Docker

Docker Containerization

Overview

Docker is a platform for developing, shipping, and running applications in containers. Containers provide isolation, consistency, and efficiency across different environments.

Core Concepts

Images vs Containers

• Image: Read-only template with application code and dependencies
• Container: Running instance of an image
• Dockerfile: Script to build an image
• Registry: Storage for images (Docker Hub, ECR)

Installation

# Ubuntu/Debian
curl -fsSL https://get.docker.com -o get-docker.sh
sudo sh get-docker.sh

# macOS
brew install --cask docker

# Verify
docker --version
docker compose version

Dockerfile

Python Application

# Multi-stage build
FROM python:3.11-slim as builder

WORKDIR /app

# Install dependencies
COPY requirements.txt .
RUN pip install --user --no-cache-dir -r requirements.txt

# Final stage
FROM python:3.11-slim

WORKDIR /app

# Copy from builder
COPY --from=builder /root/.local /root/.local

# Copy application
COPY . .

# Make sure scripts in .local are usable
ENV PATH=/root/.local/bin:$PATH

# Expose port
EXPOSE 8000

# Run application
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

FastAPI Production

FROM python:3.11-slim

WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    gcc \
    && rm -rf /var/lib/apt/lists/*

# Install Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application
COPY . .

# Create non-root user
RUN useradd -m -u 1000 appuser && chown -R appuser:appuser /app
USER appuser

# Expose port
EXPOSE 8000

# Health check
HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
  CMD python -c "import requests; requests.get('http://localhost:8000/health')"

# Run with gunicorn
CMD ["gunicorn", "main:app", "--workers", "4", "--bind", "0.0.0.0:8000"]

ML Application

FROM nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu22.04

ENV DEBIAN_FRONTEND=noninteractive

# Install Python
RUN apt-get update && apt-get install -y \
    python3.10 \
    python3-pip \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Install ML dependencies
COPY requirements.txt .
RUN pip3 install --no-cache-dir -r requirements.txt

# Copy application
COPY . .

# Expose port
EXPOSE 8000

# Set environment
ENV PYTHONPATH=/app
ENV TORCH_HOME=/app/.cache/torch

# Run
CMD ["python3", "-m", "uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

Best Practices

1. Use Multi-Stage Builds

# Build stage
FROM node:18 AS builder
WORKDIR /app
COPY package*.json ./
RUN npm ci
COPY . .
RUN npm run build

# Production stage
FROM node:18-alpine
WORKDIR /app
COPY --from=builder /app/dist ./dist
COPY package*.json ./
RUN npm ci --only=production
CMD ["node", "server.js"]

2. Minimize Image Size

# Use alpine variants when possible
FROM python:3.11-alpine

# Clean up in same layer
RUN apt-get update && apt-get install -y \
    package \
    && rm -rf /var/lib/apt/lists/*

# Use .dockerignore
# node_modules
# .git
# *.md

3. Don't Run as Root

RUN adduser -D -u 1000 appuser
USER appuser

4. Use Specific Versions

FROM python:3.11.4-slim  # Not just python:3-slim

RUN pip install requests==2.31.0  # Not just pip install requests

5. Leverage Build Cache

# Copy requirements first (changes less often)
COPY requirements.txt .
RUN pip install -r requirements.txt

# Then copy application code
COPY . .

6. Add Health Checks

HEALTHCHECK --interval=30s --timeout=3s \
  CMD curl -f http://localhost:8000/health || exit 1

Docker Compose

Multi-Service Application

version: '3.8'

services:
  web:
    build: .
    ports:
      - "8000:8000"
    environment:
      - DATABASE_URL=postgresql://db:5432/app
      - REDIS_URL=redis://redis:6379
    depends_on:
      - db
      - redis
    volumes:
      - ./app:/app
    networks:
      - app-network

  db:
    image: postgres:15-alpine
    environment:
      POSTGRES_DB: app
      POSTGRES_USER: user
      POSTGRES_PASSWORD: password
    volumes:
      - postgres_data:/var/lib/postgresql/data
    networks:
      - app-network

  redis:
    image: redis:7-alpine
    ports:
      - "6379:6379"
    networks:
      - app-network

  worker:
    build: .
    command: celery -A app.tasks worker --loglevel=info
    environment:
      - DATABASE_URL=postgresql://db:5432/app
      - REDIS_URL=redis://redis:6379
    depends_on:
      - db
      - redis
    networks:
      - app-network

volumes:
  postgres_data:

networks:
  app-network:
    driver: bridge

Development Configuration

version: '3.8'

services:
  app:
    build:
      context: .
      dockerfile: Dockerfile.dev
    volumes:
      - .:/app
    ports:
      - "8000:8000"
    environment:
      - DEBUG=1
      - RELOAD=1
    command: uvicorn main:app --host 0.0.0.0 --port 8000 --reload

