# Dockerfile - Multi-stage build for smaller image
FROM node:20-slim AS builder
WORKDIR /app
COPY package*.json ./
RUN npm ci --only=production
 
FROM node:20-slim
WORKDIR /app
 
# Copy only production dependencies
COPY --from=builder /app/node_modules ./node_modules
COPY src ./src
COPY package.json ./
 
# Cloud Run uses PORT env variable
ENV PORT=8080
EXPOSE 8080
 
# Run as non-root user
USER node
 
CMD ["node", "src/index.js"]

// src/index.js
const express = require('express');
const app = express();
app.use(express.json());
// Health check endpoint
app.get('/health', (req, res) => {
  res.status(200).send('OK');
});
// API routes
app.get('/api/items/:id', async (req, res) => {
  try {
    const item = await getItem(req.params.id);
    res.json(item);
  } catch (error) {
    console.error('Error:', error);
    res.status(500).json({ error: 'Internal server error' });
  }
});
// Graceful shutdown
process.on('SIGTERM', () => {
  console.log('SIGTERM received, shutting down gracefully');
  server.close(() => {
    console.log('Server closed');
    process.exit(0);
  });
});
const PORT = process.env.PORT || 8080;
const server = app.listen(PORT, () => {
  console.log(`Server listening on port ${PORT}`);
});

# cloudbuild.yaml
steps:
  # Build the container image
  - name: 'gcr.io/cloud-builders/docker'
    args: ['build', '-t', 'gcr.io/$PROJECT_ID/my-service:$COMMIT_SHA', '.']
 
  # Push the container image
  - name: 'gcr.io/cloud-builders/docker'
    args: ['push', 'gcr.io/$PROJECT_ID/my-service:$COMMIT_SHA']
 
  # Deploy to Cloud Run
  - name: 'gcr.io/google.com/cloudsdktool/cloud-sdk'
    entrypoint: gcloud
    args:
      - 'run'
      - 'deploy'
      - 'my-service'
      - '--image=gcr.io/$PROJECT_ID/my-service:$COMMIT_SHA'
      - '--region=us-central1'
      - '--platform=managed'
      - '--allow-unauthenticated'
      - '--memory=512Mi'
      - '--cpu=1'
      - '--min-instances=1'
      - '--max-instances=100'
      - '--concurrency=80'
      - '--cpu-boost'
 
images:
  - 'gcr.io/$PROJECT_ID/my-service:$COMMIT_SHA'

// HTTP Function
// index.js
const functions = require('@google-cloud/functions-framework');
functions.http('helloHttp', (req, res) => {
  const name = req.query.name || req.body.name || 'World';
  res.send(`Hello, ${name}!`);
});

// Pub/Sub Function
const functions = require('@google-cloud/functions-framework');
functions.cloudEvent('processPubSub', (cloudEvent) => {
  // Decode Pub/Sub message
  const message = cloudEvent.data.message;
  const data = message.data
    ? JSON.parse(Buffer.from(message.data, 'base64').toString())
    : {};
  console.log('Received message:', data);
  // Process message
  processMessage(data);
});

// Cloud Storage Function
const functions = require('@google-cloud/functions-framework');
functions.cloudEvent('processStorageEvent', async (cloudEvent) => {
  const file = cloudEvent.data;
  console.log(`Event: ${cloudEvent.type}`);
  console.log(`Bucket: ${file.bucket}`);
  console.log(`File: ${file.name}`);
  if (cloudEvent.type === 'google.cloud.storage.object.v1.finalized') {
    await processUploadedFile(file.bucket, file.name);
  }
});

# Deploy HTTP function
gcloud functions deploy hello-http \
  --gen2 \
  --runtime nodejs20 \
  --trigger-http \
  --allow-unauthenticated \
  --region us-central1
 
# Deploy Pub/Sub function
gcloud functions deploy process-messages \
  --gen2 \
  --runtime nodejs20 \
  --trigger-topic my-topic \
  --region us-central1
 
