Deploying Airflow

curl -LfO 'https://airflow.apache.org/docs/apache-airflow/stable/docker-compose.yaml'

x-airflow-common: &airflow-common
  image: apache/airflow:3  # Use the latest Airflow 3.x release
  environment: &airflow-common-env
    AIRFLOW__CORE__EXECUTOR: LocalExecutor
    AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
    AIRFLOW__CORE__LOAD_EXAMPLES: 'false'
    AIRFLOW__CORE__DAGS_FOLDER: /opt/airflow/dags
  volumes:
    - ./dags:/opt/airflow/dags
    - ./logs:/opt/airflow/logs
    - ./plugins:/opt/airflow/plugins
  depends_on:
    postgres:
      condition: service_healthy

services:
  postgres:
    image: postgres:16
    environment:
      POSTGRES_USER: airflow
      POSTGRES_PASSWORD: airflow
      POSTGRES_DB: airflow
    volumes:
      - postgres-db-volume:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD", "pg_isready", "-U", "airflow"]
      interval: 10s
      retries: 5
      start_period: 5s

  airflow-init:
    <<: *airflow-common
    entrypoint: /bin/bash
    command:
      - -c
      - |
        airflow db migrate
        airflow users create \
          --username admin \
          --firstname Admin \
          --lastname User \
          --role Admin \
          --email admin@example.com \
          --password admin
    depends_on:
      postgres:
        condition: service_healthy

  airflow-apiserver:
    <<: *airflow-common
    command: airflow api-server
    ports:
      - "8080:8080"
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s

  airflow-scheduler:
    <<: *airflow-common
    command: airflow scheduler

  airflow-dag-processor:
    <<: *airflow-common
    command: airflow dag-processor

  airflow-triggerer:
    <<: *airflow-common
    command: airflow triggerer

volumes:
  postgres-db-volume:

# Start all services
docker compose up -d

# Stop all services
docker compose down

# View logs
docker compose logs -f airflow-scheduler

# Restart after requirements change
docker compose down && docker compose up -d --build

# Run a one-off Airflow CLI command
docker compose exec airflow-apiserver airflow dags list

# Add to requirements.txt, then:
docker compose down
docker compose up -d --build

FROM apache/airflow:3  # Pin to a specific version (e.g., 3.1.7) for reproducibility
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

x-airflow-common: &airflow-common
  build:
    context: .
    dockerfile: Dockerfile
  # ... rest of config

environment:
  # Core settings
  AIRFLOW__CORE__EXECUTOR: LocalExecutor
  AIRFLOW__CORE__PARALLELISM: 32
  AIRFLOW__CORE__MAX_ACTIVE_TASKS_PER_DAG: 16

  # Email
  AIRFLOW__EMAIL__EMAIL_BACKEND: airflow.utils.email.send_email_smtp
  AIRFLOW__SMTP__SMTP_HOST: smtp.example.com

  # Connections (as URI)
  AIRFLOW_CONN_MY_DB: postgresql://user:pass@host:5432/db

# Add the Airflow Helm repo
helm repo add apache-airflow https://airflow.apache.org
helm repo update

# Install with default values
helm install airflow apache-airflow/airflow \
  --namespace airflow \
  --create-namespace

# Install with custom values
helm install airflow apache-airflow/airflow \
  --namespace airflow \
  --create-namespace \
  -f values.yaml

# Executor type
executor: KubernetesExecutor  # or CeleryExecutor, LocalExecutor

# Airflow image (pin to your desired version)
defaultAirflowRepository: apache/airflow
defaultAirflowTag: "3"  # Or pin: "3.1.7"

# Git-sync for DAGs (recommended for production)
dags:
  gitSync:
    enabled: true
    repo: https://github.com/your-org/your-dags.git
    branch: main
    subPath: dags
    wait: 60  # seconds between syncs

# API server (replaces webserver in Airflow 3)
apiServer:
  resources:
    requests:
      cpu: "250m"
      memory: "512Mi"
    limits:
      cpu: "500m"
      memory: "1Gi"
  replicas: 1

# Scheduler
scheduler:
  resources:
    requests:
      cpu: "500m"
      memory: "1Gi"
    limits:
      cpu: "1000m"
      memory: "2Gi"

# Standalone DAG processor
dagProcessor:
  enabled: true
  resources:
    requests:
      cpu: "250m"
      memory: "512Mi"
    limits:
      cpu: "500m"
      memory: "1Gi"

# Triggerer (for deferrable tasks)
triggerer:
  resources:
    requests:
      cpu: "250m"
      memory: "512Mi"
    limits:
      cpu: "500m"
      memory: "1Gi"

# Worker resources (CeleryExecutor only)
workers:
  resources:
    requests:
      cpu: "500m"
      memory: "1Gi"
    limits:
      cpu: "2000m"
      memory: "4Gi"
  replicas: 2

# Log persistence
logs:
  persistence:
    enabled: true
    size: 10Gi

# PostgreSQL (built-in)
postgresql:
  enabled: true

# Or use an external database
# postgresql:
#   enabled: false
# data:
#   metadataConnection:
#     user: airflow
#     pass: airflow
#     host: your-rds-host.amazonaws.com
#     port: 5432
#     db: airflow

# Upgrade with new values
helm upgrade airflow apache-airflow/airflow \
  --namespace airflow \
  -f values.yaml

# Upgrade to a new Airflow version
helm upgrade airflow apache-airflow/airflow \
  --namespace airflow \
  --set defaultAirflowTag="<version>"

# Check pod status
kubectl get pods -n airflow

# View scheduler logs
kubectl logs -f deployment/airflow-scheduler -n airflow

# Port-forward the API server
kubectl port-forward svc/airflow-apiserver 8080:8080 -n airflow

# Run a one-off CLI command
kubectl exec -it deployment/airflow-scheduler -n airflow -- airflow dags list