¡Hola! Estoy disponible para responder a cualquier pregunta que tengas. Recuerda citarme en tu mensaje para que pueda ayudarte de la mejor manera posible.
Haz un resumen de esto en español.
Chrome usage data shows that 90% of a user's time on a page is spent after it loads, Thus, careful measurement of responsiveness throughout the page lifecycle is important. This is what the INP metric assesses.
Good responsiveness means that a page responds quickly to interactions made with it. When a page responds to an interaction, the result is visual feedback, which is presented by the browser in the next frame the browser presents. Visual feedback tells you if, for example, an item you add to an online shopping cart is indeed being added, whether a mobile navigation menu has opened, if a login form's contents are being authenticated by the server, and so forth.
Some interactions will naturally take longer than others, but for especially complex interactions, it's important to quickly present some initial visual feedback as a cue to the user that something is happening. The time until the next paint is the earliest opportunity to do this. Therefore, the intent of INP is not to measure all the eventual effects of the interaction (such as network fetches and UI updates from other asynchronous operations), but the time in which the next paint is being blocked. By delaying visual feedback, you may be giving users the impression that the page is not responding to their actions.
The goal of INP is to ensure the time from when a user initiates an interaction until the next frame is painted is as short as possible, for all or most interactions the user makes.
In the following video, the example on the right gives immediate visual feedback that an accordion is opening. It also demonstrates how poor responsiveness can cause multiple unintended responses to input because the user thinks the experience is broken.
An example of poor versus good responsiveness. At left, long tasks block the accordion from opening. This causes the user to click multiple times, thinking the experience is broken. When the main thread catches up, it processes the delayed inputs, resulting in the accordion opening and closing unexpectedly.
This article explains how INP works, how to measure it, and points to resources for improving it.
What is INP? #
INP is a metric that assesses a page's overall responsiveness to user interactions by observing the latency of all click, tap, and keyboard interactions that occur throughout the lifespan of a user's visit to a page. The final INP value is the longest interaction observed, ignoring outliers.
A note on how INP is calculated
An interaction is a group of event handlers that fire during the same logical user gesture. For example, "tap" interactions on a touchscreen device include multiple events, such as pointerup, pointerdown, and click. An interaction can be driven by JavaScript, CSS, built-in browser controls (such as form elements), or a combination thereof.
An interaction's latency consists of the single longest duration of a group of event handlers that drives the interaction, from the time the user begins the interaction to the moment the next frame is presented with visual feedback.
What is a good INP score? #
Pinning labels such as "good" or "poor" on a responsiveness metric is difficult. On one hand, you want to encourage development practices that prioritize good responsiveness. On the other hand, you must account for the fact that there's considerable variability in the capabilities of devices people use to set achievable development expectations.
To ensure you're delivering user experiences with good responsiveness, a good threshold to measure is the 75th percentile of page loads recorded in the field, segmented across mobile and desktop devices:
An INP below or at 200 milliseconds means that your page has good responsiveness.
An INP above 200 milliseconds and below or at 500 milliseconds means that your page's responsiveness needs improvement.
An INP above 500 milliseconds means that your page has poor responsiveness.
What's in an interaction? #
A diagram depicting an interaction on the main thread. The user makes an input while blocking tasks run. The input is delayed until those tasks complete, after which the pointerup, mouseup, and click event handlers run, then rendering and painting work is kicked off until the next frame is presented.
The life of an interaction. An input delay occurs until event handlers begin running, which may be caused by factors such as long tasks on the main thread. The interaction's event handlers then run, and a delay occurs before the next frame is presented.
The primary driver of interactivity is often JavaScript, though browsers do provide interactivity through controls not powered by JavaScript, such as checkboxes, radio buttons, and controls powered by CSS.
As far as INP goes, only the following interaction types are observed:
Clicking with a mouse.
Tapping on a device with a touchscreen.
Pressing a key on either a physical or onscreen keyboard.