# Deploy Cloud Storage function
gcloud functions deploy process-uploads \
  --gen2 \
  --runtime nodejs20 \
  --trigger-event-filters="type=google.cloud.storage.object.v1.finalized" \
  --trigger-event-filters="bucket=my-bucket" \
  --region us-central1

gcloud run deploy my-service \
  --cpu-boost \
  --region us-central1

gcloud run deploy my-service \
  --min-instances 1 \
  --region us-central1

# Use distroless for minimal image
FROM node:20-slim AS builder
WORKDIR /app
COPY package*.json ./
RUN npm ci --only=production
 
FROM gcr.io/distroless/nodejs20-debian12
WORKDIR /app
COPY --from=builder /app/node_modules ./node_modules
COPY src ./src
CMD ["src/index.js"]

// Lazy load heavy libraries
let bigQueryClient = null;
function getBigQueryClient() {
  if (!bigQueryClient) {
    const { BigQuery } = require('@google-cloud/bigquery');
    bigQueryClient = new BigQuery();
  }
  return bigQueryClient;
}
// Only initialize when needed
app.get('/api/analytics', async (req, res) => {
  const client = getBigQueryClient();
  const results = await client.query({...});
  res.json(results);
});

# Higher memory = more CPU during startup
gcloud run deploy my-service \
  --memory 1Gi \
  --cpu 2 \
  --region us-central1

# Default concurrency is 80
# Adjust based on your workload
 
# For I/O-bound workloads (most web apps)
gcloud run deploy my-service \
  --concurrency 80 \
  --cpu 1
 
# For CPU-bound workloads
gcloud run deploy my-service \
  --concurrency 1 \
  --cpu 1
 
# For memory-intensive workloads
gcloud run deploy my-service \
  --concurrency 10 \
  --memory 2Gi

// Node.js is single-threaded but handles I/O concurrently
// Use async/await for all I/O operations
// GOOD - async I/O
app.get('/api/data', async (req, res) => {
  const [users, products] = await Promise.all([
    fetchUsers(),
    fetchProducts()
  ]);
  res.json({ users, products });
});
// BAD - blocking operation
app.get('/api/compute', (req, res) => {
  const result = heavyCpuOperation(); // Blocks other requests!
  res.json(result);
});

FROM python:3.11-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY . .
 
# 4 workers for concurrency
CMD exec gunicorn --bind :$PORT --workers 4 --threads 2 main:app

# main.py
from flask import Flask
app = Flask(__name__)
@app.route('/api/data')
def get_data():
    return {'status': 'ok'}

# Create topic
gcloud pubsub topics create orders
 
# Create push subscription to Cloud Run
gcloud pubsub subscriptions create orders-push \
  --topic orders \
  --push-endpoint https://my-service-xxx.run.app/pubsub \
  --ack-deadline 600

// Handle Pub/Sub push messages
const express = require('express');
const app = express();
app.use(express.json());
app.post('/pubsub', async (req, res) => {
  // Verify the request is from Pub/Sub
  if (!req.body.message) {
    return res.status(400).send('Invalid Pub/Sub message');
  }
  try {
    // Decode message data
    const message = req.body.message;
    const data = message.data
      ? JSON.parse(Buffer.from(message.data, 'base64').toString())
      : {};
    console.log('Processing order:', data);
    await processOrder(data);
    // Return 200 to acknowledge
    res.status(200).send('OK');
  } catch (error) {
    console.error('Processing failed:', error);
    // Return 500 to trigger retry
    res.status(500).send('Processing failed');
  }
});

const { PubSub } = require('@google-cloud/pubsub');
const pubsub = new PubSub();
async function publishOrder(order) {
  const topic = pubsub.topic('orders');
  const messageBuffer = Buffer.from(JSON.stringify(order));
  const messageId = await topic.publishMessage({
    data: messageBuffer,
    attributes: {
      type: 'order_created',
      priority: 'high'
    }
  });
  console.log(`Published message ${messageId}`);
  return messageId;
}

# Create DLQ topic
gcloud pubsub topics create orders-dlq
 
# Update subscription with DLQ
gcloud pubsub subscriptions update orders-push \
  --dead-letter-topic orders-dlq \
  --max-delivery-attempts 5

# Deploy with Cloud SQL connection
gcloud run deploy my-service \
  --add-cloudsql-instances PROJECT:REGION:INSTANCE \
  --set-env-vars INSTANCE_CONNECTION_NAME="PROJECT:REGION:INSTANCE" \
  --set-env-vars DB_NAME="mydb" \
  --set-env-vars DB_USER="myuser"

