1904545 - 3% ares6 (Windows 10) regression on Fri June 14 2024

Status: RESOLVED WONTFIX

(Core :: JavaScript Engine: JIT, defect)

Description

[Florin Bilt]

Perfherder has detected a browsertime performance regression from push 10768998f471b5c3fecddeccf0506045102d1b3c. As author of one of the patches included in that push, we need your help to address this regression.

Regressions:

Ratio	Test	Platform	Options	Absolute values (old vs new)	Performance Profiles
3%	ares6	windows10-64-shippable-qr	fission webrender	26.47 -> 27.14	Before/After

Improvements:

Ratio	Test	Platform	Options	Absolute values (old vs new)	Performance Profiles
40%	speedometer3 NewsSite-Nuxt/NavigateToPolitics/Async	macosx1400-64-shippable-qr	fission webrender	18.02 -> 10.81	Before/After
32%	speedometer3 NewsSite-Nuxt/NavigateToPolitics/Async	windows10-64-shippable-qr	fission webrender	49.06 -> 33.44	Before/After
32%	speedometer3 NewsSite-Nuxt/NavigateToPolitics/Async	windows10-64-nightlyasrelease-qr	fission webrender	48.45 -> 33.18	Before/After
31%	speedometer3 NewsSite-Nuxt/NavigateToPolitics/Async	macosx1015-64-shippable-qr	fission webrender	48.21 -> 33.17	Before/After
31%	speedometer3 NewsSite-Nuxt/NavigateToPolitics/Async	linux1804-64-nightlyasrelease-qr	fission webrender	60.02 -> 41.67	Before/After
...	...	...	...	...	...
5%	welcome loadtime	windows10-64-shippable-qr	cold fission webrender	54.77 -> 52.29	Before/After

Details of the alert can be found in the alert summary, including links to graphs and comparisons for each of the affected tests. Please follow our guide to handling regression bugs and let us know your plans within 3 business days, or the patch(es) may be backed out in accordance with our regression policy.

If you need the profiling jobs you can trigger them yourself from treeherder job view or ask a sheriff to do that for you.

You can run these tests on try with ./mach try perf --alert 853

For more information on performance sheriffing please see our FAQ.

Comment 1

[BugBot [:suhaib / :marco/ :calixte]]

Set release status flags based on info from the regressing bug 1900466

Comment 2

[Jon Coppeard (:jonco)]

(In reply to Florin Bilt from comment #0)
The title says regression, but this subtests is an improvement as shown in the description.

We'll take ares6 regression (which is due to GC timing and is not actually a regression as described in bug 1900466 comment 4).

Comment 3

[Jeff Muizelaar [:jrmuizel]]

sparky, it seems like the title is wrong can we fix that?

Comment 4

[Greg Mierzwinski [:sparky]]

I've filed a bug for this issue, and manually updated the title of this bug to mention the test that regressed.