Open Bug 1692426 Opened 4 years ago Updated 3 years ago

11.15 - 11.5% amazon-search LastVisualChange (android-hw-g5-7-0-arm7-api-16-shippable) regression on push bd2b705457a3a72b97d343eb1ffa29a3bd9a7ecd (Tue February 9 2021)

Categories

(Core :: Panning and Zooming, defect)

defect

Tracking

()

Tracking Status
firefox-esr78 --- unaffected
firefox85 --- unaffected
firefox86 --- unaffected
firefox87 --- wontfix
firefox88 --- wontfix
firefox89 --- wontfix
firefox90 --- fix-optional

People

(Reporter: Bebe, Unassigned, NeedInfo)

References

(Regression)

Details

(Keywords: perf, perf-alert, regression)

Perfherder has detected a browsertime performance regression from push bd2b705457a3a72b97d343eb1ffa29a3bd9a7ecd. As author of one of the patches included in that push, we need your help to address this regression.

Regressions:

Ratio Suite Test Platform Options Absolute values (old vs new)
12% amazon-search LastVisualChange android-hw-g5-7-0-arm7-api-16-shippable nocondprof warm webrender 3,955.67 -> 4,410.75
11% amazon-search LastVisualChange android-hw-g5-7-0-arm7-api-16-shippable nocondprof warm webrender 3,994.42 -> 4,439.83

Details of the alert can be found in the alert summary, including links to graphs and comparisons for each of the affected tests. Please follow our guide to handling regression bugs and let us know your plans within 3 business days, or the offending patch(es) will be backed out in accordance with our regression policy.

For more information on performance sheriffing please see our FAQ.

Flags: needinfo?(tnikkel)

Bug 1691160 was fixing a regression from bug 1687927. Bug 1687927 caused several perf improvements. So I suspect that the regression here is just returning us to the old baseline before bug 1687927 landed. Looking at the graph there was an improvment when bug 1687927 landed, but not as large as this regression. Since we do want to give pages non-zero display ports on load I'm probably going to suggest we just take this unless there are more widespread regressions.

Flags: needinfo?(tnikkel)

== Change summary for alert #28764 (as of Fri, 12 Feb 2021 08:52:47 GMT) ==

Regressions:

Ratio Suite Test Platform Options Absolute values (old vs new)
12% raptor-tp6-google-firefox-cold fcp windows10-64-shippable nocondprof 326.21 -> 366.67
11% raptor-tp6-google-firefox-cold fcp windows10-64-shippable nocondprof 327.75 -> 363.33
9% raptor-tp6-google-firefox-cold loadtime windows10-64-shippable nocondprof 1,065.50 -> 1,164.33
5% raptor-tp6-google-firefox-cold windows10-64-shippable nocondprof 411.35 -> 432.60

Improvements:

Ratio Suite Test Platform Options Absolute values (old vs new)
8% raptor-tp6-wikipedia-firefox-cold loadtime windows10-64-shippable nocondprof 2,180.38 -> 2,009.83

For up to date results, see: https://treeherder.mozilla.org/perfherder/alerts?id=28764

Set release status flags based on info from the regressing bug 1691160

Flags: needinfo?(tnikkel)

Maybe we can look into suppressing displayport (more?) during page load or something.

Flags: needinfo?(aionescu)
Flags: needinfo?(aionescu)
Has Regression Range: --- → yes
You need to log in before you can comment on or make changes to this bug.