DEV Community

Cover image for How to Serialize Concurrent Operations in JavaScript: Callbacks, Promises, and Async/Await
Nested Software
Nested Software

Posted on • Edited on • Originally published at nestedsoftware.com

How to Serialize Concurrent Operations in JavaScript: Callbacks, Promises, and Async/Await

#javascript #callbacks #promises #await

Overview

This article is about how to specify the order of concurrent operations in JavaScript.

Often we don't care about the order that concurrent operations are completed in. For example, let's say we have a Web server that is processing requests from clients. The time that each request takes can vary, and the order in which the responses are sent back doesn't matter.

However, it's not unusual for situations to arise where we do care about the ordering. Sometimes when we execute an asynchronous operation, we need for it to run to completion before we can execute the next operation. That's what this post is about.

There are basically 3 ways to do this in modern JavaScript.

  • The oldest way is to use only callbacks. This approach is perhaps conceptually the most pure, but it also can lead to so-called callback hell: A kind of spaghetti code that can be hard to understand and debug.
  • Another approach is to use promises, which allows the sequence of operations to be specified in a more procedural manner.
  • More recently, JavaScript has introduced async and await.

These approaches are not mutually exclusive, but rather are complementary: async/await builds on promises, and promises use callbacks.

I'll show a simple example implemented in each of these 3 ways, first with callbacks, then with promises, and finally with async/await.

For this example, we have a hypothetical application that can automatically deploy some custom software to multiple computers concurrently. Let's say that each deployment has 3 steps:

  • Install the OS
  • Deploy our software
  • Run tests

For any given target, these 3 operations need to run in sequence, but they can be executed concurrently across targets (thanks to edA-qa for suggesting this practical example!).

Concurrent Execution

First let's look at some code that runs these tasks concurrently without serializing them at all (unserialized.js):

const random = (min, max) => Math.floor(Math.random() * (max - min + 1)) + min

const installOS = () => asyncTask("Install OS")

const deploySoftware = () => asyncTask("Deploy Software")

const runTests = () => asyncTask("Run Tests")

const taskDone = (name) => console.log(`Completed async "${name}"`)

const asyncTask = (name) =>  {
    console.log(`Started async "${name}"...`)
    setTimeout(() => taskDone(name), random(1,3) * 1000)
    console.log(`Returning from async "${name}"`)
}

const main = ()=> {
    installOS()
    deploySoftware()
    runTests()
}

main()
Enter fullscreen mode Exit fullscreen mode

We simulate our operations by calling asyncTask, which uses setTimeout to wait between 1 and 3 seconds before completing its task and calling taskDone.

Below is a typical output (the actual order will change each time this code is run):

C:\dev\asyncio>node unserialized.js
Started async "Install OS"...
Returning from async "Install OS"
Started async "Deploy Software"...
Returning from async "Deploy Software"
Started async "Run Tests"...
Returning from async "Run Tests"
Completed async "Deploy Software"
Completed async "Install OS"
Completed async "Run Tests"
Enter fullscreen mode Exit fullscreen mode

As we can see, this is not so good: We deployed our software before the OS was even done installing!

Using Callbacks

All right, let's use callbacks to fix this problem (callbacks.js):

const random = (min, max) => Math.floor(Math.random() * (max - min + 1)) + min

const installOS = (nextTask) => asyncTask("Install OS", nextTask)

const deploySoftware = (nextTask) => asyncTask("Deploy Software", nextTask)

const runTests = () => asyncTask("Run Tests")

const taskDone = (name, nextTask) => {
    console.log(`Completed async "${name}"`)
    if (nextTask) {
        nextTask()
    }
}

const asyncTask = (name, nextTask) =>  {
    console.log(`Started async "${name}"...`)
    setTimeout(() => taskDone(name, nextTask), 
        random(1,3) * 1000)
    console.log(`Returning from async "${name}"`)
}

const main = ()=> {
    installOS(()=>deploySoftware(()=>runTests()))
}

main()
Enter fullscreen mode Exit fullscreen mode

We call installOS with a callback that will run deploySoftware once installOS is done. Once deploySoftware is done, it will call its own callback, the runTests function.

Each time an operation is done, the taskDone function will log the operation as completed and start the next operation.

Let's see if it works:

C:\dev\asyncio>node callbacks.js
Started async "Install OS"...
Returning from async "Install OS"
Completed async "Install OS"
Started async "Deploy Software"...
Returning from async "Deploy Software"
Completed async "Deploy Software"
Started async "Run Tests"...
Returning from async "Run Tests"
Completed async "Run Tests"
Enter fullscreen mode Exit fullscreen mode

Good, we can see that each step happens in order.

However, there are still a number of issues with this code. Even with such a bare-bones example, I think that the code is a little difficult to read.

