ced4568
4e8fa1d413
Self-hosted, no paid SaaS. Host/container/Postgres metrics, uptime probes against the new /healthz endpoints, alert rules split critical (pages) vs warning (informational), one starter Grafana dashboard. Deliberately separate from the application's instructor learning analytics (Phase 3B) - different audience, different data. Validated: promtool check config (valid), promtool check rules (11 rules, valid), amtool check-config (1 inhibit rule, 2 receivers, valid).
32 lines
1.3 KiB
Bash
Executable File
32 lines
1.3 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Local test (Phase 4 §29): renders prometheus.yml.j2 with dummy values and validates it plus
|
|
# the alert rules with the REAL promtool (via the official Prometheus Docker image, no local
|
|
# install needed). Also validates alertmanager.yml.j2 with amtool if the image supports it.
|
|
set -euo pipefail
|
|
cd "$(dirname "$0")"
|
|
|
|
TMPDIR="$(mktemp -d)"
|
|
trap 'rm -rf "$TMPDIR"' EXIT
|
|
mkdir -p "$TMPDIR/rules"
|
|
|
|
sed -e 's/{{ lab_host_ip }}/10.10.10.20/g' prometheus/prometheus.yml.j2 > "$TMPDIR/prometheus.yml"
|
|
cp prometheus/rules/*.yml "$TMPDIR/rules/"
|
|
chmod -R a+rX "$TMPDIR"
|
|
|
|
echo "==> promtool check config"
|
|
docker run --rm -v "$TMPDIR:/etc/prometheus:ro" --entrypoint promtool prom/prometheus:latest \
|
|
check config /etc/prometheus/prometheus.yml
|
|
|
|
echo
|
|
echo "==> amtool check-config (Alertmanager)"
|
|
TMPDIR2="$(mktemp -d)"
|
|
trap 'rm -rf "$TMPDIR" "$TMPDIR2"' EXIT
|
|
sed -e "s/{{ vault_alertmanager_webhook_url | default('http:\/\/example.invalid\/webhook') }}/http:\/\/example.invalid\/webhook/g" \
|
|
alertmanager/alertmanager.yml.j2 > "$TMPDIR2/alertmanager.yml"
|
|
chmod -R a+rX "$TMPDIR2"
|
|
docker run --rm -v "$TMPDIR2:/etc/alertmanager:ro" --entrypoint amtool prom/alertmanager:latest \
|
|
check-config /etc/alertmanager/alertmanager.yml
|
|
|
|
echo
|
|
echo "OK: monitoring configs are valid"
|