Blue/Green Stateful Workers: Drain In-Flight Jobs Before Old Tasks Die

RUNNING → DRAINING (SIGTERM) → IDLE (in-flight=0) → EXIT 0
 ↘ DEADLINE → nack/extend visibility → EXIT 1 (deploy retries)

// ✅ Node SQS worker drain
import { Consumer } from "sqs-consumer";

let accepting = true;
const inFlight = new Set<Promise<void>>();

const app = Consumer.create({
 queueUrl: process.env.QUEUE_URL!,
 handleMessage: async (msg) => {
 if (!accepting) throw new Error("draining"); // ✅ don't start new work
 const p = processMessage(msg).finally(() => inFlight.delete(p));
 inFlight.add(p);
 await p;
 },
 bodyParser: JSON.parse,
});

async function shutdown(signal: string) {
 console.info({ signal, msg: "drain_start", inFlight: inFlight.size });
 accepting = false;
 app.stop(); // stop polling
 const deadline = Date.now() + 25_000; // < ECS stopTimeout (30s)
 while (inFlight.size && Date.now() < deadline) {
 await Promise.race([...inFlight, sleep(200)]);
 }
 if (inFlight.size) {
 console.error({ left: inFlight.size, msg: "drain_timeout" });
 process.exit(1); // ✅ visibility timeout will redeliver
 }
 process.exit(0);
}

process.on("SIGTERM", () => void shutdown("SIGTERM"));
app.start();

# ✅ ECS task def: stopTimeout seconds must exceed drain deadline
# stopTimeout: 60
# ❌ default 30s with 45s video transcodes → SIGKILL every deploy