Common Commands

Image Management

# Build image
docker build -t myapp:latest .

# Tag image
docker tag myapp:latest myrepo/myapp:1.0

# Push to registry
docker push myrepo/myapp:1.0

# Pull image
docker pull myrepo/myapp:1.0

# List images
docker images

# Remove image
docker rmi myapp:latest

# Prune unused images
docker image prune -a

Container Management

# Run container
docker run -d -p 8000:8000 --name myapp myapp:latest

# Run with environment variables
docker run -d -e DATABASE_URL=postgresql://... myapp:latest

# Run with volume
docker run -d -v $(pwd)/data:/app/data myapp:latest

# List containers
docker ps -a

# Stop container
docker stop myapp

# Start container
docker start myapp

# Remove container
docker rm myapp

# View logs
docker logs -f myapp

# Execute command in container
docker exec -it myapp bash

# Inspect container
docker inspect myapp

Docker Compose

# Start services
docker compose up -d

# Build and start
docker compose up -d --build

# Stop services
docker compose down

# View logs
docker compose logs -f

# Execute in service
docker compose exec web bash

# Scale services
docker compose up -d --scale worker=3

# Run one-off command
docker compose run web python manage.py migrate

Networking

Create Network

# Create bridge network
docker network create my-network

# Connect container to network
docker network connect my-network myapp

# Disconnect
docker network disconnect my-network myapp

Compose Networks

services:
  web:
    networks:
      - frontend
      - backend

  db:
    networks:
      - backend

networks:
  frontend:
  backend:
    driver: bridge

Volumes

Create Volume

# Create named volume
docker volume create my-data

# Use volume
docker run -d -v my-data:/app/data myapp

# List volumes
docker volume ls

# Inspect volume
docker volume inspect my-data

# Remove volume
docker volume rm my-data

Compose Volumes

services:
  app:
    volumes:
      - data:/app/data
      - ./config:/app/config:ro  # Read-only
      - /host/path:/container/path  # Bind mount

volumes:
  data:
    driver: local

Optimization

Reduce Image Size

# Use .dockerignore to exclude unnecessary files
**/node_modules
**/.git
**/__pycache__
**/*.pyc
**/.pytest_cache

# Combine RUN statements
RUN apt-get update && apt-get install -y \
    package1 \
    package2 \
    && rm -rf /var/lib/apt/lists/*

# Use buildx for multi-platform builds
docker buildx build --platform linux/amd64,linux/arm64 -t myapp:latest .

Caching Strategy

# Cache dependencies
COPY requirements.txt .
RUN pip install -r requirements.txt

# Then copy application
COPY . .

Layer Ordering

# Put frequently changed files last
COPY requirements.txt .
RUN pip install -r requirements.txt

# Application code changes more often
COPY . .

Security

Scan Images

# Use Trivy
trivy image myapp:latest

# Use Docker Scout
docker scout cves myapp:latest

Security Best Practices

# Use specific version tags
FROM python:3.11.4-slim

# Run as non-root user
RUN adduser -D -u 1000 appuser
USER appuser

# Use COPY instead of ADD (ADD can extract archives)
COPY file.txt /app/

# Don't include secrets
# Use environment variables or secrets management

# Scan for vulnerabilities
RUN apk add --no-cache dumb-init && \
    dumb-init --version && \
    apk del dumb-init

CI/CD Integration

GitHub Actions

name: Docker

on:
  push:
    branches: [main]

jobs:
  build:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Build image
        run: docker build -t myapp:${{ github.sha }} .

      - name: Log in to registry
        run: docker login -u ${{ secrets.USER }} -p ${{ secrets.PASS }}

      - name: Push image
        run: docker push myapp:${{ github.sha }}

Production Deployment

ECS/EKS

# Task definition for ECS
{
  "family": "myapp",
  "containerDefinitions": [
    {
      "name": "myapp",
      "image": "myrepo/myapp:latest",
      "memory": 512,
      "cpu": 256,
      "essential": true,
      "portMappings": [
        {"containerPort": 8000}
      ]
    }
  ]
}

Kubernetes Deployment

apiVersion: apps/v1
kind: Deployment
metadata:
  name: myapp
spec:
  replicas: 3
  selector:
    matchLabels:
      app: myapp
  template:
    metadata:
      labels:
        app: myapp
    spec:
      containers:
      - name: myapp
        image: myrepo/myapp:latest
        ports:
        - containerPort: 8000
        resources:
          requests:
            memory: "256Mi"
            cpu: "250m"
          limits:
            memory: "512Mi"
            cpu: "500m"

Integration

• AWS: ECR, ECS, EKS, Lambda
• CI/CD: GitHub Actions, GitLab CI
• Monitoring: Prometheus, Grafana
• Logging: ELK Stack, CloudWatch