Ionuț Goldan [:igoldan] Reporter
	Description • 6 years ago

Talos has detected a Firefox performance regression from push:

https://hg.mozilla.org/integration/mozilla-inbound/pushloghtml?changeset=40ed437da7ae4407ece2ad47cd8fe3c7943f9eb9

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

Regressions:

  6%  tsvgr_opacity linux64 opt e10s stylo     183.43 -> 193.73
  5%  tsvgr_opacity linux64 opt e10s stylo     185.18 -> 193.73
  1%  tsvgr_opacity linux64 pgo e10s stylo     175.63 -> 177.64
  1%  tsvgr_opacity linux64-qr opt e10s stylo  109.37 -> 110.13


You can find links to graphs and comparison views for each of the above tests at: https://treeherder.mozilla.org/perf.html#/alerts?id=14154

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

	Ionuț Goldan [:igoldan] Reporter
	Comment 1 • 6 years ago

(In reply to Ionuț Goldan [:igoldan], Performance Sheriffing from comment #0)
> Regressions:
> 
>   6%  tsvgr_opacity linux64 opt e10s stylo     183.43 -> 193.73
>   5%  tsvgr_opacity linux64 opt e10s stylo     185.18 -> 193.73

There's only one regression here. The automatic message duplicated the same alert.

	Ionuț Goldan [:igoldan] Reporter
	Comment 2 • 6 years ago

Here are the Gecko profiles for tsvgr_opacity, on Linux 64 opt:

before: https://perf-html.io/from-url/https%3A%2F%2Fqueue.taskcluster.net%2Fv1%2Ftask%2FcbpRpNG7Q260zhWf3Dk2UQ%2Fruns%2F0%2Fartifacts%2Fpublic%2Ftest_info%2Fprofile_tsvgr_opacity.zip

after: https://perf-html.io/from-url/https%3A%2F%2Fqueue.taskcluster.net%2Fv1%2Ftask%2FUTkSQPhAQQGVgsSne22dEg%2Fruns%2F0%2Fartifacts%2Fpublic%2Ftest_info%2Fprofile_tsvgr_opacity.zip

	Dave Townsend [:mossop] Assignee
	Comment 3 • 6 years ago

Favicons will cause a small bit of additional network traffic and work in the
content process for any loaded page that doesn't specify a favicon. This turns
off attempts to guess a favicon when one isn't specified in performance tests.

	Phabricator Automation
	Comment 4 • 6 years ago

Comment on attachment 8989696 [details]
Bug 1473004: Don't attempt to guess a favicon in performance tests.

Joel Maher ( :jmaher ) (UTC-4) has approved the revision.

https://phabricator.services.mozilla.com/D1936

	Pulsebot
	Comment 5 • 6 years ago

Pushed by dtownsend@mozilla.com:
https://hg.mozilla.org/integration/autoland/rev/6aee046a67d4
Don't attempt to guess a favicon in performance tests. r=jmaher

	Dave Townsend [:mossop] Assignee
	Comment 6 • 6 years ago

I was seeing 3-4% improvements on the try push for this so I'm hoping that this will take care of the regression.

	Raul Gurzau (:RaulG)
	Comment 7 • 6 years ago
bugherder

https://hg.mozilla.org/mozilla-central/rev/6aee046a67d4

	Cristina Coroiu [:ccoroiu]
	Comment 8 • 6 years ago
bugherder

https://hg.mozilla.org/mozilla-central/rev/6aee046a67d4

	Ionuț Goldan [:igoldan] Reporter
	Comment 9 • 6 years ago

(In reply to Dave Townsend [:mossop] from comment #6)
> I was seeing 3-4% improvements on the try push for this so I'm hoping that
> this will take care of the regression.

Yep, it did take care. Thanks!