1452761 - 2.84% kraken (linux64) regression on push 81ef11104ebb7871c6efe1794a40d4505a80c8dd (Sun Apr 8 2018)

Status: RESOLVED WONTFIX

(Core :: JavaScript Engine: JIT, defect)

Description

[Joel Maher ( :jmaher ) (UTC -8)]

Talos has detected a Firefox performance regression from push:

https://hg.mozilla.org/integration/mozilla-inbound/pushloghtml?changeset=81ef11104ebb7871c6efe1794a40d4505a80c8dd

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

Regressions:

  3%  kraken linux64 opt e10s stylo     898.79 -> 924.30


You can find links to graphs and comparison views for each of the above tests at: https://treeherder.mozilla.org/perf.html#/alerts?id=12588

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 Talos jobs in a pushlog format.

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

For information on reproducing and debugging the regression, either on try or locally, see: https://wiki.mozilla.org/Buildbot/Talos/Running

*** Please let us know your plans within 3 business days, or the offending patch(es) will be backed out! ***

Our wiki page outlines the common responses and expectations: https://wiki.mozilla.org/Buildbot/Talos/RegressionBugsHandling

Comment 1

[Joel Maher ( :jmaher ) (UTC -8)]

:jandem, the changes you made in bug 1448887 seem to have caused a slight regression in kraken on linux/windows.

here are the subtests:
https://treeherder.mozilla.org/perf.html#/comparesubtest?originalProject=mozilla-inbound&originalRevision=ac22879df707357a8169c81d20b737ed81251205&newProject=mozilla-inbound&newRevision=81ef11104ebb7871c6efe1794a40d4505a80c8dd&originalSignature=123a08fb5b7095bf46b82502d49f9b71e16aa3ad&newSignature=123a08fb5b7095bf46b82502d49f9b71e16aa3ad&framework=1

Can you look into this and determine if this is something expected, should be fixed, or should be backed out?

Comment 2

[Ryan VanderMeulen [:RyanVM]]

https://bugzilla.mozilla.org/show_bug.cgi?id=1448887#c10 makes it sound like they were expected.

Comment 3

[Jan de Mooij [:jandem]]

(In reply to Ryan VanderMeulen [:RyanVM] from comment #2)
> https://bugzilla.mozilla.org/show_bug.cgi?id=1448887#c10 makes it sound like
> they were expected.

Yeah it's unfortunate but bug 1448887 fixes a crash (bug 1446907), removes some really complicated (and platform-specific) code, and should improve performance in some other cases (workers) so we decided landing that was the right trade-off.

Comment 4

[Ryan VanderMeulen [:RyanVM]]

Resolving as wontfix as it was an expected change with trade-offs weighed and accepted.