Fly.io Core Workflow B: Postgres, Volumes & Networking

Overview

Set up Fly Postgres, persistent Fly Volumes, and private networking between apps. Fly Postgres runs as a regular Fly app with automated replication. Volumes provide persistent NVMe storage attached to specific machines.

Instructions

Step 1: Create Fly Postgres

# Create a Postgres cluster
fly postgres create --name my-db --region iad --vm-size shared-cpu-1x --volume-size 10

# Attach to your app (sets DATABASE_URL secret automatically)
fly postgres attach my-db -a my-app

# Connect directly
fly postgres connect -a my-db
# psql> SELECT version();

# Proxy to local machine for dev tools
fly proxy 5432 -a my-db
# Now connect: psql postgres://postgres:password@localhost:5432

Step 2: Create Persistent Volumes

# Create a volume (same region as your machine)
fly volumes create data --size 10 --region iad -a my-app

# List volumes
fly volumes list -a my-app

# Mount in fly.toml

# fly.toml
[mounts]
  source = "data"
  destination = "/data"

# Deploy to pick up mount
fly deploy

# Verify mount inside machine
fly ssh console -C "df -h /data"

Step 3: Private Networking (6PN)

# Apps in the same org can reach each other via .internal DNS
# my-app can reach my-db at: my-db.internal:5432

# Internal DNS format: <app-name>.internal
# Machine-specific: <machine-id>.vm.<app-name>.internal

# Example: connect from app code
DATABASE_URL=postgres://postgres:password@my-db.internal:5432/my_db

// Access internal services (no public internet)
const dbUrl = `postgres://postgres:${process.env.DB_PASSWORD}@my-db.internal:5432/mydb`;
const apiUrl = `http://my-api.internal:3000/health`;  // Internal HTTP

Step 4: Postgres Backups and Failover

# List backups
fly postgres barman list-backups -a my-db

# Create manual backup
fly postgres barman backup -a my-db

# Check replication status
fly postgres barman check -a my-db

# Failover to standby (if primary fails)
fly postgres failover -a my-db

Error Handling

Instructions

Strategy 1: Auto-Stop Idle Machines

# fly.toml — stop machines when no traffic
[http_service]
  auto_stop_machines = "stop"     # Full stop (cheapest, ~5s cold start)
  auto_start_machines = true
  min_machines_running = 0        # Allow all machines to stop
  # Use min_machines_running = 1 only for production apps

Strategy 2: Suspend for Faster Resume

# Suspend keeps memory state — resumes in ~100ms but costs ~$0.50/month
[http_service]
  auto_stop_machines = "suspend"

Strategy 3: Audit and Clean Up

# List all apps and their machine counts
fly apps list

# Find idle/stopped machines
fly machine list -a my-app --json | jq '.[] | select(.state != "started") | {id, state, region}'

# Destroy unused apps
fly apps destroy old-app --yes

# List and delete orphaned volumes
fly volumes list -a my-app
fly volumes destroy vol_xxx

Strategy 4: Right-Size VMs

# Check memory usage to see if oversized
fly ssh console -a my-app -C "cat /proc/meminfo | head -3"

# Downgrade if using <50% of allocated memory
fly scale vm shared-cpu-1x --memory 256 -a my-app

Cost Monitoring

# Check current month's usage
fly billing  # Shows org-level billing

# Estimate per-app cost
fly scale show -a my-app  # See VM count and size

Resources

• Fly.io Pricing
• Auto Stop/Start

Next Steps

For architecture design, see flyio-reference-architecture.

Fly.io Debug Bundle

Overview

Collect machine state, app health, volume status, deploy history, network connectivity, and platform diagnostics into a single archive for Fly.io support tickets. This bundle captures everything needed to troubleshoot stuck deployments, machine boot failures, volume corruption, and edge networking problems.

