Firefox Front-End Performance Update #13

It’s been just a little over two weeks since my last update, so let’s see where we are!

A number of our projects are centered around trying to improve start-up time. Start-up can mean a lot of things, so we’re focused specifically on cold start-up on the Windows 10 2018 reference device when the machine is at rest.

If you want to improve something, the first thing to do is measure it. There are lots of ways to measure start-up time, and one of the ways we’ve been starting to measure is by doing frame recording analysis. This is when we capture display output from a testing device, and then analyze the videos.

This animated GIF shows eight videos. The four on the left are Firefox Nightly, and the four on the right are Google Chrome (71.0.3578.98). The videos are aligned so that both browsers are started at the same time.

The four on the left are Firefox Nightly, and the four on the right are Google Chrome (71.0.3578.98)

Some immediate observations:

  • Firefox Nightly is consistently faster to reach first paint (that’s the big white window)
  • Firefox Nightly is consistently faster to draw its toolbar and browser UI
  • Google Chrome is faster at painting its initial content

This last bullet is where the team will be focusing its efforts – we want to have the initial content painted and settled much sooner than we currently do.

Document Splitting Foundations (In-Progress by Doug Thayer)

After some pretty significant refactorings to work better with APZ, Doug posted a new stack of patches late last week which will sit upon the already large stack of patches that have already landed. There are still a number of reviews pending on the main stack, but this work appears to be getting pretty close to conclusion, as the patches are in the final review and polish stage.

After this, once retained display lists are enabled in the parent process, and an API is introduced to WebRender to generate frames for multiple documents in a single transaction, we can start thinking about enabling document splitting by default.

Warm-up Service (In-Progress by Doug Thayer)

A Heartbeat survey went out a week or so back to get some user feedback about a service that would speed up the launching of Firefox at the cost of adding some boot time to Windows. The responses we’ve gotten back have been quite varied, but can be generally bucketed into three (unsurprising) groups:

  • Users who say they do not want to make this trade
  • Users who say they would love to make this trade
  • Users who don’t care at all about this trade

Each group is sufficiently large to warrant further exploration. Our next step is to build a version of this service that we can turn on and off with a pref and test either in a lab and/or out in the wild with a SHIELD study.

Startup Cache Telemetry (In-Progress by Doug Thayer)

We do a number of things to try to improve real and perceived start-up time. One of those things is to cache things that we calculate at runtime during start-up to the disk, so that for subsequent start-ups, we don’t have to do those calculations again.

There are a number of mechanisms that use this technique, and Doug is currently adding some Telemetry to see how they’re behaving in the wild. We want to measure cache hits and misses, so that we know how healthy our cache system is out in the wild. If we get signals back that our start-up caches are missing more than we expect, this will highlight an important area for us to focus on.

Smoother Tab Animations (In-Progress by Felipe Gomes)

UX has gotten back to us with valuable feedback on the current implementation, and Felipe is going through it and trying to find the simplest way forward to address their concerns.

Having been available (though disabled by default) on Nightly, we’ve discovered one bug where the tab strip can become unresponsive to mouse events. Felipe is currently working on this.

Lazy Hidden Window (In-Progress by Felipe Gomes)

Under the hood, Firefox’s front-end has a notion of a “hidden window”. This mysterious hidden window was originally introduced long long ago1 for MacOS, where it’s possible to close all windows yet keep the application running.

Since then, it’s been (ab)used for Linux and Windows as well, as a safe-ish place to do various operations that require a window (since that window will always be around, and not go away until shutdown).

That window opens pretty early during start-up, and Felipe found an old patch that was written, and then abandoned to make its construction lazier. Felipe thinks we can still make this idea work, and has noted that in our internal benchmarks, this shaves off a few percentage points on our start-up tests

Activity Stream seems to depend on the hidden window early enough that we think we’re going to have to find an alternative there, but once we do, we should get a bit of a win on start-up time.

Browser Adjustment Project (In-Progress by Gijs Kruitbosch)

Gijs updated the patch so that the adjustment causes the main thread to skip every other VSync rather than swithing us to 30fps globally2.

We passed the patch off to Denis Palmeiro, who has a sophisticated set-up that allows him to measure a pageload benchmark using frame recording. Unfortunately, the results we got back suggested that the new approach regressed visual page load time significantly in the majority of cases.

We’re in the midst of using the same testing rig to test the original global 30fps patch to get a sense of the magnitude of any improvements we could get here. Denis is also graciously measuring the newer patch to see if it has any positive benefits towards power consumption.

Better about:newtab Preloading (In-Progress by Gijs Kruitbosch)

By default, users see about:newtab / a.k.a Activity Stream when they open new tabs. One of the perceived performance optimizations we’ve done for many years now is to preload the next about:newtab in the background so that the next time that the user opens a tab, the about:newtab is all ready to roll.

This is a perceived performance optimization where we’re moving work around rather than doing less work.

Right now, we preload a tab almost immediately after the first tab is opened in a window. That means that the first opened tab is never preloaded, but the second one is. This is for historical reasons, but we think we can do better.

Gijs is working on making it so that we choose a better time to preload the tab – namely, when we’ve found an idle pocket of time where the user doesn’t appear to be doing anything. This should also mean that the first new tab that gets opened might also be preloaded, assuming that enough idle time was made available to trigger the preload. And if there wasn’t any idle time, that’s also good news – we never got in the users way by preloading when it’s clear they were busy doing something else

Experiments with the Process Priority Manager (In-Progress by Mike Conley)

The Process Priority Manager has been enabled on Nightly for a few weeks now. Except for a (now fixed) issue where audio playing in background tabs would drop samples periodically, it’s been all quiet for regression reports.

The next step is to file a bug to run an experiment on Beta to see how this work impacts page load time.

Enable the separate Activity Stream content process by default (Stalled by Mike Conley)

This work is temporarily stalled while I work on other things, so there’s not too much to report here.

Grab bag of notable performance work

  1. Check out that commit date – 2003! 

  2. The idea here being that we can then continue to composite scrolling and video at 60fps, but main thread paints will only be updated at 30fps