PeerPad has a really bad time with WebRender

RESOLVED FIXED

Status

()

P4
normal
RESOLVED FIXED
a year ago
23 days ago

People

(Reporter: jrmuizel, Assigned: ethlin)

Tracking

(Blocks: 3 bugs)

unspecified
Points:
---
Dependency tree / graph

Firefox Tracking Flags

(firefox57 unaffected, firefox58 unaffected)

Details

(Whiteboard: [wr-reserve])

Whiteboard: [wr-mvp] [triage]
(Reporter)

Comment 1

a year ago
This is probably blur related. We should retry after https://github.com/servo/webrender/pull/1961 lands.
Blocks: 1386669
status-firefox57: --- → unaffected
status-firefox58: --- → unaffected
Priority: -- → P2
Whiteboard: [wr-mvp] [triage] → [wr-mvp]
I believe #1961 landed and this page is still pretty bad (and renders incorrectly).
This is indeed blur related. The two <a> elements for "IPFS" and for "CRDTs" each have an ::after pseudo element which has box-shadow: -350px -20px 1000px 22px #23e0f7 set on it. That's a 1000px radius blur.
(Assignee)

Comment 4

a year ago
I take a look.
Assignee: nobody → ethlin
Status: NEW → ASSIGNED
Priority: P2 → P1
(Assignee)

Comment 5

a year ago
Looks like the performance bottleneck is not box-shadow anymore. I sent a PR 2096[1] to fix the rendering problem. I will keep investigating the next performance bottleneck in this page.

[1] https://github.com/servo/webrender/pull/2096
(Assignee)

Comment 6

a year ago
I should say the blur is not the bottleneck. According to my local test, we spend 25ms on GPU, and clip takes more than 10ms. I think it's because the clip shape is ellipse and webrender doesn't handle ellipse clip efficiently. I'll have a PR to fix it.
(Assignee)

Comment 8

a year ago
PR 2158[1] also helps. Right now the GPU time is about 11ms on my MBP.

[1] https://github.com/servo/webrender/pull/2158
(Assignee)

Comment 9

a year ago
The FPS of scrolling on my device is about 50~60fps now. Jeff, do you think we can close this bug?
Flags: needinfo?(jmuizelaar)
(Reporter)

Comment 10

a year ago
I only get around 30fps on that page and see 30+ ms composites: https://perfht.ml/2nE69al
Flags: needinfo?(jmuizelaar)
Whiteboard: [wr-mvp] → [wr-reserve]
(Reporter)

Comment 11

6 months ago
This is better but still not great.
(Reporter)

Updated

6 months ago
Blocks: 1477376
Priority: P3 → P4
Jeff -- What issues remain?  How bad are they?  How difficult are they to hit?
Flags: needinfo?(jmuizelaar)
(Reporter)

Comment 13

4 months ago
I tried this out on some older nvidia desktop hardware and still got 30ms composites. So we could definitely do better.
Depends on: 1494775
Flags: needinfo?(jmuizelaar)
(Reporter)

Comment 14

23 days ago

This seems to work reasonably well now.

Status: ASSIGNED → RESOLVED
Last Resolved: 23 days ago
Resolution: --- → FIXED
You need to log in before you can comment on or make changes to this bug.