采集Kubernetes Pod文本日志（Sidecar模式）

通过内容过滤降低成本

{"level":"WARNING","timestamp":"2025-09-23T19:11:40+0800","cluster":"yilu-cluster-0728","message":"Disk space is running low","freeSpace":"15%"}
{"level":"ERROR","timestamp":"2025-09-23T19:11:42+0800","cluster":"yilu-cluster-0728","message":"Failed to connect to database","errorCode":5003}
{"level":"INFO","timestamp":"2025-09-23T19:11:47+0800","cluster":"yilu-cluster-0728","message":"User logged in successfully","userId":"user-123"}

{"level":"WARNING","timestamp":"2025-09-23T19:11:40+0800","cluster":"yilu-cluster-0728","message":"Disk space is running low","freeSpace":"15%"}
{"level":"ERROR","timestamp":"2025-09-23T19:11:42+0800","cluster":"yilu-cluster-0728","message":"Failed to connect to database","errorCode":5003}

通过黑名单控制采集范围

容器过滤

配置日志主题（Topic）

当多个应用或实例的日志格式相同但路径不同时（如 /apps/app-A/run.log 和 /apps/app-B/run.log），采集日志难以区分来源。此时可基于机器组、自定义名称或文件路径提取方式生成 Topic，灵活区分不同业务或路径来源的日志。

日志打标

短生命周期（Job/CronJob）

apiVersion: batch/v1
kind: Job
metadata:
  name: demo-job
spec:
  backoffLimit: 3                   
  activeDeadlineSeconds: 3600        
  completions: 1                     
  parallelism: 1                    
  
  template:
    spec:
      restartPolicy: Never         
      terminationGracePeriodSeconds: 300 
      
      containers:
        # 业务容器
        - name: demo-job
          image: debian:bookworm-slim
          command: ["/bin/bash", "-c"]
          args:
            - |
              # 等待LoongCollector准备就绪
              echo "[$(date)] Business: Waiting for LoongCollector to be ready..."
              until [[ -f /tasksite/cornerstone ]]; do 
                sleep 1
              done
              echo "[$(date)] Business: LoongCollector is ready, starting business logic"
              
              # 执行业务逻辑
              echo "Hello, World!" >> /app/logs/business.log
              
              # 保存退出码
              retcode=$?
              echo "[$(date)] Business: Task completed with exit code: $retcode"
              
              # 通知LoongCollector业务完成
              touch /tasksite/tombstone
              echo "[$(date)] Business: Tombstone created, exiting"
              
              exit $retcode
          
          # 资源限制
          resources:
            requests:
              cpu: "100m"
              memory: "128Mi"
            limits:
              cpu: "500"
              memory: "512Mi"
          
          # 卷挂载
          volumeMounts:
            - name: app-logs
              mountPath: /app/logs
            - name: tasksite
              mountPath: /tasksite


        # LoongCollector Sidecar容器
        - name: loongcollector
          image: aliyun-observability-release-registry.cn-hongkong.cr.aliyuncs.com/loongcollector/loongcollector:v3.1.1.0-20fa5eb-aliyun
          command: ["/bin/bash", "-c"]
          args:
            - |
              echo "[$(date)] LoongCollector: Starting initialization"
              
              # 启动LoongCollector服务
              /etc/init.d/loongcollectord start
              
              # 等待配置下载和服务就绪
              sleep 15
              
              # 验证服务状态
              if /etc/init.d/loongcollectord status; then
                echo "[$(date)] LoongCollector: Service started successfully"
                touch /tasksite/cornerstone
              else
                echo "[$(date)] LoongCollector: Failed to start service"
                exit 1
              fi
              
              # 等待业务容器完成
              echo "[$(date)] LoongCollector: Waiting for business container to complete"
              until [[ -f /tasksite/tombstone ]]; do 
                sleep 2
              done
              
              echo "[$(date)] LoongCollector: Business completed, waiting for log transmission"
              # 给足够时间传输剩余日志
              sleep 30
              
              echo "[$(date)] LoongCollector: Stopping service"
              /etc/init.d/loongcollectord stop
              
              echo "[$(date)] LoongCollector: Shutdown complete"
          
          # 健康检查
          livenessProbe:
            exec:
              command: ["/etc/init.d/loongcollectord", "status"]
            initialDelaySeconds: 30
            periodSeconds: 10
            timeoutSeconds: 5
            failureThreshold: 3
          
