Simple Log Service:Instalar o LoongCollector no Kubernetes

1. Faça login no console do ACK. No painel de navegação à esquerda, clique em Clusters.

2. Clique em Create Cluster. Na página Component Configurations, marque a caixa de seleção Enable Log Service e selecione Create New Project ou Use Existing Project.

   Este tópico aborda apenas as configurações relacionadas ao SLS. Outras configurações do cluster estão documentadas em Criar um cluster ACK gerenciado .

3. Se você selecionar Create Project, o SLS criará automaticamente os seguintes recursos. Visualize-os no console do Simple Log Service.

   Tipo	Parâmetro	Descrição
   Projeto	k8s-log-${cluster_id}	Unidade de gerenciamento de recursos que isola logs de diferentes serviços.
   Grupo de máquinas	k8s-group-${cluster_id}	Grupo de máquinas para coleta de logs do loongcollector-ds.
   	k8s-group-${cluster_id}-cluster	Grupo de máquinas para coleta de métricas do loongcollector-cluster.
   	k8s-group-${cluster_id}-singleton	Grupo de máquinas para coleta de instância única.

   Importante

   O LoongCollector não cria um LogStore chamado config-operation-log. Se esse LogStore já existir, o LoongCollector não gravará dados nele.

# 1. Wait for LoongCollector to be ready
echo "[$(date)] Application: Waiting for LoongCollector to be ready..."
until [[ -f /tasksite/cornerstone ]]; do
  sleep 1
done
echo "[$(date)] Application: LoongCollector is ready, starting application logic"
# 2. Execute core application logic (ensure logs are written to the shared directory)
echo "Hello, World!" >> /app/logs/business.log
# 3. Save the exit code
retcode=$?
echo "[$(date)] Application: Task completed with exit code: $retcode"
# 4. Notify LoongCollector that the application task is complete
touch /tasksite/tombstone
echo "[$(date)] Application: Tombstone created, exiting"
exit $retcode

# Define the signal handler function
_term_handler() {
    echo "[$(date)] [nginx-demo] Caught SIGTERM, starting graceful shutdown..."
    # Send a QUIT signal to Nginx for a graceful stop
    if [ -n "$NGINX_PID" ]; then
        kill -QUIT "$NGINX_PID" 2>/dev/null || true
        echo "[$(date)] [nginx-demo] Sent SIGQUIT to Nginx PID: $NGINX_PID"
        # Wait for Nginx to stop gracefully
        wait "$NGINX_PID"
        EXIT_CODE=$?
        echo "[$(date)] [nginx-demo] Nginx stopped with exit code: $EXIT_CODE"
    fi
    # Notify LoongCollector that the application container has stopped
    echo "[$(date)] [nginx-demo] Writing tombstone file"
    touch /tasksite/tombstone
    exit $EXIT_CODE
}
# Register the signal handler
trap _term_handler SIGTERM SIGINT SIGQUIT
# Wait for LoongCollector to be ready
echo "[$(date)] [nginx-demo]: Waiting for LoongCollector to be ready..."
until [[ -f /tasksite/cornerstone ]]; do 
    sleep 1
done
echo "[$(date)] [nginx-demo]: LoongCollector is ready, starting application logic"
# Start Nginx
echo "[$(date)] [nginx-demo] Starting Nginx..."
nginx -g 'daemon off;' &
NGINX_PID=$!
echo "[$(date)] [nginx-demo] Nginx started with PID: $NGINX_PID"
# Wait for the Nginx process
wait $NGINX_PID
EXIT_CODE=$?
# Also notify LoongCollector if the exit was not caused by a signal
if [ ! -f /tasksite/tombstone ]; then
    echo "[$(date)] [nginx-demo] Unexpected exit, writing tombstone"
    touch /tasksite/tombstone
fi
exit $EXIT_CODE

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:
        # Application container
        - name: demo-job
          image: debian:bookworm-slim
          command: ["/bin/bash", "-c"]
          args:
            - |
              # Wait for LoongCollector to be ready.
              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"
              # Run the application logic.
              echo "Hello, World!" >> /app/logs/business.log
              # Save the exit code.
              retcode=$?
              echo "[$(date)] Business: Task completed with exit code: $retcode"
              # Notify LoongCollector that the task is finished.
              touch /tasksite/tombstone
              echo "[$(date)] Business: Tombstone created, exiting"
              exit $retcode
          # Resource requests and limits
          resources:
            requests:
              cpu: "100m"
              memory: "128Mi"
            limits:
              cpu: "500"
              memory: "512Mi"
          # volume mounts
          volumeMounts:
            - name: app-logs
              mountPath: /app/logs
            - name: tasksite
              mountPath: /tasksite
        # LoongCollector sidecar container
        - name: loongcollector
          image: aliyun-observability-release-registry.cn-hongkong.cr.aliyuncs.com/loongcollector/loongcollector:v3.1.1.0-20fa5eb-aliyun
          command: ["/bin/bash", "-c"]
          args:
            - |
              echo "[$(date)] LoongCollector: Starting initialization"
              # Start the LoongCollector service.
              /etc/init.d/loongcollectord start
              # Wait for the configuration to download and the service to be ready.
              sleep 15
              # Verify the service status.
              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
              # Wait for the application container to finish.
              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"
              # Allow sufficient time to send remaining logs.
              sleep 30
              echo "[$(date)] LoongCollector: Stopping service"
              /etc/init.d/loongcollectord stop
              echo "[$(date)] LoongCollector: Shutdown complete"
          # health check
          livenessProbe:
            exec:
              command: ["/etc/init.d/loongcollectord", "status"]
            initialDelaySeconds: 30
            periodSeconds: 10
            timeoutSeconds: 5
            failureThreshold: 3
          # Resource requests and limits
          resources:
            requests:
              cpu: "100m"
              memory: "128Mi"
            limits:
              cpu: "500m"
              memory: "512Mi"
          # environment variables
          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_"
            # Inject pod metadata.
            - 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
          # volume mounts
          volumeMounts:
            - name: app-logs
              mountPath: /app/logs
              readOnly: true
            - name: tasksite
              mountPath: /tasksite
            - name: tz-config
              mountPath: /etc/localtime
              readOnly: true
      # Volume definitions
      volumes:
        - name: app-logs
          emptyDir: {}
        - name: tasksite
          emptyDir:
            medium: Memory
            sizeLimit: "10Mi"
        - name: tz-config
          hostPath:
            path: /usr/share/zoneinfo/Asia/Shanghai

