Files
nixos-servers/services/monitoring/blackbox.nix
Torjus Håkestad 75210805d5
Some checks failed
Run nix flake check / flake-check (push) Has been cancelled
nix-cache01: decommission and remove all references
Removed:
- hosts/nix-cache01/ directory
- services/nix-cache/build-flakes.{nix,sh} (replaced by NATS builder)
- Vault secret and AppRole for nix-cache01
- Old signing key variable from terraform
- Old trusted public key from system/nix.nix

Updated:
- flake.nix: removed nixosConfiguration
- README.md: nix-cache01 -> nix-cache02
- Monitoring rules: removed build-flakes alerts, updated harmonia to nix-cache02
- Simplified proxy.nix (no longer needs hostname conditional)

nix-cache02 is now the sole binary cache host.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-10 23:40:51 +01:00

93 lines
2.4 KiB
Nix

{ pkgs, ... }:
let
# TLS endpoints to monitor for certificate expiration
# These are all services using ACME certificates from OpenBao PKI
tlsTargets = [
# Direct ACME certs (security.acme.certs)
"https://vault.home.2rjus.net:8200"
"https://auth.home.2rjus.net"
"https://testvm01.home.2rjus.net"
# Caddy auto-TLS on http-proxy
"https://nzbget.home.2rjus.net"
"https://radarr.home.2rjus.net"
"https://sonarr.home.2rjus.net"
"https://ha.home.2rjus.net"
"https://z2m.home.2rjus.net"
"https://prometheus.home.2rjus.net"
"https://alertmanager.home.2rjus.net"
"https://grafana.home.2rjus.net"
"https://jelly.home.2rjus.net"
"https://pyroscope.home.2rjus.net"
"https://pushgw.home.2rjus.net"
# Caddy auto-TLS on nix-cache02
"https://nix-cache.home.2rjus.net"
# Caddy auto-TLS on grafana01
"https://grafana-test.home.2rjus.net"
];
in
{
services.prometheus.exporters.blackbox = {
enable = true;
configFile = pkgs.writeText "blackbox.yml" ''
modules:
https_cert:
prober: http
timeout: 10s
http:
fail_if_not_ssl: true
preferred_ip_protocol: ip4
valid_status_codes:
- 200
- 204
- 301
- 302
- 303
- 307
- 308
- 400
- 401
- 403
- 404
- 405
- 500
- 502
- 503
'';
};
# Add blackbox scrape config to Prometheus
# Alert rules are in rules.yml (certificate_rules group)
services.prometheus.scrapeConfigs = [
{
job_name = "blackbox_tls";
metrics_path = "/probe";
params = {
module = [ "https_cert" ];
};
static_configs = [{
targets = tlsTargets;
}];
relabel_configs = [
# Pass the target URL to blackbox as a parameter
{
source_labels = [ "__address__" ];
target_label = "__param_target";
}
# Use the target URL as the instance label
{
source_labels = [ "__param_target" ];
target_label = "instance";
}
# Point the actual scrape at the local blackbox exporter
{
target_label = "__address__";
replacement = "127.0.0.1:9115";
}
];
}
];
}