Debug Collection Script

#!/bin/bash
set -euo pipefail
APP="${1:?Usage: fly-debug.sh <app-name>}"
BUNDLE="debug-flyio-${APP}-$(date +%Y%m%d-%H%M%S)"
mkdir -p "$BUNDLE"

# Environment check
echo "=== Fly.io Debug Bundle: $APP ===" | tee "$BUNDLE/summary.txt"
echo "Generated: $(date -u +%Y-%m-%dT%H:%M:%SZ)" >> "$BUNDLE/summary.txt"
echo "FLY_API_TOKEN: ${FLY_API_TOKEN:+[SET]}" >> "$BUNDLE/summary.txt"
echo "flyctl: $(fly version 2>/dev/null || echo 'not found')" >> "$BUNDLE/summary.txt"

# API connectivity
HTTP=$(curl -s -o /dev/null -w "%{http_code}" \
  -H "Authorization: Bearer ${FLY_API_TOKEN}" \
  https://api.machines.dev/v1/apps 2>/dev/null || echo "000")
echo "Machines API: HTTP $HTTP" >> "$BUNDLE/summary.txt"

# App status and machine state
fly status -a "$APP" > "$BUNDLE/status.txt" 2>&1 || true
fly machine list -a "$APP" --json > "$BUNDLE/machines.json" 2>&1 || true

# Recent logs (last 200 lines)
fly logs -a "$APP" --no-tail 2>&1 | tail -200 > "$BUNDLE/logs.txt" || true

# Volumes, releases, and doctor
fly volumes list -a "$APP" > "$BUNDLE/volumes.txt" 2>&1 || true
fly releases -a "$APP" > "$BUNDLE/releases.txt" 2>&1 || true
fly doctor > "$BUNDLE/doctor.txt" 2>&1 || true

# Network and platform status
curl -s -o /dev/null -w "App endpoint: HTTP %{http_code}\n" \
  "https://${APP}.fly.dev/" >> "$BUNDLE/summary.txt" 2>/dev/null || echo "App: unreachable" >> "$BUNDLE/summary.txt"
curl -s https://status.flyio.net/api/v2/status.json 2>/dev/null | \
  jq -r '"Platform: " + .status.description' >> "$BUNDLE/summary.txt" || true

tar -czf "$BUNDLE.tar.gz" "$BUNDLE" && rm -rf "$BUNDLE"
echo "Bundle: $BUNDLE.tar.gz"

Analyzing the Bundle

tar -xzf debug-flyio-*.tar.gz
cat debug-flyio-*/summary.txt                 # Quick health overview
jq '.[] | {id, state, region}' debug-flyio-*/machines.json  # Machine states
grep -i "error\|fail\|crash" debug-flyio-*/logs.txt         # Error patterns
cat debug-flyio-*/doctor.txt                  # Fly.io self-diagnosis

C

Fly.io Deploy Integration

Overview

Deploy edge applications on Fly.io with Docker containers and the fly.toml configuration file. This skill covers building production images optimized for Fly's micro-VM architecture, configuring fly.toml for services, health checks, and multi-region placement, verifying API connectivity from edge locations, and executing rolling updates with automatic rollback. Fly.io deploys as Firecracker micro-VMs, so containers start in under a second and scale to zero when idle.

Docker Configuration

FROM node:20-slim AS builder
WORKDIR /app
COPY package*.json ./
RUN npm ci
COPY tsconfig.json ./
COPY src/ ./src/
RUN npm run build

FROM node:20-slim
RUN addgroup --system app && adduser --system --ingroup app app
WORKDIR /app
COPY --from=builder /app/dist ./dist
COPY --from=builder /app/node_modules ./node_modules
COPY package*.json ./
USER app
EXPOSE 8080
CMD ["node", "dist/index.js"]

Fly.io Configuration

# fly.toml
app = "my-integration"
primary_region = "iad"

[build]
  dockerfile = "Dockerfile"

[env]
  LOG_LEVEL = "info"
  PORT = "8080"

[http_service]
  internal_port = 8080
  force_https = true
  auto_stop_machines = true
  auto_start_machines = true

[[http_service.checks]]
  interval = "30s"
  timeout = "5s"
  grace_period = "10s"
  method = "GET"
  path = "/health"

