Reliability: - Add swap role (2GB, swappiness=10, idempotent via /etc/fstab) - Add mem_limit to plane-worker (512m) and plane-beat (256m) - Add health checks to all services (traefik, vaultwarden, forgejo, plane-*, syncthing, prometheus, grafana, loki) Code quality: - Remove Traefik Docker labels (file provider used, labels were dead code) - Add comment explaining file provider architecture Observability: - Add AlertManager with Telegram notifications - Add Prometheus alert rules: CPU, RAM, disk, swap, container health - Add Loki + Promtail for centralized log aggregation - Add Loki datasource to Grafana - Enable Traefik /ping endpoint for health checks Backups: - Add backup role: pg_dump for forgejo + plane DBs, tar for vaultwarden and forgejo data - 7-day retention, daily cron at 03:00 - Backup script at /usr/local/bin/backup-services Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
36 lines
673 B
Django/Jinja
36 lines
673 B
Django/Jinja
# Generated by Ansible — do not edit manually
|
|
auth_enabled: false
|
|
|
|
server:
|
|
http_listen_port: 3100
|
|
grpc_listen_port: 9096
|
|
|
|
common:
|
|
instance_addr: 127.0.0.1
|
|
path_prefix: /loki
|
|
storage:
|
|
filesystem:
|
|
chunks_directory: /loki/chunks
|
|
rules_directory: /loki/rules
|
|
replication_factor: 1
|
|
ring:
|
|
kvstore:
|
|
store: inmemory
|
|
|
|
schema_config:
|
|
configs:
|
|
- from: 2020-10-24
|
|
store: tsdb
|
|
object_store: filesystem
|
|
schema: v13
|
|
index:
|
|
prefix: index_
|
|
period: 24h
|
|
|
|
limits_config:
|
|
retention_period: 30d
|
|
|
|
compactor:
|
|
working_directory: /loki/retention
|
|
delete_request_store: filesystem
|
|
retention_enabled: true
|