1902251 - 292.73 - 6.04% bing-search LastVisualChange / bing-search PerceptualSpeedIndex + 14 more (Linux, Windows) regression on Wed June 12 2024

Status: RESOLVED WONTFIX

(Testing :: Raptor, defect, P5)

Description

[Florin Bilt]

Perfherder has detected a browsertime performance change from push 3a39c1639f88e7e148ef325f22d7817c4cfdbd25.

Regressions:

Ratio	Test	Platform	Options	Absolute values (old vs new)	Performance Profiles
293%	bing-search LastVisualChange	windows10-64-shippable-qr	bytecode-cached fission warm webrender	767.18 -> 3,012.96	Before/After
292%	bing-search LastVisualChange	windows10-64-shippable-qr	fission warm webrender	847.30 -> 3,322.38	Before/After
261%	bing-search LastVisualChange	linux1804-64-shippable-qr	fission warm webrender	937.65 -> 3,384.32	Before/After
245%	bing-search LastVisualChange	linux1804-64-shippable-qr	bytecode-cached fission warm webrender	900.85 -> 3,109.42	Before/After
103%	bing-search LastVisualChange	windows10-64-shippable-qr	bytecode-cached cold fission webrender	2,044.68 -> 4,149.72	Before/After
88%	bing-search LastVisualChange	windows10-64-shippable-qr	cold fission webrender	2,151.18 -> 4,048.96	Before/After
63%	bing-search loadtime	windows10-64-shippable-qr	bytecode-cached cold fission webrender	175.53 -> 286.17	Before/After
60%	bing-search loadtime	windows10-64-shippable-qr	cold fission webrender	179.62 -> 286.82	Before/After
52%	bing-search largestContentfulPaint	windows10-64-shippable-qr	bytecode-cached cold fission webrender	190.95 -> 289.33	Before/After
45%	bing-search largestContentfulPaint	windows10-64-shippable-qr	cold fission webrender	198.87 -> 289.17	Before/After
...	...	...	...	...	...
39%	bing-search LastVisualChange	linux1804-64-shippable-qr	cold fission webrender	3,180.25 -> 4,427.16	Before/After
36%	bing-search FirstVisualChange	windows10-64-shippable-qr	fission warm webrender	79.05 -> 107.51	Before/After
35%	bing-search FirstVisualChange	windows10-64-shippable-qr	bytecode-cached fission warm webrender	82.94 -> 111.98	Before/After
6%	bing-search fcp	windows10-64-shippable-qr	bytecode-cached cold fission webrender	155.83 -> 165.70	Before/After
6%	bing-search PerceptualSpeedIndex	windows10-64-shippable-qr	fission warm webrender	288.50 -> 305.92	Before/After

Improvements:

Ratio	Test	Platform	Options	Absolute values (old vs new)	Performance Profiles
77%	bing-search FirstVisualChange	linux1804-64-shippable-qr	cold fission webrender	958.28 -> 225.01	Before/After
76%	bing-search FirstVisualChange	linux1804-64-shippable-qr	bytecode-cached cold fission webrender	958.22 -> 226.96	Before/After
71%	bing-search ContentfulSpeedIndex	linux1804-64-shippable-qr	cold fission webrender	1,682.52 -> 494.92	Before/After
69%	bing-search ContentfulSpeedIndex	linux1804-64-shippable-qr	bytecode-cached cold fission webrender	1,687.06 -> 523.17	Before/After
69%	bing-search FirstVisualChange	windows10-64-shippable-qr	cold fission webrender	604.71 -> 188.73	Before/After
...	...	...	...	...	...
12%	bing-search loadtime	windows10-64-shippable-qr	fission warm webrender	112.89 -> 99.15	Before/After

As author of one of the patches included in that push, we need your help to address this regression.
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 705

For more information on performance sheriffing please see our FAQ.

Comment 1

[BugBot [:suhaib / :marco]]

Set release status flags based on info from the regressing bug 1901047

Comment 2

[Kash Shampur [:kshampur] ⌚EST]

I think these changes should be accepted as the previous recording was incorrect

Comment 3

[Liz Henry (:lizzard)]

afinder does Comment 2 mean we should close this issue? Or do you prefer to leave it open at this low severity and priority?
If you agree with Comment 2 then maybe closing the issue as wontfix would be best.