1595480 - 10.04 - 44.58% tp5n main_startup_fileio (windows10-64-shippable, windows10-64-shippable-qr) regression on push a09c768d2dc0649a82c15788e5a33052616d7f16 (Tue October 29 2019)

Status: RESOLVED WONTFIX

(Core :: mozglue, defect)

Description

[Alexandru Ionescu (needinfo me) [:alexandrui]]

Talos has detected a Firefox performance regression from push:

https://hg.mozilla.org/integration/autoland/pushloghtml?changeset=a09c768d2dc0649a82c15788e5a33052616d7f16

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

Regressions:

45% tp5n main_startup_fileio windows10-64-shippable-qr opt e10s stylo 488,043.17 -> 705,598.42
26% tp5n main_startup_fileio windows10-64-shippable-qr opt e10s stylo 592,017.67 -> 746,812.33
10% tp5n main_startup_fileio windows10-64-shippable opt e10s stylo 585,617.67 -> 644,412.33

Improvements:

11% tp5n nonmain_normal_fileio windows10-64-shippable opt e10s stylo 479,405,532.42 -> 426,655,106.50
11% tp5n nonmain_normal_fileio windows10-64-shippable-qr opt e10s stylo 479,118,053.75 -> 426,867,460.17

You can find links to graphs and comparison views for each of the above tests at: https://treeherder.mozilla.org/perf.html#/alerts?id=23787

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/TestEngineering/Performance/Talos

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

Comment 1

[(No longer employed by Mozilla) Aaron Klotz]

We're not backing this out. The patch in question does not explicitly touch anything on the main thread. If the test is showing increased main thread I/O, then it's because of something inside the OS that we do not control.

It might be undoing some of what was seen in https://bugzilla.mozilla.org/show_bug.cgi?id=1542830#c44.