Files
nixos-servers/services/monitoring/prometheus.nix
Torjus Håkestad 3cccfc0487
Some checks failed
Run nix flake check / flake-check (push) Failing after 7m36s
monitoring: implement monitoring gaps coverage
Add exporters and scrape targets for services lacking monitoring:
- PostgreSQL: postgres-exporter on pgdb1
- Authelia: native telemetry metrics on auth01
- Unbound: unbound-exporter with remote-control on ns1/ns2
- NATS: HTTP monitoring endpoint on nats1
- OpenBao: telemetry config and Prometheus scrape with token auth
- Systemd: systemd-exporter on all hosts for per-service metrics

Add alert rules for postgres, auth (authelia + lldap), jellyfin,
vault (openbao), plus extend existing nats and unbound rules.

Add Terraform config for Prometheus metrics policy and token. The
token is created via vault_token resource and stored in KV, so no
manual token creation is needed.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-05 21:44:13 +01:00

201 lines
4.8 KiB
Nix

{ self, lib, ... }:
let
monLib = import ../../lib/monitoring.nix { inherit lib; };
externalTargets = import ./external-targets.nix;
nodeExporterTargets = monLib.generateNodeExporterTargets self externalTargets;
autoScrapeConfigs = monLib.generateScrapeConfigs self externalTargets;
in
{
# OpenBao token for scraping metrics
vault.secrets.openbao-token = {
secretPath = "hosts/monitoring01/openbao-token";
extractKey = "token";
outputDir = "/run/secrets/prometheus";
mode = "0400";
owner = "prometheus";
services = [ "prometheus" ];
};
services.prometheus = {
enable = true;
# syntax-only check because we use external credential files (e.g., openbao-token)
checkConfig = "syntax-only";
alertmanager = {
enable = true;
configuration = {
global = {
};
route = {
receiver = "webhook_natstonotify";
group_wait = "30s";
group_interval = "5m";
repeat_interval = "1h";
group_by = [ "alertname" ];
};
receivers = [
{
name = "webhook_natstonotify";
webhook_configs = [
{
url = "http://localhost:5001/alert";
}
];
}
];
};
};
alertmanagers = [
{
static_configs = [
{
targets = [ "localhost:9093" ];
}
];
}
];
retentionTime = "30d";
globalConfig = {
scrape_interval = "15s";
};
rules = [
(builtins.readFile ./rules.yml)
];
scrapeConfigs = [
# Auto-generated node-exporter targets from flake hosts + external
{
job_name = "node-exporter";
static_configs = [
{
targets = nodeExporterTargets;
}
];
}
# Systemd exporter on all hosts (same targets, different port)
{
job_name = "systemd-exporter";
static_configs = [
{
targets = map (t: builtins.replaceStrings [":9100"] [":9558"] t) nodeExporterTargets;
}
];
}
# Local monitoring services (not auto-generated)
{
job_name = "prometheus";
static_configs = [
{
targets = [ "localhost:9090" ];
}
];
}
{
job_name = "loki";
static_configs = [
{
targets = [ "localhost:3100" ];
}
];
}
{
job_name = "grafana";
static_configs = [
{
targets = [ "localhost:3000" ];
}
];
}
{
job_name = "alertmanager";
static_configs = [
{
targets = [ "localhost:9093" ];
}
];
}
{
job_name = "pushgateway";
honor_labels = true;
static_configs = [
{
targets = [ "localhost:9091" ];
}
];
}
{
job_name = "labmon";
static_configs = [
{
targets = [ "monitoring01.home.2rjus.net:9969" ];
}
];
}
# TODO: nix-cache_caddy can't be auto-generated because the cert is issued
# for nix-cache.home.2rjus.net (service CNAME), not nix-cache01 (hostname).
# Consider adding a target override to homelab.monitoring.scrapeTargets.
{
job_name = "nix-cache_caddy";
scheme = "https";
static_configs = [
{
targets = [ "nix-cache.home.2rjus.net" ];
}
];
}
# pve-exporter with complex relabel config
{
job_name = "pve-exporter";
static_configs = [
{
targets = [ "10.69.12.75" ];
}
];
metrics_path = "/pve";
params = {
module = [ "default" ];
cluster = [ "1" ];
node = [ "1" ];
};
relabel_configs = [
{
source_labels = [ "__address__" ];
target_label = "__param_target";
}
{
source_labels = [ "__param_target" ];
target_label = "instance";
}
{
target_label = "__address__";
replacement = "127.0.0.1:9221";
}
];
}
# OpenBao metrics with bearer token auth
{
job_name = "openbao";
scheme = "https";
metrics_path = "/v1/sys/metrics";
params = {
format = [ "prometheus" ];
};
static_configs = [{
targets = [ "vault01.home.2rjus.net:8200" ];
}];
authorization = {
type = "Bearer";
credentials_file = "/run/secrets/prometheus/openbao-token";
};
}
] ++ autoScrapeConfigs;
pushgateway = {
enable = true;
web = {
external-url = "https://pushgw.home.2rjus.net";
};
};
};
}