feat: prometheus 기반 리소스 모니터링 시스템 구축 (#98)

* refactor: 프로메테우스 그라파나 설정

* refactor: 모니터링 관련 배포 스크립트 추가

* fix: 경로 불일치로 인한 no data 픽스

* refactor: include *로 변경

Author: LeeHanEum

.github/workflows/DeployToDev.yml

@@ -61,7 +61,7 @@ jobs:
           username: ${{ secrets.NCP_SERVER_USERNAME }}
           password: ${{ secrets.NCP_SERVER_PASSWORD }}
           port: ${{ secrets.NCP_SERVER_PORT }}
-          source: infra/development/docker/docker-compose.yml
+          source: "infra/development/docker/docker-compose.yml, infra/development/docker/monitoring-docker-compose.yml"
           target: ${{ secrets.DOCKER_COMPOSE_YAML_PATH }}
           strip_components: 3
 
@@ -75,6 +75,8 @@ jobs:
           script: |
             docker-compose -f ${{ secrets.DOCKER_COMPOSE_YAML_PATH }}/docker-compose.yml pull
             docker-compose -f ${{ secrets.DOCKER_COMPOSE_YAML_PATH }}/docker-compose.yml --env-file ${{ secrets.ENV_FILE_PATH }} up -d
+            docker-compose -f ${{ secrets.DOCKER_COMPOSE_YAML_PATH }}/monitoring-docker-compose.yml pull
+            docker-compose -f ${{ secrets.DOCKER_COMPOSE_YAML_PATH }}/monitoring-docker-compose.yml --env-file ${{ secrets.ENV_FILE_PATH }} up -d
 
   check:
     needs: deploy
@@ -97,4 +99,4 @@ jobs:
           fields: repo,message,commit,author,eventName,workflow,job,took,pullRequest
         env:
           SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEB_HOOK_URL }}
-        if: always()
+        if: always()

build.gradle

@@ -58,9 +58,11 @@ dependencies {
 
 	//JACKSON
 	implementation 'com.fasterxml.jackson.datatype:jackson-datatype-jsr310:2.16.0'
-
 	implementation 'com.fasterxml.jackson.module:jackson-module-jsonSchema:2.15.0'
 
+	// MONITORING
+	implementation 'org.springframework.boot:spring-boot-starter-actuator'
+	runtimeOnly 'io.micrometer:micrometer-registry-prometheus'
 }
 
 

infra/development/docker/monitoring-docker-compose.yml

@@ -0,0 +1,36 @@
+version: '3.8'
+
+services:
+  prometheus:
+    image: prom/prometheus:latest
+    container_name: onepiece-prometheus
+    user: "$UID:$GID"
+    ports:
+      - "${PROMETHEUS_PORT}:9090"
+    volumes:
+      - ./prometheus:/etc/prometheus
+    command:
+      - '--web.enable-lifecycle'
+      - '--config.file=/etc/prometheus/prometheus.yml'
+    networks:
+      - monitoring-network
+
+  grafana:
+    image: grafana/grafana:latest
+    container_name: onepiece-grafana
+    user: "$UID:$GID"
+    ports:
+      - "${GRAFANA_PORT}:3000"
+    volumes:
+      - 'grafana_storage:/var/lib/grafana'
+    depends_on:
+      - prometheus
+    networks:
+      - monitoring-network
+
+networks:
+  monitoring-network:
+    driver: bridge
+
+volumes:
+  grafana_storage: {}

monitoring/prometheus/prometheus.rules.yml

@@ -0,0 +1,21 @@
+groups:
+  - name: cpu-node
+    rules:
+      - record: job_instance_mode:node_cpu_seconds:avg_rate5m
+        expr: avg by (job, instance, mode) (rate(node_cpu_seconds_total[5m]))
+
+  - name: system-monitor
+    rules:
+    - alert: ApplicationDown
+      expr: up == 0
+      for: 5m
+      annotations:
+        summary: "Instance {{ $labels.instance }} down"
+        description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."
+
+    - alert: HighRequestLatency
+      expr: histogram_quantile(0.5, rate(api_http_request_duration_seconds_bucket[5m])) > 1
+      for: 5m
+      annotations:
+        summary: "High request latency on {{ $labels.instance }}"
+        description: "{{ $labels.instance }} has a median request latency above 1s (current value: {{ $value }}s)"

monitoring/prometheus/prometheus.yml

@@ -0,0 +1,19 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+  # Attach these extra labels to all timeseries collected by this Prometheus instance.
+  external_labels:
+    monitor: 'codelab-monitor'
+
+rule_files:
+  - 'prometheus.rules.yml'
+
+scrape_configs:
+  - job_name: 'prometheus'
+    metrics_path: '/actuator/prometheus'
+
+    static_configs:
+      - targets: ['172.17.0.1:8080']
+        labels:
+          group: 'prometheus'

src/main/resources/application.yml

@@ -65,3 +65,9 @@ cloud:
 encryption:
   secret-key: ${ENCRYPTION_SECRET_KEY}
   algorithm: ${ENCRYPTION_ALGORITHM}
+
+management:
+  endpoints:
+    web:
+      exposure:
+        include: "*"