Talos has detected a Firefox performance regression from push 69364e8ccec54a3a2ea81467d186dec19c8ca161. As author of one of the patches included in that push, we need your help to address this regression. Regressions: 9% tp5n nonmain_normal_netio windows7-32 opt 171375707.67 -> 186356064.25 You can find links to graphs and comparison views for each of the above tests at: https://treeherder.mozilla.org/perf.html#/alerts?id=6175 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

Could you please confirm this is related to bug 1358586?

The blamed cset ( https://hg.mozilla.org/integration/autoland/rev/69364e8ccec5 ) was simply a tweak to a test manifest file which is not part of the build & which is not used at all during Talos. So it's impossible for that changeset to actually be related to the reported perf regression. Assuming there's a real regression here, it must've really been caused by a nearby changeset before/after this one.

[Sorry, typo -- s/flag/flat/. Reposting.] Looking at the graph[1], the overall trend seems flat, and no "regression" seems to have stuck. And the reported value seems to be in the range of values that had previously been experienced by the test. I wonder if this was just a spurious report, from this test happening to arbitrarily trigger several higher-than-normal reports in a row, just by chance? (The "blamed" data point for 69364e8ccec5 is one of the yellowy circles in the pile of datapoints just before the "Apr 25 00:00" vertical-line, in the presentation of the graph that I'm seeing.) [1] https://treeherder.mozilla.org/perf.html#/graphs?timerange=604800&series=%5Bmozilla-inbound,294241d76b7e991ebd8cf32213ee616ff1978215,1,1%5D&series=%5Bautoland,294241d76b7e991ebd8cf32213ee616ff1978215,1,1%5D

I agree, this looks like an alert but happens to be noise, apology for any randomizations.

Thanks, :dholbert, for elucidating this.

Moving from Core::Untriaged to Core::General https://bugzilla.mozilla.org/show_bug.cgi?id=1407598