Environment Variables

export FLY_API_TOKEN="fo1_xxxxxxxxxxxx"
fly secrets set FLYIO_APP_NAME="my-integration"
fly secrets set LOG_LEVEL="info"

Health Check Endpoint

import express from 'express';

const app = express();

app.get('/health', async (req, res) => {
  try {
    const region = process.env.FLY_REGION || 'unknown';
    const appName = process.env.FLY_APP_NAME || 'unknown';
    res.json({ status: 'healthy', service: 'flyio-integration', region, app: appName, timestamp: new Date().toISOString() });
  } catch (error) {
    res.status(503).json({ status: 'unhealthy', error: (error as Error).message });
  }
});

Deployment Steps

Step 1: Build

fly launch --no-deploy

Step 2: Run

fly deploy --strategy rolling

Step 3: Verify

fly status
curl -s https://my-integration.fly.dev/health | jq .

Step 4: Rolling Update

fly deploy --strategy rolling --wait-timeout 300
fly releases --image
fly releases rollback   # if health check fails

Error Handling

# Create a new directory with a Dockerfile
mkdir fly-hello && cd fly-hello

cat > Dockerfile << 'EOF'
FROM node:20-alpine
WORKDIR /app
COPY server.js .
EXPOSE 3000
CMD ["node", "server.js"]
EOF

cat > server.js << 'EOF'
const http = require('http');
const server = http.createServer((req, res) => {
  res.writeHead(200, { 'Content-Type': 'application/json' });
  res.end(JSON.stringify({
    message: 'Hello from Fly.io!',
    region: process.env.FLY_REGION,
    app: process.env.FLY_APP_NAME,
  }));
});
server.listen(3000, () => console.log('Listening on :3000'));
EOF

# Launch — creates app, generates fly.toml, deploys
fly launch --name hello-fly --region iad --now

# Check status
fly status

# Open in browser
fly open

# View logs
fly logs

# Test with cURL
curl https://hello-fly.fly.dev/
# {"message":"Hello from Fly.io!","region":"iad","app":"hello-fly"}

const FLY_API = 'https://api.machines.dev';
const headers = {
  'Authorization': `Bearer ${process.env.FLY_API_TOKEN}`,
  'Content-Type': 'application/json',
};

// Create an app
const app = await fetch(`${FLY_API}/v1/apps`, {
  method: 'POST',
  headers,
  body: JSON.stringify({
    app_name: 'hello-api',
    org_slug: 'personal',
  }),
}).then(r => r.json());

// Create a machine in the app
const machine = await fetch(`${FLY_API}/v1/apps/hello-api/machines`, {
  method: 'POST',
  headers,
  body: JSON.stringify({
    region: 'iad',
    config: {
      image: 'nginx:alpine',
      services: [{
        ports: [{ port: 443, handlers: ['tls', 'http'] }],
        protocol: 'tcp',
        internal_port: 80,
      }],
      guest: { cpu_kind: 'shared', cpus: 1, memory_mb: 256 },
    },
  }),
}).then(r => r.json());

console.log(`Machine ${machine.id} created in ${machine.region}`);

Machine e784079f004d86 created in iad
App URL: https://hello-api.fly.dev

# macOS / Linux
curl -L https://fly.io/install.sh | sh

# Or via Homebrew
brew install flyctl

# Verify
fly version

# Interactive login (opens browser)
fly auth login

# Or with token (CI/CD)
fly auth token  # Get current token
export FLY_API_TOKEN="fo1_your_token_here"

# Verify auth
fly auth whoami

# Create deploy token (scoped to an app)
fly tokens create deploy -a my-app

# Create org-level token
fly tokens create org

# Use with Machines API
curl -s -H "Authorization: Bearer $FLY_API_TOKEN" \
  https://api.machines.dev/v1/apps | jq '.[].name'

const FLY_API = 'https://api.machines.dev';

async function verifyFlyAccess() {
  const res = await fetch(`${FLY_API}/v1/apps`, {
    headers: { 'Authorization': `Bearer ${process.env.FLY_API_TOKEN}` },
  });
  const apps = await res.json();
  console.log(`Connected. Found ${apps.length} apps.`);
  apps.forEach((app: any) => console.log(`  ${app.name} (${app.organization.slug})`));
}

