1772501 - 0.7 - 0.47% Base Content JS / Base Content JS + 2 more (Linux, OSX, Windows) regression on Mon May 30 2022

Status: RESOLVED WONTFIX

(GeckoView :: General, defect)

Description

[Acasandrei Beatrice (needinfo me)]

Perfherder has detected a awsy performance regression from push 0a0d086bae3ef7d715c88ef29fbf77082e6afb00. 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)
1%	Base Content JS	macosx1015-64-shippable-qr	fission	1,621,928.00 -> 1,633,282.67
1%	Base Content JS	macosx1015-64-shippable-qr	fission	1,622,065.33 -> 1,633,154.67
0.49%	Base Content JS	windows10-64-2004-shippable-qr	fission	1,600,869.33 -> 1,608,664.00
0.47%	Base Content JS	linux1804-64-shippable-qr	fission	1,599,022.00 -> 1,606,556.00

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 offending patch(es) will 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.

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 1738012

Comment 2

[Frank Doty [:fdoty]]

per the perf results, is this still an issue?

Comment 3

[Chris Peterson [:cpeterson]]

Attachment: Perfherder_screenshot.png

(In reply to Frank Doty [:fdoty] from comment #2)

per the perf results, is this still an issue?

I think we can WONTFIX this bug and accept this small regression in Base Content JS. While bug 1738012 caused this bug to be filed for this 0.5% - 1% regression, it also improved page load perf (FCP, SpeedIndex, and FirstVisualChange for dailymail.co.uk) by 4-5% (https://bugzilla.mozilla.org/show_bug.cgi?id=1738012#c16). I think that's a reasonable tradeoff.

Plus, the current Base Content JS is still better than it was before May 23 (when Remote Settings bug 1702759 landed a big improvement) and Base Content JS metric has improved a couple times since this May 30 regression:

1. June 8: TypedArray bug 1763606 improved this metric about 0.30%: https://treeherder.mozilla.org/perfherder/alerts?id=34391
2. June 15: Some other change (probably lazy getter bug 1773829): https://hg.mozilla.org/integration/autoland/pushloghtml?fromchange=28cf8d7e972301be7da0472bc7448deb06555c17&tochange=b93803e048621ff2fc8c37c50929bc7d6175a48d

Perfherder graph:

https://treeherder.mozilla.org/perfherder/graphs?highlightAlerts=1&highlightChangelogData=1&highlightCommonAlerts=0&series=autoland,3807462,1,4&timerange=7776000&zoom=1650982384258,1655425661236,1614591.1111111117,1641680.88888889