An under-appreciated concept in JavaScript is how objects and functions are references, and that directly impacts React performance. If you were to create two functions that are completely identical, they are still not equal. Try for yourself:
const functionOne = function() { alert('Hello world!'); };
const functionTwo = function() { alert('Hello world!'); };
functionOne === functionTwo; // false
But check out the difference if you assign a variable to an already-existing function:
const functionThree = function() { alert('Hello world!'); };
const functionFour = functionThree;
functionThree === functionFour; // true
Objects work the same way.
const object1 = {};
const object2 = {};
const object3 = object1;
object1 === object2; // false
object1 === object3; // true
If you have experience in other languages, you may be familiar with pointers. What is happening here is that each time you create an object, you are allocating some amount of memory on the device. When I said that object1 = {}
, I have created a chunk of bytes in the user’s RAM that is dedicated specifically to object1
. It is fair to imagine object1
as an address that contains where in RAM its key-value pairs are located. When I said object2 = {}
, I created a different chunk of bytes in the user’s RAM that is dedicated specifically to object2
. Does the address of object1
match the address of object2
? No. That is why the equality check for the two variables does not pass. Their key-value pairs may be exactly the same, but their addresses in memory are different, and that is what is being compared.
When I assigned object3 = object1
, I am assigning the value of object3
to be the address of object1
. It is not a new object. It is that same location in memory. You can verify this like so:
const object1 = { x: true };
const object3 = object1;
object3.x = false;
object1.x; // false
In this example, I created an object in memory and assigned it to object1
. I then assigned object3
to that same address in memory. By mutating object3
, I have changed the value at that location in memory, meaning all other references to that location in memory change as well. object1
, which still points to that location in memory, now has a changed value.
This is a very common error for junior developers to make, and likely warrants an in-depth tutorial of its own; but this particular tutorial is about React performance, which may be compromised even by developers with more seniority who have simply not considered the implications of variable references.
What does this have to do with React? React has an intelligent way of saving processing time to boost performance: If a PureComponent’s props and state have not changed, then the output of render
must not have changed either. Clearly, if all things are equal, nothing has changed. If nothing has changed, render
must return the same output, so let’s not bother executing it. This is what makes React fast. It only renders as needed.
React determines if its props and state are equal the same way JavaScript does — by simply comparing them with the ==
operator. React does not shallow or deep compare objects to determine if they are equal. Shallow comparison is a term used to describe comparing each key-value pair of an object, as opposed to comparing the memory address. Deep comparison is going one step further and, if any of the values in the key-value pair are also objects, comparing those key-value pairs as well, ad nauseum. React does neither: it merely checks if the references are the same.
If you were to change a component’s prop from { x: 1 }
to another object { x: 1 }
, React will re-render, because those two objects do not reference the same location in memory. If you were to change a component’s prop from object1
(from above) to object3
, React would not re-render, because those two objects are the same reference.
In JavaScript, functions are handled the same way. If React receives an identical function with a different memory address, it will re-render. If React receives the same function reference, it will not.
This is an unfortunately common scenario I come across during code review:
class SomeComponent extends React.PureComponent {
get instructions() {
if (this.props.do) {
return 'Click the button: ';
}
return 'Do NOT click the button: ';
}
render() {
return (
<div>
{this.instructions}
<Button onClick={() => alert('!')} />
</div>
);
}
}
This is a pretty straightforward component. There’s a button, and when it is clicked, it alerts. Instructions tell you whether or not you should click it, which is controlled by the do={true}
or do={false}
prop of SomeComponent
.
What happens here is that every time SomeComponent
is re-rendered (such as do
toggling from true
to false
), Button
is re-rendered too! The onClick
handler, despite being exactly the same, is being created every render
call. Each render, a new function is created (because it is created in the render function) in memory, a new reference to a new address in memory is passed to <Button />
, and the Button
component is re-rendered, despite absolutely nothing having changed in its output.
The Fix
If your function does not depend on your component (no this
contexts), you can define it outside of the component. All instances of your component will use the same function reference, since the function is identical in all cases.
const createAlertBox = () => alert('!');
class SomeComponent extends React.PureComponent {
get instructions() {
if (this.props.do) {
return 'Click the button: ';
}
return 'Do NOT click the button: ';
}
render() {
return (
<div>
{this.instructions}
<Button onClick={createAlertBox} />
</div>
);
}
}
In contrast to the previous example, createAlertBox
remains the same reference to the same location in memory during every render
. Button
therefore never has to re-render.