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-minute graceful shutdown period
      containers:
        # Application container - Web application
        - name: nginx-demo
          image: anolis-registry.cn-zhangjiakou.cr.aliyuncs.com/openanolis/nginx:1.14.1-8.6          
          # Startup command and signal handling
          command: ["/bin/sh", "-c"]
          args:
            - |
              # Define the signal handler.
              _term_handler() {
                  echo "[$(date)] [nginx-demo] Caught SIGTERM, starting graceful shutdown..."
                  # Send the QUIT signal to Nginx for a graceful stop.
                  if [ -n "$NGINX_PID" ]; then
                      kill -QUIT "$NGINX_PID" 2>/dev/null || true
                      echo "[$(date)] [nginx-demo] Sent SIGQUIT to Nginx PID: $NGINX_PID"
                      # Wait for Nginx to stop gracefully.
                      wait "$NGINX_PID"
                      EXIT_CODE=$?
                      echo "[$(date)] [nginx-demo] Nginx stopped with exit code: $EXIT_CODE"
                  fi
                  # Notify LoongCollector that the application container has stopped.
                  echo "[$(date)] [nginx-demo] Writing tombstone file"
                  touch /tasksite/tombstone
                  exit $EXIT_CODE
              }
              # Register the signal handler.
              trap _term_handler SIGTERM SIGINT SIGQUIT
              # Wait for LoongCollector to be ready.
              echo "[$(date)] [nginx-demo]: Waiting for LoongCollector to be ready..."
              until [[ -f /tasksite/cornerstone ]]; do 
                sleep 1
              done
              echo "[$(date)] [nginx-demo]: LoongCollector is ready, starting business logic"
              # Start Nginx.
              echo "[$(date)] [nginx-demo] Starting Nginx..."
              nginx -g 'daemon off;' &
              NGINX_PID=$!
              echo "[$(date)] [nginx-demo] Nginx started with PID: $NGINX_PID"
              # Wait for the Nginx process to exit.
              wait $NGINX_PID
              EXIT_CODE=$?
              # If the process exits without a signal, notify LoongCollector.
              if [ ! -f /tasksite/tombstone ]; then
                  echo "[$(date)] [nginx-demo] Unexpected exit, writing tombstone"
                  touch /tasksite/tombstone
              fi
              exit $EXIT_CODE
          # Resource requests and limits
          resources:
            requests:
              cpu: "200m"
              memory: "256Mi"
            limits:
              cpu: "1000m"
              memory: "1Gi"
          # volume mounts
          volumeMounts:
            - name: nginx-logs
              mountPath: /var/log/nginx
            - name: tasksite
              mountPath: /tasksite
            - name: tz-config
              mountPath: /etc/localtime
              readOnly: true
        # LoongCollector sidecar container
        - name: loongcollector
          image: aliyun-observability-release-registry.cn-shenzhen.cr.aliyuncs.com/loongcollector/loongcollector:v3.1.1.0-20fa5eb-aliyun
          command: ["/bin/bash", "-c"]
          args:
            - |
              echo "[$(date)] LoongCollector: Starting initialization"
              # Start the LoongCollector service.
              /etc/init.d/loongcollectord start
              # Wait for the configuration to download and the service to be ready.
              sleep 15
              # Verify the service status.
              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
              # Wait for the application container to finish.
              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"
              # Allow sufficient time to send remaining logs.
              sleep 30
              echo "[$(date)] LoongCollector: Stopping service"
              /etc/init.d/loongcollectord stop
              echo "[$(date)] LoongCollector: Shutdown complete"
          # health check
          livenessProbe:
            exec:
              command: ["/etc/init.d/loongcollectord", "status"]
            initialDelaySeconds: 30
            periodSeconds: 10
            timeoutSeconds: 5
            failureThreshold: 3
          # Resource requests and limits
          resources:
            requests:
              cpu: "100m"
              memory: "128Mi"
            limits:
              cpu: "2000m"
              memory: "2048Mi"
          # environment variables
          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"
            # Enable full drain mode to send all logs when the pod stops.
            - name: enable_full_drain_mode
              value: "true"
            # Append pod environment information as log tags.
            - name: "ALIYUN_LOG_ENV_TAGS"
              value: "_pod_name_|_pod_ip_|_namespace_|_node_name_|_node_ip_"
            # Get pod and node information.
            - 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
          # volume mounts
          volumeMounts:
            - name: nginx-logs
              mountPath: /var/log/nginx
              readOnly: true
            - name: tasksite
              mountPath: /tasksite
            - name: tz-config
              mountPath: /etc/localtime
              readOnly: true
      # Volume definitions
      volumes:
        - name: nginx-logs
          emptyDir: {}
        - name: tasksite
          emptyDir:
            medium: Memory
            sizeLimit: "50Mi"
        - name: tz-config
          hostPath:
            path: /usr/share/zoneinfo/Asia/Shanghai