# Build and run locally — same Dockerfile used by Fly
docker build -t my-app .
docker run -p 3000:3000 \
  -e NODE_ENV=development \
  -e DATABASE_URL="postgres://localhost:5432/dev" \
  my-app

# Test
curl http://localhost:3000/health

# Proxy Fly Postgres to localhost:5432
fly proxy 5432 -a my-db &

# Now use local tools against remote Fly Postgres
psql postgres://postgres:password@localhost:5432/mydb
npx prisma studio  # Prisma GUI works against proxied DB

# Proxy Redis
fly proxy 6379 -a my-redis &
redis-cli -h localhost -p 6379

# fly.dev.toml — dev overrides (not committed)
app = "my-app-dev"
primary_region = "iad"

[env]
  NODE_ENV = "development"
  LOG_LEVEL = "debug"

[http_service]
  internal_port = 3000
  auto_stop_machines = "off"  # Keep running for debugging
  min_machines_running = 1

[[vm]]
  cpu_kind = "shared"
  cpus = 1
  memory = "256mb"  # Smaller for dev

# Deploy to dev app
fly deploy -a my-app-dev --config fly.dev.toml

# Watch logs while testing
fly logs -a my-app-dev --no-tail &

# SSH in for debugging
fly ssh console -a my-app-dev

# Quick restart after config change
fly apps restart my-app-dev

{
  "scripts": {
    "dev": "tsx watch src/index.ts",
    "docker:build": "docker build -t my-app .",
    "docker:run": "docker run -p 3000:3000 --env-file .env.local my-app",
    "fly:dev": "fly deploy -a my-app-dev --config fly.dev.toml",
    "fly:proxy:db": "fly proxy 5432 -a my-db",
    "fly:logs": "fly logs -a my-app-dev",
    "fly:ssh": "fly ssh console -a my-app-dev"
  }
}

# fly.toml — suspend instead of stop for faster resume (~100ms vs ~5s)
[http_service]
  auto_stop_machines = "suspend"   # Suspend to RAM, not full stop
  auto_start_machines = true
  min_machines_running = 1          # Always-warm in primary region

# For latency-critical: keep machines running in all regions
# min_machines_running applies globally

# Check current allocation
fly scale show -a my-app

# Start small, scale up based on metrics
fly scale vm shared-cpu-1x --memory 256    # Start here
fly scale vm shared-cpu-1x --memory 512    # If memory-constrained
fly scale vm shared-cpu-2x --memory 1024   # If CPU-bound
fly scale vm performance-2x --memory 4096  # For compute-heavy workloads

# Deploy close to your users
fly scale count 1 --region iad    # US East
fly scale count 1 --region lhr    # Europe
fly scale count 1 --region nrt    # Asia Pacific

# Fly automatically routes to nearest region via Anycast
# Verify: curl with timing
curl -w "DNS: %{time_namelookup}s, Connect: %{time_connect}s, Total: %{time_total}s\n" \
  -o /dev/null -s https://my-app.fly.dev/health

// Use connection pooling for Fly Postgres
// PgBouncer runs on port 5433 (pooled) vs 5432 (direct)
const pooledUrl = process.env.DATABASE_URL?.replace(':5432/', ':5433/');

// Prisma: add pgbouncer=true
// DATABASE_URL="postgres://user:pass@my-db.internal:5433/db?pgbouncer=true"