          # 资源配置
          resources:
            requests:
              cpu: "100m"
              memory: "128Mi"
            limits:
              cpu: "500m"
              memory: "512Mi"
          
          # 环境变量配置
          env:
            - name: ALIYUN_LOGTAIL_USER_ID
              value: "your-user-id"
            - name: ALIYUN_LOGTAIL_USER_DEFINED_ID
              value: "your-user-defined-id"
            - name: ALIYUN_LOGTAIL_CONFIG
              value: "/etc/ilogtail/conf/cn-hongkong/ilogtail_config.json"
            - name: ALIYUN_LOG_ENV_TAGS
              value: "_pod_name_|_pod_ip_|_namespace_|_node_name_"
            
            # Pod信息注入
            - name: "_pod_name_"
              valueFrom:
                fieldRef:
                  fieldPath: metadata.name
            - name: "_pod_ip_"
              valueFrom:
                fieldRef:
                  fieldPath: status.podIP
            - name: "_namespace_"
              valueFrom:
                fieldRef:
                  fieldPath: metadata.namespace
            - name: "_node_name_"
              valueFrom:
                fieldRef:
                  fieldPath: spec.nodeName
          
          # 卷挂载
          volumeMounts:
            - name: app-logs
              mountPath: /app/logs
              readOnly: true
            - name: tasksite
              mountPath: /tasksite
            - name: tz-config
              mountPath: /etc/localtime
              readOnly: true
      
      # 卷定义
      volumes:
        - name: app-logs
          emptyDir: {}
        - name: tasksite
          emptyDir:
            medium: Memory
            sizeLimit: "10Mi"
        - name: tz-config
          hostPath:
            path: /usr/share/zoneinfo/Asia/Shanghai

长生命周期（Deployment / StatefulSet）

apiVersion: apps/v1
kind: Deployment
metadata:
  name: nginx-demo
  namespace: production
  labels:
    app: nginx-demo
    version: v1.0.0
spec:
  replicas: 3
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxUnavailable: 1      
      maxSurge: 1          
  selector:
    matchLabels:
      app: nginx-demo
  template:
    metadata:
      labels:
        app: nginx-demo
        version: v1.0.0    
    spec:
      terminationGracePeriodSeconds: 600  # 10分钟优雅停止时间
      
      containers:
        # 业务容器 - Web应用
        - name: nginx-demo
          image: anolis-registry.cn-zhangjiakou.cr.aliyuncs.com/openanolis/nginx:1.14.1-8.6          
          # 启动命令和信号处理
          command: ["/bin/sh", "-c"]
          args:
            - |
              # 定义信号处理函数
              _term_handler() {
                  echo "[$(date)] [nginx-demo] Caught SIGTERM, starting graceful shutdown..."
                  
                  # 发送QUIT信号给Nginx进行优雅停止
                  if [ -n "$NGINX_PID" ]; then
                      kill -QUIT "$NGINX_PID" 2>/dev/null || true
                      echo "[$(date)] [nginx-demo] Sent SIGQUIT to Nginx PID: $NGINX_PID"
                      
                      # 等待Nginx优雅停止
                      wait "$NGINX_PID"
                      EXIT_CODE=$?
                      echo "[$(date)] [nginx-demo] Nginx stopped with exit code: $EXIT_CODE"
                  fi
                  
                  # 通知LoongCollector业务容器已停止
                  echo "[$(date)] [nginx-demo] Writing tombstone file"
                  touch /tasksite/tombstone
                  
                  exit $EXIT_CODE
              }
              
              # 注册信号处理
              trap _term_handler SIGTERM SIGINT SIGQUIT

              # 等待LoongCollector准备就绪
              echo "[$(date)] [nginx-demo]: Waiting for LoongCollector to be ready..."
              until [[ -f /tasksite/cornerstone ]]; do 
                sleep 1
              done
              echo "[$(date)] [nginx-demo]: LoongCollector is ready, starting business logic"
              
              # 启动Nginx
              echo "[$(date)] [nginx-demo] Starting Nginx..."
              nginx -g 'daemon off;' &
              NGINX_PID=$!
              echo "[$(date)] [nginx-demo] Nginx started with PID: $NGINX_PID"
              