Error handling is also perhaps not as straightforward as it could be. For example, let's modify the deploySoftware function to throw an error:

const deploySoftware = (nextTask) => {
    throw new Error('deploying software failed')
    asyncTask("Deploy Software", 
    nextTask)
}
Enter fullscreen mode Exit fullscreen mode

And let's try to naively wrap our main call with an exception handler:

const main = ()=> {
    try {
        installOS(()=>deploySoftware(()=>runTests()))
    } catch (error) {
        console.log(`*** Error caught: '${error}' ***`)
    }
}
Enter fullscreen mode Exit fullscreen mode

Unfortunately, the catch block is never executed and the exception ends up popping the stack:

C:\dev\asyncio\callbacks.js:7
        throw new Error('deploying software failed')
        ^

Error: deploying software failed
    at deploySoftware (C:\dev\asyncio\callbacks.js:7:8)
    at installOS (C:\dev\asyncio\callbacks.js:30:17)
    at taskDone (C:\dev\asyncio\callbacks.js:17:3)
    at Timeout.setTimeout [as _onTimeout] (C:\dev\asyncio\callbacks.js:23:19)
    at ontimeout (timers.js:458:11)
    at tryOnTimeout (timers.js:296:5)
    at Timer.listOnTimeout (timers.js:259:5)
Enter fullscreen mode Exit fullscreen mode

The problem is that installOS has already returned by the time the error happens. Clearly some additional effort will have to go into dealing with errors. I'll leave that as an exercise for the reader. As we will see, promises will make the error handling easier.

Using Promises

Let's modify our code slightly to use promises (promises.js):

const random = (min, max) => Math.floor(Math.random() * (max - min + 1)) + min

const installOS = () => asyncTask("Install OS")

const deploySoftware = () => asyncTask("Deploy Software")

const runTests = () => asyncTask("Run Tests")

const taskDone = (name) => console.log(`Completed async "${name}"`)

const asyncTask = (name) =>  {
    console.log(`Started async "${name}"...`)

    const promise = new Promise((resolve, reject) => {
        setTimeout(()=>resolve(name), random(1,3) * 1000)
    })

    console.log(`Returning from async "${name}"`)

    return promise
}

const main = ()=> {
    installOS().then(name=>{
        taskDone(name)
        return deploySoftware()
    }).then(name=>{
        taskDone(name)
        return runTests()
    }).then(taskDone)
}

main()
Enter fullscreen mode Exit fullscreen mode

We can see that we've been able to remove the nextTask callback from our tasks. Now each task can run independently. The job of linking them together has been moved into main.

To accomplish this, we've modified asyncTask to return a promise.

How does this work? When the results from an asynchronous operation are ready, we call the promise's resolve callback. Promises have a method then which can be supplied with a callback as a parameter. When we trigger the resolve function, it will run the callback we supplied to the promise's then method.

This allows us to serialize our asynchronous operations. When installOS is done, we supply a callback to then that calls deploySoftware. The deploySoftware function returns another promise, which resolves by calling runTests. When runTests is done, we just supply a trivial callback that just logs the job as done.

By returning promise objects from our tasks, we can chain together the tasks that we want to complete one after the other.

The details of how promises are implemented are beyond the scope of this post. If you're interested in this topic, I found an interesting article about the design of the Q promise library.

I think this code is easier to read than the callback example.

It also makes it easier to handle errors. Let's again modify deploySoftware to throw an error:

const deploySoftware = () => {
    throw new Error('"Deploy Software" failed')
    return asyncTask("Deploy Software")
}
Enter fullscreen mode Exit fullscreen mode

Promises have a convenient way to deal with this. We simply append a catch method to the end of our promise chain:

const main = ()=> {
    installOS().then(name=>{
        taskDone(name)
        return deploySoftware()
    }).then(name=>{
        taskDone(name)
        return runTests()
    }).then(taskDone)
    .catch((error)=>console.log(`*** Error caught: '${error}' ***`))
}
Enter fullscreen mode Exit fullscreen mode

If an error occurs while trying to resolve a promise, this catch method is called.

Let's see what happens when we run this code:

C:\dev\asyncio>node serialize_with_promises.js
Started async "Install OS"...
Returning from async "Install OS"
Completed async "Install OS"
*** Error caught: 'Error: "Deploy Software" failed' ***
Enter fullscreen mode Exit fullscreen mode

Great, we caught our error! I think this looks much more straightforward than the pure callbacks example.

Using Async/Await

Aync/Await is the last example we'll look at. This syntax works together with promises to make serializing asynchronous operations look like regular synchronous code.

