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:
@@ -27,12 +27,29 @@ JWT_AUDIENCE=next-edu-cloud
|
||||
API_GATEWAY_PORT=8080
|
||||
TEACHER_PORTAL_PORT=3000
|
||||
|
||||
# ============ Kafka(P3 阶段启用,P1 留空)============
|
||||
# ============ Kafka(P3+ 启用,留空则 Outbox publisher 持续重试)============
|
||||
KAFKA_BROKERS=
|
||||
|
||||
# ============ 可观测性(P6 阶段启用,P1 留空)============
|
||||
OTEL_EXPORTER_OTLP_ENDPOINT=
|
||||
# ============ 可观测性(P6 启用)============
|
||||
# OTLP collector 端点,留空则服务跳过 trace 上报
|
||||
OTEL_EXPORTER_OTLP_ENDPOINT=http://otel-collector:4318
|
||||
LOG_LEVEL=info
|
||||
|
||||
# ============ 镜像 tag(由 CI 注入,手动部署时可改)============
|
||||
# IMAGE_TAG=latest ← 默认 latest,CI 通过 export IMAGE_TAG 覆盖
|
||||
# ============ Neo4j(content 服务,留空则降级模式)============
|
||||
NEO4J_URL=
|
||||
NEO4J_PASSWORD=
|
||||
|
||||
# ============ Elasticsearch(msg 服务,留空则降级模式)============
|
||||
ES_URL=
|
||||
|
||||
# ============ ClickHouse(data-ana 服务,留空则降级模式)============
|
||||
CLICKHOUSE_HOST=
|
||||
CLICKHOUSE_PORT=8123
|
||||
CLICKHOUSE_DATABASE=edu_analytics
|
||||
CLICKHOUSE_USER=
|
||||
CLICKHOUSE_PASSWORD=
|
||||
|
||||
# ============ LLM 配置(ai 服务,留空则降级模式)============
|
||||
OPENAI_API_KEY=
|
||||
OPENAI_BASE_URL=https://api.openai.com/v1
|
||||
ANTHROPIC_API_KEY=
|
||||
|
||||
@@ -18,6 +18,9 @@
|
||||
name: edu
|
||||
|
||||
services:
|
||||
# ============================================================
|
||||
# 应用服务(10 个:api-gateway + 3 Go/Python + 6 NestJS)
|
||||
# ============================================================
|
||||
api-gateway:
|
||||
build:
|
||||
context: ./repo/services/api-gateway
|
||||
@@ -34,6 +37,11 @@ services:
|
||||
CLASSES_SERVICE_URL: http://classes:3001
|
||||
IAM_SERVICE_URL: http://iam:3002
|
||||
TEACHER_BFF_URL: http://teacher-bff:3003
|
||||
CORE_EDU_SERVICE_URL: http://core-edu:3004
|
||||
CONTENT_SERVICE_URL: http://content:3005
|
||||
DATA_ANA_SERVICE_URL: http://data-ana:3006
|
||||
MSG_SERVICE_URL: http://msg:3007
|
||||
AI_SERVICE_URL: http://ai:3008
|
||||
OTEL_EXPORTER_OTLP_ENDPOINT: ${OTEL_EXPORTER_OTLP_ENDPOINT:-http://otel-collector:4318}
|
||||
LOG_LEVEL: ${LOG_LEVEL:-info}
|
||||
ports:
|
||||
@@ -59,7 +67,6 @@ services:
|
||||
restart: unless-stopped
|
||||
environment:
|
||||
PORT: 3001
|
||||
# 连接服务器已有的 MySQL(容器名 edu-mysql,需在 edu-shared 网络)
|
||||
DATABASE_URL: ${DATABASE_URL}
|
||||
REDIS_URL: ${REDIS_URL}
|
||||
KAFKA_BROKERS: ${KAFKA_BROKERS:-}
|
||||
@@ -75,6 +82,214 @@ services:
|
||||
- edu-net
|
||||
- edu-shared
|
||||
|
||||
iam:
|
||||
build:
|
||||
context: ./repo
|
||||
dockerfile: services/iam/Dockerfile
|
||||
container_name: edu-iam
|
||||
restart: unless-stopped
|
||||
environment:
|
||||
PORT: 3002
|
||||
DATABASE_URL: ${DATABASE_URL}
|
||||
REDIS_URL: ${REDIS_URL}
|
||||
JWT_SECRET: ${JWT_SECRET}
|
||||
JWT_ISSUER: ${JWT_ISSUER:-next-edu-cloud}
|
||||
JWT_AUDIENCE: ${JWT_AUDIENCE:-next-edu-cloud}
|
||||
OTEL_EXPORTER_OTLP_ENDPOINT: ${OTEL_EXPORTER_OTLP_ENDPOINT:-http://otel-collector:4318}
|
||||
LOG_LEVEL: ${LOG_LEVEL:-info}
|
||||
NODE_ENV: production
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "--quiet", "--spider", "http://localhost:3002/healthz"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