              # 等待Nginx进程
              wait $NGINX_PID
              EXIT_CODE=$?
              
              # 非信号导致的退出也要通知LoongCollector
              if [ ! -f /tasksite/tombstone ]; then
                  echo "[$(date)] [nginx-demo] Unexpected exit, writing tombstone"
                  touch /tasksite/tombstone
              fi
              
              exit $EXIT_CODE
                    
          # 资源配置
          resources:
            requests:
              cpu: "200m"
              memory: "256Mi"
            limits:
              cpu: "1000m"
              memory: "1Gi"
          
          # 卷挂载
          volumeMounts:
            - name: nginx-logs
              mountPath: /var/log/nginx
            - name: tasksite
              mountPath: /tasksite
            - name: tz-config
              mountPath: /etc/localtime
              readOnly: true

        # LoongCollector Sidecar容器
        - name: loongcollector
          image: aliyun-observability-release-registry.cn-shenzhen.cr.aliyuncs.com/loongcollector/loongcollector:v3.1.1.0-20fa5eb-aliyun
          command: ["/bin/bash", "-c"]
          args:
            - |
              echo "[$(date)] LoongCollector: Starting initialization"
              
              # 启动LoongCollector服务
              /etc/init.d/loongcollectord start
              
              # 等待配置下载和服务就绪
              sleep 15
              
              # 验证服务状态
              if /etc/init.d/loongcollectord status; then
                echo "[$(date)] LoongCollector: Service started successfully"
                touch /tasksite/cornerstone
              else
                echo "[$(date)] LoongCollector: Failed to start service"
                exit 1
              fi
              
              # 等待业务容器完成
              echo "[$(date)] LoongCollector: Waiting for business container to complete"
              until [[ -f /tasksite/tombstone ]]; do 
                sleep 2
              done
              
              echo "[$(date)] LoongCollector: Business completed, waiting for log transmission"
              # 给足够时间传输剩余日志
              sleep 30
              
              echo "[$(date)] LoongCollector: Stopping service"
              /etc/init.d/loongcollectord stop
              
              echo "[$(date)] LoongCollector: Shutdown complete"
          
          # 健康检查
          livenessProbe:
            exec:
              command: ["/etc/init.d/loongcollectord", "status"]
            initialDelaySeconds: 30
            periodSeconds: 10
            timeoutSeconds: 5
            failureThreshold: 3
          # 资源配置
          resources:
            requests:
              cpu: "100m"
              memory: "128Mi"
            limits:
              cpu: "2000m"
              memory: "2048Mi"
          
          # 环境变量配置
          env:
            - name: ALIYUN_LOGTAIL_USER_ID
              value: "${your_aliyun_user_id}"
            - name: ALIYUN_LOGTAIL_USER_DEFINED_ID
              value: "${your_machine_group_user_defined_id}"
            - name: ALIYUN_LOGTAIL_CONFIG
              value: "/etc/ilogtail/conf/${your_region_config}/ilogtail_config.json"
            
            # 启用全量排空模式，确保Pod停止时发送所有日志
            - name: enable_full_drain_mode
              value: "true"
            
            # 追加 Pod 环境信息作为日志标签
            - name: "ALIYUN_LOG_ENV_TAGS"
              value: "_pod_name_|_pod_ip_|_namespace_|_node_name_|_node_ip_"
            # 获取 Pod 和 Node 的信息
            - name: "_pod_name_"
              valueFrom:
                fieldRef:
                  fieldPath: metadata.name
            - name: "_pod_ip_"
              valueFrom:
                fieldRef:
                  fieldPath: status.podIP
            - name: "_namespace_"
              valueFrom:
                fieldRef:
                  fieldPath: metadata.namespace
            - name: "_node_name_"
              valueFrom:
                fieldRef:
                  fieldPath: spec.nodeName
            - name: "_node_ip_"
              valueFrom:
                fieldRef:
                  fieldPath: status.hostIP
          
          # 卷挂载
          volumeMounts:
            - name: nginx-logs
              mountPath: /var/log/nginx
              readOnly: true
            - name: tasksite
              mountPath: /tasksite
            - name: tz-config
              mountPath: /etc/localtime
              readOnly: true
      
      # 卷定义
      volumes:
        - name: nginx-logs
          emptyDir: {}
        - name: tasksite
          emptyDir:
            medium: Memory
            sizeLimit: "50Mi"
        - name: tz-config
          hostPath:
            path: /usr/share/zoneinfo/Asia/Shanghai