// Using Unix socket connection
const { Pool } = require('pg');
const pool = new Pool({
  user: process.env.DB_USER,
  password: process.env.DB_PASS,
  database: process.env.DB_NAME,
  // Cloud SQL connector uses Unix socket
  host: `/cloudsql/${process.env.INSTANCE_CONNECTION_NAME}`,
  max: 5,  // Connection pool size
  idleTimeoutMillis: 30000,
  connectionTimeoutMillis: 10000,
});
app.get('/api/users', async (req, res) => {
  const client = await pool.connect();
  try {
    const result = await client.query('SELECT * FROM users LIMIT 100');
    res.json(result.rows);
  } finally {
    client.release();
  }
});

# Python with SQLAlchemy
import os
from sqlalchemy import create_engine
def get_engine():
    instance_connection_name = os.environ["INSTANCE_CONNECTION_NAME"]
    db_user = os.environ["DB_USER"]
    db_pass = os.environ["DB_PASS"]
    db_name = os.environ["DB_NAME"]
    engine = create_engine(
        f"postgresql+pg8000://{db_user}:{db_pass}@/{db_name}",
        connect_args={
            "unix_sock": f"/cloudsql/{instance_connection_name}/.s.PGSQL.5432"
        },
        pool_size=5,
        max_overflow=2,
        pool_timeout=30,
        pool_recycle=1800,
    )
    return engine

# Create secret
echo -n "my-secret-value" | gcloud secrets create my-secret --data-file=-
 
# Mount as environment variable
gcloud run deploy my-service \
  --update-secrets=API_KEY=my-secret:latest
 
# Mount as file volume
gcloud run deploy my-service \
  --update-secrets=/secrets/api-key=my-secret:latest

// Access mounted as environment variable
const apiKey = process.env.API_KEY;
// Access mounted as file
const fs = require('fs');
const apiKey = fs.readFileSync('/secrets/api-key', 'utf8');
// Access via Secret Manager API (when not mounted)
const { SecretManagerServiceClient } = require('@google-cloud/secret-manager');
const client = new SecretManagerServiceClient();
async function getSecret(name) {
  const [version] = await client.accessSecretVersion({
    name: `projects/${projectId}/secrets/${name}/versions/latest`
  });
  return version.payload.data.toString();
}

# cloudbuild.yaml
steps:
  - name: 'gcr.io/cloud-builders/gcloud'
    args:
      - 'run'
      - 'deploy'
      - 'my-service'
      - '--memory=1Gi'  # Include /tmp overhead
      - '--image=gcr.io/$PROJECT_ID/my-service'

# BAD - buffers entire file in /tmp
def process_large_file(bucket_name, blob_name):
    blob = bucket.blob(blob_name)
    blob.download_to_filename('/tmp/large_file')
    with open('/tmp/large_file', 'rb') as f:
        process(f.read())
# GOOD - stream processing
def process_large_file(bucket_name, blob_name):
    blob = bucket.blob(blob_name)
    with blob.open('rb') as f:
        for chunk in iter(lambda: f.read(8192), b''):
            process_chunk(chunk)

from google.cloud import storage
def process_with_gcs(bucket_name, input_blob, output_blob):
    client = storage.Client()
    bucket = client.bucket(bucket_name)
    # Process directly to/from GCS
    input_blob = bucket.blob(input_blob)
    output_blob = bucket.blob(output_blob)
    with input_blob.open('rb') as reader:
        with output_blob.open('wb') as writer:
            for chunk in iter(lambda: reader.read(65536), b''):
                processed = transform(chunk)
                writer.write(processed)

import psutil
import logging
def log_memory():
    memory = psutil.virtual_memory()
    logging.info(f"Memory: {memory.percent}% used, "
                f"{memory.available / 1024 / 1024:.0f}MB available")

# For I/O-bound workloads (most web apps)
gcloud run deploy my-service \
  --concurrency=80 \
  --max-instances=100
 
# For CPU-bound workloads
gcloud run deploy my-service \
  --concurrency=4 \
  --cpu=2
 
# Only use 1 when absolutely necessary
gcloud run deploy my-service \
  --concurrency=1 \
  --max-instances=1000  # Be prepared for many instances