While Button
is likely a small, quick-to-render component, you may see these inline definitions on large, complex, slow-to-render components, and it can really bog down your React application. It is good practice to simply never define these functions inside the render method.
If your function does depend on your component such that you cannot define it outside the component, you can pass a method of your component as the event handler:
class SomeComponent extends React.PureComponent {
createAlertBox = () => {
alert(this.props.message);
};
get instructions() {
if (this.props.do) {
return 'Click the button: ';
}
return 'Do NOT click the button: ';
}
render() {
return (
<div>
{this.instructions}
<Button onClick={this.createAlertBox} />
</div>
);
}
}
In this case, each instance of SomeComponent
has a different alert box. The click event listener for Button
needs to be unique to SomeComponent
. By passing the createAlertBox
method, it does not matter if SomeComponent
re-renders. It doesn’t even matter if the message
prop changes! The address in memory of createAlertBox
does not change, meaning Button
does not have to re-render, and you save processing time and improve rendering speed of your application.
But what if my functions are dynamic?
The Fix (Advanced)
Author’s Note: I wrote the following examples off the top of my head as a way to repeatedly reference the same function in memory. These examples are meant to make comprehension of references easy. While I would recommend reading this section for the purpose of comprehending references, I have included a better implementation at the end that was generously contributed by Chris Ryan via comment. His solution takes into account cache invalidation and React’s built-in memory management.
There is a very common use case that you have a lot of unique, dynamic event listeners in a single component, such as when mapping an array.
class SomeComponent extends React.PureComponent {
render() {
return (
<ul>
{this.props.list.map(listItem =>
<li key={listItem.text}>
<Button onClick={() => alert(listItem.text)} />
</li>
)}
</ul>
);
}
}
In this case, you have a variable number of buttons, making a variable number of event listeners, each with a unique function that you cannot possibly know what is when creating your SomeComponent
. How can you possible solve this conundrum?
Enter memoization, or what may be easier to refer to as simply, caching. For each unique value, create and cache a function; for all future references to that unique value, return the previously cached function.
This is how I would implement the above example.
class SomeComponent extends React.PureComponent {
// Each instance of SomeComponent has a cache of click handlers
// that are unique to it.
clickHandlers = {};
// Generate and/or return a click handler,
// given a unique identifier.
getClickHandler(key) {
// If no click handler exists for this unique identifier, create one.
if (!Object.prototype.hasOwnProperty.call(this.clickHandlers, key)) {
this.clickHandlers[key] = () => alert(key);
}
return this.clickHandlers[key];
}
render() {
return (
<ul>
{this.props.list.map(listItem =>
<li key={listItem.text}>
<Button onClick={this.getClickHandler(listItem.text)} />
</li>
)}
</ul>
);
}
}
Each item in the array is passed through the getClickHandler
method. Said method will, the first time it is called with a value, create a function unique to that value, then return it. All future calls to that method with that value will not create a new function; instead, it will return the reference to the previously created function in memory.
As a result, re-rendering SomeComponent
will not cause Button
to re-render. Similarly, adding items to the list
prop will create event listeners for each button dynamically.
You may need to use your own cleverness for generating unique identifiers for each handler when they are determined by more than one variable, but it is not much harder than simply generating a unique key
prop for each JSX object in the mapped result.
A word of warning for using the index
as the identifier: You may get the wrong result if the list changes order or removes items. When your array changes from [ 'soda', 'pizza' ]
to just [ 'pizza' ]
and you have cached your event listener as listeners[0] = () => alert('soda')
, you will find that when you users click the now-index-0 button for pizza that it alerts soda
. This is the same reason React advises against using array indices for key props.
A Better Implementation
Courtesy of Medium user Chris Ryan.
Conclusion
If you liked this article, feel free to give it a heart or a unicorn. It’s quick, it’s easy, and it’s free! If you have any questions or relevant great advice, please leave them in the comments below.
To read more of my columns, you may follow me on LinkedIn, Medium, and Twitter, or check out my portfolio on CharlesStover.com.
Top comments (2)
Interesting point of view. Did you test performance difference?
There are too many variables to make a blanket statement that memoization will always improve performance of a Component. For some Components, memoization may take longer than a full re-render!
I discovered this issue specifically due to a performance problem in one of my applications that was re-rendering on a short interval. The event listeners were being recreated each interval, and the application slowed to a crawl as a result. Memoization removed the lag entirely.
This article hopefully just educates on how it works, and each developer can determine if and how best to apply it to their own projects.