Files
nixos/manifests/monitoring/config.yaml
T
root df2f9d69fe
buildbot/nix-eval Build done. (1 warning)
fix: address PR feedback + expand infrastructure coverage
- Replace unpoller-credentials plain Secret with ExternalSecret
  pulling from Bitwarden item 15bfc957-5de5-49b2-ab6c-b41800e71564
  via bitwarden-login ClusterSecretStore (username + password)
- Pull UP_UNIFI_DEFAULT_USER from secret as well (was hardcoded)

- Add OpenWRT access point (10.42.0.3) to genesis DNS hosts file
  as ap.thehellings.lan (discovered during network scan)

- Add blackbox exporter to genesis (port 9115, ICMP module)
  for probing non-NixOS infrastructure that has no node_exporter:
  OpenWRT AP, Joel, pve1, chronicles, nas1, odoo, mattermost,
  homeassistant, USW-Pro-HD-24 UniFi switch

- Add infra_ping scrape job to Prometheus using blackbox prober
  targeting all non-NixOS LAN hosts via genesis blackbox exporter
2026-03-25 09:25:16 -05:00

152 lines
5.3 KiB
YAML

apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-config
data:
prometheus.yml: |
global:
scrape_interval: 10s
evaluation_interval: 10s
alerting:
alertmanagers: []
rule_files:
- /etc/prometheus/alerts.yml
scrape_configs:
# This scrapes endpoints on my servers
- job_name: node
static_configs:
- targets:
- "genesis.shire-zebra.ts.net:9100"
- "isaiah.shire-zebra.ts.net:9100"
- "jeremiah.shire-zebra.ts.net:9100"
- "zeke.shire-zebra.ts.net:9100"
- "hosea.shire-zebra.ts.net:9100"
- "exodus.shire-zebra.ts.net:9100"
- "linode.shire-zebra.ts.net:9100"
- job_name: systemd
static_configs:
- targets:
- "genesis.shire-zebra.ts.net:9558"
- "isaiah.shire-zebra.ts.net:9558"
- "jeremiah.shire-zebra.ts.net:9558"
- "zeke.shire-zebra.ts.net:9558"
- "hosea.shire-zebra.ts.net:9558"
- "exodus.shire-zebra.ts.net:9558"
- "linode.shire-zebra.ts.net:9558"
- job_name: ping
static_configs:
- targets:
- "genesis.shire-zebra.ts.net:9427"
- "isaiah.shire-zebra.ts.net:9427"
- "jeremiah.shire-zebra.ts.net:9427"
- "zeke.shire-zebra.ts.net:9427"
- "hosea.shire-zebra.ts.net:9427"
- "exodus.shire-zebra.ts.net:9427"
- "linode.shire-zebra.ts.net:9427"
# ICMP ping reachability for non-NixOS infrastructure
- job_name: infra_ping
metrics_path: /probe
params:
module: [icmp]
static_configs:
- targets:
- "10.42.0.3" # OpenWRT access point
- "10.42.0.4" # Joel (Proxmox)
- "10.42.1.1" # pve1 (Proxmox)
- "10.42.1.4" # chronicles (Synology NAS)
- "10.42.1.14" # nas1 (TrueNAS)
- "10.42.2.57" # odoo
- "10.42.2.89" # mattermost
- "10.42.2.155" # homeassistant
- "10.42.3.58" # USW-Pro-HD-24 (UniFi switch)
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: instance
- target_label: __address__
replacement: "genesis.shire-zebra.ts.net:9115"
- job_name: kea
static_configs:
- targets:
- "genesis.shire-zebra.ts.net:9547"
- job_name: dnsmasq
static_configs:
- targets:
- "genesis.shire-zebra.ts.net:9153"
# Converter from TrueNAS
- job_name: graphite
static_configs:
- targets:
- "hosea.shire-zebra.ts.net:9108"
# Restic rest-server backup metrics
- job_name: restic_backups
static_configs:
- targets:
- "nas1.shire-zebra.ts.net:30248"
# Mattermost metrics
- job_name: mattermost
metrics_path: /metrics
static_configs:
- targets:
- "mattermost.thehellings.lan:8065"
# UniFi metrics via unpoller
- job_name: unifi
static_configs:
- targets:
- "unpoller.monitoring.svc.cluster.local:9130"
# This scrapes metrics from the Kubernetes kubelets
- job_name: kubelet
kubernetes_sd_configs:
- role: node
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
authorization:
credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
# This scrapes metrics about the containers themselves
- job_name: cadvisor
kubernetes_sd_configs:
- role: node
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
metrics_path: /metrics/cadvisor
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
#authorization:
# credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
# This scrapes Service endpoints in Kubernetes
- job_name: 'k8sservices'
kubernetes_sd_configs:
- role: endpointslice
relabel_configs:
- source_labels:
- __meta_kubernetes_namespace
- __meta_kubernetes_service_name
action: drop
regex: "default;kubernetes"
- source_labels:
- __meta_kubernetes_namespace
regex: default
action: keep
- source_labels:
- __meta_kubernetes_service_name
target_label: job
authorization:
credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
# This scrapes any exposed pod port named "metrics", assuming that it is
# a prometheus source
- job_name: k8spods
kubernetes_sd_configs:
- role: pod
relabel_configs:
- source_labels:
- __meta_kubernetes_pod_container_port_name
regex: metrics
action: keep
- source_labels:
- __meta_kubernetes_pod_container_name
target_label: job
authorization:
credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token