Interactions happen in the main document or in iframes embedded in the document—for example clicking play on an embedded video. End users will not be aware what is in an iframe or not. Therefore, INP within iframes are needed to measure the user experience for the top level page. Note JavaScript Web APIs will not have access to the iframe contents so may not be able to measure INP within an iframe and this will show as a difference between CrUX and RUM.
Interactions may consist of two parts, each with multiple events. For example, a keystroke consists of the keydown, keypress, and keyup events. Tap interactions contain pointerup and pointerdown events. The event with the longest duration within the interaction is chosen as the interaction's latency.
A depiction of more complex interaction containing two interactions. The first is a mousedown event, which produces a frame before the mouse button is let up, which kicks off more work until yet another frame is presented as the result.
A depiction of an interaction with multiple event handlers. The first part of the interaction receives an input when the user clicks down on a mouse button. However, before they release the mouse button, a frame is presented. When the user releases the mouse button, another series of event handlers must run before the next frame is presented.
INP is calculated when the user leaves the page, resulting in a single value that is representative of the page's overall responsiveness throughout the entire page's lifecycle. A low INP means that a page is reliably responsive to user input.
How is INP different from First Input Delay (FID)? #
Where INP considers all page interactions, First Input Delay (FID) only accounts for the first interaction. It also only measures the first interaction's input delay, not the time it takes to run event handlers, or the delay in presenting the next frame.
Given that FID is also a load responsiveness metric, the rationale behind it is that if the first interaction made with a page in the loading phase has little to no perceptible input delay, the page has made a good first impression.
INP is more than about first impressions. By sampling all interactions, responsiveness can be assessed comprehensively, making INP a more reliable indicator of overall responsiveness than FID.
What if no INP value is reported? #
It's possible that a page can return no INP value. This can happen for a number of reasons:
The page was loaded, but the user never clicked, tapped, or pressed a key on their keyboard.
The page was loaded, but the user interacted with the page using gestures that did not involve clicking, tapping, or using the keyboard. For example, scrolling or hovering over elements does not factor into how INP is calculated.
The page is being accessed by a bot such as a search crawler or headless browser that has not been scripted to interact with the page.
How to measure INP #
INP can be measured both in the field and in the lab through a variety of tools.
In the field #
Ideally, your journey in optimizing INP will start with field data. At its best, field data from Real User Monitoring (RUM) will give you not only a page's INP value, but also contextual data that highlights what specific interaction was responsible for the INP value itself, whether the interaction occurred during or after page load, the type of interaction (click, keypress, or tap), and other valuable information.
If your website qualifies for inclusion in the Chrome User Experience Report (CrUX), you can quickly get field data for INP via CrUX in PageSpeed Insights (and other Core Web Vitals). At a minimum, you can get an origin-level picture of your website's INP, but in some cases, you can also get page-level data as well.
However, while CrUX is useful to tell you that there is a problem at a high level, it often doesn't provide enough detail to help fully understand what the problem is. A RUM solution can help you drill down into more detail as to the pages, users or user interactions which are experiencing slow interactions. Being able to attribute INP to individual interactions avoids guesswork and wasted effort.
In the lab #
Optimally, you'll want to start testing in the lab once you have field data that suggests you have slow interactions. In the absence of field data, however, there are some strategies for reproducing slow interactions in the lab. Such strategies include following common user flows and testing interactions along the way, as well as interacting with the page during load—when the main thread is often busiest—in order to surface slow interactions during that crucial part of the user experience.
How to improve INP #
A collection of guides on optimizing INP is available to guide you through the process of identifying slow interactions in the field and using lab data to drill down and optimize them in a variety of ways.
CHANGELOG #
Occasionally, bugs are discovered in the APIs used to measure metrics, and sometimes in the definitions of the metrics themselves. As a result, changes must sometimes be made, and these changes can show up as improvements or regressions in your internal reports and dashboards.
