1391681 - 2.88 - 3.1% tp5o_scroll (linux64) regression on push 4d2ae762f65a12dd2010e67314794fc195c29d12 (Thu Aug 17 2017)

Status: RESOLVED WORKSFORME

(Core :: XPCOM, defect)

Description

[Robert Wood [:rwood]]

Talos has detected a Firefox performance regression from push:

https://hg.mozilla.org/integration/mozilla-inbound/pushloghtml?changeset=4d2ae762f65a12dd2010e67314794fc195c29d12

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

Regressions:

  3%  tp5o_scroll summary linux64 pgo e10s     4.28 -> 4.41
  3%  tp5o_scroll summary linux64 opt e10s     4.31 -> 4.43


You can find links to graphs and comparison views for each of the above tests at: https://treeherder.mozilla.org/perf.html#/alerts?id=8852

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

[Robert Wood [:rwood]]

Hi :billm, could you please have a look at this performance regression? Thanks!

Comment 2

[Bill McCloskey [inactive unless it's an emergency] (:billm)]

The actual regression seems to have been from here:
https://hg.mozilla.org/integration/mozilla-inbound/rev/36ef70762b74 (bug 1382922)

Interestingly, the regression disappeared when I checked in this changeset:
https://hg.mozilla.org/integration/mozilla-inbound/rev/13ad384d29fb (bug 1397956)

Both of these are related to the event loop, but there isn't any other connection between them. I suspect this was just caused by some event loop jitter that somehow affects this test on Linux. Since it's Linux-only, I'm not inclined to investigate any further.