We’re only a few weeks away from Firefox 67 merging from the Nightly channel to Beta, and since my last update, a number of things have landed.
It’s the end of a long week for me, so I apologize for the brevity here. Let’s check it out!
Document Splitting Foundations for WebRender (In-Progress by Doug Thayer)
dthayer is still trucking along here – he’s ironed out a number of glitches, and kats is giving feedback on some APZ-related changes. dthayer is also working on a WebRender API endpoint for generating frames for multiple documents in a single transaction, which should help reduce the window of opportunity for nasty synchronization bugs.
Warm-up Service (In-Progress by Doug Thayer)
dthayer is pressing ahead with this experiment to warm up a number of critical files for Firefox shortly after the OS boots. He is working on a prototype that can be controlled via a pref that we’ll be able to test on users in a lab-setting (and perhaps in the wild as a SHIELD experiment).
Startup Cache Telemetry (In-Progress by Doug Thayer)
dthayer landed this Telemetry early in the week, and data has started to trickle in. After a few more days, it should be easier for us to make inferences on how the startup caches are operating out in the wild for our Nightly users.
Smoother Tab Animations (In-Progress by Felipe Gomes)
UX, Product and Engineering are currently hashing out the remainder of the work here. Felipe is also aiming to have the non-responsive tab strip bug fixed soon.
Lazier Hidden Window (Completed by Felipe Gomes)
After a few rounds of landings and backouts, this appears to have stuck! The hidden window is now created after the main window has finished painting, and this has resulted in a nice ts_paint (startup paint) win on our Talos benchmark!
There’s still potential for more improvements on the hidden window, but that’s been split out to a separate project / bug.
Browser Adjustment Project (In-Progress by Gijs Kruitbosch)
This project appears to be reaching its conclusion, but with rather unsatisfying results. Denis Palmeiro from Vicky Chin’s team has done a bunch of testing of both the original set of patches that Gijs landed to lower the global frame rate (painting and compositing) from 60fps to 30fps for low-end machines, as well as the new patches that decrease the frequency of main-thread painting (but not compositing) to 30fps. Unfortunately, this has not yielded the page load wins that we wanted1. We’re still waiting to see if there’s a least a power-usage win here worth pursuing, but we’re almost ready the pull the plug on this one.
Better about:newtab Preloading (In-Progress by Gijs Kruitbosch)
Gijs has a set of patches that should make this possible, which will mean (in theory) that we’ll present a ready-to-roll about:newtab when users request one more often than not.
Unfortunately, there’s a small snag with a test failure in automation, but Gijs is on the case.
Experiments with the Process Priority Manager (In-Progress by Mike Conley)
The Process Priority Manager has been enabled in Nightly for a number of weeks now, and no new bugs have been filed against it. I filed a bug earlier this week to run a pref-flip experiment on Beta after the Process Priority Manager patches are uplifted later this month. Our hope is that this has a neutral or positive impact on both page load time and user retention!
Make the PageStyleChild load lazily (Completed by Mike Conley)
There’s an infrequently used feature in Firefox that allows users to switch between different CSS stylesheets that a page might offer. I’ve made the component that scans the document for alternative stylesheets much lazier, and also made it skip non web-pages, which means (at the very least) less code running when loading about:home and about:newtab
This was unexpected – we ran an experiment late in 2018 where we noticed that lowering the frame rate manually via the layout.frame_rate pref had a positive impact on page load time… unfortunately, this effect is no longer being observed. This might be due to other refresh driver work that has occurred in the meantime. ↩