1623828 - 2.78% - 13.52% tp5n nonmain_normal_fileio (windows10-64-shippable) regression on push 1692426a9549efd97f3241b8fc314eac0786a750 (Mon March 9 2020)

Status: RESOLVED WONTFIX

(Firefox :: New Tab Page, defect)

Description

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

Talos has detected a Firefox performance regression from push:

https://hg.mozilla.org/integration/autoland/pushloghtml?changeset=718652138136a4e4903197925698b752a5c793b6

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

Regressions:

Compare view

You can find links to graphs and comparison views for each of the above tests at: https://treeherder.mozilla.org/perf.html#/alerts?id=25297

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

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

This took pretty much to be discovered because there was a high interval of revisions with busted builds so I had to backout and bisect a bunch of them.

Comment 2

[Mike Conley (:mconley) (:⚙️)]

So I've looked into this.

This is accounted for by the fact that the privileged about content process is able to read scripts for about:home out of the ScriptPreloader, which pulls those out of the script cache off of the main thread. Yes, this increases how much non-main-thread IO that we do, but also means less time is spent parsing the JavaScript at runtime, and seeking around inside of omni.ja.

I think this is a WONTFIX.