chore: monitoring 연동

.gitignore

@@ -56,3 +56,8 @@ out/
 
 .DS_Store
 .env
+
+monitor/prometheus/volume/*
+monitor/grafana/alerting/*
+monitor/grafana/volume/*
+monitor/grafana/*.db

docker-compose.monitoring.yml

@@ -0,0 +1,69 @@
+version: '3'
+services:
+  spring-app:
+    container_name: spring-app
+    build: .
+    restart: unless-stopped
+    ports:
+      - "8080:8080"
+    environment:
+      - SPRING_DATASOURCE_URL=jdbc:mysql://${DB_URL}
+      - SPRING_DATASOURCE_USERNAME=${DB_USERNAME}
+      - SPRING_DATASOURCE_PASSWORD=${DB_PASSWORD}
+    networks:
+      - network
+
+  node_exporter:
+    container_name: node_exporter
+    image: prom/node-exporter:latest
+    command:
+      - '--path.rootfs=/host'
+      - '--path.procfs=/host/proc'
+      - '--path.sysfs=/host/sys'
+      - --collector.filesystem.ignored-mount-points
+      - "^/(sys|proc|dev|host|etc|rootfs/var/lib/docker/containers|rootfs/var/lib/docker/overlay2|rootfs/run/docker/netns|rootfs/var/lib/docker/aufs)($$|/)"
+    ports:
+      - "9100:9100"
+    networks:
+      - network
+    restart: unless-stopped
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+
+  prometheus:
+    container_name: prometheus
+    image: prom/prometheus:latest
+    user: root
+    ports:
+      - "9090:9090"
+    volumes:
+      - ./monitor/prometheus/config/:/etc/prometheus/
+      - ./monitor/prometheus/volume:/prometheus
+    command:
+      - '--web.enable-lifecycle'
+      - '--config.file=/etc/prometheus/prometheus.yml'
+    restart: always
+    depends_on:
+      - spring-app
+      - node_exporter
+    networks:
+      - network
+
+  grafana:
+    container_name: grafana
+    image: grafana/grafana:latest
+    ports:
+      - "3000:3000"
+    depends_on:
+      - prometheus
+    volumes:
+      - ./monitor/grafana:/var/lib/grafana
+    restart: always
+    networks:
+      - network
+
+networks:
+  network:
+    driver: bridge

monitor/prometheus/config/prometheus.yml

@@ -0,0 +1,33 @@
+global:
+  scrape_interval: 15s     # scrap target의 기본 interval을 15초로 변경 / default = 1m
+  scrape_timeout: 15s      # scrap request 가 timeout 나는 길이 / default = 10s
+  evaluation_interval: 2m  # rule 을 얼마나 빈번하게 검증하는지 / default = 1m
+
+  # Attach these labels to any time series or alerts when communicating with
+  # external systems (federation, remote storage, Alertmanager).
+  external_labels:
+    monitor: 'codelab-monitor'       # 기본적으로 붙여줄 라벨
+  query_log_file: query_log_file.log # prometheus의 쿼리 로그들을 기록, 없으면 기록안함
+
+rule_files:
+  - "rule.yml"  # 파일 위치는 prometheus.yml 이 있는 곳과 동일 위치
+
+scrape_configs:
+  - job_name: 'node_exporter' # job_name 은 모든 scrap 내에서 고유해야함
+    scrape_interval: 10s      # global에서 default 값을 정의해주었기 떄문에 안써도됨
+    scrape_timeout: 10s       # global에서 default 값을 정의해주었기 떄문에 안써도됨
+    metrics_path: '/metrics'     # 옵션 - prometheus가 metrics를 얻기위해 참조하는 URI를 변경할 수 있음 | default = /metrics
+    honor_labels: false       # 옵션 - 라벨 충동이 있을경우 라벨을 변경할지설정(false일 경우 라벨 안바뀜) | default = false
+    honor_timestamps: false   # 옵션 - honor_labels이 참일 경우, metrics timestamp가 노출됨(true일 경우) | default = false
+    scheme: 'http'            # 옵션 - request를 보낼 scheme 설정 | default = http
+
+    static_configs:
+      - targets: ['host.docker.internal:9100'] ## prometheus가 scrap할 대상을 설정
+        labels: # 옵션 - scrap 해서 가져올 metrics 들 전부에게 붙여줄 라벨
+          service : 'server-1'
+
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']
+        labels:
+          service: 'prometheus'

monitor/prometheus/config/rule.yml

@@ -0,0 +1,20 @@
+groups:
+  - name: example
+    rules:
+      # Alert for any instance that is unreachable for >5 minutes.
+      - alert: InstanceDown
+        expr: up == 0
+        for: 5m
+        labels:
+          severity: page
+        annotations:
+          summary: "Instance {{ $labels.instance }} down"
+          description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."
+
+      # Alert for any instance that has a median request latency >1s.
+      - alert: APIHighRequestLatency
+        expr: api_http_request_latencies_second{quantile="0.5"} > 1
+        for: 10m
+        annotations:
+          summary: "High request latency on {{ $labels.instance }}"
+          description: "{{ $labels.instance }} has a median request latency above 1s (current value: {{ $value }}s)"