1556706 - 0.49 - 0.79% Base Content JS (linux64-shippable, linux64-shippable-qr, macosx1010-64-shippable, windows10-64-shippable, windows10-64-shippable-qr, windows7-32-shippable) regression on push d5c768b50d69599582f6bff5376fa5acc300fa3e (Fri May 31 2019)

Status: RESOLVED FIXED

(Core :: JavaScript: GC, defect, P2)

Description

[Ionuț Goldan [:igoldan]]

We have detected an awsy regression from push:

https://hg.mozilla.org/integration/autoland/pushloghtml?fromchange=98e75ac2cf4fc6a43dea8bd7a77c0625a7456ccf&tochange=d5c768b50d69599582f6bff5376fa5acc300fa3e

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

Regressions:

1% Base Content JS linux64-shippable opt 3,978,016.00 -> 4,009,529.33
1% Base Content JS linux64-shippable-qr opt 3,977,997.33 -> 4,009,597.33
1% Base Content JS macosx1010-64-shippable opt 3,979,161.33 -> 4,010,378.67
1% Base Content JS windows10-64-shippable-qr opt 4,034,853.33 -> 4,066,186.67
1% Base Content JS windows10-64-shippable opt 4,034,982.67 -> 4,066,340.67
0.5% Base Content JS windows7-32-shippable opt 3,138,018.67 -> 3,153,524.00

You can find links to graphs and comparison views for each of the above tests at: https://treeherder.mozilla.org/perf.html#/alerts?id=21193

On the page above you can see an alert for each affected platform as well as a link to a graph showing the history of scores for this test. There is also a link to a treeherder page showing the jobs in a pushlog format.

To learn more about the regressing test(s), please see: https://wiki.mozilla.org/AWSY/Tests

Comment 1

[Jon Coppeard (:jonco)]

This is probably due to this change:

617df479fac177b567090102c9804734e258e577 Steve Fink — Bug 1167452 - Split mark stack into black and gray. r=jonco

Bug 1553332 has already been filed to address this.

Comment 2

[Ryan VanderMeulen [:RyanVM]]

Bug 1167452 was backed out. Does this look better now, Ionut?

Comment 3

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

Changing the priority to p2 as the bug is tracked by a release manager for the current nightly.
See What Do You Triage for more information

Comment 4

[Ryan VanderMeulen [:RyanVM]]

Florin, maybe you can comment while Ionut is on PTO?

Comment 5

[Steve Fink [:sfink] [:s:]]

(In reply to Ryan VanderMeulen [:RyanVM] from comment #2)

Bug 1167452 was backed out. Does this look better now, Ionut?

Did I only reply to this on another bug? The relevant part here was not backed out. Bug 1553332 is still the intended fix.

Comment 6

[Florin Strugariu [:Bebe]]

as of :sfink comment and also checking the graphs this regression is still there and we are waiting for bug Bug 1553332

Comment 7

[Liz Henry (:lizzard) (relman/hg->git project)]

Jon, since bug 1553332 is P3 and unassigned, does that mean you're accepting this regression for 69 and possibly also for 70?

Comment 8

[Jon Coppeard (:jonco)]

(In reply to Liz Henry (:lizzard) (use needinfo) from comment #7)
I know Steve is actively working on this. I'll update the assignment.

Comment 9

[Ryan VanderMeulen [:RyanVM]]

I don't think we're going to get a fix for 69 at this point. Leaving it on the radar for 70, though.

Comment 10

[Steve Fink [:sfink] [:s:]]

This is fixed with a backout:

changeset: https://hg.mozilla.org/mozilla-central/rev/4ad75b878827
user: Steve Fink
date: Wed Jul 24 14:29:22 2019 -0700
summary: Backed out changeset 617df479fac1 (bug 1167452)

I filed bug 1580888 for re-landing this sometime, though my preliminary results are still showing the exact same regression (0.8%)