[http_service.concurrency]
  type = "requests"       # or "connections"
  hard_limit = 250        # Max before rejecting
  soft_limit = 200        # Start scaling at this point

async function checkFlyioReadiness(): Promise<void> {
  const checks: { name: string; pass: boolean; detail: string }[] = [];
  // Fly.io API connectivity
  try {
    const res = await fetch('https://api.machines.dev/v1/apps', {
      headers: { Authorization: `Bearer ${process.env.FLY_API_TOKEN}` },
    });
    checks.push({ name: 'Fly API', pass: res.ok, detail: res.ok ? 'Connected' : `HTTP ${res.status}` });
  } catch (e: any) { checks.push({ name: 'Fly API', pass: false, detail: e.message }); }
  // Token present
  checks.push({ name: 'API 

class FlyRateLimiter {
  private tokens: number;
  private lastRefill: number;
  private readonly max: number;
  private readonly refillRate: number;
  private queue: Array<{ resolve: () => void }> = [];

  constructor(maxPerMinute: number) {
    this.max = maxPerMinute;
    this.tokens = maxPerMinute;
    this.lastRefill = Date.now();
    this.refillRate = maxPerMinute / 60_000;
  }

  async acquire(): Promise<void> {
    this.refill();
    if (this.tokens >= 1) { this.tokens -= 1; return; }
    return new Promise(resolve => this.queue.push({ resolve }));
  }

  private refill() {
    const now = Date.now();
    this.tokens = Math.min(this.max, this.tokens + (now - this.lastRefill) * this.refillRate);
    this.lastRefill = now;
    while (this.tokens >= 1 && this.queue.length) {
      this.tokens -= 1;
      this.queue.shift()!.resolve();
    }
  }
}

const writeLimiter = new FlyRateLimiter(8);  // leave headroom under 10/min
const readLimiter = new FlyRateLimiter(100);

async function flyRetry<T>(fn: () => Promise<Response>, maxRetries = 4): Promise<T> {
  for (let attempt = 0; attempt <= maxRetries; attempt++) {
    const res = await fn();
    if (res.ok) return res.json();
    if (res.status === 429) {
      const retryAfter = parseInt(res.headers.get("Retry-After") || "10", 10);
      const delay = retryAfter * 1000 + Math.random() * 2000;
      await new Promise(r => setTimeout(r, delay));
      continue;
    }
    if (res.status >= 500 && attempt < maxRetries) {
      await new Promise(r => setTimeout(r, Math.pow(2, attempt) * 1000));
      continue;
    }
 

           ┌─────────── Fly.io Anycast DNS ──────────┐
           │                                          │
    ┌──────▼──────┐  ┌──────────────┐  ┌─────────────▼───┐
    │  Web (iad)  │  │  Web (lhr)   │  │   Web (nrt)     │
    │  shared-1x  │  │  shared-1x   │  │   shared-1x     │
    └──────┬──────┘  └──────┬───────┘  └────────┬────────┘
           │                │                    │
    ───────┴────────────────┴────────────────────┴─── .internal DNS
           │                │                    │
    ┌──────▼──────┐  ┌──────▼───────┐  ┌────────▼────────┐
    │ Postgres    │  │ Postgres     │  │   Redis          │
    │ Primary     │  │ Replica      │  │   (upstash.io)   │
    │ (iad)       │  │ (lhr)        │  │                  │
    └─────────────┘  └──────────────┘  └──────────────────┘
           │
    ┌──────▼──────┐
    │  Worker     │
    │  (iad)      │
    │  shared-1x  │
    └─────────────┘

# 1. Web app — multi-region
fly launch --name my-web --region iad
fly scale count 1 --region lhr
fly scale count 1 --region nrt

# 2. Postgres with replica
fly postgres create --name my-db --region iad
fly postgres attach my-db -a my-web
# Add read replica in Europe
fly machine clone <primary-machine-id> --region lhr -a my-db

# 3. Background worker (same codebase, different process)
fly launch --name my-worker --region iad --no-deploy
# fly.toml for worker: no [http_service], use [processes]

# 4. All communicate via .internal DNS
# my-db.internal:5432 (Postgres)
# my-web.internal:3000 (internal API)

app = "my-web"
primary_region = "iad"

[http_service]
  internal_port = 3000
  force_https = true
  auto_stop_machines = "suspend"
  min_machines_running = 1

