:latest
@@ -95,7 +123,7 @@ spec:
rules:
- alert: FritzBoxExporterOffline
expr: up{job="fritzbox-exporter"} == 0
for: 5m
for: 1h
labels:
severity: warning
annotations: