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).
39 lines
1.2 KiB
Django/Jinja
39 lines
1.2 KiB
Django/Jinja
# Promtail on rn-lab-host-01 — same shape as promtail-config.platform.yml, but pushes to Loki
|
|
# over the network (Loki lives on rn-platform-01, not locally) since these two hosts don't
|
|
# share a Docker network. {{ platform_ip }} is an Ansible variable, rendered by the lab-host
|
|
# role — see infra/firewall/rn-platform-01.rules for the matching inbound rule (3100, this
|
|
# host's IP only).
|
|
|
|
server:
|
|
http_listen_port: 9080
|
|
|
|
positions:
|
|
filename: /tmp/positions.yaml
|
|
|
|
clients:
|
|
- url: "http://{{ platform_ip }}:3100/loki/api/v1/push"
|
|
|
|
scrape_configs:
|
|
- job_name: docker
|
|
docker_sd_configs:
|
|
- host: unix:///var/run/docker.sock
|
|
refresh_interval: 15s
|
|
relabel_configs:
|
|
- source_labels: [__meta_docker_container_name]
|
|
target_label: container
|
|
- source_labels: [__meta_docker_container_label_com_docker_compose_service]
|
|
target_label: service
|
|
pipeline_stages:
|
|
- replace:
|
|
expression: '(?i)(password|token|secret)=[^&\s]+'
|
|
replace: '$1=***REDACTED***'
|
|
|
|
- job_name: journal
|
|
journal:
|
|
max_age: 24h
|
|
labels:
|
|
job: systemd-journal
|
|
relabel_configs:
|
|
- source_labels: [__journal__systemd_unit]
|
|
target_label: unit
|