Okay, no more waiting - let's modify our previous example to use async/await (async_await.js)!

const random = (min, max) => Math.floor(Math.random() * (max - min + 1)) + min

const installOS = () => asyncTask("Install OS") 

const deploySoftware = () => asyncTask("Deploy Software") 

const runTests = () => asyncTask("Run Tests") 

const taskDone = (name) => console.log(`Completed async "${name}"`)

const asyncTask = (name) =>  {
    console.log(`Started async "${name}"...`)

    const promise = new Promise((resolve, reject) => {
        setTimeout(()=>resolve(name), random(1,3) * 1000)
    })

    console.log(`Returning from async "${name}"`)

    return promise
}

const main = async ()=> {
    const installOSResult = await installOS()
    taskDone(installOSResult)

    const deploySoftwareResult = await deploySoftware()
    taskDone(deploySoftwareResult)

    const runTestsResult = await runTests()
    taskDone(runTestsResult)
}

main()
Enter fullscreen mode Exit fullscreen mode

What changes have we made? First, we've labelled main as an async function. Next, instead of a promise chain, we await the results of our asynchronous operations.

await will automatically wait for the promise returned by a function to resolve itself. It's non-blocking like all of the code we've looked at today, so other things can run concurrently while an expression is being awaited. However, the next line of code following an await won't run until the promise has been resolved. Any function that contains an await has to be marked as async.

Let's run this code and look at the results:

C:\dev\asyncio>async_await.js
Started async "Install OS"...
Returning from async "Install OS"
Completed async "Install OS"
Started async "Deploy Software"...
Returning from async "Deploy Software"
Completed async "Deploy Software"
Started async "Run Tests"...
Returning from async "Run Tests"
Completed async "Run Tests"
Enter fullscreen mode Exit fullscreen mode

Great, it works!

We can again make a small change to cause deploySoftware to throw an error:

const deploySoftware = () => {
    throw new Error('"Deploy Software" failed')
    return asyncTask("Deploy Software")
}
Enter fullscreen mode Exit fullscreen mode

Let's see how we can handle this:

const main = async ()=> {
    try {
        const installOSResult = await installOS()
        taskDone(installOSResult)

        const deploySoftwareResult = await deploySoftware()
        taskDone(deploySoftwareResult)

        const runTestsResult = await runTests()
        taskDone(runTestsResult)
    } catch(error) {
        console.log(`*** Error caught: '${error}' ***`)     
    }
}
Enter fullscreen mode Exit fullscreen mode

This works:

C:\dev\asyncio>node async_await.js
Started async "Install OS"...
Returning from async "Install OS"
Completed async "Install OS"
*** Error caught: 'Error: "Deploy Software" failed' ***
Enter fullscreen mode Exit fullscreen mode

As we can see, async/await makes it possible to use standard synchronous syntax to handle any errors that are produced by our asynchronous code!

Before concluding this article, I thought I'd just add a bit of code to show that await really is non-blocking. Let's add a timer that will run concurrently with our other code:

const timer = () => setInterval(()=>console.log('tick'), 500)

const main = async ()=> {
    const t = timer()

    const installOSResult = await installOS()
    taskDone(installOSResult)

    const deploySoftwareResult = await deploySoftware()
    taskDone(deploySoftwareResult)

    const runTestsResult = await runTests()
    taskDone(runTestsResult)

    clearInterval(t)
}
Enter fullscreen mode Exit fullscreen mode

Here's the result:

C:\dev\asyncio>node async_await.js
Started async "Install OS"...
Returning from async "Install OS"
tick
Completed async "Install OS"
Started async "Deploy Software"...
Returning from async "Deploy Software"
tick
tick
tick
tick
tick
tick
Completed async "Deploy Software"
Started async "Run Tests"...
Returning from async "Run Tests"
tick
tick
Completed async "Run Tests"
Enter fullscreen mode Exit fullscreen mode

We can confirm that the timer continues to run while we await our tasks. Great!

When using await, I think it is helpful to keep in mind that it is roughly equivalent to getting a promise back from the asynchronous call and calling its then method.

Some gotchas: You have to use await in a function marked with async. That means that you can't await something in the top level of JavaScript code. When writing top level code, you can use the then syntax of promises instead or wrap the code in a self-executing function that you mark as async.

Also, if you need to run a bunch of tasks concurrently, and you just want to execute some code when all of them have finished, see Promise.all

Related:

Top comments (2)

Collapse
 
patrickcole profile image
Patrick Cole •

Thanks for providing an outline on the progress of synchronous code execution in an asynchronous world! This was super helpful for someone like me who is just getting their head wrapped around async/await.

Collapse
 
nestedsoftware profile image
Nested Software •

Thank you. I really appreciate the positive feedback!

Read next

santanaluc94 profile image

Como funcionam Bindings de Fluxo de Controle no KnockoutJs

Lucas Teixeira dos Santos Santana -

nozibul_islam_113b1d5334f profile image

The Art of Clean Code: A Practical Guide to Writing Maintainable JavaScript

Nozibul Islam -

hamzakhan profile image

🌀 State Management in React: Comparing Redux Toolkit vs. Zustand 📊

Hamza Khan -

siisee11 profile image

Langgraph Human In The Loop with socket

Jaeyoun Nam -