1875265 - 9.56 - 9.38% linkedin fcp / linkedin fcp (Linux) regression on Wed January 10 2024

Status: RESOLVED FIXED

(Core :: Networking: HTTP, defect, P2)

Description

[Andra Esanu (needinfo me)]

Perfherder has detected a browsertime performance regression from push bb70fac152fd85ba50fbd9a7725552ba32f070e0. As author of one of the patches included in that push, we need your help to address this regression.

Regressions:

Ratio	Test	Platform	Options	Absolute values (old vs new)	Performance Profiles
10%	linkedin fcp	linux1804-64-shippable-qr	fission warm webrender	147.89 -> 162.03	Before/After
9%	linkedin fcp	linux1804-64-shippable-qr	fission warm webrender	148.05 -> 161.93	Before/After

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 patch(es) may be backed out in accordance with our regression policy.

If you need the profiling jobs you can trigger them yourself from treeherder job view or ask a sheriff to do that for you.

You can run these tests on try with ./mach try perf --alert 41061

For more information on performance sheriffing please see our FAQ.

Comment 1

[BugBot [:suhaib / :marco/ :calixte]]

Set release status flags based on info from the regressing bug 1871048

Comment 2

[Frederik Braun [:freddy] (OOO - Back April 8th)]

Maybe we should have just rip application/http-index-format out of HTTP (bug 1871048) instead of fixing bug 1824325. Malte was going to take this, but given that he's working part-time and this per issue here might be come too annoying, I think we could take a look if someone from Necko could steal bug 1871048 from Malte?

Comment 4

[Kershaw Chang [:kershaw]]

Attachment: Bug 1875265 - Allow to call OnDataFinished on main thread, r=sunil

Apparently, calling OnDataFinshed on main thread brings some performance improvement, so let's allow it.

Comment 5

[BugBot [:suhaib / :marco/ :calixte]]

Set release status flags based on info from the regressing bug 1871048

Comment 6

[Pulsebot]

Pushed by [e-mail]:
https://hg.mozilla.org/integration/autoland/rev/0af2852bd44b
Allow to call OnDataFinished on main thread, r=sunil

Comment 7

[Cristian Tuns]

https://hg.mozilla.org/mozilla-central/rev/0af2852bd44b

Comment 8

[BugBot [:suhaib / :marco/ :calixte]]

The patch landed in nightly and beta is affected.
:kershaw, is this bug important enough to require an uplift?

• If yes, please nominate the patch for beta approval.
• If no, please set status-firefox123 to wontfix.

For more information, please visit BugBot documentation.

Comment 9

[Kershaw Chang [:kershaw]]

Attachment: Bug 1875265 - Allow to call OnDataFinished on main thread, r=sunil

Apparently, calling OnDataFinshed on main thread brings some performance improvement, so let's allow it.

Original Revision: https://phabricator.services.mozilla.com/D199324

Comment 10

[Phabricator Automation]

Uplift Approval Request

• Steps to reproduce for manual QE testing: N/A
• Code covered by automated testing: yes
• Is Android affected?: yes
• Fix verified in Nightly: yes
• Explanation of risk level: Low risk because this patch simply reverts the regressed one.
• User impact if declined: Possible performance regression
• Needs manual QE test: no
• String changes made/needed: N/A
• Risk associated with taking this patch: Low

Comment 11

[Donal Meehan [:dmeehan]]

:kershaw what about adding a release uplift request on this?
We have a scheduled Fx122 dot release that builds on 2024-02-05. If this can be included or it should ride the train with Fx123.

Comment 12

[Pulsebot]

https://hg.mozilla.org/releases/mozilla-beta/rev/bac162dca4db

Comment 13

[Kershaw Chang [:kershaw]]

(In reply to Donal Meehan [:dmeehan] from comment #11)

:kershaw what about adding a release uplift request on this?
We have a scheduled Fx122 dot release that builds on 2024-02-05. If this can be included or it should ride the train with Fx123.

It's fine to let this ride the train with Fx123.

Comment 14

[Acasandrei Beatrice (needinfo me)]

(In reply to Pulsebot from comment #6)

Pushed by [e-mail]:
https://hg.mozilla.org/integration/autoland/rev/0af2852bd44b
Allow to call OnDataFinished on main thread, r=sunil

Perfherder has detected the following browsertime performance improvement:

== Change summary for alert #41285 (as of Fri, 02 Feb 2024 07:06:37 GMT) ==

Improvements:

Ratio	Test	Platform	Options	Absolute values (old vs new)	Performance Profiles
8%	linkedin fcp	linux1804-64-shippable-qr	fission warm webrender	161.05 -> 148.48	Before/After
7%	linkedin FirstVisualChange	linux1804-64-shippable-qr	fission warm webrender	176.78 -> 164.16	Before/After
7%	linkedin FirstVisualChange	linux1804-64-shippable-qr	fission warm webrender	178.75 -> 166.72	Before/After

For up to date results, see: https://treeherder.mozilla.org/perfherder/alerts?id=41285

At the moment some jobs are failing to run and I can't properly determine the push that is causing this improvement. Could you let me know if you think this alert was a result of push 0af2852bd44b?

Comment 15

[Kershaw Chang [:kershaw]]

(In reply to Acasandrei Beatrice (needinfo me) from comment #14)

(In reply to Pulsebot from comment #6)

Pushed by [e-mail]:
https://hg.mozilla.org/integration/autoland/rev/0af2852bd44b
Allow to call OnDataFinished on main thread, r=sunil

Perfherder has detected the following browsertime performance improvement:

== Change summary for alert #41285 (as of Fri, 02 Feb 2024 07:06:37 GMT) ==

Improvements:

Ratio	Test	Platform	Options	Absolute values (old vs new)	Performance Profiles
8%	linkedin fcp	linux1804-64-shippable-qr	fission warm webrender	161.05 -> 148.48	Before/After
7%	linkedin FirstVisualChange	linux1804-64-shippable-qr	fission warm webrender	176.78 -> 164.16	Before/After
7%	linkedin FirstVisualChange	linux1804-64-shippable-qr	fission warm webrender	178.75 -> 166.72	Before/After

For up to date results, see: https://treeherder.mozilla.org/perfherder/alerts?id=41285

At the moment some jobs are failing to run and I can't properly determine the push that is causing this improvement. Could you let me know if you think this alert was a result of push 0af2852bd44b?

Yes, it is expected.