Closed Bug 1258094 Opened 8 years ago Closed 8 years ago

8.24 - 35.8% tp5o_scroll / tresize / tscrollx (windowsxp) regression on push d916e4520180 (Wed Mar 16 2016)

Categories

(Core :: Graphics: Layers, defect)

defect
Not set
normal

Tracking

()

RESOLVED FIXED
mozilla48
Tracking Status
firefox48 --- fixed

People

(Reporter: jmaher, Assigned: sotaro)

References

Details

(Keywords: perf, regression, Whiteboard: [talos_regression])

Attachments

(1 file)

Talos has detected a Firefox performance regression from push d916e4520180. As author of one of the patches included in that push, we need your help to address this regression.

This is a list of all known regressions and improvements related to the push:
https://treeherder.mozilla.org/perf.html#/alerts?id=468

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#tresize
https://wiki.mozilla.org/Buildbot/Talos/Tests#tscrollx
https://wiki.mozilla.org/Buildbot/Talos/Tests#tp5o_scroll

Reproducing and debugging the regression:

If you would like to re-run this Talos test on a potential fix, use try with the following syntax:
try: -b o -p win32 -u none -t chromez-e10s[Windows XP],svgr-e10s[Windows XP],g1-e10s[Windows XP] --rebuild 5  # add "mozharness: --spsProfile" to generate profile data

(we suggest --rebuild 5 to be more confident in the results)

To run the test locally and do a more in-depth investigation, first set up a local Talos environment:
https://wiki.mozilla.lorg/Buildbot/Talos/Running#Running_locally_-_Source_Code

Then run the following command from the directory where you set up Talos:
talos --develop -e [path]/firefox -a tresize:tscrollx:tp5o_scroll

(add --e10s to run tests in e10s mode)

Making a decision:
As the patch author we need your feedback to help us handle this regression.
*** Please let us know your plans by Tuesday, 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
I did a lot of retriggers (mostly to backfill data), and I have data showing the differences from this patch vs the previous one:
https://treeherder.mozilla.org/perf.html#/compare?originalProject=mozilla-inbound&originalRevision=4da14b8142a5&newProject=mozilla-inbound&newRevision=d916e4520180&framework=1

These are all winxp, and the regressions are on e10s.  We are really strict on e10s vs non e10s for release criteria, so there is extra scrutiny on that.

:sotaro, can you take a look at this and let us know the next steps by Tuesday?
Flags: needinfo?(sotaro.ikeda.g)
it looks like we had a big win from bug 1255320 a few days earlier and this for the most part took that win away- in fact it looked like a backout on winxp- maybe this is a net zero type of bug when looking at a few days.
Monday was public holiday in Japan. I am going to check it soon.
Thanks Sotaro!
One option with this patch is to wait until we switch to an image surface for the backbuffer. That will have more predictable and controllable performance.
Thanks for the advice. It seems better to disable the patch until we switch to an image surface.
Flags: needinfo?(sotaro.ikeda.g)
Attachment #8733188 - Flags: review?(jmuizelaar)
Assignee: nobody → sotaro.ikeda.g
Attachment #8733188 - Flags: review?(jmuizelaar) → review+
https://hg.mozilla.org/mozilla-central/rev/b68566e511b7
Status: NEW → RESOLVED
Closed: 8 years ago
Resolution: --- → FIXED
Target Milestone: --- → mozilla48
You need to log in before you can comment on or make changes to this bug.