Enhance Node.js Server Performance with Worker Threads

#javascript #coding #node #tutorial

Scenarios:

Before we dive into worker threads, let's consider some scenarios...

Suppose a client uploads a large file to a server that needs to be modified or involves processing thousands of data points in the background. If the server waits for this task to finish, the client is left waiting and unable to explore other features. Imagine if a client had to wait for 5 minutes without being able to do anything else—this would be frustrating and far from user-friendly!

Consider another situation where you upload a profile image, and it takes a long time to process, convert, and store in the database. During this time, if the server prevents you from performing other tasks, it significantly reduces the user experience.

In the first case, wouldn't it be better if the server allowed you to explore other features while the file is still being processed? This way, you wouldn't have to wait (since the server wouldn't block you), resulting in a smoother experience.

In the second case, what if the image processing happens in the background, allowing you to continue using other features without waiting?

Solution:

So, what's an effective way to optimize the system's performance in these scenarios? While there are several approaches, using worker threads is a great solution. Worker threads were introduced in Node.js version 10 and are especially useful for performing CPU-intensive tasks in parallel, reducing the load on the main CPU.
Worker threads operate in the background, creating a separate thread that handles intensive computations without blocking the main thread, thus allowing the server to remain responsive for other tasks. While JavaScript is traditionally a single-threaded language and Node.js operates in a single-threaded environment, worker threads enable multithreading by distributing operations across multiple threads. This parallel execution optimizes resource usage and significantly reduces processing time.

Implementation of worker_thread:

Today we will implement a simple nodejs application with default package worker_threads . First create an express server where a simple get request executes.

First initialize the project:

$ npm init -y

Install express module and nodemon:

$ npm i express nodemon

Creating a simple nodejs server which runs on port 3000.

Import express from ‘express’;
const app = express();
const port = 3000;


// Basic endpoint to test server
app.get(‘/’, (req, res) => {
   res.send(‘Hello World!’);
});


app.listen(port, () => console.log(`Server running on port ${port}`));

Here we created a server which will run on port 3000.
To run, let's modify our package.json file.
Add type as module as below to get the ES6 modules. Also modify under the scripts portion as below.

{
 "name": "worker_express",
 "version": "1.0.0",
 "description": "",
 "main": "index.js",
 "type": "module",
 "scripts": {
   "test": "echo \"Error: no test specified\" && exit 1",
   "start": "node index.js",
   "dev": "nodemon index.js"
 },
 "keywords": [],
 "author": "",
 "license": "ISC",
 "dependencies": {
   "dotenv": "^16.4.5",
   "express": "^4.19.2",
   "nodemon": "^3.1.4"
 }
}

Now let’s run our application as dev mode with nodemon:

$ npm run dev

You will see the message Server running on port 3000. Now go to the localhost:3000 and you can see the Hello World! As far we did just a simple nodejs express server.

Now lets’ create another file named service.js
Here we can create a fibonacci sequence function that finds the nth number fibonacci sequence.

// service.js
function fibonacci(n) {
   if (n <= 1) return 1;
   return fibonacci(n-1) + fibonacci(n-2);
}


export default fibonacci;

Now let’s add another api endpoint to the index.js file and call the fibonacci function from the service.js file. We will calculate the 40th Fibonacci number as an example.

import fibonacci from "./service.js";


// Fibonacci endpoint
app.get('/fibonacci', (req, res) => {
   fibonacci(40)
   res.send('fibonacci called');
})

If you hit the URL http://localhost:3000/fibonacci, you will see that it delays a bit, making you wait. The delay time depends on the computation.

You can try again by commenting the function and see it takes less time which is about millisecond.

In this case you might have to do other heavy operations which are time consuming and reduce performance.

In this case, we can use the worker_threads module, which has been available by default in Node.js since version 10. Now let’s modify the code to apply worker_threads and see the effect.

Import Worker from worker_thread which is node js default package.

import { Worker } from "worker_threads";

Now modify the api endpoint like below.

// Endpoint using worker thread for CPU-intensive task
app.get('/fibonacci', (req, res) => {
   const worker = new Worker('./service.js', {workerData: 40});

   // Handle messages from worker thread
   worker.on('message', (resolve) => console.log(resolve));


   res.send('fibonacci called');
})

Here, we create a worker instance and set the file name service.js as the first argument, while the second argument passes parameters through workerData. You can change the workerData parameter to any other data instead of 40.

worker.on(‘message’, ….) This sets up an event listener on the worker for the ‘message’ event. The message event is emitted by the worker when it sends data back to the main thread using parentrPort.postMessage(...).
(resolve) => console.log(resolve) this is a callback function that will be executed when the worker sends back the data after operation. The received message(data) is passed to this function as the resolve parameter.

Now let’s update our service.js file.

import { workerData, parentPort } from 'worker_threads';


// Function to compute Fibonacci sequence
function fibonacci(n) {
   if (n <= 1) return 1;
   return fibonacci(n-1) + fibonacci(n-2);
}


// Compute Fibonacci using workerData
const fibonacciAt =  fibonacci(workerData);


// Send result back to the main thread
parentPort.postMessage(fibonacciAt);

Here, we import workerData and parentPort, which allow us to receive the data sent through workerData and return the result via the postMessage method of parentPort, both imported from worker_threads.

Test the Setup:
Now, send a request to http://localhost:3000/fibonacci and notice that the server no longer blocks the main thread. The time-consuming operation occurs in the background on a separate thread, significantly reducing the response time and improving user experience.