Background Job Orchestrator

// Horizontal scaling with multiple workers
const worker = new Worker('email-queue', async (job) => {
  await processEmail(job.data);
}, {
  connection: redis,
  concurrency: 5  // Process 5 jobs concurrently per worker
});

// Run multiple worker processes (PM2, Kubernetes, etc.)
// Each worker processes concurrency * num_workers jobs

// Set up alerts for queue depth
setInterval(async () => {
  const waiting = await queue.getWaitingCount();
  if (waiting > 1000) {
    alert('Queue depth exceeds 1000, scale workers!');
  }
}, 60000);

// Queue setup
const emailQueue = new Queue('email-campaign', { connection: redis });

// Enqueue batch
async function sendCampaign(userIds: number[], template: string) {
  const jobs = userIds.map(userId => ({
    name: 'send',
    data: { userId, template },
    opts: {
      attempts: 3,
      backoff: { type: 'exponential', delay: 5000 }
    }
  }));

  await emailQueue.addBulk(jobs);
}

// Worker with retry logic
const worker = new Worker('email-campaign', async (job) => {
  const { userId, template } = job.data;

  const user = await db.users.findById(userId);
  const email = renderTemplate(template, user);

  try {
    await sendgrid.send({
      to: user.email,
      subject: email.subject,
      html: email.body
    });
  } catch (error) {
    if (error.code === 'ECONNREFUSED') {
      throw error; // Retry
    }
    // Invalid email, don't retry
    console.error(`Invalid email for user ${userId}`);
  }
}, {
  connection: redis,
  concurrency: 10
});

// Daily report at 9 AM
await queue.add('daily-report', {
  type: 'sales',
  recipients: ['admin@company.com']
}, {
  repeat: {
    pattern: '0 9 * * *', // Cron syntax
    tz: 'America/New_York'
  }
});

// Worker generates and emails report
worker.process('daily-report', async (job) => {
  const { type, recipients } = job.data;

  const data = await generateReport(type);
  const pdf = await createPDF(data);

  await emailQueue.add('send', {
    to: recipients,
    subject: `Daily ${type} Report`,
    attachments: [{ filename: 'report.pdf', content: pdf }]
  });
});

// Multi-stage job with progress tracking
await videoQueue.add('transcode', {
  videoId: 123,
  formats: ['720p', '1080p', '4k']
}, {
  attempts: 2,
  timeout: 3600000 // 1 hour timeout
});

worker.process('transcode', async (job) => {
  const { videoId, formats } = job.data;

  for (let i = 0; i < formats.length; i++) {
    const format = formats[i];

    // Update progress
    await job.updateProgress((i / formats.length) * 100);

    // Transcode
    await ffmpeg.transcode(videoId, format);
  }

  await job.updateProgress(100);
});

// Client polls for progress
app.get('/videos/:id/status', async (req, res) => {
  const job = await queue.getJob(req.params.jobId);
  res.json({
    state: await job.getState(),
    progress: job.progress
  });
});

// Queue health dashboard
async function getQueueMetrics() {
  const [waiting, active, completed, failed, delayed] = await Promise.all([
    queue.getWaitingCount(),
    queue.getActiveCount(),
    queue.getCompletedCount(),
    queue.getFailedCount(),
    queue.getDelayedCount()
  ]);

  return {
    waiting,    // Jobs waiting to be processed
    active,     // Jobs currently processing
    completed,  // Successfully completed
    failed,     // Failed after retries
    delayed,    // Scheduled for future
    health: waiting < 1000 && failed < 100 ? 'healthy' : 'degraded'
  };
}

// Development: Monitor jobs visually
import { createBullBoard } from '@bull-board/api';
import { BullMQAdapter } from '@bull-board/api/bullMQAdapter';
import { ExpressAdapter } from '@bull-board/express';

const serverAdapter = new ExpressAdapter();

createBullBoard({
  queues: [
    new BullMQAdapter(emailQueue),
    new BullMQAdapter(videoQueue)
  ],
  serverAdapter
});

app.use('/admin/queues', serverAdapter.getRouter());
// Visit http://localhost:3000/admin/queues

□ Dead letter queue configured
□ Retry strategy with exponential backoff
□ Job timeout limits set
□ Rate limiting for third-party APIs
□ Idempotency keys for critical operations
□ Worker concurrency tuned (CPU cores * 2)
□ Horizontal scaling configured (multiple workers)
□ Queue depth monitoring with alerts
□ Failed job inspection workflow
□ Job data doesn't contain PII in logs
□ Redis persistence enabled (AOF or RDB)
□ Graceful shutdown handling (SIGTERM)