1481726 - 40.64 - 49.25% stylebench (linux64, linux64-qr, osx-10-10, windows10-64, windows10-64-qr, windows7-32) regression on push fdfa18c465db01a735176c83a6c950c6b368943e (Tue Aug 7 2018)

Status: RESOLVED WONTFIX

(Core :: CSS Parsing and Computation, defect)

Description

[Ionuț Goldan [:igoldan]]

Talos has detected a Firefox performance regression from push:

https://hg.mozilla.org/integration/autoland/pushloghtml?changeset=fdfa18c465db01a735176c83a6c950c6b368943e

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

Regressions:

 49%  stylebench osx-10-10 opt e10s stylo     19.13 -> 9.71
 44%  stylebench windows10-64 opt e10s stylo  41.60 -> 23.44
 43%  stylebench windows7-32 opt e10s stylo   41.54 -> 23.69
 42%  stylebench windows10-64-qr opt e10s stylo42.70 -> 24.86
 41%  stylebench linux64-qr opt e10s stylo    39.90 -> 23.35
 41%  stylebench linux64 opt e10s stylo       38.06 -> 22.59


You can find links to graphs and comparison views for each of the above tests at: https://treeherder.mozilla.org/perf.html#/alerts?id=14795

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

[Ionuț Goldan [:igoldan]]

We usually just accepted regressions caused by harness updates, unless there's something fishy with the new baseline.
:emilio are the results expected?

Comment 2

[Emilio Cobos Álvarez (:emilio)]

Yeah, this looks fine, the test is doing way more work now, I'm slightly surprised the regression isn't higher.

Comment 3

[Ionuț Goldan [:igoldan]]

We usually resolve baseline updates as WONTFIXes. Changed this here for consistency.