[[vm]]
  cpu_kind = "shared"
  cpus = 1
  memory = "512mb"

app = "my-worker"
primary_region = "iad"

[processes]
  worker = "node dist/worker.js"

# No [http_service] — worker doesn't serve HTTP

[[vm]]
  cpu_kind = "shared"
  cpus = 1
  memory = "512mb"

const FLY_API = 'https://api.machines.dev';
let _client: FlyClient | null = null;
export function getClient(appName: string): FlyClient {
  if (!_client) {
    const token = process.env.FLY_API_TOKEN;
    if (!token) throw new Error('FLY_API_TOKEN must be set');
    _client = new FlyClient(appName, token);
  }
  return _client;
}
class FlyClient {
  private h: Record<string, string>;
  constructor(private app: string, token: string) {
    this.h = { 'Authorization': `Bearer ${token}`, 'Content-Type': 'application/json' };
  }
  async listMachines(): Promise<FlyMachine[]> {
    const r = await fetch(`${FLY_API}/v1/apps/${this.app}/machines`, { headers: this.h });
    if (!r.ok) throw new FlyError(r.status, await r.text()); return r.json();
  }
  async createMachine(config: MachineConfig, region: string): Promise<FlyMachine> {
    const r = await fetch(`${FLY_API}/v1/apps/${this.app}/machines`, {
      method: 'POST', headers: this.h, body: JSON.stringify({ region, config }) });
    if (!r.ok) throw new FlyError(r.status, await r.text()); return r.json();
  }
  async waitForState(id: string, state: string, timeout = 30): Promise<void> {
    const r = await fetch(`${FLY_API}/v1/apps/${this.app}/machines/${id}/wait?state=${state}&timeout=${timeout}`,
      { headers: this.h });
    if (!r.ok) throw new FlyError(r.status, `Wait for ${state} timed out`);
  }
}

export class FlyError extends Error {
  constructor(public status: number, message: string) { super(message); this.name = 'FlyError'; }
}
export async function safeCall<T>(operation: string, fn: () => Promise<T>): Promise<T> {
  try { return await fn(); }
  catch (err: any) {
    if (err instanceof FlyError && err.status === 429) { await new Promise(r => setTimeout(r, 2000)); return fn(); }
    if (err instanceof FlyError && err.status === 401) throw new FlyError(401, 'Invalid FLY_API_TOKEN');
    throw new FlyError(err.status ?? 0, `${operation} failed: ${err.message}`);
  }
}

class DeployBuilder {
  private regions: string[] = []; private config: Partial<MachineConfig> = {};
  toRegions(...r: string[]) { this.regions = r; return this; }
  withImage(img: string) { this.config.image = 

function validateFlyToken(): void {
  const token = process.env.FLY_API_TOKEN;
  if (!token) {
    throw new Error("Missing FLY_API_TOKEN — use `fly tokens create deploy -a <app>`");
  }
  // Never log tokens; log only token type for debugging
  const isDeployToken = token.startsWith("FlyV1");
  console.log("Fly.io token loaded, type:", isDeployToken ? "deploy" : "personal");
}

import crypto from "crypto";
import { Request, Response, NextFunction } from "express";

function verifyFlyWebhook(req: Request, res: Response, next: NextFunction): void {
  const signature = req.headers["x-fly-signature"] as string;
  const secret = process.env.FLY_WEBHOOK_SECRET!;
  const expected = crypto.createHmac("sha256", secret).update(req.body).digest("hex");
  if (!signature || !crypto.timingSafeEqual(Buffer.from(signature), Buffer.from(expected))) {
    res.status(401).send("Invalid signature");
    return;
  }
  next();
}

import { z } from "zod";