start_period: 30s
|
||||
retries: 5
|
||||
networks:
|
||||
- edu-net
|
||||
- edu-shared
|
||||
|
||||
teacher-bff:
|
||||
build:
|
||||
context: ./repo
|
||||
dockerfile: services/teacher-bff/Dockerfile
|
||||
container_name: edu-teacher-bff
|
||||
restart: unless-stopped
|
||||
environment:
|
||||
PORT: 3003
|
||||
IAM_SERVICE_URL: http://iam:3002
|
||||
CLASSES_SERVICE_URL: http://classes:3001
|
||||
CORE_EDU_SERVICE_URL: http://core-edu:3004
|
||||
LOG_LEVEL: ${LOG_LEVEL:-info}
|
||||
NODE_ENV: production
|
||||
depends_on:
|
||||
iam:
|
||||
condition: service_healthy
|
||||
classes:
|
||||
condition: service_healthy
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "--quiet", "--spider", "http://localhost:3003/healthz"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
start_period: 20s
|
||||
retries: 3
|
||||
networks:
|
||||
- edu-net
|
||||
- edu-shared
|
||||
|
||||
core-edu:
|
||||
build:
|
||||
context: ./repo
|
||||
dockerfile: services/core-edu/Dockerfile
|
||||
container_name: edu-core-edu
|
||||
restart: unless-stopped
|
||||
environment:
|
||||
PORT: 3004
|
||||
DATABASE_URL: ${DATABASE_URL}
|
||||
REDIS_URL: ${REDIS_URL}
|
||||
KAFKA_BROKERS: ${KAFKA_BROKERS:-}
|
||||
OTEL_EXPORTER_OTLP_ENDPOINT: ${OTEL_EXPORTER_OTLP_ENDPOINT:-http://otel-collector:4318}
|
||||
LOG_LEVEL: ${LOG_LEVEL:-info}
|
||||
NODE_ENV: production
|
||||
DEV_MODE: "false"
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "--quiet", "--spider", "http://localhost:3004/healthz"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
start_period: 30s
|
||||
retries: 5
|
||||
networks:
|
||||
- edu-net
|
||||
- edu-shared
|
||||
|
||||
content:
|
||||
build:
|
||||
context: ./repo
|
||||
dockerfile: services/content/Dockerfile
|
||||
container_name: edu-content
|
||||
restart: unless-stopped
|
||||
environment:
|
||||
PORT: 3005
|
||||
DATABASE_URL: ${DATABASE_URL}
|
||||
REDIS_URL: ${REDIS_URL}
|
||||
NEO4J_URL: ${NEO4J_URL:-}
|
||||
NEO4J_PASSWORD: ${NEO4J_PASSWORD:-}
|
||||
ES_URL: ${ES_URL:-}
|
||||
OTEL_EXPORTER_OTLP_ENDPOINT: ${OTEL_EXPORTER_OTLP_ENDPOINT:-http://otel-collector:4318}
|
||||
LOG_LEVEL: ${LOG_LEVEL:-info}
|
||||
NODE_ENV: production
|
||||
DEV_MODE: "false"
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "--quiet", "--spider", "http://localhost:3005/healthz"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
start_period: 30s
|
||||
retries: 5
|
||||
networks:
|
||||
- edu-net
|
||||
- edu-shared
|
||||
|
||||
msg:
|
||||
build:
|
||||
context: ./repo
|
||||
dockerfile: services/msg/Dockerfile
|
||||
container_name: edu-msg
|
||||
restart: unless-stopped
|
||||
environment:
|
||||
PORT: 3007
|
||||
DATABASE_URL: ${DATABASE_URL}
|
||||
REDIS_URL: ${REDIS_URL}
|
||||
KAFKA_BROKERS: ${KAFKA_BROKERS:-}
|
||||
ES_URL: ${ES_URL:-}
|
||||
PUSH_GATEWAY_URL: http://push-gateway:8081
|
||||
OTEL_EXPORTER_OTLP_ENDPOINT: ${OTEL_EXPORTER_OTLP_ENDPOINT:-http://otel-collector:4318}
|
||||
LOG_LEVEL: ${LOG_LEVEL:-info}
|
||||
NODE_ENV: production
|
||||
DEV_MODE: "false"
|
||||
depends_on:
|
||||
push-gateway:
|
||||
condition: service_healthy
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "--quiet", "--spider", "http://localhost:3007/healthz"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
