1824679 - 13.35 - 8.7% damp custom.netmonitor.open.DAMP / damp custom.netmonitor.open.DAMP + 2 more (Linux, Windows) regression on Tue March 21 2023

Status: RESOLVED WONTFIX

(DevTools :: Netmonitor, defect, P3)

Description

[Julian Descottes [:jdescottes]]

Perfherder has detected a devtools performance regression from push 7f9fd030d7be7ee90bb0c8fbf66a6dac20bce39b. 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)
13%	damp custom.netmonitor.open.DAMP	linux1804-64-shippable-qr	e10s fission stylo webrender	223.97 -> 253.86
12%	damp custom.netmonitor.open.DAMP	linux1804-64-shippable-qr	e10s fission stylo webrender-sw	220.43 -> 246.03
9%	damp custom.netmonitor.open.DAMP	windows10-64-shippable-qr	e10s fission stylo webrender-sw	185.60 -> 201.91
9%	damp custom.netmonitor.open.DAMP	windows10-64-shippable-qr	e10s fission stylo webrender	185.41 -> 201.54

Improvements:

Ratio	Test	Platform	Options	Absolute values (old vs new)
3%	damp custom.jsdebugger.pretty-print.DAMP	windows10-64-shippable-qr	e10s fission stylo webrender	323.21 -> 314.45
2%	damp custom.jsdebugger.pretty-print.DAMP	windows10-64-shippable-qr	e10s fission stylo webrender-sw	321.44 -> 314.73

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) 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.

For more information on performance sheriffing please see our FAQ.

Comment 1

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

The Bugbug bot thinks this bug should belong to the 'DevTools::Netmonitor' component, and is moving the bug to that component. Please correct in case you think the bot is wrong.

Comment 2

[Julian Descottes [:jdescottes]]

For reference we actually suspect the following pushlog: https://hg.mozilla.org/integration/autoland/pushloghtml?fromchange=de00b51e1339607931cf2dd5c86803564f10c142&tochange=0f2ee243a2b4595f524dde15df7593400a7c8911

It might just be a test side effect though, so we will do a few additional pushes to verify that.

Comment 3

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

This bug has been marked as a regression. Setting status flag for Nightly to affected.

Comment 4

[Nicolas Chevobbe [:nchevobbe]]

I pushed to TRY to see if that would be caused by Bug 1819128 since it triggered another alert and point to a similar timerange: https://treeherder.mozilla.org/perfherder/compare?originalProject=try&originalRevision=43346b4b8e12d523e12e73d4ffd9e1587a55bc39&newProject=try&newRevision=e63bcd7ea7afb9d2c1694852330e3fd7d29c7588&page=1&framework=12

Comment 5

[Julian Descottes [:jdescottes]]

Thanks! For the record my pushes are in progress at https://treeherder.mozilla.org/jobs?repo=try&author=jdescottes%40mozilla.com&fromchange=2507ae1c98181c0fa60a43bf558f6ceff49a7a88&tochange=152a9091a4cb70526dbcf390ac64b85016b63511

Comment 6

[Nicolas Chevobbe [:nchevobbe]]

(In reply to Nicolas Chevobbe [:nchevobbe] from comment #4)

I pushed to TRY to see if that would be caused by Bug 1819128 since it triggered another alert and point to a similar timerange: https://treeherder.mozilla.org/perfherder/compare?originalProject=try&originalRevision=43346b4b8e12d523e12e73d4ffd9e1587a55bc39&newProject=try&newRevision=e63bcd7ea7afb9d2c1694852330e3fd7d29c7588&page=1&framework=12

doesn't seem like Bug 1819128 caused this, I'm getting pretty similar number between base and the push with the backouts

Comment 7

[Julian Descottes [:jdescottes]]

So when running all tests for the devtools pushlog, we can see the 10% regression:
https://treeherder.mozilla.org/perfherder/comparesubtest?originalProject=try&newProject=try&newRevision=876969549df3ada8c07b214edeb22d81c7c1b4e5&originalSignature=3130994&newSignature=3130994&framework=12&application=&originalRevision=152a9091a4cb70526dbcf390ac64b85016b63511&page=1&showOnlyImportant=1

However, if I only keep the custom.netmonitor test in the manifest, the regression is gone:
https://treeherder.mozilla.org/perfherder/comparesubtest?originalProject=try&newProject=try&newRevision=d1615fcc991fce2f8f732af13fb23678d7108f09&originalSignature=3130994&newSignature=3130994&framework=12&application=&originalRevision=2507ae1c98181c0fa60a43bf558f6ceff49a7a88&page=1&showOnlyImportant=1

So I think we can close this as wontfix, this is most likely just a test side effect.