// With high concurrency, ensure async operations
const express = require('express');
const app = express();
app.get('/api/data', async (req, res) => {
  // All I/O should be async
  const data = await fetchFromDatabase();
  const enriched = await enrichData(data);
  res.json(enriched);
});
// Concurrency 80+ is safe for async I/O workloads

from fastapi import FastAPI
import asyncio
import httpx
app = FastAPI()
@app.get("/api/data")
async def get_data():
    # Async I/O allows high concurrency
    async with httpx.AsyncClient() as client:
        response = await client.get("https://api.example.com/data")
        return response.json()
# Concurrency 80+ safe with async framework

concurrency = memory_limit / per_request_memory
 
Example:
- 512MB container
- 20MB per request overhead
- Safe concurrency: ~25

# CPU allocated even outside requests
gcloud run deploy my-service \
  --cpu-throttling=false \
  --min-instances=1
 
# Note: This increases costs but enables background work

# Boost CPU during cold start only
gcloud run deploy my-service \
  --cpu-boost \
  --cpu-throttling=true  # Default, throttle after request

from google.cloud import tasks_v2
import json
def create_background_task(payload):
    client = tasks_v2.CloudTasksClient()
    parent = client.queue_path(
        "my-project", "us-central1", "my-queue"
    )
    task = {
        "http_request": {
            "http_method": tasks_v2.HttpMethod.POST,
            "url": "https://my-service.run.app/process",
            "body": json.dumps(payload).encode(),
            "headers": {"Content-Type": "application/json"}
        }
    }
    client.create_task(parent=parent, task=task)
# Handle response immediately, background via Cloud Tasks
@app.post("/api/order")
async def create_order(order: Order):
    order_id = await save_order(order)
    # Queue background processing
    create_background_task({"order_id": order_id})
    return {"order_id": order_id, "status": "processing"}

# Move heavy processing to separate service
steps:
  # Main service - responds quickly
  - name: 'gcr.io/cloud-builders/gcloud'
    args: ['run', 'deploy', 'api-service',
           '--cpu-throttling=true']
 
  # Worker service - processes messages
  - name: 'gcr.io/cloud-builders/gcloud'
    args: ['run', 'deploy', 'worker-service',
           '--cpu-throttling=false',
           '--min-instances=1']

# SQLAlchemy with connection recycling
from sqlalchemy import create_engine
engine = create_engine(
    DATABASE_URL,
    pool_size=5,
    max_overflow=2,
    pool_recycle=300,  # Recycle connections every 5 minutes
    pool_pre_ping=True  # Validate connection before use
)

import socket
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
sock.setsockopt(socket.SOL_SOCKET, socket.SO_KEEPALIVE, 1)
sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_KEEPIDLE, 60)
sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_KEEPINTVL, 60)
sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_KEEPCNT, 5)

import redis
pool = redis.ConnectionPool(
    host=REDIS_HOST,
    port=6379,
    socket_keepalive=True,
    socket_keepalive_options={
        socket.TCP_KEEPIDLE: 60,
        socket.TCP_KEEPINTVL: 60,
        socket.TCP_KEEPCNT: 5
    },
    health_check_interval=30
)
client = redis.Redis(connection_pool=pool)

# Use Cloud SQL connector which handles reconnection
# requirements.txt
cloud-sql-python-connector[pg8000]

from google.cloud.sql.connector import Connector
import sqlalchemy
connector = Connector()
def getconn():
    return connector.connect(
        "project:region:instance",
        "pg8000",
        user="user",
        password="password",
        db="database"
    )
engine = sqlalchemy.create_engine(
    "postgresql+pg8000://",
    creator=getconn
)

gcloud run deploy my-service \
  --cpu-boost \
  --startup-cpu-boost

from functools import lru_cache
from fastapi import FastAPI
app = FastAPI()
# Don't load at import time
model = None
@lru_cache()
def get_model():
    global model
    if model is None:
        # Load on first request, not at startup
        model = load_heavy_model()
    return model
@app.get("/predict")
async def predict(data: dict):
    model = get_model()  # Loads on first call only
    return model.predict(data)
# Startup is fast - model loads on first request