start_period: 30s
|
||||
retries: 5
|
||||
networks:
|
||||
- edu-net
|
||||
- edu-shared
|
||||
|
||||
ai:
|
||||
build:
|
||||
context: ./repo/services/ai
|
||||
dockerfile: Dockerfile
|
||||
container_name: edu-ai
|
||||
restart: unless-stopped
|
||||
environment:
|
||||
PORT: 3008
|
||||
OPENAI_API_KEY: ${OPENAI_API_KEY:-}
|
||||
OPENAI_BASE_URL: ${OPENAI_BASE_URL:-https://api.openai.com/v1}
|
||||
ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY:-}
|
||||
OTEL_ENDPOINT: ${OTEL_EXPORTER_OTLP_ENDPOINT:-http://otel-collector:4318}
|
||||
LOG_LEVEL: ${LOG_LEVEL:-info}
|
||||
DEV_MODE: "false"
|
||||
healthcheck:
|
||||
test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:3008/healthz')"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
start_period: 20s
|
||||
retries: 3
|
||||
networks:
|
||||
- edu-net
|
||||
- edu-shared
|
||||
|
||||
data-ana:
|
||||
build:
|
||||
context: ./repo/services/data-ana
|
||||
dockerfile: Dockerfile
|
||||
container_name: edu-data-ana
|
||||
restart: unless-stopped
|
||||
environment:
|
||||
PORT: 3006
|
||||
CLICKHOUSE_HOST: ${CLICKHOUSE_HOST:-}
|
||||
CLICKHOUSE_PORT: ${CLICKHOUSE_PORT:-8123}
|
||||
CLICKHOUSE_DATABASE: ${CLICKHOUSE_DATABASE:-edu_analytics}
|
||||
CLICKHOUSE_USER: ${CLICKHOUSE_USER:-}
|
||||
CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD:-}
|
||||
OTEL_ENDPOINT: ${OTEL_EXPORTER_OTLP_ENDPOINT:-http://otel-collector:4318}
|
||||
LOG_LEVEL: ${LOG_LEVEL:-info}
|
||||
DEV_MODE: "false"
|
||||
KAFKA_BROKERS: ${KAFKA_BROKERS:-}
|
||||
healthcheck:
|
||||
test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:3006/healthz')"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
start_period: 20s
|
||||
retries: 3
|
||||
networks:
|
||||
- edu-net
|
||||
- edu-shared
|
||||
|
||||
push-gateway:
|
||||
build:
|
||||
context: ./repo/services/push-gateway
|
||||
dockerfile: Dockerfile
|
||||
container_name: edu-push-gateway
|
||||
restart: unless-stopped
|
||||
environment:
|
||||
PUSH_GATEWAY_PORT: 8081
|
||||
JWT_SECRET: ${JWT_SECRET}
|
||||
REDIS_URL: ${REDIS_URL}
|
||||
DEV_MODE: "false"
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "--quiet", "--spider", "http://localhost:8081/healthz"]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
start_period: 10s
|
||||
retries: 3
|
||||
networks:
|
||||
- edu-net
|
||||
- edu-shared
|
||||
|
||||
teacher-portal:
|
||||
build:
|
||||
context: ./repo
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -13,3 +13,12 @@ datasources:
|
||||
timeInterval: "15s"
|
||||
httpMethod: POST
|
||||
manageAlerts: false
|
||||
|
||||
- name: Loki
|
||||
type: loki
|
||||
uid: loki
|
||||
access: proxy
|
||||
url: http://loki:3100
|
||||
editable: false
|
||||
jsonData:
|
||||
maxLines: 1000
|
||||
|
||||
@@ -2,11 +2,93 @@ global:
|
||||
scrape_interval: 15s
|
||||
evaluation_interval: 15s
|
||||
|
||||
scrape_configs:
|
||||
- job_name: 'api-gateway'
|
||||
static_configs:
|
||||
- targets: ['host.docker.internal:8080']
|
||||
# 告警规则文件
|
||||
rule_files:
|
||||
- /etc/prometheus/rules.yml
|
||||
|
||||
# 告警管理器
|
||||
alerting:
|
||||
alertmanagers:
|
||||
- static_configs:
|
||||
- targets:
|
||||
- alertmanager:9093
|
||||
|
||||
scrape_configs:
|
||||
