infrapuzzle/k8s/monitoring/fritzbox-exporter.yaml

132 lines
3.8 KiB
YAML

apiVersion: apps/v1
kind: Deployment
metadata:
name: fritzbox-exporter
namespace: monitoring
labels:
app: fritzbox-exporter
spec:
replicas: 1
selector:
matchLabels:
app: fritzbox-exporter
template:
metadata:
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
imagePullPolicy: IfNotPresent
env:
- name: USERNAME
valueFrom:
secretKeyRef:
name: fritzbox-exporter-secret
key: username
- name: PASSWORD
valueFrom:
secretKeyRef:
name: fritzbox-exporter-secret
key: password
- name: GATEWAY_URL
value: "http://192.168.10.1:49000"
- name: LISTEN_ADDRESS
value: "0.0.0.0:9042"
ports:
- name: http-metrics
containerPort: 9042
resources:
requests:
cpu: 10m
memory: 32Mi
limits:
cpu: 100m
memory: 64Mi
---
apiVersion: v1
kind: Service
metadata:
name: fritzbox-exporter
namespace: monitoring
labels:
app: fritzbox-exporter
spec:
ports:
- name: http-metrics
port: 9042
targetPort: 9042
protocol: TCP
selector:
app: fritzbox-exporter
---
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
name: fritzbox-exporter
namespace: monitoring
labels:
app: fritzbox-exporter
release: prometheus-operator
spec:
selector:
matchLabels:
app: fritzbox-exporter
namespaceSelector:
matchNames:
- monitoring
endpoints:
- port: http-metrics
path: /metrics
interval: 60s
scrapeTimeout: 15s
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: fritzbox-exporter-alerts
namespace: monitoring
labels:
release: prometheus-operator
spec:
groups:
- name: fritzbox-exporter.rules
rules:
- alert: FritzBoxExporterOffline
expr: up{job="fritzbox-exporter"} == 0
for: 1h
labels:
severity: warning
annotations:
summary: "FritzBox exporter is offline"
description: "The FritzBox exporter pod in the cluster cannot reach the router at 192.168.10.1 or the exporter itself is down."