feat(infra): p6 hardening - observability and deploy compose

- 5 NestJS services add /metrics endpoint via app.getHttpAdapter()
- prometheus.yml scales to 8 services with rule_files and alertmanager
- monitoring compose replaces blackbox with Loki+Promtail
- Grafana datasource adds Loki
- docker-compose.deploy.yml scales to 11 services
- deploy.env.example completes Neo4j/ES/ClickHouse/LLM vars
- teacher-bff adds health.controller
- CI removes continue-on-error on lint step
- teacher-portal lint script changed to eslint src
This commit is contained in:
SpecialX
2026-07-09 10:21:06 +08:00
parent 3ca654619f
commit 566060fade
21 changed files with 554 additions and 59 deletions

View File

@@ -14,6 +14,8 @@ volumes:
name: edu-alertmanager-data
grafana-data:
name: edu-grafana-data
loki-data:
name: edu-loki-data
services:
# ============================================================
@@ -104,16 +106,35 @@ services:
- edu-network
# ============================================================
# blackbox-exporter - 黑盒探测HTTP / TCP / ICMP
# Loki - 日志聚合P6 硬化新增
# ============================================================
blackbox-exporter:
image: prom/blackbox-exporter:v0.25.0
container_name: edu-blackbox-exporter
loki:
image: grafana/loki:3.2.1
container_name: edu-loki
profiles: ["monitoring"]
restart: unless-stopped
command: -config.file=/etc/loki/local-config.yaml
ports:
- "9115:9115"
- "3100:3100"
volumes:
- ./blackbox/blackbox.yml:/etc/blackbox_exporter/config.yml:ro
- loki-data:/loki
networks:
- edu-network
# ============================================================
# Promtail - 日志采集(收集 Docker 容器日志发送到 Loki
# ============================================================
promtail:
image: grafana/promtail:3.2.1
container_name: edu-promtail
profiles: ["monitoring"]
restart: unless-stopped
command: -config.file=/etc/promtail/config.yml
volumes:
- ./promtail/config.yml:/etc/promtail/config.yml:ro
- /var/lib/docker/containers:/var/lib/docker/containers:ro
- /var/run/docker.sock:/var/run/docker.sock:ro
networks:
- edu-network
depends_on:
- loki