import asyncio
from fastapi import FastAPI
import uvicorn
app = FastAPI()
# Global state for async initialization
initialized = asyncio.Event()
@app.on_event("startup")
async def startup():
    # Start background initialization
    asyncio.create_task(async_init())
async def async_init():
    # Heavy initialization happens after server starts
    await load_models()
    await warm_up_connections()
    initialized.set()
@app.get("/ready")
async def ready():
    if not initialized.is_set():
        raise HTTPException(503, "Still initializing")
    return {"status": "ready"}
@app.get("/health")
async def health():
    # Always respond - health check passes
    return {"status": "healthy"}

# Build stage - slow
FROM python:3.11 as builder
WORKDIR /app
COPY requirements.txt .
RUN pip wheel --no-cache-dir --wheel-dir /wheels -r requirements.txt
 
# Runtime stage - fast startup
FROM python:3.11-slim
WORKDIR /app
COPY --from=builder /wheels /wheels
RUN pip install --no-cache /wheels/* && rm -rf /wheels
COPY . .
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8080"]

# Don't migrate on startup - use Cloud Build
steps:
  # Run migrations first
  - name: 'gcr.io/cloud-builders/gcloud'
    entrypoint: 'bash'
    args:
      - '-c'
      - |
        gcloud run jobs execute migrate-job --wait
 
  # Then deploy
  - name: 'gcr.io/cloud-builders/gcloud'
    args: ['run', 'deploy', 'my-service', ...]

# First generation (legacy)
gcloud run deploy my-service \
  --execution-environment=gen1
 
# Second generation (recommended for most)
gcloud run deploy my-service \
  --execution-environment=gen2

# Second-gen doesn't auto-redirect HTTP to HTTPS
from fastapi import FastAPI, Request
from fastapi.responses import RedirectResponse
app = FastAPI()
@app.middleware("http")
async def redirect_https(request: Request, call_next):
    # Check X-Forwarded-Proto header
    if request.headers.get("X-Forwarded-Proto") == "http":
        url = request.url.replace(scheme="https")
        return RedirectResponse(url, status_code=301)
    return await call_next(request)

# GPUs only available in second-gen
gcloud run deploy ml-service \
  --execution-environment=gen2 \
  --gpu=1 \
  --gpu-type=nvidia-l4

import os
def get_execution_environment():
    # Second-gen has different /proc structure
    try:
        with open('/proc/version', 'r') as f:
            version = f.read()
            if 'gVisor' in version:
                return 'gen2'
    except:
        pass
    return 'gen1'

# Increase request timeout (max 3600s for HTTP)
gcloud run deploy my-service \
  --timeout=900  # 15 minutes

from fastapi import FastAPI, BackgroundTasks
import httpx
app = FastAPI()
@app.post("/process")
async def process(data: dict, background_tasks: BackgroundTasks):
    task_id = create_task_id()
    # Start background processing
    background_tasks.add_task(
        long_running_process,
        task_id,
        data,
        data.get("callback_url")
    )
    # Return immediately
    return {"task_id": task_id, "status": "processing"}
async def long_running_process(task_id, data, callback_url):
    result = await heavy_computation(data)
    # Callback when done
    if callback_url:
        async with httpx.AsyncClient() as client:
            await client.post(callback_url, json={
                "task_id": task_id,
                "result": result
            })

from google.cloud import tasks_v2
def create_long_running_task(data):
    client = tasks_v2.CloudTasksClient()
    parent = client.queue_path(PROJECT, REGION, "long-tasks")
    task = {
        "http_request": {
            "http_method": tasks_v2.HttpMethod.POST,
            "url": "https://worker.run.app/process",
            "body": json.dumps(data).encode(),
            "headers": {"Content-Type": "application/json"}
        },
        "dispatch_deadline": {"seconds": 1800}  # 30 min
    }
    return client.create_task(parent=parent, task=task)

from fastapi import FastAPI
from fastapi.responses import StreamingResponse
@app.get("/large-report")
async def large_report():
    async def generate():
        for chunk in process_large_data():
            yield chunk
    return StreamingResponse(generate(), media_type="text/plain")