Open Bug 1428746 Opened 6 years ago Updated 2 years ago

6.79 - 16% glterrain (linux64, osx-10-10) regression on push 2ba0c8df9a6786d5a70065b03ac66ffbe05695cb (Sat Jan 6 2018)

Categories

(Core :: Graphics: CanvasWebGL, defect, P3)

defect

Tracking

()

People

(Reporter: igoldan, Unassigned)

References

Details

(Keywords: perf, regression, talos-regression, Whiteboard: gfx-noted)

Talos has detected a Firefox performance regression from push:

https://hg.mozilla.org/integration/mozilla-inbound/pushloghtml?changeset=2ba0c8df9a6786d5a70065b03ac66ffbe05695cb

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

Regressions:

 16%  glterrain osx-10-10 opt e10s     3.29 -> 3.81
  7%  glterrain linux64 opt e10s       10.61 -> 11.38
  7%  glterrain linux64 pgo e10s       10.39 -> 11.09


You can find links to graphs and comparison views for each of the above tests at: https://treeherder.mozilla.org/perf.html#/alerts?id=11097

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/Buildbot/Talos/Tests

For information on reproducing and debugging the regression, either on try or locally, see: https://wiki.mozilla.org/Buildbot/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/Buildbot/Talos/RegressionBugsHandling
Component: Untriaged → Canvas: WebGL
Product: Firefox → Core
:jgilbert Can you please look over these regressions? They happen an all platforms, including Windows.
Flags: needinfo?(jgilbert)
We expected something like this. Bug 1427668 is a halfway point between two optimized states. We're going to finish optimizing this now that bug 1427668 has landed.
No longer blocks: 1427668
Depends on: 1427668
Flags: needinfo?(jgilbert)
It's also worth noting that I expect this isn't a 16% hit, but rather a 0.5-0.6ms hit per frame, which is much more acceptable.
Assignee: nobody → jgilbert
Priority: -- → P1
Whiteboard: gfx-noted
This is actually a 0.4ms /improvement/ on Windows aa=true, though it's a 0.5ms regression on aa=false.
0.05ms regression on linux with aa=true,alpha=true.
No regression is worse than 1ms.

Making this P2.
Priority: P1 → P2
Depends on: 1428898
Assignee: jgilbert → nobody
Severity: normal → minor
Priority: P2 → P3
Severity: minor → S4
You need to log in before you can comment on or make changes to this bug.