const FlyDeploySchema = z.object({
  app_name: z.string().regex(/^[a-z0-9-]+$/).max(63),
  region: z.enum(["iad", "ord", "lax", "sjc", "ams", "lhr", "nrt", "syd", "gru"]),
  image: z.string().regex(/^registry\..+\/.+:.+$/),
  vm_size: z.enum(["shared-cpu-1x", "shared-cpu-2x", "performance-1x", "performance-2x"]).optional(),
  min_machines: z.number().int().min(0).max(20).optional(),
});

function validateDeployConfig(data: unknown) {
  return FlyDeploySchema.parse(data);
}

const FLY_SENSITIVE_FIELDS = ["fly_api_token", "deploy_token", "db_password", "wireguard_private_key", "tls_private_key"];

function redactFlyLog(record: Record<string, unknown>): Record<string, unknown> {
  const redacted = { ...record };
  for (const field of FLY_SENSITIVE_FIELDS) {
    if (field in redacted) redacted[field] = "[REDACTED]";
  }
  return redacted;
}

# Check current platform version
fly status -a my-app  # Look for "Platform: machines" vs "nomad"

# Migrate to Apps v2 (Machines)
fly migrate-to-v2 -a my-app

# Verify
fly status -a my-app
fly machine list -a my-app

# Check current version
fly version

# Upgrade
fly version update

# Or reinstall
curl -L https://fly.io/install.sh | sh

# Check current version
fly postgres connect -a my-db -c "SELECT version();"

# Create new cluster with target version
fly postgres create --name my-db-v16 --region iad --image-ref flyio/postgres-flex:16

# Migrate data
fly postgres import pg_dump_url -a my-db-v16

# Update app to point to new cluster
fly postgres detach my-db -a my-app
fly postgres attach my-db-v16 -a my-app
fly deploy -a my-app  # Picks up new DATABASE_URL

# Add machines in new region
fly scale count 1 --region fra -a my-app

# Verify new region is healthy
fly status -a my-app

# Remove machines from old region
fly scale count 0 --region iad -a my-app

# For volumes: create new volume, migrate data, destroy old
fly volumes create data --size 10 --region fra -a my-app

// Monitor machine state transitions via Machines API
async function watchMachines(appName: string, callback: (event: MachineEvent) => void) {
  const client = new FlyClient(appName, process.env.FLY_API_TOKEN!);
  const stateCache = new Map<string, string>();

  setInterval(async () => {
    const machines = await client.listMachines();
    for (const m of machines) {
      const prev = stateCache.get(m.id);
      if (prev && prev !== m.state) {
        callback({
          machineId: m.id,
          region: m.region,
          previousState: prev,
          currentState: m.state,
          timestamp: new Date(),
        });
      }
      stateCache.set(m.id, m.state);
    }
  }, 10_000);  // Check every 10 seconds
}

interface MachineEvent {
  machineId: string;
  region: string;
  previousState: string;
  currentState: string;
  timestamp: Date;
}

// Implement health check that reports machine health
// Fly.io uses this to auto-restart unhealthy machines

import express from 'express';
const app = express();

app.get('/health', async (req, res) => {
  const checks = {
    database: await checkPostgres(),
    redis: await checkRedis(),
    memory: process.memoryUsage().heapUsed < 500 * 1024 * 1024,  // < 500MB
  };

  const healthy = Object.values(checks).every(Boolean);
  res.status(healthy ? 200 : 503).json({
    status: healthy ? 'healthy' : 'unhealthy',
    region: process.env.FLY_REGION,
    machine: process.env.FLY_MACHINE_ID,
    checks,
  });
});

# Stream logs and process with jq
fly logs -a my-app --json | jq -c 'select(.level == "error")' | while read -r line; do
  echo "$line" >> errors.jsonl
  # Send to Slack, PagerDuty, etc.
done

# Search recent logs for specific patterns
fly logs -a my-app --no-tail | grep -i "error\|crash\|oom"

# Post-deploy notification in CI
fly deploy -a my-app && \
curl -X POST "$SLACK_WEBHOOK_URL" \
  -H "Content-Type: application/json" \
  -d "{\"text\": \"Deployed my-app to Fly.io. Status: $(fly status -a my-app --json | jq -r '.Status')\"}"