dda6a9d032
utility-101-shadow: - Add full monitoring stack (Prometheus + Blackbox Exporter + Alertmanager) with Docker Compose and a systemd unit (monitoring.service) - Prometheus scrapes: itself, blackbox-exporter, and node-exporter on the docker host (docker:9100); blackbox probes cover HTTPS endpoints with TLS cert monitoring - Alertmanager routes warnings to Slack/Discord, critical alerts also to email (Gmail SMTP); inhibit rule suppresses SSLCertExpiringSoon when SSLCertExpired already fires - Alert rules: 11 node-exporter alerts (host down, CPU, memory, disk fill/prediction, iowait, OOM kill, systemd failed units) + 3 blackbox alerts (probe failed, SSL expiring, SSL expired) - readme: add services list and Docker Engine installation steps docker host: - Add node-exporter container running with host pid/network and read-only mounts of /proc, /sys, / for full host metrics visibility - Enable --collector.systemd for systemd unit state metrics - Add systemd unit (node-exporter.service) to manage the container Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
114 lines
3.6 KiB
YAML
114 lines
3.6 KiB
YAML
modules:
|
|
|
|
# ── HTTP ──────────────────────────────────────────────────────────────────
|
|
|
|
# Plain HTTP GET, expects 2xx response
|
|
http_2xx:
|
|
prober: http
|
|
timeout: 10s
|
|
http:
|
|
method: GET
|
|
valid_http_versions: ["HTTP/1.1", "HTTP/2.0"]
|
|
valid_status_codes: [] # defaults to 2xx
|
|
follow_redirects: true
|
|
preferred_ip_protocol: "ip4"
|
|
|
|
# HTTP POST with JSON body, expects 2xx response
|
|
http_post_2xx:
|
|
prober: http
|
|
timeout: 10s
|
|
http:
|
|
method: POST
|
|
headers:
|
|
Content-Type: application/json
|
|
body: '{}'
|
|
valid_status_codes: [] # defaults to 2xx
|
|
follow_redirects: true
|
|
preferred_ip_protocol: "ip4"
|
|
|
|
# HTTP GET for endpoints that must return 401 (e.g. unauthenticated API)
|
|
http_401_expected:
|
|
prober: http
|
|
timeout: 10s
|
|
http:
|
|
method: GET
|
|
valid_status_codes: [401]
|
|
follow_redirects: false
|
|
preferred_ip_protocol: "ip4"
|
|
|
|
# ── HTTPS ─────────────────────────────────────────────────────────────────
|
|
|
|
# HTTPS GET, TLS certificate verified (chain + expiry)
|
|
# Use this for production endpoints — probe_ssl_earliest_cert_expiry is populated
|
|
https_2xx:
|
|
prober: http
|
|
timeout: 10s
|
|
http:
|
|
method: GET
|
|
valid_status_codes: [] # defaults to 2xx
|
|
follow_redirects: true
|
|
preferred_ip_protocol: "ip4"
|
|
tls_config:
|
|
insecure_skip_verify: false
|
|
|
|
# HTTPS GET, skip TLS certificate verification
|
|
# Use for self-signed certs or internal CAs not trusted by the exporter
|
|
https_insecure:
|
|
prober: http
|
|
timeout: 10s
|
|
http:
|
|
method: GET
|
|
valid_status_codes: [] # defaults to 2xx
|
|
follow_redirects: true
|
|
preferred_ip_protocol: "ip4"
|
|
tls_config:
|
|
insecure_skip_verify: true
|
|
|
|
# ── TCP ───────────────────────────────────────────────────────────────────
|
|
|
|
# Raw TCP connect — checks port is open and accepting connections
|
|
# Target format: host:port (e.g. "192.168.0.30:5432")
|
|
tcp_connect:
|
|
prober: tcp
|
|
timeout: 10s
|
|
tcp:
|
|
preferred_ip_protocol: "ip4"
|
|
|
|
# ── ICMP ──────────────────────────────────────────────────────────────────
|
|
|
|
# ICMP ping — checks host reachability and latency
|
|
# Note: requires NET_RAW capability or running as root
|
|
icmp:
|
|
prober: icmp
|
|
timeout: 10s
|
|
icmp:
|
|
preferred_ip_protocol: "ip4"
|
|
|
|
# ── DNS ───────────────────────────────────────────────────────────────────
|
|
|
|
# DNS lookup via UDP (standard)
|
|
# Target: resolver IP (e.g. "8.8.8.8")
|
|
# Query name and type set in prometheus.yml per target via params
|
|
dns_udp:
|
|
prober: dns
|
|
timeout: 10s
|
|
dns:
|
|
transport_protocol: "udp"
|
|
preferred_ip_protocol: "ip4"
|
|
query_name: "example.com"
|
|
query_type: "A"
|
|
valid_rcodes:
|
|
- NOERROR
|
|
|
|
# DNS lookup via TCP
|
|
dns_tcp:
|
|
prober: dns
|
|
timeout: 10s
|
|
dns:
|
|
transport_protocol: "tcp"
|
|
preferred_ip_protocol: "ip4"
|
|
query_name: "example.com"
|
|
query_type: "A"
|
|
valid_rcodes:
|
|
- NOERROR
|