# ============================================================
|
||||
# 应用服务(NestJS / FastAPI 暴露 /metrics)
|
||||
# ============================================================
|
||||
- job_name: 'classes-service'
|
||||
static_configs:
|
||||
- targets: ['host.docker.internal:3001']
|
||||
- targets: ['host.docker.internal:3001']
|
||||
labels:
|
||||
service: classes
|
||||
|
||||
- job_name: 'iam-service'
|
||||
static_configs:
|
||||
- targets: ['host.docker.internal:3002']
|
||||
labels:
|
||||
service: iam
|
||||
|
||||
- job_name: 'teacher-bff'
|
||||
static_configs:
|
||||
- targets: ['host.docker.internal:3003']
|
||||
labels:
|
||||
service: teacher-bff
|
||||
|
||||
- job_name: 'core-edu-service'
|
||||
static_configs:
|
||||
- targets: ['host.docker.internal:3004']
|
||||
labels:
|
||||
service: core-edu
|
||||
|
||||
- job_name: 'content-service'
|
||||
static_configs:
|
||||
- targets: ['host.docker.internal:3005']
|
||||
labels:
|
||||
service: content
|
||||
|
||||
- job_name: 'data-ana-service'
|
||||
static_configs:
|
||||
- targets: ['host.docker.internal:3006']
|
||||
labels:
|
||||
service: data-ana
|
||||
|
||||
- job_name: 'msg-service'
|
||||
static_configs:
|
||||
- targets: ['host.docker.internal:3007']
|
||||
labels:
|
||||
service: msg
|
||||
|
||||
- job_name: 'ai-service'
|
||||
static_configs:
|
||||
- targets: ['host.docker.internal:3008']
|
||||
labels:
|
||||
service: ai
|
||||
|
||||
# ============================================================
|
||||
# 基础设施(docker-compose.minimal/minimal.override)
|
||||
# ============================================================
|
||||
- job_name: 'mysql'
|
||||
static_configs:
|
||||
- targets: ['host.docker.internal:9104']
|
||||
labels:
|
||||
service: mysql
|
||||
|
||||
- job_name: 'redis'
|
||||
static_configs:
|
||||
- targets: ['host.docker.internal:9121']
|
||||
labels:
|
||||
service: redis
|
||||
|
||||
# ============================================================
|
||||
# 监控栈自身
|
||||
# ============================================================
|
||||
- job_name: 'prometheus'
|
||||
static_configs:
|
||||
- targets: ['localhost:9090']
|
||||
|
||||
- job_name: 'node-exporter'
|
||||
static_configs:
|
||||
- targets: ['node-exporter:9100']
|
||||
labels:
|
||||
service: node-exporter
|
||||
|
||||
28
infra/promtail/config.yml
Normal file
28
infra/promtail/config.yml
Normal file
@@ -0,0 +1,28 @@
|
||||
server:
|
||||
http_listen_port: 9080
|
||||
grpc_listen_port: 0
|
||||
|
||||
positions:
|
||||
filename: /tmp/positions.yaml
|
||||
|
||||
clients:
|
||||
- url: http://loki:3100/loki/api/v1/push
|
||||
|
||||
scrape_configs:
|
||||
# 采集 Docker 容器日志
|
||||
- job_name: docker
|
||||
docker_sd_configs:
|
||||
- host: unix:///var/run/docker.sock
|
||||
refresh_interval: 5s
|
||||
relabel_configs:
|
||||
# 只采集带 edu- 前缀的容器日志
|
||||
- source_labels: ['__meta_docker_container_name']
|
||||
regex: '/(edu-.*).*'
|
||||
action: keep
|
||||
# 提取容器名作为 label
|
||||
- source_labels: ['__meta_docker_container_name']
|
||||
regex: '/(.*)'
|
||||
target_label: container_name
|
||||
# 提取镜像名
|
||||
- source_labels: ['__meta_docker_container_log_stream']
|
||||
target_label: stream
|
||||
Reference in New Issue
Block a user