Open Bug 1667250 Opened 4 years ago Updated 3 years ago

Fenix loads adobe.com 4 seconds slower than Chrome

Categories

(Core :: Performance, defect, P2)

defect

Tracking

()

Performance Impact low
Tracking Status
firefox83 --- affected

People

(Reporter: yoasif, Unassigned)

Details

(Keywords: perf:pageload)

Basic information

Saw a video shared on social media with a test between Brave and Fenix: https://vimeo.com/461247541

Recreated the test with Chrome vs. Fenix on a Moto G XT1031 with Warp enabled.

adobe.com

chrome - 6 seconds
firefox - 10 seconds


More information

Profile URL: https://share.firefox.dev/364n6zh

Basic systems configuration:

OS version: Android 5.1

GPU model: Adreno 305

Number of cores: Quad-core 1.2 GHz Cortex-A7

Amount of memory (RAM): 1GB

Thanks so much for your help.

Status: NEW → RESOLVED
Closed: 4 years ago
Resolution: --- → WORKSFORME
Status: RESOLVED → REOPENED
Resolution: WORKSFORME → ---
Summary: Fenix loads adobe.com 5 seconds slower than Chrome → Fenix loads adobe.com 9 seconds slower than Chrome
Status: REOPENED → NEW
Summary: Fenix loads adobe.com 9 seconds slower than Chrome → Fenix loads adobe.com 4 seconds slower than Chrome

Is this reliable for you Asif? I can't seem to reproduce on my end.

Flags: needinfo?(yoasif)

The worst case scenario for Fenix here seems to be at the initial page load. Refreshes are more similar vs. Chrome - within a second or so. On a faster device (Optimus G on wireless N) the difference on initial page load is closer to a second or two, and refreshes are too similar to note.

Flags: needinfo?(yoasif)
Severity: -- → S3
Priority: -- → P2
Whiteboard: [qf:p1:pageload]

I can't seem to reproduce this on my Moto G5 either. Just now, for the initial page load, I got 7 seconds in Chrome and 6 seconds in Fenix.

Marc said he has a very low end phone he can test this on.

Flags: needinfo?(mleclair)

There is a lot of time spent doing delazification during the JS execution and perhaps this is a bigger bottleneck on much older devices. The work in bug 1662110 may help improve this situation by moving some delazification off thread.

Whiteboard: [qf:p1:pageload] → [qf:p3:pageload]
Flags: needinfo?(mleclair)
Performance Impact: --- → P3
Keywords: perf:pageload
Whiteboard: [qf:p3:pageload]
You need to log in before you can comment on or make changes to this bug.